Assessment of documents related to drug discovery

1. A system configured to determine an assessment value of a document, the document being related to a current research work of one or more researchers, the system comprising a server arrangement comprising a processor communicably coupled via a data communication network with a client device, wherein the processor of the server arrangement is configured to execute machine readable instructions that cause the server arrangement to:

obtain, from the client device, information pertaining to the document, and process the information pertaining to the document, at the client device, to identify a technical field of the current research work and to identify entities and semantic inter-relationships specific to the current research work, wherein the information pertaining to the document comprises at least one of: an abstract of the document, a hypothesis of the current research work, a brief note provided as an input by a user, or any set of information, which is indicative of entities and semantic inter-relationships between the entities as mentioned in the document;

generate a current-work graph representing the entities and the semantic inter-relationships specific to the current research work;

access information indicative of entities and semantic inter-relationships specific to a previous research work of at least one of the one or more researchers;

generate a previous-work graph representing the entities and the semantic inter-relationships specific to the previous research work, based upon the information indicative of the entities and the semantic inter-relationships specific to the previous research work of the at least one of the one or more researchers;

compare the entities and the semantic inter-relationships specific to the current research work with the information indicative of entities and the semantic inter-relationships specific to the previous research work by unifying the current-work graph and the previous-work graph into a unified graph to determine an association factor indicative of one or more of: an existence of and/or an extent of an association between the current research work and the previous research work of the one or more researchers;

access information indicative of entities and semantic inter-relationships related to the technical field of the current research work;

generate a knowledge graph representing the entities and the semantic inter-relationships related to the technical field of the current research work, based upon the information indicative of the entities and the semantic inter-relationships related to the technical field of the current research work;

compare the entities and the semantic inter-relationships specific to the current research work with the entities and the semantic inter-relationships related to the technical field to determine a status factor associated with the document by employing a link prediction technique, wherein the status factor is a measure of an actual contribution of the current research work of the one or more researchers to the knowledge available publicly, including information that is being contributed and conveyed by the document, and wherein the status factor is determined by calculating a probability of the current research work given the knowledge available publicly;

determine the assessment value of the document, based at least upon the association factor and the status factor, wherein the assessment value is determined using a neural network, and wherein labeled training data is employed to train the neural network;

access assessment values of a plurality of documents related to the technical field of the current research work; and

sort the document and the plurality of documents based on the determined assessment value of the document and the accessed assessment values of the other documents.

2. The system of claim 1 , wherein the processor of the server arrangement is configured to execute machine readable instructions that cause the server arrangement to determine a confidence score associated with the assessment value of the document to validate an accuracy of the assessment value.

3. The system of claim 1 , wherein the processor of the server arrangement is configured to execute machine readable instructions that cause the server arrangement to determine the assessment value of the document using at least one of: a statistical analysis, machine learning, or a rule-based analysis.

4. The system of claim 1 , wherein the processor of the server arrangement is configured to execute machine readable instructions that cause the server arrangement to:

obtain, from the client device or from at least one database server, information about the one or more researchers;

process the information about the one or more researchers to determine a reputation factor associated with the document; and

determine the assessment value of the document, based upon the reputation factor.

5. The system of claim 1 , wherein the processor of the server arrangement is configured to execute machine readable instructions that cause the server arrangement to:

obtain, from the client device, information pertaining to cost incurred in the current research work of the one or more researchers;

process the information pertaining to the cost to determine a cost factor associated with the document; and

determine the assessment value of the document, based upon the cost factor.

6. The system of claim 1 , wherein the processor of the server arrangement is configured to execute machine readable instructions that cause the server arrangement to:

obtain, from the client device, information about a statistical significance of the current research work and information about a research organization where the current research work has been performed;

process the information about the statistical significance, whilst taking into account a rank of the research organization, to determine a statistical-significance factor associated with the document; and

determine the assessment value of the document, based upon the statistical-significance factor.

7. The system of claim 1 , wherein the processor of the server arrangement is configured to execute machine readable instructions that cause the server arrangement to:

obtain, from a plurality of database servers, a plurality of documents pertaining to the technical field of the current research work;

process the plurality of documents to identify the entities and the semantic inter-relationships related to the technical field; and

store the information indicative of the entities and the semantic inter-relationships related to the technical field.

