SYSTEMS AND METHODS FOR ADAPTIVE WEIGHTING OF MACHINE LEARNING MODELS

1 . A non-transitory computer readable medium including instructions that are executable by one or more processors to cause a system to perform a method for generating a personalized virtual network, the method comprising:

acquiring a request for a service, wherein the request is associated with a user and the user's preferences;

identifying one or more conditions of the user based on stored user information and the acquired request;

determining a propensity for each condition of the identified one or more conditions using a first set of one or more machine learning models with the stored user information as input;

identifying a second set of one or more machine learning models based on the identified one or more conditions;

evaluating weights for the second set of one or more machine learning models based on the determined propensities of one or more conditions; and

applying the evaluated weights to the second set of models to generate a personalized virtual network for the user.

2 . The non-transitory computer readable medium of claim 1 , wherein identifying of one or more conditions of the user based on the stored user information and the acquired request comprises:

predicting the one or more conditions based on a third set of machine learning models using past conditions in the stored user information as input.

3 . The non-transitory computer readable medium of claim 1 , wherein the first set of one or more machine learning models are trained using insights from other users having features similar to the user and interacting with the personalized virtual network.

4 . The non-transitory computer readable medium of claim 3 , wherein the other users similarity to the user is based on the type of the requested service and similarity of preferences of the other users and the user's preferences.

5 . The non-transitory computer readable medium of claim 1 , wherein identifying the second set of the one or more machine learning models comprises:

determining relevancy of each of the second set of one or models based on the stored user information and the user's preferences.

6 . The non-transitory computer readable medium of claim 5 , wherein determining the relevancy of each of the second set of one or more models comprises:

determining the compatibility of each model with the other models in the second set of one or more models.

7 . The non-transitory computer readable medium of claim 1 , wherein the second set of one or more machine learning models are associated with a stored set of service providers.

8 . The non-transitory computer readable medium of claim 5 , wherein the second set of one or more machine learning models includes at least one of: service providers quality models, service providers expertise models, service providers location models.

9 . The non-transitory computer readable medium of claim 1 , wherein generating a personalized virtual network comprises:

evaluating order of the personalized virtual network based on the user's stored information.

10 . The non-transitory computer readable medium of claim 9 , wherein the generating a personalized virtual network of service provider further comprises:

generation of a subset of service providers for each of the identified one or more conditions.

11 . A method performed by a system for generating a personalized virtual network, the method comprising:

acquiring a request for a service, wherein the request is associated with a user and the user's preferences;

identifying one or more conditions of the user based on stored user information and the acquired request;

determining a propensity for each condition of the identified one or more conditions using a first set of one or more machine learning models with the stored user information as input;

identifying a second set of one or more machine learning models based on the identified one or more conditions;

evaluating weights for the second set of one or more machine learning models based on the determined propensities of one or more conditions; and

applying the evaluated weights to the second set of models to generate a personalized virtual network for the user.

12 . The method of claim 11 , wherein identifying of one or more conditions of the user based on the stored user information and the acquired request comprises:

predicting the one or more conditions based on a third set of machine learning models using past conditions in the stored user information as input.

13 . The method of claim 11 , wherein the first set of one or more machine learning models are trained using insights from other users having features similar to the user and interacting with the personalized virtual network.

14 . The method of claim 13 , wherein the other users similarity to the user is based on the type of the requested service and similarity of preferences of the other users and the user's preferences.

15 . The method of claim 11 , wherein the identifying the second set of the one or more machine learning models comprises:

determining relevancy of each of the second set of one or more models based on the stored user information and the user's preferences.

16 . The method of claim 15 , wherein determining the relevancy of each of the second set of one or more models comprises:

determining the compatibility of each model with the other models in the second set of one or more models.

17 . The method of claim 11 , wherein the second set of one or more machine learning models are associated with a stored set of service providers.

18 . The method of claim 15 , wherein the second set of one or more machine learning models includes at least one of: service providers quality models, service providers expertise models, service providers location models.

19 . The method of claim 11 , wherein generating a personalized virtual network comprises:

evaluating order of the personalized virtual network based on the user's stored information.

20 . An adaptive weighting system comprising:

a network;

one or more memory devices storing processor-executable instructions; and

one or more processors configured to execute the instructions to cause the adaptive weighting system to perform:

acquiring a request for a service, wherein the request is associated with a user and the user's preferences;

identifying one or more conditions of the user based on stored user information and the acquired request;

determining a propensity for each condition of the identified one or more conditions using a first set of one or more machine learning models with the stored user information as input;

identifying a second set of one or more machine learning models based on the identified one or more conditions;

evaluating weights for the second set of one or more machine learning models based on the determined propensities of one or more conditions; and

applying the evaluated weights to the second set of models to generate a personalized virtual network for the user.

