System and method of extraction of information and graphical representation for design of formulated products

1. A implemented method of extracting an information associated with design of formulated products and representing as a graph, comprising:

(a) receiving, via one or more hardware processors, a graph domain model of a plurality of vertices as an input;

(b) receiving, via the one or more hardware processors, at least one formulation text as at least one text file;

(c) applying, via the one or more hardware processors, information extraction, to identify at least one sentence and extract at least one subject-verb-object triple from every sentence of the at least one formulation text ,wherein information is processed to obtain a heat map of a plurality of count of co-occurrences from one or more formulations, wherein a zero value indicates two ingredients do not occur together in one or more formulations, a positive value indicates a total count of the co-occurrences of the two ingredients in a same phase, and a negative value indicates a total count of the co-occurrences in a same formulation and in a different phase ;

(d) classifying, via the one or more hardware processors, at least one of: (i) sentences comprising an ingredient listing and associated weights indicated by presence of weight numerals, and (ii) sentences comprising at least one verb from the at least one subject-verb-object based on the graph domain model;

(e) generating, via the one or more hardware processors, a representation of the recipe text based on the at least one sentence which is classified in terms of at least one action (A), mixtures (M) on which the at least one action is performed, and at least one condition (C);

(f) generating, via the one or more hardware processors, an insert query string from the generated representation based on the graph domain model; and

(g) executing, via the one or more hardware processors, the generated insert query string to store the formulations as the graph.

2. The processor implemented method as claimed in claim 1 , wherein the plurality of vertices corresponds to at least one of: (i) a formulation type, (ii) a formulation category, (iii) a formulation ingredient, (iv) a mixture, (v) the recipe text, (vi) an action, (vii) a condition, and combination thereof.

3. The processor implemented method as claimed in claim 1 , further comprising, segregating, via the one or more hardware processors, at least one of: (i) a name, (ii) an ingredient list, and (iii) the recipe text from the at least one formulation text based on a predefined list of verbs and at least one mixture indicator.

4. The processor implemented method as claimed in claim 1 , wherein the at least one verb from the predefined list of verbs to separate the ingredient listing from the recipe text, wherein the at least one action corresponds to the at least one verb from the predefined list of verbs.

5. The processor implemented method as claimed in claim 1 , wherein the recipe text is extracted by creating plurality of dictionary of verbs that are representative of actions performed on the ingredients and the mixtures.

6. A system to extract an information associated with design of formulated products and representation as a graph, comprising:

a memory storing instructions;

one or more communication interfaces; and

one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to:

(a) receive, a graph domain model of a plurality of vertices as an input;

(b) receive, at least one formulation text as at least one text file;

(c) apply, information extraction, to identify at least one sentence and extract at least one subject-verb-object triple from every sentence of the at least one formulation text ,wherein information is processed to obtain a heat map of a plurality of count of co-occurrences from one or more formulations, wherein a zero value indicates two ingredients do not occur together in one or more formulations, a positive value indicates a total count of the co-occurrences of the two ingredients in a same phase, and a negative value indicates a total count of the co-occurrences in a same formulation and in a different phase;

(d) classify, at least one of: (i) sentences comprising an ingredient listing and associated weights indicated by presence of weight numerals, and (ii) sentences comprising at least one verb from the at least one subject-verb-object based on the graph domain model;

(e) generate, a representation of the recipe text based on the at least one sentence which is classified in terms of at least one action (A), mixtures (M) on which the at least one action is performed, and at least one condition (C);

(f) generate, an insert query string from the generated representation based on the graph domain model; and

(g) execute, the generated insert query string to store the formulations as the graph.

7. The system as claimed in claim 6 , wherein the plurality of vertices corresponds to at least one of: (i) a formulation type, (ii) a formulation category, (iii) a formulation ingredient, (iv) a mixture, (v) the recipe text, (vi) an action, (vii) a condition, and combination thereof.

8. The system as claimed in claim 6 , wherein the one or more hardware processors ( 104 ) are further configured by the instructions to: segregate at least one of: (i) a name, (ii) an ingredient list, and (iii) the recipe text from the at least one formulation text based on a predefined list of verbs and at least one mixture indicator.

9. The system as claimed in claim 6 , wherein the at least one verb from the predefined list of verbs to separate the ingredient listing from the recipe text, wherein the at least one action corresponds to the at least one verb from the predefined list of verbs.

10. The system as claimed in claim 6 , wherein the recipe text is extracted by creating plurality of dictionary of verbs that are representative of actions performed on the ingredients and the mixtures.

11. One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors perform actions comprising:

(a) receiving, a graph domain model of a plurality of vertices as an input;

(b) receiving, at least one formulation text as at least one text file;

(c) applying, information extraction, to identify at least one sentence and extract at least one subject-verb-object triple from every sentence of the at least one formulation text, wherein information is processed to obtain a heat map of a plurality of count of co-occurrences from one or more formulations, wherein a zero value indicates two ingredients do not occur together in one or more formulations, a positive value indicates a total count of the co-occurrences of the two ingredients in a same phase, and a negative value indicates a total count of the co-occurrences in a same formulation and in a different phase;

(d) classifying, at least one of: (i) sentences comprising an ingredient listing and associated weights indicated by presence of weight numerals, and (ii) sentences comprising at least one verb from the at least one subject-verb-object based on the graph domain model;

(e) generating, a representation of the recipe text based on the at least one sentence which is classified in terms of at least one action (A), mixtures (M) on which the at least one action is performed, and at least one condition (C);

(f) generating, an insert query string from the generated representation based on the graph domain model; and

(g) executing, the generated insert query string to store the formulations as the graph.

12. The one or more non-transitory machine-readable information storage mediums of claim 11 , wherein the plurality of vertices corresponds to at least one of: (i) a formulation type, (ii) a formulation category, (iii) a formulation ingredient, (iv) a mixture, (v) the recipe text, (vi) an action, (vii) a condition, and combination thereof.

13. The one or more non-transitory machine-readable information storage mediums of claim 11 , wherein the step of extracting an information associated with design of formulated products comprises segregating, at least one of: (i) a name, (ii) an ingredient list, and (iii) the recipe text from the at least one formulation text based on a predefined list of verbs and at least one mixture indicator.

14. The one or more non-transitory machine-readable information storage mediums of claim 11 , wherein the at least one verb from the predefined list of verbs to separate the ingredient listing from the recipe text, wherein the at least one action corresponds to the at least one verb from the predefined list of verbs.

15. The one or more non-transitory machine-readable information storage mediums of claim 11 , wherein the recipe text is extracted by creating plurality of dictionary of verbs that are representative of actions performed on the ingredients and the mixtures.