8. The system of claim 7 , wherein the processor of the server arrangement is configured to execute machine readable instructions that cause the server arrangement to assign weights to the semantic inter-relationships related to the technical field, based upon at least one of: types of causal relationships represented by the semantic inter-relationships between the entities, the number of documents in which the semantic inter-relationships occurred, ranks of digital libraries where the documents were published.

9. The system of claim 8 , wherein the processor of the server arrangement is configured to execute machine readable instructions that cause the server arrangement to assign weights to the semantic inter-relationships specific to the current research work, based upon the weights of the semantic inter-relationships related to the technical field.

10. The system of claim 1 , wherein the processor of the server arrangement is configured to execute machine readable instructions that cause the server arrangement to:

obtain, from a plurality of database servers, other documents authored by the at least one of the one or more researchers;

process the other documents to identify the entities and the semantic inter-relationships specific to the previous research work; and

store the information indicative of the entities and the semantic inter-relationships specific to the previous research work.

11. The system of claim 10 , wherein the processor of the server arrangement is configured to execute machine readable instructions that cause the server arrangement to assign weights to the semantic inter-relationships specific to the previous research work, based upon at least one of: types of causal relationships represented by the semantic inter-relationships between the entities, the number of documents authored by the at least one of the one or more researchers in which the semantic inter-relationships occurred, ranks of digital libraries where the documents were published.

12. The system of claim 1 , wherein the technical field of the document is related to drug discovery.

13. The system of claim 1 , wherein the assessment value is in a crypto-currency for enabling future transactions of the document using a blockchain.

14. The system according to claim 1 , wherein the server arrangement is configured to use the determined assessment value to price the document when making the document available for sale.

15. The system according to claim 1 further comprising the server arrangement being configured to enable a sorting of different documents based on the determined assessment value.

16. A method of determining an assessment value of a document, the document being related to a current research work of one or more researchers, the method being implemented via a computer system, the computer system comprising a server arrangement comprising a processor communicably coupled via a data communication network with a client device, the method comprising:

obtaining, from the client device, information pertaining to the document, and processing the information pertaining to the document, at the client device, to identify a technical field of the current research work and to identify entities and semantic inter-relationships specific to the current research work, wherein the information pertaining to the document comprises at least one of: an abstract of the document, a hypothesis of the current research work, a brief note provided as an input by a user, or any set of information, which is indicative of entities and semantic inter-relationships between the entities as mentioned in the document;

generating a current-work graph representing the entities and the semantic inter-relationships specific to the current research work;

accessing information indicative of entities and semantic inter-relationships specific to a previous research work of at least one of the one or more researchers;

generating a previous-work graph representing the entities and the semantic inter-relationships specific to the previous research work, based upon the information indicative of the entities and the semantic inter-relationships specific to the previous research work of the at least one of the one or more researchers,

comparing the entities and the semantic inter-relationships specific to the current research work with the information indicative of entities and the semantic inter-relationships specific to the previous research work by unifying the current-work graph and the previous-work graph into a unified graph to determine an association factor indicative of one or more of: an existence of and/or an extent of an association between the current research work and the previous research work of the one or more researchers;

accessing information indicative of entities and semantic inter-relationships related to the technical field of the current research work;

generating a knowledge graph representing the entities and the semantic inter-relationships related to the technical field of the current research work, based upon the information indicative of the entities and the semantic inter-relationships related to the technical field of the current research work; and

comparing the entities and the semantic inter-relationships specific to the current research work with the entities and the semantic inter-relationships related to the technical field to determine a status factor associated with the document by employing a link prediction technique, wherein the status factor is measure of an actual contribution of the current research work of the one or more researchers to the knowledge available publicly, including information that is being contributed and conveyed by the document, and wherein the status factor is determined by calculating a probability of the current research work given the knowledge available publicly;

determining the assessment value of the document, based at least upon the association factor and the status factor, wherein the assessment value is determined using a neural network, and wherein labeled training data is employed to train the neural network;

accessing assessment values of plurality of documents related to the technical field of the current research work; and

sorting different the documents and the plurality of documents based on the determined assessment value of the document and the accessed assessment values of the other documents.

17. The method of claim 16 , further comprising determining a confidence score associated with the assessment value of the document to validate an accuracy of the assessment value.

18. The method of claim 16 , further comprising:

obtaining, from the client device or from at least one database server, information about the one or more researchers; and

processing the information about the one or more researchers to determine a reputation factor associated with the document, wherein the step of determining the assessment value is performed based upon the reputation factor.

