Locality Sensitive Hashing to Generate N-dimensional Vectors of Risks and Conduct Risk Analysis

20240161038

18/054774

November 11, 2022

Systems, apparatuses and methods provide technology that identifies first characteristics of a first risk associated with a system and applies a locality sensitive hashing process to the first characteristics to map the first characteristics to first buckets of a plurality of buckets. The technology further generates a first vector based on the first characteristics being mapped to the first buckets, and identifies a mitigation plan to at least partially mitigate the first risk based on the first vector.

Meta Platforms, Inc. (Menlo Park, CA, US)

1. At least one computer readable storage medium comprising a set of instructions, which when executed by a computing device, cause the computing device to: identify first characteristics of a first risk associated with a system; apply a locality sensitive hashing process to the first characteristics to map the first characteristics to first buckets of a plurality of buckets; generate a first vector based on the first characteristics being mapped to the first buckets; and identify a mitigation plan to at least partially mitigate the first risk based on the first vector.

2. The at least one computer readable storage medium of claim 1, wherein the instructions, when executed, cause the computing device to: apply a locality sensitive hashing process to second characteristics of a second risk to map the second characteristics to second buckets of the plurality of buckets; generate a second vector based on the second characteristics being mapped to the second buckets; and determine that the second risk is similar to the first risk based on a comparison of the first vector to the second vector, wherein at least a first subset of the first buckets is the same as a second subset of the second buckets.

3. The at least one computer readable storage medium of claim 2, wherein the comparison includes executing an eigen-decomposition on the first vector and the second vector to determine whether one or more of the first characteristics are similar to one or more of the second characteristics.

4. The at least one computer readable storage medium of claim 2, wherein the instructions, when executed, cause the computing device to: identify that the mitigation plan was implemented to at least partially mitigate the second risk; determine that the mitigation plan is applicable to mitigate the first risk based on the second risk being determined to be similar to the first risk; apply the mitigation plan to one or more of the first vector or the first risk to generate a third vector; and determine whether to recommend the mitigation plan to mitigate the first risk based on the third vector.

5. The at least one computer readable storage medium of claim 1, wherein the set of instructions, which when executed by the computing: receive a natural language input; apply natural language processing to the natural language input to filter the natural language input into first text that bypasses second text of the natural language input; and generate the first vector based on the first text.

6. The at least one computer readable storage medium of claim 1, wherein each of the first characteristics is represented as a dimension of the first vector.

7. The at least one computer readable storage medium of claim 1, wherein the locality sensitive hashing process includes a simhash function or a minhash function.

8. A system comprising: one or more processors; and a memory coupled to the one or more processors, the memory comprising instructions executable by the one or more processors, the one or more processors being operable when executing the instructions to: identify first characteristics of a first risk associated with a system; apply a locality sensitive hashing process to the first characteristics to map the first characteristics to first buckets of a plurality of buckets; generate a first vector based on the first characteristics being mapped to the first buckets; and identify a mitigation plan to at least partially mitigate the first risk based on the first vector.

9. The system of claim 8, wherein the one or more processors are further operable when executing the instructions to: apply a locality sensitive hashing process to second characteristics of a second risk to map the second characteristics to second buckets of the plurality of buckets; generate a second vector based on the second characteristics being mapped to the second buckets; and determine that the second risk is similar to the first risk based on a comparison of the first vector to the second vector, wherein at least a first subset of the first buckets is the same as a second subset of the second buckets.

10. The system of claim 9, wherein the comparison includes executing an eigen-decomposition on the first vector and the second vector to determine whether one or more of the first characteristics are similar to one or more of the second characteristics.

11. The system of claim 9, wherein the one or more processors are further operable when executing the instructions to: identify that the mitigation plan was implemented to at least partially mitigate the second risk; determine that the mitigation plan is applicable to mitigate the first risk based on the second risk being determined to be similar to the first risk; apply the mitigation plan to one or more of the first vector or the first risk to generate a third vector; and determine whether to recommend the mitigation plan to mitigate the first risk based on the third vector.

12. The system of claim 8, wherein the one or more processors are further operable when executing the instructions to: receive a natural language input; apply natural language processing to the natural language input to filter the natural language input into first text that bypasses second text of the natural language input; and generate the first vector based on the first text.

13. The system of claim 8, wherein each of the first characteristics is represented as a dimension of the first vector.

14. The system of claim 8, wherein the locality sensitive hashing process includes a simhash function or a minhash function.

15. A method comprising: identifying first characteristics of a first risk associated with a system; applying a locality sensitive hashing process to the first characteristics to map the first characteristics to first buckets of a plurality of buckets; generating a first vector based on the first characteristics being mapped to the first buckets; and identifying a mitigation plan to at least partially mitigate the first risk based on the first vector.

16. The method of claim 15, further comprising: applying a locality sensitive hashing process to second characteristics of a second risk to map the second characteristics to second buckets of the plurality of buckets; generating a second vector based on the second characteristics being mapped to the second buckets; and determining that the second risk is similar to the first risk based on a comparison of the first vector to the second vector, wherein at least a first subset of the first buckets is the same as a second subset of the second buckets.

17. The method of claim 16, wherein the comparison includes executing an eigen-decomposition on the first vector and the second vector to determine whether one or more of the first characteristics are similar to one or more of the second characteristics.

18. The method of claim 16, further comprising: identifying that the mitigation plan was implemented to at least partially mitigate the second risk; determining that the mitigation plan is applicable to mitigate the first risk based on the second risk being determined to be similar to the first risk; applying the mitigation plan to one or more of the first vector or the first risk to generate a third vector; and determining whether to recommend the mitigation plan to mitigate the first risk based on the third vector.

19. The method of claim 15, further comprising: receiving a natural language input; applying natural language processing to the natural language input to filter the natural language input into first text that bypasses second text of the natural language input; and generating the first vector based on the first text.

20. The method of claim 15, wherein: each of the first characteristics is represented as a dimension of the first vector; and the locality sensitive hashing process includes a simhash function or a minhash function.

06

edspap.20240161038