Computer-enabled method of assisting to generate an innovation

• US 10,459,925 B2
• Filed: 12/08/2014
• Issued: 10/29/2019
• Est. Priority Date: 12/08/2014
• Status: Active Grant

• Current Assignee: Iprova Sari
• Original Assignee: Iprova Sari
• Inventors: Biswas, Debmalya, Nolan, Julian C., Lawrenson, Matthew J.
• Primary Examiner(s): Mamillapalli, Pavan
• Application Number:
  US14/563,339
• Publication Number:
  US 20160162486A1
• Time in Patent Office: 1,786 Days
• Field of Search: 707729
• 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 method comprising:

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

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

defining one or more ontologies;

generating all possible combinations of documents from the first set (d_x) with documents in said second set (d_y);

determining respective composite novelty scores for said combinations of documents (d_x, d_y), wherein the composite novelty score for one of the combinations of documents (d_x, d_y) represents a likelihood that a merging of solutions in said combination of documents (d_x, d_y) will provide a novel solution, and wherein determining the composite novelty score for said combination of documents (d_x, d_y) includes;

identifying sets of words and/or terms c(d_x) and c(d_y) included in the documents (d_x, d_y) which are not included in one or more other documents which belong to a same one of the first domain (D₁) or second domain (D2) to which the document (d_x, d_y) belongs; and

determining the composite novelty score based on a number of words and/or terms which are common to the sets of words and/or terms for the documents (|c(d_x)∩

c(d_y)|);

determining composite proximity scores for said combinations of documents (d_x, d_y), wherein the composite proximity score for one of the combinations of documents (d_x, d_y) represents a proximity of each of said documents to the one or more defined ontologies;

determining composite impact scores for said combinations of documents (d_x, d_y), wherein the composite impact score for one of the combinations of documents (d_x, d_y) represents a feasibility of combining the solutions in said two or more documents; and

selecting one or more of the combinations of documents (d_x, d_y) based on the composite novelty scores, the composite proximity scores, and the composite impact scores, and providing a recommendation related to generating an innovation based on the selected one or more of the combinations of documents,

wherein providing the recommendation includes presenting a solution template S_xy in which the respective solutions in the selected combination of documents are merged to provide a new solution which differs from the respective solutions in the selected combination of documents.

2. A method according to claim 1, further comprising:

forming the solution template S_xy, wherein forming the solution template S_xy includes replacing parts of known solutions in a domain with the solutions disclosed in said selected one or more combination of documents when the determined composite impact score for the selected one or more combinations of documents is above a predefined maximum threshold value to provide an integrated solution; and

wherein providing the recommendation includes presenting said integrated solution.

3. A method according to claim 1 further comprising:

for each of said combinations of documents (d_x, d_y), identifying another document (d_z), which differs from said (d_x) and (d_y), and which includes at least a threshold number of the words and/or terms listed in the common sets of words and/or terms (c(d_x)∩

c(d_y)) for said documents (d_x) and (d_y)

wherein providing the recommendation further includes presenting said identified document (d_z) for at least one of the selected one or more combinations of documents.

4. A method according to claim 1, wherein defining the one or more ontologies includes:

identifying ones of the domains to which said two or more documents belong; and

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

5. A method according to claim 4, further comprising:

identifying a pair of keywords and/or concepts from one of the ontologies which are also disclosed in each of said documents;

identifying a path in said one of the ontologies which links said pair of keywords and/or concepts; and

identifying another document (d_z), which differs from said documents, and which includes at least a threshold number of the keywords and/or concepts which are included along said identified path;

wherein providing the recommendation further includes presenting said identified document (d_z) for at least one of the selected one or more combinations of documents.

6. A method according to claim 1, wherein providing the recommendation further includes:

recommending one or more domains which are likely to contain solutions which are usable to merge the solutions disclosed in said selected one or more combinations of documents when at least one of the determined composite proximity score or the determined composite impact score for the selected one or more combinations of documents are below respective minimum threshold values.

7. A method according to claim 6,

wherein defining the one or more ontologies includes:

identifying the domains to which said two or more documents belong; and

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

wherein the method further includes;

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, the other ontology including at least a threshold number of keywords and/or concepts in common with the identifies one or more ontologies; and

wherein providing the recommendation further includes presenting one of the domains to which said two or more documents belong which corresponds to the identified other ontology.

