Dynamic modification of information presentation and linkage based on usage patterns and sentiments

1. An apparatus comprising:

at least one processing platform comprising a plurality of processing devices comprising one or more processors coupled to one or more memories;

said at least one processing platform being configured to:

define a machine learning model corresponding to a plurality of layouts for content based on a plurality of target user types;

process the content to identify a theme of the content;

generate at least one electronic document for the content based on the theme of the content and at least one of the plurality layouts for the content;

analyze a plurality of interactions of at least one user with the electronic document, wherein the plurality of interactions include at least one of one or more searches performed by the at least one user to retrieve the electronic document, and one or more steps taken by the at least one user to consume the content in the electronic document;

identify at least one pattern of the at least one user corresponding to at least one of the retrieval and the consumption of the content based on the analyzing;

train the machine learning model based on the at least one pattern by applying one or more machine learning algorithms to data from the plurality of interactions; and

dynamically modify the electronic document based on the training;

wherein in dynamically modifying the electronic document, said at least one processing platform is configured to modify a table of contents of the electronic document based on a determination of whether or not the table of contents enables the at least one user to navigate to the content;

wherein, in defining the machine learning model, said at least one processing platform is configured to:

periodically generate a guidance model for the content based on data being consumed by a plurality of users against a plurality of search key phrases and a plurality of search keywords used by the plurality of users; and

measure performance of the periodically generated guidance model against a secondary guidance model including a plurality of rules for the plurality of the layouts, wherein the plurality of the rules correspond to respective ones of the plurality of target user types;

wherein in analyzing the plurality of interactions of the at least one user with the electronic document, said at least one processing platform is configured to:

monitor and identify accessing by the at least one user of one or more parts of the table of contents; and

record an electronic path followed by the at least one user after accessing the one or more parts of the table of contents; and

wherein the training of the machine learning model and the modifying of the table of contents are based at least in part on the recorded electronic path.

2. The apparatus of claim 1 wherein said at least one processing platform is further configured to implement a content optimizer, wherein the content optimizer validates one or more parameters being used in connection with the content.

3. The apparatus of claim 2 wherein the content optimizer comprises a format checker configured to analyze the content and identify different types of source files and output files in use in connection with the content.

4. The apparatus of claim 3 wherein the format checker is further configured to confirm whether the identified different types of source files and output files are available for a specific set of documents associated with the content.

5. The apparatus of claim 2 wherein content optimizer removes at least one of redundant and injected information from the content.

6. The apparatus of claim 2 wherein the content optimizer comprises a link engine configured to verify whether hyperlinks to different sources within or from the content are correct.

7. The apparatus of claim 2 wherein the content optimizer comprises a link engine configured to generate customized hyperlinks across electronic documents based on at least one of the trained machine learning model and a thematic structure of a product associated with the content.

8. The apparatus of claim 1 wherein in processing the content to identify the theme of the content, said at least one processing platform is configured to extract from the content one or more elements from which the theme can be identified.

9. The apparatus of claim 8 wherein the one or more elements comprise at least one of an image, a table, a statement, a numeric combination, and an expressed sentiment.

10. The apparatus of claim 1 wherein in processing the content to identify the theme of the content, said at least one processing platform is configured to identify at least one of one or more keywords and one or more key phrases in the content.

11. The apparatus of claim 1 wherein in analyzing the plurality of interactions of the at least one user with the electronic document, said at least one processing platform is further configured to monitor and identify one or more keywords or key phrases used by the at least one user in connection with the one or more searches.

12. The apparatus of claim 11 wherein in training the machine learning model, said at least one processing platform is configured to dynamically map the one or more keywords or key phrases used by the at least one user to the content in the electronic document being consumed by the at least one user.

13. The apparatus of claim 1 wherein in analyzing the plurality of interactions of at least one user with the electronic document, said at least one processing platform is further configured to monitor and identify an amount of time the at least one user spends on one or more portions of the electronic document.

14. The apparatus of claim 1 wherein said at least one processing platform is further configured to define a new target user type in addition to the plurality of target user types based on the training.

