Methods and systems for path selection using vehicle route guidance

1. A method of path selection using vehicle route guidance the method comprising:

receiving, by a computing device, a plurality of requests, wherein each request comprises a respective alimentary combination to be assembled by alimentary providers and a respective destination;

generating, by the computing device, a nutritionally guided order volume based on recommend nutritional quantities, using a first machine-learning process, wherein generating the nutritionally guided order volume comprises training the first machine-learning process using training data comprising associations between a plurality of past nutritionally guided order volumes and a plurality of past extrinsic circumstances and wherein the trained first machine-learning process is configured to receive the plurality of requests as an input and output the nutritionally guided order volume as a function of the plurality of requests;

computing, by the computing device, a guidance-free order volume as a function of at least a current extrinsic circumstance using a second machine-learning process;

determining, by the computing device, a plurality of assembly times as a function of the nutritionally guided order volume and the guidance-free order volume using a third machine-learning process, wherein each assembly time includes a respective assembly time for each alimentary combination of the plurality of requests;

determining, by the computing device, an average rate for time durations between events on an alimentary provider timeline for each of the alimentary providers using a neural network in the third machine-learning process and historical performance of each of the alimentary providers as inputs;

generating, by the computing device, a plurality of predicted routes, including at least a compound route as a function of shared potential courier travel paths, as a function of the determined assembly times, wherein each predicted route of the plurality of predicted routes comprises:

a retrieval from at least a respective alimentary provider; and

a respective destination of the plurality of requests; and

pairing, by the computing device, a predicted route of the plurality of predicted routes with a courier using a greedy algorithm process, wherein pairing further comprises:

generating an objective function based on a plurality of objectives, wherein the

plurality of objectives includes at least historical courier data indicating a courier's familiarity with a particular area and;

a numerical score representing a pairing between the courier and a respective predicted route of the plurality of predicted routes;

pairing, with the courier, the predicted route according to the objective function and the numerical score representing a pairing between the courier and a respective predicted route of the plurality of predicted routes.

2. The method of claim 1 , wherein computing the nutritionally guided order volume further comprises:

training the first machine-learning process using training data correlating the past nutritionally guided order volumes with the plurality of past extrinsic circumstances;

receiving at least a current extrinsic circumstance; and

computing the nutritionally guided order volume as a function of the at least a current extrinsic circumstance using the machine-learning process.

3. The method of claim 1 , wherein computing the nutritionally guided order volume further comprises computing a per-provider nutritionally guided order volume.

4. The method of claim 1 , wherein computing a guidance-free order volume further comprises:

training the second machine-learning process using training data correlating past guidance-free order volumes with a plurality of past extrinsic circumstances;

receiving the at least a current extrinsic circumstance; and

computing the guidance-free order volume as a function of the at least a current extrinsic circumstance using the second machine-learning process.

5. The method of claim 1 , wherein computing the guidance-free order volume further comprises computing a per-provider guidance-free order volume.

6. The method of claim 1 , wherein generating a plurality of predicted routes further comprises generating at least a compound route.

7. The method of claim 1 , wherein pairing the predicted route of the plurality of predicted routes with the courier further comprises:

identifying a plurality of currently active couriers; and

assigning the predicted route to a courier of the plurality of active couriers.

8. The method of claim 1 , wherein the objective function further comprises a mixed-integer program.

9. A system for path selection using vehicle route guidance the system comprising a computing device configured to:

receive a plurality of requests, wherein each request comprises a respective alimentary combination to be assembled by alimentary providers and a respective destination;

generate a nutritionally guided order volume based on recommend nutritional quantities, using a first machine-learning process, wherein generating the nutritionally guided order volume comprises training the first machine-learning process by a training data comprising associations between a plurality of past nutritionally guided order volumes with a plurality of past extrinsic circumstances and wherein the trained first machine-learning process is configured to receive the plurality of requests as an input and output the nutritionally guided order volume as a function of the plurality of requests and the training data;

compute a guidance-free order volume as a function of at least a current extrinsic circumstance using a second machine-learning process;

determine a plurality of assembly times as a function of the nutritionally guided order volume and the guidance-free order volume using a third machine-learning process, wherein each assembly time includes a respective assembly time for each alimentary combination of the plurality of requests;

determine an average rate for time durations between events on an alimentary provider timeline for each of the alimentary providers using a neural network in the third machine-learning process and historical performance of each of the alimentary providers as inputs;

generate a plurality of predicted routes, including at least a compound route as a function of shared potential courier travel paths, as a function of the determined assembly times, wherein each predicted route of the plurality of predicted routes comprises:

a retrieval from at least a respective alimentary provider; and

a respective destination of the plurality of requests; and

pair a predicted route of the plurality of predicted routes with a courier using a greedy algorithm process, wherein pairing further comprises:

generating an objective function based on a plurality of objectives, wherein the plurality of objectives includes:

at least historical courier data indicating a courier's familiarity with a particular area and;

a numerical score representing a pairing between the courier and a respective predicted route of the plurality of predicted routes;

pairing, with the courier, the predicted route according to the objective function and the numerical score representing a pairing between the courier and a respective predicted route of the plurality of predicted routes.

10. The system of claim 9 , wherein the computing device is further configured to compute the nutritionally guided order volume by:

training the first machine-learning process using training data correlating the past nutritionally guided order volumes with the plurality of past extrinsic circumstances;

receiving at least a current extrinsic circumstance; and

computing the nutritionally guided order volume as a function of the at least a current extrinsic circumstance using the machine-learning process.

11. The system of claim 9 , wherein the computing device is further configured to compute the nutritionally guided order volume by computing a per-provider nutritionally guided order volume.

12. The system of claim 9 , wherein computing a guidance-free order volume further comprises:

training a second machine-learning process using training data correlating past guidance-free order volumes with a plurality of past extrinsic circumstances;

receiving at least a current extrinsic circumstance; and

computing the nutritionally guided order volume as a function of the at least a current extrinsic circumstance using the second machine-learning process.

13. The system of claim 9 , wherein computing the guidance-free order volume further comprises computing a per-provider guidance-free order volume.

14. The system of claim 9 , wherein the computing device is further configured to generate a plurality of predicted routes by generating at least a compound route.

15. The system of claim 9 , wherein the computing device is further configured to pair the predicted route with the courier:

identifying a plurality of currently active couriers; and

assigning the predicted route to a courier of the plurality of active couriers.

16. The system of claim 9 , wherein the objective function further comprises a mixed-integer program.