8. A method according to claim 6, further comprising:

identifying another flowchart, from a predefined library of flowcharts which represent known solutions from a plurality of domains which are different from the domains to which the two or more documents belong, the other flowchart including at least a threshold number of steps which can be replaced by the solutions in said two or more documents;

wherein providing the recommendation further includes presenting one of the plurality of domains which corresponds to the identified flowchart.

9. A method according to claim 1, wherein defining the one or more ontologies includes:

identifying the domains to 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.

10. A method according to claim 9, further comprising:

applying weights to each of said selected keywords and/or concepts; and

defining the ontology corresponding to a domain based on the weights.

11. A method according to claim 1, further comprising:

creating one or more flowcharts which represent known solutions in said domains to which said two or more documents belong.

12. A method according to claim 11 wherein creating the one or more flowcharts includes:

identifying the domains to 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.

13. A method according to claim 12, wherein creating the one or more includes:

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.

14. A method comprising:

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

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

selecting all possible combinations of documents from the first set (D₁) with all documents in said second set (D₂);

determining a composite novelty score for each of said combinations of documents (d_x,d_y), wherein each of the composite novelty scores represents a likelihood that a merging of the solutions in two or more of the documents (d_x,d_y) will provide a novel solution;

defining one or more ontologies for the first and second domains;

determining a composite proximity score for each of said combination of documents (d_x,d_y), wherein each of the composite proximity scores represents a proximity of each of said two or more documents to the one or more ontologies;

determining a composite impact score for each of said combinations of documents, wherein each of the composite impact scores represents a feasibility of combining the solutions in said two or more documents;

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

providing a recommendation related to generating an innovation based on the selected one or more of the combinations of documents,

wherein presenting the at least one of said combination of documents includes presenting a solution template S_xy in which the at least one of said combination of documents are merged to provide a new solution which differs from the respective solutions in the at least one of said combination of documents.

15. A method comprising:

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

retrieving 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;

defining one or more ontologies;

determining a composite novelty score for each of said combination of documents, wherein each of the composite novelty scores represents a likelihood that a merging of solutions in corresponding two or more documents will provide a novel solution;

determining a composite proximity score for each of said combinations of documents, wherein each of the composite proximity scores represents a proximity of each of said documents to the one or more ontologies, wherein for each of said documents, the number of keywords and/or concepts (P_O1(d_x), P_O2(d_x), P_O1(d_y), P_O2(d_y)) mentioned in each ontology and which are mentioned in that document are determined and the number of keywords and/or concepts determined for each of said two or more documents in one of the combinations are added to determine the corresponding composite proximity score for that combination of documents;

determining a composite impact score for each of said combinations of documents, wherein each of the composite impact scores represents a feasibility of combining the solutions which are disclosed in said two or more documents; and

based on the determined composite novelty scores, the determined composite proximity scores, and the determined composite impact scores, providing a recommendation related to generating an innovation,

wherein providing the recommendation includes presenting a solution template S_xy in which respective solutions in a selected combination of documents are merged to provide a new solution which differs from the respective solutions in the selected combination of documents.

16. A method comprising:

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

retrieving 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;

defining one or more ontologies;

determining a composite novelty score for each of said combination of documents, wherein each of the composite novelty scores represents a likelihood that merging solutions two or more documents in a corresponding combination will provide a novel solution;

determining a composite proximity score for each of said combination of documents, wherein each of the composite proximity scores represents a proximity of each of said documents to the one or more ontologies;

determining a composite impact score for each of said combination of documents, wherein each of the composite impact scores represents a feasibility of combining the solutions which are disclosed in said two or more documents, wherein the composite impact score is determined using the formula;