1 .- 20 . (canceled)

21 . A non-transitory computer readable medium including instructions that are executable by one or more processors to cause a system to perform a method for generating a personalized virtual network, the method comprising:

acquiring a request for a service, wherein the request is associated with a user and the user's preferences;

identifying one or more conditions of the user based the request, wherein each condition of the identified one or more conditions is associated with a care provider model;

determining a propensity for each condition of the identified one or more conditions using a first set of one or more machine learning models with the user's preferences as input, wherein the first set of one or more models is trained using insights from other users having features similar to the user;

identifying a second set of one or more machine learning models based on the identified one or more conditions, the second set of one or more models including the associated care provider model;

evaluating weights for the second set of one or more machine learning models based on the determined propensities of one or more conditions; and

applying the evaluated weights to the second set of models to generate a personalized virtual care provider network for the user based on applying the features to the second set of models.

22 . The non-transitory computer readable medium of claim 21 , wherein identifying of one or more conditions of the user based on stored user information and the acquired request comprises:

predicting the one or more conditions based on a third set of machine learning models using past conditions in the stored user information as input.

23 . The non-transitory computer readable medium of claim 21 , wherein determining the propensity comprises predicting, using the first set of one or more machine learning models, a likelihood of the one or more conditions occurring for the user.

24 . The non-transitory computer readable medium of claim 23 , wherein the other users similarity to the user is based on the type of the requested service and similarity of preferences of the other users and the user's preferences.

25 . The non-transitory computer readable medium of claim 21 , wherein identifying the second set of the one or more machine learning models comprises:

determining relevancy of each of the second set of one or models based on stored user information and the user's preferences.

26 . The non-transitory computer readable medium of claim 25 , wherein determining the relevancy of each of the second set of one or more models comprises:

determining a compatibility of each model with the other models in the second set of one or more models.

27 . The non-transitory computer readable medium of claim 21 , wherein the second set of one or more machine learning models are associated with a stored set of service providers.

28 . The non-transitory computer readable medium of claim 21 , wherein the second set of one or more machine learning models includes at least one of: service providers quality models, service providers expertise models, service providers location models.

29 . The non-transitory computer readable medium of claim 21 , wherein the generated personalized virtual care provider network comprises an ordered listing of service providers.

30 . The non-transitory computer readable medium of claim 29 , wherein the generating a personalized virtual network of service provider further comprises:

generation of a subset of service providers for each of the identified one or more conditions.

31 . A method performed by a system for generating a personalized virtual network, the method comprising:

acquiring a request for a service, wherein the request is associated with a user and the user's preferences;

identifying one or more conditions of the user based the request, wherein each condition of the identified one or more conditions is associated with a care provider model;

determining a propensity for each condition of the identified one or more conditions using a first set of one or more machine learning models with the user's preference as input, wherein the first set of one or more models is trained using insights from other users having features similar to the user;

identifying a second set of one or more machine learning models based on the identified one or more conditions, the second set of one or more models including the associated care provider model;

evaluating weights for the second set of one or more machine learning models based on the determined propensities of one or more conditions; and

applying the evaluated weights to the second set of models to generate a personalized virtual care provider network for the user based on applying the features to the second set of models.

32 . The method of claim 31 , wherein identifying of one or more conditions of the user based on stored user information and the acquired request comprises:

predicting the one or more conditions based on a third set of machine learning models using past conditions in the stored user information as input.

33 . The method of claim 31 , wherein determining the propensity comprises predicting, using the first set of one or more machine learning models, a likelihood of the one or more conditions occurring for the user.

34 . The method of claim 33 , wherein the other users similarity to the user is based on the type of the requested service and similarity of preferences of the other users and the user's preferences.

35 . The method of claim 31 , wherein the identifying the second set of the one or more machine learning models comprises:

determining relevancy of each of the second set of one or more models based on stored user information and the user's preferences.

36 . The method of claim 35 , wherein determining the relevancy of each of the second set of one or more models comprises:

determining a compatibility of each model with the other models in the second set of one or more models.

37 . The method of claim 31 , wherein the second set of one or more machine learning models are associated with a stored set of service providers.

38 . The method of claim 31 , wherein the second set of one or more machine learning models includes at least one of: service providers quality models, service providers expertise models, service providers location models.

39 . The method of claim 31 , wherein generating a personalized virtual network comprises:

evaluating order of the personalized virtual network based on stored information of the user.

40 . An adaptive weighting system comprising:

one or more memory devices storing processor-executable instructions; and

one or more processors configured to execute the instructions to cause the adaptive weighting system to perform:

acquiring a request for a service, wherein the request is associated with a user and the user's preferences;

identifying one or more conditions of the user based the request, wherein each condition of the identified one or more conditions is associated with a care provider model;

determining a propensity for each condition of the identified one or more conditions using a first set of one or more machine learning models with the user's preferences as input, wherein the first set of one or more models is trained using insights from other users having features similar to the user;

identifying a second set of one or more machine learning models based on the identified one or more conditions, the second set of one or more models including the associated care provider model;

evaluating weights for the second set of one or more machine learning models based on the determined propensities of one or more conditions; and

applying the evaluated weights to the second set of models to generate a personalized virtual care provider network for the user based on applying the features to the second set of models.