Machine learning systems architectures for ranking
Computing systems, computing apparatuses, computing methods, and computer program products are disclosed for machine learning ranking. An example computing method includes receiving a search query and determining a plurality of machine learning model execution engines based on the search query and a plurality of search result types. The example computing method further includes generating a plurality of subsets of search results based on the search query and the plurality of machine learning model execution engines. The example computing method further includes generating a set of search results comprising at least one search result from each of the plurality of subsets of search results.
1. An apparatus comprising a processor and a non-transitory memory storing program instructions, wherein the non-transitory memory and the program instructions are configured to, with the processor, cause the apparatus to:
train a first machine learning model associated with a first machine learning model execution engine and a second machine learning model associated with a second machine learning model execution engine based at least in part on a plurality of training datasets, wherein the first machine learning model is different from the second machine learning model;
receive a search query;
generate a first search results subset based on the first machine learning model execution engine and the search query;
generate a second search results subset based on the second machine learning model execution engine and the search query; and
generate a search results set by aggregating the first search results subset and the second search results subset.
2. The apparatus of claim 1 , wherein, when aggregating the first search results subset and the second search results subset, the non-transitory memory and the program instructions are configured to, with the processor, cause the apparatus to:
combine at least one search result from the first search results subset and at least one search result from the second search results subset.
3. The apparatus of claim 1 , wherein the non-transitory memory and the program instructions are configured to, with the processor, cause the apparatus to:
determine the first machine learning model execution engine based on the search query and a first search result type, and
determine the second machine learning model execution engine based on the search query and a second search result type.
4. The apparatus of claim 1 , wherein the second search results subset comprises one or more search results that are not in the first search results subset.
5. The apparatus of claim 1 , wherein the non-transitory memory and the program instructions are configured to, with the processor, cause the apparatus to:
generate a third search results subset based on a third machine learning model execution engine and the search query.
6. The apparatus of claim 5 , wherein the search results set further comprises at least one search result from the third search results subset.
7. The apparatus of claim 5 , wherein the non-transitory memory and the program instructions are configured to, with the processor, cause the apparatus to:
determine the third machine learning model execution engine based on the search query and a third search result type.
8. A computer-implemented method comprising:
training a first machine learning model associated with a first machine learning model execution engine and a second machine learning model associated with a second machine learning model execution engine based at least in part on a plurality of training datasets, wherein the first machine learning model is different from the second machine learning model;
receiving a search query;
generating a first search results subset based on the first machine learning model execution engine and the search query;
generating a second search results subset based on the second machine learning model execution engine and the search query; and
generating a search results set by aggregating the first search results subset and the second search results subset.
9. The computer-implemented method of claim 8 , wherein, when aggregating the first search results subset and the second search results subset, the computer-implemented method further comprises:
combining at least one search result from the first search results subset and at least one search result from the second search results subset.
10. The computer-implemented method of claim 8 further comprising:
determining the first machine learning model execution engine based on the search query and a first search result type, and
determining the second machine learning model execution engine based on the search query and a second search result type.
11. The computer-implemented method of claim 8 , wherein the second search results subset comprises one or more search results that are not in the first search results subset.
12. The computer-implemented method of claim 8 further comprising:
generating a third search results subset based on a third machine learning model execution engine and the search query.
13. The computer-implemented method of claim 12 , wherein the search results set comprises at least one search result from the third search results subset.
14. The computer-implemented method of claim 12 further comprising:
determining the third machine learning model execution engine based on the search query and a third search result type.
15. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, wherein the computer-readable program code portions comprise an executable portion configured to:
train a first machine learning model associated with a first machine learning model execution engine and a second machine learning model associated with a second machine learning model execution engine based at least in part on a plurality of training datasets, wherein the first machine learning model is different from the second machine learning model;
receive a search query;
generate a first search results subset based on the first machine learning model execution engine and the search query;
generate a second search results subset based on the second machine learning model execution engine and the search query; and
generate a search results set by aggregating the first search results subset and the second search results subset.
16. The computer program product of claim 15 , wherein the computer-readable program code portions comprise the executable portion configured to:
determine the first machine learning model execution engine based on the search query and a first search result type, and
determine the second machine learning model execution engine based on the search query and a second search result type.
17. The computer program product of claim 15 , wherein the second search results subset comprises one or more search results that are not in the first search results subset.
18. The computer program product of claim 15 , wherein the computer-readable program code portions comprise the executable portion configured to:
generate a third search results subset based on a third machine learning model execution engine and the search query.
19. The computer program product of claim 18 , wherein the search results set comprises at least one search result from the third search results subset.
20. The computer program product of claim 18 , wherein the computer-readable program code portions comprise the executable portion configured to:
determine the third machine learning model execution engine based on the search query and a third search result type.