CI_{F1,F2, . . . ,Fn}(d₁,d₂, . . . ,d_n)=max[(|F₁₁|+|F₁₂|+ . . . +|F_1n|−

|F₁₁∩

F₁₂∩

. . . ∩

F_1n|)/|F₁|,(|F₁₂|+|F₂₂|+ . . . +|F_2n|−

|F₁₂∩

F₂₂∩

. . . ∩

F_2n|)/|F₂|,(|F_1n|+|F_n2|+ . . . +|F_nn|−

|F_1n∩

F_2n∩

. . . ∩

F_nn|)/|F_n|],

wherein |F₁₁| is the number of steps (i.e. number of nodes) in flowchart F₁, which can be, optimized, or improved, by processes/workflows which are described in document d₁;

|F₁₂| is the number of steps (i.e. number of nodes) in flowchart F₁, which can be, optimized, or improved, by processes/workflows which are described in document d₂;

|F_1n| is the number of steps (i.e. number of nodes) in flowchart F₁, which can be, optimized, or improved, by processes/workflows which are described in the ‘

n’

th document d_n;

|F₂₁| is the number of steps (i.e. number of nodes) in flowchart F₂, which can be, optimized, or improved, by processes/workflows which are described in document d₁;

|F₂₂| is the number of steps (i.e. number of nodes) in flowchart F₂, which can be, optimized, or improved, by processes/workflows which are described in document d₂;

|F_2n| is the number of steps (i.e. number of nodes) in flowchart F₂, which can be, optimized, or improved, by processes/workflows which are described in the ‘

n’

th document d_n;

|F_n1| is the number of steps (i.e. number of nodes) in the ‘

n’

th flowchart F_n, which can be, optimized, or improved, by processes/workflows which are described in document d₁;

|F_n2| is the number of steps (i.e. number of nodes) in the ‘

n’

th flowchart F_n, which can be, optimized, or improved, by processes/workflows which are described in document d₂;

|F_nn| is the number of steps (i.e. number of nodes) in the ‘

n’

th flowchart F_n, which can be, optimized, or improved, by processes/workflows which are described in the ‘

n’

th document d_n;

|F₁₁∩

F₁₂∩

. . . ∩

F_1n| is the number of overlapping steps (i.e. number of nodes) in flowchart F₁, which can be, optimized, or improved, by processes/workflows which are described in documents (d₁, d₂, . . . , d_n);

|F₂₁∩

F₂₂∩

. . . ∩

F_2n| is the number of overlapping steps (i.e. number of nodes) in flowchart F₂, which can be, optimized, or improved, by processes/workflows which are described in documents (d₁, d₂, . . . , d_n);

|F_n1∩

F_n2∩

. . . ∩

F_nn is the number of overlapping steps (i.e. number of nodes) in the ‘

n’

th flowchart F_n, which can be, optimized, or improved, by processes/workflows which are described in documents (d₁, d₂, . . . , d_n);

|F₁| is the number of steps (i.e. nodes) in flowchart F₁;

|F₂| is the number of steps (i.e. nodes) in flowchart F₂;

|F_n| is the number of steps (i.e. nodes) in the ‘

n’

th flowchart F_n;

creating one or more flowcharts which represent known solutions in said domains to which said two or more documents belong; and

based on the determined composite novelty scores, the determined composite proximity scores, and the determined composite impact scores, providing a recommendation related to generating an innovation,

wherein providing the recommendation includes presenting a solution template S_xy in which respective solutions in a selected combination of documents are merged to provide a new solution which differs from the respective solutions in the selected combination of documents.

17. A method comprising:

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

retrieving 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;

determining a composite novelty score for each of said combination of documents, wherein each of the composite novelty score scores represents a likelihood that a merging of solutions in two or more documents in a corresponding combination will provide a novel solution;

determining a composite proximity score for each of said combination of documents, wherein each of the composite proximity scores represents a proximity of each of said documents to the one or more ontologies;

determining a composite impact score for each of said combination of documents, wherein each of the composite impact scores represent a feasibility of combining the solutions which are disclosed in said two or more documents; and

based on the determined composite novelty scores, the determined composite proximity scores, and the determined impact scores, providing a recommendation which can assist related to generating an innovation,

wherein providing the recommendation includes presenting a solution template S_xy in which respective solutions in a selected combination of documents are merged to provide a new solution which differs from the respective solutions in the selected combination of documents, and

wherein providing said recommendation further includes at least one of;

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

providing a second recommendation of one or more other documents, each of which disclose a solution which is compatible for integration with the solution disclosed in at least one of said two or more documents in the selected combination, if the determined composite impact score for the selected combination 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 in the selected combination, if at least one of the determined composite proximity score or the determined composite impact score for the selected combination is below a predefined minimum threshold value.