Computer implemented method and device for ranking items of data

1. A computer implemented method of ranking items of data stored in a database comprising a plurality of records, wherein each record is associated with one or more items of data, the method comprising using the computer to:

a) generate a concordance of the items of data associated with the records in the database;

b) assign each record to a first group of records or to a second group of records;

c) determine for each item of data a first indicator representative of its occurrences in the records of the first group;

d) determine for each item of data a second indicator representative of its occurrences in the records of the second group; and

e) determine for each item of data a score S representative of a discriminative power of that item of data on the basis of the first and second indicator of that item of data, wherein the score S is determined as S=(I 1 N −I 2 N )/(I 1 +I 2 ) M , wherein I 1 is the first score, I 2 is the second score, N is a parameter between ⅓ and 3 and M is a parameter between ⅓ and 3.

2. The method of claim 1 , wherein the first group consists of records that are within a predetermined query, and the second group consists of records data files that are outside said predetermined query.

3. The method of claim 1 , further comprising using the computer to:

f) determine a first plurality of items of data having the highest discriminative powers for the first group of records.

4. The method of claim 3 , further comprising using the computer to:

generate data representing a user interface representative of the first plurality of items of data;

respond to receipt of a user selection of an item of data from the first plurality of items of data by assigning all records including the selected item of data to the first group of records, and all records not including the selected item of data to the second group of records;

repeat steps c), d), e) and f) for determining a new first plurality of items of data having the highest discriminative powers for the first group of records; and

generate data representing a user interface representative of the new first plurality of items of data.

5. The method of claim 3 , further comprising using the computer to:

g) determine a second plurality of items of data having the highest discriminative powers for the second group of records.

6. The method of claim 5 , further comprising using the computer to generate data representing a user interface including a first view with data representative of the first and/or second pluralities of items of data, and a second view with further data representative of the records.

7. The method of claim 3 , further comprising using the computer to generate data representing a user interface including a first view with data representative of the first plurality of items of data, and a second view with further data representative of the records.

8. The method of claim 7 , further comprising using the computer to:

respond to receipt of a user selection of one or more items of data from the second view by assigning all records including the selected items of data to the first group of records, and all records not including the selected items of data to the second group of records;

repeat steps c), d), e), and f) for determining a new first plurality of items of data having the highest discriminative powers for the first group; and

generate data representing a user interface representative of the new first plurality of items of data.

9. The method of claim 3 , wherein the query items query items are one or more of words, groups of words, texts, image fragments, images, video fragments, audio fragments, numbers, chemical formula fragments, chemical formulae, biological formulae fragments, biological formulae, mathematical formula fragments, mathematical formulae, statistical properties.

10. The method of claim 3 , wherein in the information relating to the data files presented in the second view is one or more of geographical data, temporal data, relationship data.

11. The method of claim 1 , further comprising using the computer to:

assign an identifier to each unique item of data, wherein the concordance of the contains the identifiers of the items of data;

generate a list of representations, each representation representing a record of the plurality of records, and each representation including the unique identifiers of the items of data identified in the respective record;

wherein the step c) includes determining for each item of data a first indicator representative of occurrences of its unique identifier in the representations of the records of the first group; and

wherein the step d) includes determining for each item of data a second indicator representative of occurrences of its unique identifier in the representations of the records of the second group.

12. A computer implemented method of ranking items of data stored in a database comprising a plurality of records, wherein each record is associated with one or more items of data, the method comprising using the computer to:

a) generate a concordance of the items of data associated with the records in the database;

b) assign each record to a first group of records or to a second group of records;

c) determine for each item of data a first indicator representative of its occurrences in the records of the first group;

d) determine for each item of data a second indicator representative of its occurrences in the records of the second group;

e) determine for each item of data a score S representative of a discriminative power of that item of data on the basis of the first and second indicator of that item of data;

f) determine a first plurality of items of data having the highest discriminative powers for the first group of records;

g) determine a second plurality of items of data having the highest discriminative powers for the second group of records;

generate data representing a user interface representative of the first plurality of items of data and the second plurality of items of data;

respond to receipt of a user selection of an item of data from the first or second plurality of items of data by assigning all records including the selected item of data to the first group of records, and all records not including the selected item of data to the second group of records;

repeat steps c), d), e), f) and g) for determining a new first plurality of items of data having the highest discriminative powers for the first group of records and a new second plurality of items of data having the highest discriminative powers for the second group of records; and

generate data representing a user interface representative of the new first plurality of items of data and the new second plurality of items of data.

13. A computer implemented method of ranking items of data stored in a database comprising a plurality of records, wherein each record is associated with one or more items of data, the method comprising using the computer to:

a) generate a concordance of the items of data associated with the records in the database;

b) assign each record to a first group of records or to a second group of records;

c) determine for each item of data a first indicator representative of its occurrences in the records of the first group;

d) determine for each item of data a second indicator representative of its occurrences in the records of the second group;

e) determine for each item of data a score S representative of a discriminative power of that item of data on the basis of the first and second indicator of that item of data;

f) determine a first plurality of items of data having the highest discriminative powers for the first group of records;

g) determine a second plurality of items of data having the highest discriminative powers for the second group of records;

generate data representing a user interface including a first view with data representative of the first and/or second pluralities of items of data, and a second view with further data representative of the records;

respond to receipt of a user selection of one or more items of data from the second view;

assign all records including the selected items of data to the first group of data files, and all records not including the selected items of data to the second group of records;

repeat steps c), d), e), f) and g) for determining a new first plurality of items of data having the highest discriminative powers for the first group and a new second plurality of items of data having the highest discriminative powers for the second group; and

generate data representing a user interface representative of the new first plurality of items of data and the new second plurality of items of data to the user.

14. A data processing system for ranking items of data, the processing system being associated with a database storing a set of records, the processing system including:

a retrieval unit arranged for retrieving records from the database;

an identification unit arranged for identifying in each record one or more items of data;

a generation unit arranged for generating a concordance of the items of data identified in the records;

a memory for storing the concordance;

an assignation unit arranged for assigning each record to a first group of records or to a second group of records; and

a processing unit arranged for:

determining for each item of data a first indicator representative of its occurrences in the records of the first group;

determining for each item of data a second indicator representative of its occurrences in the records of the second group; and

determining for each item of data a score S representative of a discriminative power of that item of data on the basis of the first and second indicator of that item of data, wherein the score S is determined as S=(I 1 N −I 2 N )/(I 1 +I 2 ) M , wherein I 1 is the first score, I 2 is the second score, N is a parameter between ⅓ and 3 and M is a parameter between ⅓ and 3.

15. The data processing system of claim 14 , wherein the assignation unit is further arranged for determining that a record belongs to the first group if one or more predetermined items of data are present in said record, and determining that a record belongs to the second group if said items of data are not present in the record.

16. A non-transitory computer readable medium storing computer implementable instructions which when implemented by a programmable computer cause the computer to:

generate a concordance of the items of data associated with the records in the database;

assign each record to a first group of records or to a second group of records;

determine for each item of data a first indicator representative of its occurrences in the records of the first group;

determine for each item of data a second indicator representative of its occurrences in the records of the second group; and

determine for each item of data a score S representative of a discriminative power of that item of data on the basis of the first and second indicator of that item of data, wherein the score S is determined as S=(I 1 N −I 2 N )/(I 1 +I 2 ) M , wherein I 1 is the first score, I 2 is the second score, N is a parameter between ⅓ and 3 and M is a parameter between ⅓ and 3.