Efficient search for combinations of matching entities given constraints

A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for executing tasks in response to matching entities using a machine learning (ML) model, the operations comprising:

• receiving a set of inference results generated by a ML model, the inference results comprising a set of query entities and a set of target entities, each query entity having one or more target entities matched thereto by the ML model;
• processing the set of inference results to generate a set of matched sub-sets of target entities by executing a search over target entities in the set of target entities based on constraints, for each problem in a set of problems, providing the problem as a tuple comprising an index value representative of a target entity in the set of target entities and a value associated with the query entity, the value comprising a constraint relative to the query entity, and executing one of:
• determining, at least partially based on the index value, that a solution to the problem is stored in memory, and in response, processing a next problem,
• determining that the value is outside of a limit range associated with the index value, and in response, determining that the problem has no matched sub-sets,
• determining that the target entity represented by the index value is a last target entity to be considered and, in response, executing one of including a value of the target entity into a singleton matched sub-set in response to determining that the value of the target entity corresponds to the value associated with the query entity, and determining that the problem has no matched sub-sets, and
• determining that the target entity represented by the index value is a last target entity to be considered and, in response, dividing the problem into sub-problems and selectively storing solutions to the sub-problems in the memory;
• and
• executing at least one task in response to one or more matched sub-sets in the set of matched sub-sets.

A system, comprising:

• a computing device;
• and
• a computer-readable storage device coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations for executing tasks in response to matching entities using a machine learning (ML) model, the operations comprising:
• receiving a set of inference results generated by a ML model, the inference results comprising a set of query entities and a set of target entities, each query entity having one or more target entities matched thereto by the ML model;
• processing the set of inference results to generate a set of matched sub-sets of target entities by executing a search over target entities in the set of target entities based on constraints, for each problem in a set of problems, providing the problem as a tuple comprising an index value representative of a target entity in the set of target entities and a value associated with the query entity, the value comprising a constraint relative to the query entity, and executing one of:
• determining, at least partially based on the index value, that a solution to the problem is stored in memory, and in response, processing a next problem,
• determining that the value is outside of a limit range associated with the index value, and in response, determining that the problem has no matched sub-sets,
• determining that the target entity represented by the index value is a last target entity to be considered and, in response, executing one of including a value of the target entity into a singleton matched sub-set in response to determining that the value of the target entity corresponds to the value associated with the query entity, and determining that the problem has no matched sub-sets, and
• determining that the target entity represented by the index value is a last target entity to be considered and, in response, dividing the problem into sub-problems and selectively storing solutions to the sub-problems in the memory;
• and
• executing at least one task in response to one or more matched sub-sets in the set of matched sub-sets.