Skill acquisition platform

1. A method, comprising:

receiving, by a device, input identifying a target skillset for a user;

generating, by the device, based on a knowledge graph, comprising current skillset data associated with a plurality of users different from the user, and using a machine learning model for relational learning on the knowledge graph, a plurality of embedded vectors, for the knowledge graph, associated with one or more career parameters associated with the plurality of users;

determining, by the device, a similarity score between each embedded vector, of the plurality of embedded vectors, and the target skillset;

clustering, by the device and based on determining the similarity score, the plurality of embedded vectors to generate a plurality of skill groups associated with the plurality of embedded vectors;

generating, by the device, a directed network graph representing one or more links between the plurality of skill groups, wherein the links between the plurality of skill groups represent moves between the plurality of skill groups taken by one or more users including the user;

identifying, by the device and in the directed network graph, one or more paths from a current skillset, associated with the user, and the target skillset, wherein each path, of the one or more or more paths, includes at least one link, of the one or more links, and represents a particular set of embedded vectors, of the plurality of embedded vectors, that the user adds to a career representation associated with the user in order to obtain or qualify for the target skillset;

determining, by the device, weighted scores for edges in the directed network graph based on a sequence of at least a subset of the plurality of embedded vectors and based on the plurality of skill groups; and

identifying, by the device, one or more optimum paths, of the one or more optimum paths, for the user between the current skillset and the target skillset based on the weighted scores.

2. The method of claim 1 , further comprising:

generating the knowledge graph on a data set that includes resume data from the plurality of users; and

generating, based on the plurality of embedded vectors, a respective career representation for each of the plurality of users.

3. The method of claim 1 , further comprising:

receiving the current skillset data; and

creating the knowledge graph based on the current skillset data.

4. The method of claim 1 , further comprising:

determining the one or more career parameters based on the input identifying the target skillset.

5. The method of claim 1 , further comprising:

automatically generating a descriptive analysis of the one or more optimum paths,

wherein the descriptive analysis of the one or more optimum paths identifies at least one of:

a graphical representation of the one or more optimum paths,

an estimated path length for each of the one or more optimum paths,

one or more links of statistical interest included in the one or more optimum paths,

an estimated difficulty of each of the one or more optimum paths, or

a frequency of occurrence of each of the one or more optimum paths.

6. The method of claim 1 , further comprising:

generating the one or more optimum paths using at least one of:

Dijkstra's algorithm, or

a breadth-first search.

7. A skill acquisition platform, comprising:

one or more memories; and

one or more processors, coupled to the one or more memories, configured to:

identify a target skillset for a user;

generate, based on a knowledge graph, comprising current skillset data associated with a plurality of users different from the user, and using a machine learning model for relational learning on the knowledge graph, a plurality of embedded vectors, for the knowledge graph, associated with one or more career parameters associated with the plurality of users;

determine a similarity score between each embedded vector, of the plurality of embedded vectors, and the target skillset;

cluster, based on determining the similarity score, the plurality of embedded vectors to generate a plurality of skill groups associated with the plurality of embedded vectors;

generate a directed network graph representing one or more links between the plurality of skill groups, wherein the links between the plurality of skill groups represent moves between the plurality of skill groups taken by one or more users including the user;

identify, in the directed network graph, one or more paths from a current skillset, associated with the user, and the target skillset, wherein each path, of the one or more or more paths, includes at least one link, of the one or more links, and represents a particular set of embedded vectors, of the plurality of embedded vectors, that the user adds to a career representation associated with the user in order to obtain or qualify for the target skillset;

determine weighted scores for edges in the directed network graph based on a sequence of at least a subset of the plurality of embedded vectors and based on the plurality of skill groups; and

identify one or more optimum paths, of the one or more optimum paths, for the user between the current skillset and the target skillset based on the weighted scores.

8. The skill acquisition platform of claim 7 , wherein the one or more processors, to determine the similarity score, are configured to:

determine embedded vector distances between each set of the plurality of embedded vectors;

perform a summation of the embedded vector distances; and

divide the summation by a quantity of the embedded vector distances to determine the similarity score.