19. The method of claim 16 , further comprising:

obtaining, from the client device, information pertaining to cost incurred in the current research work of the one or more researchers; and

processing the information pertaining to the cost to determine a cost factor associated with the document,

wherein the step of determining the assessment value is performed based upon the cost factor.

20. The method of claim 16 , further comprising:

obtaining, from the client device, information about a statistical significance of the current research work and information about a research organization where the current research work has been performed; and

processing the information about the statistical significance, whilst taking into account a rank of the research organization, to determine a statistical-significance factor associated with the document, wherein the step of determining the assessment value is performed based upon the statistical-significance factor.

21. The method of claim 16 , further comprising:

obtaining, from a plurality of database servers, a plurality of documents pertaining to the technical field of the current research work;

processing the plurality of documents to identify the entities and the semantic inter-relationships related to the technical field; and

storing the information indicative of the entities and the semantic inter-relationships related to the technical field.

22. The method of claim 21 , further comprising assigning weights to the semantic inter-relationships related to the technical field, based upon at least one of: types of causal relationships represented by the semantic inter-relationships between the entities, the number of documents in which the semantic inter-relationships occurred, ranks of digital libraries where the documents were published.

23. The method of claim 22 , further comprising assigning weights to the semantic inter-relationships specific to the current research work, based upon the weights of the semantic inter-relationships related to the technical field.

24. The method of claim 16 , further comprising:

obtaining, from a plurality of database servers, other documents authored by the at least one of the one or more researchers;

processing the other documents to identify the entities and the semantic inter-relationships specific to the previous research work; and

storing the information indicative of the entities and the semantic inter-relationships specific to the previous research work.

25. The method of claim 24 , further comprising assigning weights to the semantic inter-relationships specific to the previous research work, based upon at least one of: types of causal relationships represented by the semantic inter-relationships between the entities, the number of documents authored by the at least one of the one or more researchers in which the semantic inter-relationships occurred, ranks of digital libraries where the documents were published.

26. A computer program product for determining an assessment value of a document, wherein the document is related to a current research work of one or more researchers, the computer program product comprising a non-transitory machine-readable data storage medium having stored thereon program instructions that, when accessed by a processing device, cause the processing device to:

obtain information pertaining to the document, and process the information pertaining to the document, at the client device, to identify a technical field of the current research work and to identify entities and semantic inter-relationships specific to the current research work, wherein the information pertaining to the document comprises at least one of: an abstract of the document, a hypothesis of the current research work, a brief note provided as an input by a user, or any set of information, which is indicative of entities and semantic inter-relationships between the entities as mentioned in the document;

generate a current-work graph representing the entities and the semantic inter-relationships specific to the current research work;

access information indicative of entities and semantic inter-relationships specific to a previous research work of at least one of the one or more researchers;

generate a previous-work graph representing the entities and the semantic inter-relationships specific to the previous research work, based upon the information indicative of the entities and the semantic inter-relationships specific to the previous research work of the at least one of the one or more researchers;

compare the entities and the semantic inter-relationships specific to the current research work with the information indicative of entities and the semantic inter-relationships specific to the previous research work by unifying the current-work graph and the previous-work graph into a unified graph to determine an association factor indicative of one or more of: an existence of and/or an extent of association between the current research work and the previous research work of the one or more researchers;

access information indicative of entities and semantic inter-relationships related to the technical field of the current research work;

generate a knowledge graph representing the entities and the semantic inter-relationships related to the technical field of the current research work, based upon the information indicative of the entities and the semantic inter-relationships related to the technical field of the current research work;

compare the entities and the semantic inter-relationships specific to the current research work with the information indicative of entities and the semantic inter-relationships related to the technical field to determine a status factor associated with the document by employing a link prediction technique, wherein the status factor is a measure of an actual contribution of the current research work of the one or more researchers to the knowledge available publicly, including information that is being contributed and conveyed by the document, and wherein the status factor is determined by calculating a probability of the current research work given the knowledge available publicly;

determine the assessment value of the document, based at least upon the association factor and the status factor, wherein the assessment value is determined using a neural network, and wherein labeled training data is employed to train the neural network;

access assessment values of a plurality of documents related to the technical field of the current research work; and

sort the document and the plurality of different documents based on the determined assessment value of the document and the accessed assessment values of the other documents.