Automatic electronic message content extraction method and apparatus

1. A method comprising:

obtaining, via a computing device, a plurality of electronic messages having an associated set of shared expressions;

identifying, via the computing device, for the plurality of electronic messages, a variable value in connection with a respective expression in the set of shared expressions, the variable value indicating that at least a portion of a value corresponding to the respective expression varies across two or more of the plurality of electronic messages;

analyzing, via the computing device, the variable value corresponding to multiple electronic messages of the plurality of electronic messages to determine an annotation indicative of a meaning of the variable value;

automatically generating, via the computing device and for the plurality of electronic messages, a data extraction rule comprising the annotation associated with the respective expression having the variable value;

receiving, via the computing device, over an electronic communications network, an electronic message;

using, via the computing device, the automatically-generated data extraction rule to extract data from the received electronic message; and

causing, via the computing device, the data extracted from the received electronic message to be displayed at a user device.

2. A method of claim 1 , further comprising:

communicating, via the computing device, the automatically extracted data to the user device.

3. A method of claim 2 , wherein the communicating is responsive to a data extraction rule creation request received from the user.

4. A method of claim 1 , wherein the causing further comprises:

communicating, via the computing device, the annotation associated with the respective expression to the user device, communication of the annotation causing the annotation to be displayed along with the extracted data in an electronic message information summary display of the user device.

5. The method of claim 1 , further comprising communicating at least some of the extracted data and the annotation to a search engine for use in generating a search index for use in electronic message searching.

6. The method of claim 1 , further comprising communicating at least some of the extracted data and annotation to a recommendation system for use in determining at least one interest of a user of the recommendation system, the at least one interest of the user for use in making at least one recommendation to the user.

7. The method of claim 6 , the recommendation system comprises an advertising content recommendation system, and the at least one interest is for use in determining advertising content for the user.

8. A method of claim 1 , further comprising:

using a value corresponding to at least one other expression of the set of shared expressions to determine the meaning of the variable value.

9. A method of claim 1 , wherein each expression in the set of shared expressions is an XPATH expression.

10. The method of claim 1 , using the automatically-generated data extraction rule to extract data from a received electronic message further comprising:

associating, via the computing device, the variable value for the respective expression with the associated annotation indicative of the meaning of the variable value.

11. The method of claim 1 , wherein the plurality of electronic messages have a common sender domain.

12. The method of claim 1 , determining the annotation for the variable value of the respective expression further comprising:

determining, by searching a dictionary using some or all of the variable value, that the dictionary includes at least a portion of the variable value, the dictionary having an associated annotation; and

using the associated annotation of the dictionary as the annotation for the variable value.

13. The method of claim 1 , determining the annotation for the variable value of the respective expression further comprising:

determining, using a pattern recognition analyzer, a pattern of at least a portion of the variable value; and

using an associated annotation of the pattern as the annotation for the variable value.

14. The method of claim 1 , further comprising automatically refining the annotation associated with the respective expression, the refining comprising:

generating, via the computing device, training data across the set of shared expressions associated with the plurality of electronic messages, the training data comprising a plurality of training examples, each training example comprising a set of features and corresponding feature values;

training, via the computing device and using machine learning, an annotation refinement model for use in refining the annotation;

generating, via the computing device, a set of features for the annotation; and

using the annotation refinement model trained with the set of features generated for the annotation to refine the annotation associated with the respective expression.

15. The method of claim 1 , automatically extracting data from the electronic message further comprising:

using the respective expression to retrieve the variable value from the received electronic message.

16. The method of claim 1 , wherein the plurality of electronic messages share a digital signature determined using the set of shared expressions.

17. The method of claim 16 , further comprising:

before automatically extracting data from the received electronic message:

determining a digital signature for the received electronic message; and

determining, via the computing device, that the digital signature determined for the received electronic message matches the digital signature shared by the plurality of electronic messages.

18. The method of claim 17 , further comprising:

determining that a sender domain of the received electronic message matches a sender domain shared by the plurality of electronic messages.

19. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions that when executed by a processor associated with a computing device perform a method comprising:

obtaining a plurality of electronic messages having an associated set of shared expressions;

identifying for the plurality of electronic messages, a variable value in connection with a respective expression in the set of shared expressions, the variable value indicating that at least a portion of a value corresponding to the respective expression varies across two or more of the plurality of electronic messages;

analyzing the variable value corresponding to multiple electronic messages of the plurality of electronic messages to determine an annotation indicative of a meaning of the variable value;

automatically generating, for the plurality of electronic messages, a data extraction rule comprising the annotation associated with the respective expression having the variable value;

receiving, over an electronic communications network, an electronic message;

using the automatically-generated data extraction rule to extract data from a received electronic message; and

causing the data extracted from the received electronic message to be displayed at a user device.

20. A computing device comprising:

a processor; and

a non-transitory storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising:

obtaining logic executed by the processor for obtaining a plurality of electronic messages having an associated set of shared expressions;

identifying logic executed by the processor for identifying for the plurality of electronic messages, a variable value in connection with a respective expression in the set of shared expressions, the variable value indicating that at least a portion of a value corresponding to the respective expression varies across two or more of the plurality of electronic messages;

analyzing logic executed by the processor for analyzing the variable value corresponding to multiple electronic messages of the plurality of electronic messages to determine an annotation indicative of a meaning of the variable value;

generating logic executed by the processor for automatically generating, for the plurality of electronic messages, a data extraction rule comprising the annotation associated with the respective expression having the variable value;

receiving logic executed by the processor for receiving, over an electronic communications network, an electronic message;

using logic executed by the processor for using the automatically-generated data extraction rule to extract data from a received electronic message; and

causing logic executed by the processor for causing the data extracted from the received electronic message to be displayed at a user device.