15. The apparatus of claim 14 wherein said at least one processing platform is further configured to define a new layout in addition to the plurality of layouts based on the new target user type.

16. A method comprising:

defining a machine learning model corresponding to a plurality of layouts for content based on a plurality of target user types;

processing the content to identify a theme of the content;

generating at least one electronic document for the content based on the theme of the content and at least one of the plurality layouts for the content;

analyzing a plurality of interactions of at least one user with the electronic document, wherein the plurality of interactions include at least one of one or more searches performed by the at least one user to retrieve the electronic document, and one or more steps taken by the at least one user to consume the content in the electronic document;

identifying at least one pattern of the at least one user corresponding to at least one of the retrieval and the consumption of the content based on the analyzing;

training the machine learning model based on the at least one pattern by applying one or more machine learning algorithms to data from the plurality of interactions; and

dynamically modifying the electronic document based on the training;

wherein the dynamically modifying of the electronic document comprises modifying a table of contents of the electronic document based on a determination of whether or not the table of contents enables the at least one user to navigate to the content;

wherein the defining of the machine learning model comprises:

periodically generating a guidance model for the content based on data being consumed by a plurality of users against a plurality of search key phrases and search keywords used by the plurality of users; and

measuring performance of the periodically generated guidance model against a secondary guidance model including a plurality of rules for the plurality of the layouts, wherein the plurality of the rules correspond to respective ones of the plurality of target user types;

wherein the analyzing of the plurality of interactions of the at least one user with the electronic document comprises:

monitoring and identifying accessing by the at least one user of one or more parts of the table of contents; and

recording an electronic path followed by the at least one user after accessing the one or more parts of the table of contents;

wherein the training of the machine learning model and the modifying of the table of contents are based at least in part on the recorded electronic path; and

wherein the method is performed by at least one processing platform comprising at least one processing device comprising a processor coupled to a memory.

17. The method of claim 16 further comprising implementing a content optimizer, wherein the content optimizer validates one or more parameters being used in connection with the content.

18. A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing platform causes said at least one processing platform to:

define a machine learning model corresponding to a plurality of layouts for content based on a plurality of target user types;

process the content to identify a theme of the content;

generate at least one electronic document for the content based on the theme of the content and at least one of the plurality layouts for the content;

analyze a plurality of interactions of at least one user with the electronic document, wherein the plurality of interactions include at least one of one or more searches performed by the at least one user to retrieve the electronic document, and one or more steps taken by the at least one user to consume the content in the electronic document;

identify at least one pattern of the at least one user corresponding to at least one of the retrieval and the consumption of the content based on the analyzing; and

train the machine learning model based on the at least one pattern by applying one or more machine learning algorithms to data from the plurality of interactions; and

dynamically modify the electronic document based on the training;

wherein in dynamically modifying the electronic document, the program code when executed by said at least one processing platform causes said at least one processing platform to modify a table of contents of the electronic document based on a determination of whether or not the table of contents enables the at least one user to navigate to the content;

wherein in defining the machine learning model, the program code when executed by said at least one processing platform causes said at least one processing platform to:

periodically generate a guidance model for the content based on data being consumed by a plurality of users against a plurality of search key phrases and search keywords used by the plurality of users; and

measure performance of the periodically generated guidance model against a secondary guidance model including a plurality of rules for the plurality of the layouts, wherein the plurality of the rules correspond to respective ones of the plurality of target user types;

wherein in analyzing the plurality of interactions of the at least one user with the electronic document, the program code when executed by said at least one processing platform causes said at least one processing platform to:

monitor and identify accessing by the at least one user of one or more parts of the table of contents; and

record an electronic path followed by the at least one user after accessing the one or more parts of the table of contents; and

wherein the training of the machine learning model and the modifying of the table of contents are based at least in part on the recorded electronic path.

19. The computer program product of claim 18 wherein the program code when executed by said at least one processing platform further causes said at least one processing platform to implement a content optimizer, wherein the content optimizer validates one or more parameters being used in connection with the content.

20. The computer program product of claim 19 wherein the content optimizer comprises a format checker configured to analyze the content and identify different types of source files and output files in use in connection with the content.