COMPUTER-ENABLED METHOD OF ASSISTING TO GENERATE AN INNOVATION

• US 20160162486A1
• Filed: 12/08/2014
• Published: 06/09/2016
• Est. Priority Date: 12/08/2014
• Status: Active Grant

• Current Assignee: Iprova Sari
• Original Assignee: Iprova Sari
• Inventors: BISWAS, Debmalya, Nolan, Julian, LAWRENSOM, Matthew J.
• Granted Patent: US 10,459,925 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/35 Clustering; Classification

Abstract

According to the present invention there is provided a computer-enabled method of assisting to generate an innovation, the method comprising the steps of: retrieving from a database a first set of more than two documents belonging to a first domain (D₁); retrieving from said database a second set of more than two documents belonging to a second domain (D₂); selecting all possible combinations of documents from the first set with all documents in said second set, and for each combination of documents: determining a composite novelty score, a composite proximity score and a composite impact score; and based on all of the determined composite novelty scores and/or composite proximity scores and/or composite impact scores, providing a recommendation which can assist to generate an innovation.

Claims

1. A computer-enabled method of assisting to generate an innovation, the method comprising the steps of:

retrieving from a database a first set of more than two documents belonging to a first domain (D₁);

retrieving from said database a second set of more than two documents belonging to a second domain (D₂);

selecting all possible combinations of documents from the first set with all documents in said second set, and for each combination of documents;

determining a composite novelty score for said documents, wherein the composite novelty score is a score representing likelihood that a merging of the solutions in said two or more documents will provide a novel solution;

determining a composite proximity score for said documents, wherein the composite proximity score is a score representing the proximity of each of said documents to one or more predefined ontologies;

determining a composite impact score for said documents, wherein the composite impact score is a score representing the feasibility of combining the solutions which are disclosed in said two or more documents;

and, based on all of the determined composite novelty scores and/or composite proximity scores and/or composite impact scores which have been determined, providing a recommendation which can assist to generate an innovation.

2. A method according to claim 1 comprising:

replacing parts of the solution which represents known solutions in a domain with the solutions disclosed in said two or more documents, if the determined composite impact score is above a predefined maximum threshold value, to provide an integrated solution; and

wherein the step of providing a recommendation comprises presenting said integrated solution.

3. A method according to claim 1 further comprising the step of, for each of said documents (d_x, d_y), identifying words and/or terms disclosed in that document which are not disclosed in a group of documents which belong to the same domain as the domain to which the document (d_x, d_y) belongs, to provide a set (c(d_x), c(d_y)) of words and/or terms for each of said documents (d_x, d_y), identifying words and/or terms which are common to all sets (c(d_x)∩

c(d_y)) to define a common-word-set;

identifying another document (d_z), which is not one of said documents (d_x, d_y), which discloses a threshold number of the words and/or terms listed in common-word-set;

wherein the step of providing a recommendation comprises presenting said identified document (d_z).

4. A method according to claim 1 further comprising the step of, defining one or more ontologies by, identifying the domains which said two or more documents belong;

for each domain identified, selecting keywords and/or concepts from a set of documents in that domain, which define an ontology corresponding to that domain.

5. A method according to claim 4 comprising the steps of,

identifying a pair of keywords and/or concepts from an ontology which are also disclosed in each of said documents (d_x, d_y);

identifying a path in said ontology which links said pair of keywords and/or concepts;

identifying another document (d_z), which is not one of said documents (d_x, d_y), which discloses a threshold number of the keywords and/or concepts which are along said identified path;

wherein the step of providing a recommendation comprises presenting said identified document (d_z).

6. A method according to claim 1 wherein the step of providing a recommendation based on the determined composite proximity score and/or composite impact score comprises, recommending one or more domains which are likely to contain solutions which are usable to merge the solutions disclosed in said two or more documents, if the determined composite proximity score and/or composite impact score is below a predefined minimum threshold value.

7. A method according to claim 6 comprising the steps of, defining one or more ontologies by, identifying the domains which said two or more documents belong;

for each domain identified, selecting keywords and/or concepts from a set of documents in that domain, which define an ontology corresponding to that domain;

identifying another ontology, from a predefined library of ontologies which correspond to domains which are different to the domains to which the two or more documents belong, which has a number of keywords and/or concepts in common with the defined one or more ontologies above a predefined threshold number;

wherein the step of providing a recommendation comprises presenting the domain which corresponds to the identified ontology.