9. The skill acquisition platform of claim 7 , wherein the one or more processors are further configured to:

receive the current skillset data; and

create the knowledge graph based on the current skillset data.

10. The skill acquisition platform of claim 7 , wherein the one or more processors are further configured to:

generate a descriptive analysis of the one or more optimum paths that identifies at least one of:

a graphical representation of the one or more optimum paths,

an estimated path length for each of the one or more optimum paths,

one or more links of statistical interest included in the one or more optimum paths,

an estimated difficulty of each of the one or more optimum paths, or

a frequency of occurrence of each of the one or more optimum paths.

11. The skill acquisition platform of claim 7 , wherein the one or more processors are further configured to at least one of:

automatically enroll the user in a class to obtain a skill included in the one or more optimum paths,

automatically identify one or more job postings associated with a role included in the one or more optimum paths,

automatically transmit, to a user device associated with the user, an instruction to display the class or the one or more job postings, or

automatically transmit, to the user device, an instruction to display a visual representation of the one or more optimum paths.

12. The skill acquisition platform of claim 7 , wherein at least one of the plurality of embeddings relates to:

a user embedded vector,

a skill embedded vector,

an experience embedded vector,

an industry embedded vector,

an education embedded vector, or

a certification embedded vector.

13. The skill acquisition platform of claim 7 , wherein the one or more processors are further configured to:

generate the one or more optimum paths using at least one of:

Dijkstra's algorithm, or

a breadth-first search.

14. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors to:

generate, based on a knowledge graph, comprising current skillset data associated with a plurality of users, and using a machine learning model for relational learning on the knowledge graph, a plurality of embedded vectors, for the knowledge graph, associated with one or more career parameters associated with the plurality of users;

determine a similarity score between each embedded vector, of the plurality of embedded vectors, and a target skillset for a user different from the plurality of users;

cluster, based on determining the similarity score, the plurality of embedded vectors to generate a plurality of skill groups associated with the plurality of embedded vectors;

generate a directed network graph representing one or more links between the plurality of skill groups, wherein the links between the plurality of skill groups represent moves between the plurality of skill groups taken by one or more users including the user;

identify, in the directed network graph, one or more paths from a current skillset, associated with the user, and the target skillset, wherein each path, of the one or more or more paths, includes at least one link, of the one or more links, and represents a particular set of embedded vectors, of the plurality of embedded vectors, that the user adds to a career representation associated with the user in order to obtain or qualify for the target skillset;

determine weighted scores for edges in the directed network graph based on a sequence of at least a subset of the plurality of embedded vectors and based on the plurality of skill groups;

identify one or more optimum paths, of the one or more optimum paths, for the user between the current skillset and the target skillset based on the weighted scores; and

automatically generate a descriptive analysis of the one or more optimal paths that identifies at least one of:

a graphical representation of the one or more optimal paths,

an estimated path length for each of the one or more optimal paths,

one or more links of statistical interest included in the one or more optimal paths,

an estimated difficulty of each of the one or more optimal paths, or

a frequency of occurrence of each of the one or more optimal paths.

15. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, that cause the one or more processors to determine the similarity score, cause the one or more processors to:

determine embedded vector distances between each set of the plurality of embedded vectors;

perform a summation of the embedded vector distances; and

divide the summation by a quantity of the plurality of embedded vectors to determine the similarity score.

16. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

receive the current skillset data; and

create the knowledge graph based on the current skillset data.

17. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

determine the one or more career parameters based on the target skillset.

18. The non-transitory computer-readable medium of claim 14 , wherein at least one of the plurality of embedded vectors relates to:

a user embedded vector,

a skill embedded vector,

an experience embedded vector,

an industry embedded vector,

an education embedded vector, or

a certification embedded vector.

19. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

generate a career representation for each of the plurality of users based on one or more corresponding embeddings of the plurality of embedding vectors.