System and method for using pattern recognition to monitor and maintain status quo
A system for prospectively identifying media characteristics for inclusion in media content is disclosed. A neural network database including media characteristic information and feature information may associate relationships among the media characteristic information and feature information. Personal characteristic information associated with target media consumers may be used to select a subset of the neural network database. A first set of nodes, representing selected feature information, may be activated. The node interactions may be calculated to detect the activation of a second set of nodes, the second set of nodes representing media characteristic information. Generally, a node is activated when an activation value of the node exceeds a threshold value. Media characteristic information may be identified for inclusion in media content based on the second set of nodes.
1. A method of training a data profiler to monitor a quality of data extracted from a content source, the method comprising:
receiving an acceptable data element for a first characteristic of data extracted from a first content source by a data extractor;
identifying, from a plurality of constraint modules, a set of one or more constraint modules applicable to the first characteristic;
adjusting, for each constraint module in the identified set of one or more constraint modules, parameters of the respective constraint module to accept the received acceptable data element;
determining, for each constraint module in the identified set of one or more constraint modules, based on the adjustments, whether each respective constraint module is stable or non-stable; and
generating a set of trusted constraint modules selected from the stable constraint modules, omitting the constraint modules determined as non-stable.
2. The method of claim 1 comprising:
receiving a second acceptable data element for the first characteristic of data extracted from the first content source;
adjusting, for each constraint module in the set of trusted constraint modules, parameters of the respective constraint module to accept the received second acceptable data element; and
removing constraint modules determined as non-stable from the set of trusted constraint modules.
3. The method of claim 2 comprising:
receiving an extracted data element extracted from the first content source, identified as being for the first characteristic;
determining, by applying the set of trusted constraint modules to the received extracted data element, that the received extracted data element does not meet the parameters of the set of trusted constraint modules; and
signaling a failure condition.
4. The method of claim 3 , wherein signaling the failure condition comprises sending a signal to at least one of: an email account, a database for entry into a log, a mobile device, an SMS system, a monitoring agent, or to a user at a computer terminal.
5. The method of claim 3 , wherein signaling the failure comprises sending an error signal to a processor, the method further comprising the processor automatically adjusting subsequent extraction of data elements from the content source.
6. The method of claim 1 wherein the first characteristic is one of a text length range, a numeric value range, a count of data elements, a value for a data element, a pattern of characters to be matched by a data element, or a comparison between data elements.
7. The method of claim 1 wherein generating the set of trusted constraint modules comprises including, in the set of trusted constraint modules, a set of applicable constraint modules that are pre-determined to be stable constraint modules.
8. The method of claim 1 wherein the non-stable constraint modules are constraint modules identified as one of:
constraint modules that have been adjusted at a frequency that exceeds a threshold value of a stability algorithm; and
constraint modules that have been adjusted at a rate that is trending away from a threshold value of a stability trending algorithm.
9. The method of claim 1 wherein the stable constraint modules are constraint modules that are identified as one of:
constraint modules that have been adjusted at a frequency within a threshold value of a stability algorithm; and
constraint modules that have been adjusted at a rate that is trending towards a threshold value of a stability trending algorithm.
10. The method of claim 1 wherein the plurality of constraint modules are sourced from a trusted set of constraint modules for the first characteristic of data extracted from a second content source.
11. A system comprising:
a data extractor configured to extract data from a first content source;
a data profiler, comprising at least one computing processor and memory storing instructions that, when executed by the at least one computing processor, cause the at least one computing processor to:
receive an acceptable data element for a first characteristic of data extracted from the first content source by the data extractor;
identify, from a plurality of constraint modules, a set of one or more constraint modules applicable to the first characteristic;
adjust, for each constraint module in the identified set of one or more constraint modules, parameters of the respective constraint module to accept the received acceptable data element;
determine, for each constraint module in the identified set of one or more constraint modules, based on the adjustments, whether each respective constraint module is stable or non-stable; and
generate a set of trusted constraint modules selected from the stable constraint modules, omitting the constraint modules determined as non-stable.
12. The system of claim 11 , wherein the instructions further cause the at least one computing processor to:
receive a second acceptable data element for the first characteristic of data extracted from the first content source;
adjust, for each constraint module in the set of trusted constraint modules, parameters of the respective constraint module to accept the received second acceptable data element; and
remove constraint modules determined as non-stable from the set of trusted constraint modules.
13. The system of claim 12 , wherein the instructions further cause the at least one computing processor to:
receive an extracted data element extracted from the first content source, identified as being for the first characteristic;
determine, by applying the set of trusted constraint modules to the received extracted data element, that the received extracted data element does not meet the parameters of the set of trusted constraint modules; and
signal a failure condition.
14. The system of claim 13 , wherein signaling the failure condition comprises sending a signal to at least one of: an email account, a database for entry into a log, a mobile device, an SMS system, a monitoring agent, or to a user at a computer terminal.
15. The system of claim 13 , wherein signaling the failure comprises sending an error signal to a processor, the method further comprising the processor automatically adjusting subsequent extraction of data elements from the content source.
16. The system of claim 11 wherein the first characteristic is one of a text length range, a numeric value range, a count of data elements, a value for a data element, a pattern of characters to be matched by a data element, or a comparison between data elements.
17. The system of claim 11 wherein generating the set of trusted constraint modules comprises including, in the set of trusted constraint modules, a set of applicable constraint modules that are pre-determined to be stable constraint modules.
18. The system of claim 11 wherein the non-stable constraint modules are constraint modules identified as one of:
constraint modules that have been adjusted at a frequency that exceeds a threshold value of a stability algorithm; and
constraint modules that have been adjusted at a rate that is trending away from a threshold value of a stability trending algorithm.
19. The system of claim 11 wherein the stable constraint modules are constraint modules that are identified as one of:
constraint modules that have been adjusted at a frequency within a threshold value of a stability algorithm; and
constraint modules that have been adjusted at a rate that is trending towards a threshold value of a stability trending algorithm.
20. The system of claim 11 wherein the plurality of constraint modules are sourced from a trusted set of constraint modules for the first characteristic of data extracted from a second content source.