8. A method according to claim 6 comprising the steps of, identifying another flowchart, from a predefined library of flowcharts which represent known solutions from a plurality of domains which are different to the domains to which the two or more documents belong, which has a number of steps which can be replaced by the solutions in said two or more documents, above a predefined threshold number;

wherein the step of providing a recommendation comprises presenting the domain which corresponds to the identified flowchart.

9. A method according to claim 1 further comprising the steps of, defining one or more ontologies.

10. A method according to claim 9 wherein the step of defining one or more ontologies comprises, identifying the domains which said two or more documents belong;

for each domain identified, selecting keywords and/or concepts from a set of documents in that domain, which define an ontology corresponding to that domain.

11. A method according to claim 10 further comprising the step of applying weights to each of said selecting keywords and/or concepts.

12. A method according to claim 1 further comprising the steps of, creating one or more flowcharts which represent known solutions in said domains which said two or more documents belong.

13. A method according to claim 12 wherein the step of creating one or more flowcharts comprises,

identifying the domains which said two or more documents belong;

for each domain identified,

creating one or more flowcharts which represent solutions which are disclosed in a set of documents in that domain.

14. A method according to claim 13 wherein the step of creating one or more flowcharts which represent solutions which are disclosed in a set of documents in that domain, comprises, creating a plurality of flowcharts each of which represents a solution disclosed in a corresponding document in the set of documents;

or, creating a single flowchart which represents an aggregation of the solutions disclosed in the set of documents.

15. A method according to claim 1 wherein the step of determining a composite novelty score comprises, for each of said documents (d_x, d_y), identifying words and/or terms disclosed in that document which are not disclosed in a group of documents which belong to the same domain as the domain to which the document (d_x, d_y) belongs, to provide a set (c(d_x), c(d_y)) of words and/or terms for each of said documents (d_x/d_y);

determining the number of words and/or terms which are common to all sets (|c(d_y)∩

c(d_y)|) to provide the composite novelty score.

16. A method according to claim 9 wherein the step of determining a composite proximity score for said documents comprises, for each of said documents, determining the number of keywords (P_O1(d_x), P_O2(d_x), P_O1(d_y), P_O2(d_y)) and/or concepts mentioned in each ontology which are mentioned in that document (d_x, d_y);

adding the number of keywords and/or concepts determined for each of said documents to provide the composite proximity score.

17. A method according to claim 12 wherein the composite impact score determined using the formula:

18. A method according to claim 1 wherein the step of providing a recommendation comprises at least one of:

providing a recommendation to merge the solutions disclosed in said two or more documents into a solution which represents known solutions in a domain, if the determined composite impact score is above a predefined maximum threshold value;

providing a recommendation of one or more other documents, each of which disclose a solution which is compatible for integration with a solution disclosed in at least one of said two or more documents, if the determined composite impact score is within a predefined range;

recommending one or more domains which are likely to contain solutions which are usable to merge the solutions disclosed in said two or more documents, if the determined composite proximity score and/or composite impact score is below a predefined minimum threshold value.

19. A method for assisting to generate an innovation, the method comprising the steps of:

retrieving from a database a first set of more than two documents belonging to a first domain (D₁);

retrieving from said database a second set of more than two documents belonging to a second domain (D₂);

causing a data analysis module (200) to select all possible combinations of documents from the first set with all documents in said second set;

for each said combination;

causing the data analysis module (200) to determine a composite novelty score for said documents, wherein the composite novelty score is a score representing likelihood that a merging of the solutions in said two or more documents will provide a novel solution;

causing the data analysis module (200) to determine a composite proximity score for said documents, wherein the composite proximity score is a score representing the proximity of each of said two or more documents to one or more predefined ontologies;

causing the data analysis module (200) to determine a composite impact score for said documents, wherein the composite impact score is a score representing the feasibility of combining the solutions which are disclosed in said two or more documents;

presenting at least one said combination of documents based on the determined composite novelty score and/or composite proximity score and/or composite impact score.