Systems and methods for performing a computer-implemented prior art search

1. A computer-implemented method for retrieving a similar document from a corpus of documents, the method comprising:

receiving a search document, the search document comprising a set of words;

applying a first encoder to the set of words to generate a first vector;

applying a second encoder to the set of words to generate a second vector;

determining a first similarity between the first vector of the search document and the first vector of each document of the corpus of documents;

determining a second similarity between the second vector of the search document and the second vector of each document of the corpus of documents;

generating a first ranked list of documents in the corpus based on the first similarity;

generating a second ranked list of documents in the corpus based on the second similarity;

applying a voting algorithm to determine a score associated with each document based on a position of each document in its relative ranked list; and

outputting a third ranked list of documents based on the determined score.

2. The method of claim 1 , further comprising:

applying a model to the set of words of the search document to generate one or more tags associated with the search document.

3. The method of claim 2 , further comprising:

based on the one or more tags, updating a node-edge graph associated with the corpus of documents with the search document; and

generate a ranked list of documents sharing an edge with the search document.

4. The method of claim 3 , wherein the score is based, in part, on the node-edge graph.

5. The method of claim 1 , wherein the first encoder comprises a neural network encoder.

6. The method of claim 1 , wherein applying the second encoder comprises parsing the set of words and removing occurrences of a stop word from the set of words, thereby generating a subset of words.

7. The method of claim 6 , further comprising:

determining the number of times each of the subset of words appears in the subset of words; and

determining a rarity of each of the subset of words.

8. The method of claim 7 , wherein the rarity comprises a number of times a word appears in the search document compared to a number of times the word appears in the corpus of documents.

9. The method of claim 1 , further comprising:

receiving a filtering rule comprising a condition;

filtering the third ranked list based on the condition; and

outputting a fourth ranked list.

10. A computer program product comprising a non-transitory computer readable medium having a computer readable program embodied therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:

receive a search document, the search document comprising a set of words;

apply a first encoder to the set of words to generate a first vector;

apply a second encoder to the set of words to generate a second vector;

determine a first similarity between the first vector of the search document and the first vector of each document of the corpus of documents;

determine a second similarity between the second vector of the search document and the second vector of each document of the corpus of documents;

generate a first ranked list of documents in the corpus based on the first similarity;

generate a second ranked list of documents in the corpus based on the second similarity;

apply a voting algorithm to determine a score associated with each document based on a position of each document in its relative ranked list; and

output a third ranked list of documents based on the determined score.

11. The computer-readable medium of claim 10 , wherein the program further causes the computing device to:

apply the first encoder using a semantic vector module comprising a deep learning encoder;

apply the second encoder using a syntactic module configured to: determine a number of times each of the set of words appears in the search document,

determine a number of times each of the set of words appears in the corpus of documents, and

generate the second vector representing a comparison of the number of times each word appears in the document to the number of times each word appears in the corpus of documents; and

apply a knowledge graph module configured to update a knowledge graph with a node comprising the search document.