System and method for machine-learning input-based data autogeneration

1. A machine-learning input-based data autogeneration system comprising:

a memory comprising: a user profile database identifying attributes of a plurality of users, wherein the plurality of users comprises a plurality of classes of users, wherein the plurality of classes of users comprise at least one class of subject-users and at least two classes of recipient-users;

a model database comprising a plurality of machine-learning models, each of the plurality of machine-learning models trained to generate a report in response to received inputs characterizing attributes of a subject-user and at least one recipient-user;

a source device configured to receive source inputs and transmit the received source inputs, wherein the source inputs relate to an attribute of the subject-user;

a recipient device configured to receive recipient inputs and transmit the received recipient inputs, wherein the recipient inputs identify an at least one attribute of a recipient-user; and

a server configured to:

generate a characterization vector characterizing a patient state;

identify a state node in a first network corresponding to the patient state, the first network comprising a plurality of nodes linked via a plurality of edges, wherein each of the edges links a pair of nodes, wherein each of the plurality of edges is associated with a conditional probability of a truth of one of the nodes in a pair of nodes linked by the edge based on a status of the other of the nodes in the pair of nodes;

identify an action node in a second network according to machine-learning model, the action node linked to the state node;

automatically update a user schedule database with information characterizing scheduling of provisioning of a medical service associated with the identified action node;

deliver the medical service associated with the identified action node;

receive a request at the server for a report characterizing attributes of the subject-user and the delivered medical service;

receive a plurality of inputs identifying attributes of the subject-user;

receive at least one input identifying an attribute of the recipient-user;

select a machine-learning model based on a comparison of the at least one attribute of the recipient-user to metadata linked with the machine-learning model;

ingest received inputs into the machine-learning model;

receive the generated report from the machine-learning model, wherein the generated report is customized to the at least one attribute of the recipient-user; and

automatically generate and deliver a message to the recipient device comprising at least portions of the generated report.

2. The system of claim 1 , wherein the request for the report comprises data identifying the at least one attribute of the recipient-user.

3. The system of claim 2 , wherein at least some of the plurality of inputs identifying attributes of the subject-user are received from the source device.

4. The system of claim 3 , further comprising an electrical analysis machine, wherein the electrical analysis machine automatically generates data indicative of an attribute of the subject-user from an interaction with the subject-user.

5. The system of claim 4 , wherein the electrical analysis machine automatically provides the data indicative of the attribute of the subject-user to the server.

6. The system of claim 5 , wherein the server is further configured to receive feedback data indicative of a responsiveness of the delivered message to the request for the report.

7. The system of claim 6 , wherein the server is further configured to receive a second request for a report from a second recipient-user.

8. The system of claim 7 , wherein the second request for the report comprises at least one input identifying an attribute of the second recipient-user, wherein the attribute of the second recipient-user is different than the attribute of the recipient-user.

9. The system of claim 8 , wherein the server is further configured to: select a second machine-learning model based on the attribute of the second recipient-user; and automatically generate and deliver a second message to the second recipient-user comprising an output of the second machine-learning model.

10. The system of claim 9 , wherein the server is further configured to: ingest the plurality of inputs identifying attributes of the subject-user into the second machine-learning model; and receive text output from the second machine-learning model, wherein the text output is customized to the second recipient-user.

11. A method of machine-learning input-based patient-report autogeneration, the method comprising:

generating a characterization vector characterizing a patient state;

identifying a state node in a first network corresponding to the patient state, the first network comprising a plurality of nodes linked via a plurality of edges, wherein each of the edges links a pair of nodes, wherein each of the plurality of edges is associated with a conditional probability of a truth of one of the nodes in a pair of nodes linked by the edge based on a status of the other of the nodes in the pair of nodes;

identifying an action node in a second network according to machine-learning model, the action node linked to the state node;

automatically updating a user schedule database with information characterizing scheduling of provisioning of a medical service associated with the identified action node;

delivering the medical service associated with the identified action node;

receiving a request for a report characterizing attributes of a subject-user and the delivered medical service;

receiving at a server a plurality of inputs from a service provisioning module on a source device, the plurality of inputs identifying attributes of the medical service provided to a subject-user, wherein at least one of the plurality of inputs comprises a note, wherein the plurality of inputs are received embedded in the request for the report;

receiving at the server at least one input from a recipient-user device identifying at least one attribute of a recipient-user;

selecting a machine-learning model from a model database based on a comparison of the at least one attribute of the recipient-user to metadata linked with the machine-learning model, the model database comprising a plurality of machine-learning models, each of the plurality of machine-learning models trained to generate a report in response to received inputs characterizing attributes of a subject-user and at least one recipient-user;

ingesting received inputs into the machine-learning model;

receiving the generated report from the machine-learning model, wherein the generated report is customized to the at least one attribute of the recipient-user; and

automatically generating and delivering a message to the recipient-user device comprising at least portions of the generated report.

12. The method of claim 11 , wherein the request for the report comprises data identifying the at least one attribute of the recipient-user.

13. The method of claim 12 , wherein at least some of the plurality of inputs identifying attributes of the subject-user are received from the source device.

14. The method of claim 13 , further comprising receiving data identifying an attribute of the subject-user at the server from an electrical analysis machine, wherein the electrical analysis machine automatically generates data from an interaction with the subject-user.

15. The method of claim 14 , wherein the electrical analysis machine automatically provides the data identifying the attribute of the subject-user to the server.

16. The method of claim 15 , further comprising receiving feedback data indicative of a responsiveness of the delivered message to the request for the report.

17. The method of claim 16 , further comprising receiving a second request for a report from a second recipient-user.

18. The method of claim 17 , wherein the second request for the report comprises at least one input identifying an attribute of the second recipient-user, wherein the attribute of the second recipient-user is different than the attribute of the recipient-user.

19. The method of claim 18 , further comprising: selecting a second machine-learning model based on the attribute of the second recipient-user; and automatically generating and delivering a second message to the second recipient-user comprising an output of the second machine-learning model.

20. The method of claim 19 , further comprising: ingesting the plurality of inputs identifying attributes of the subject-user into the second machine-learning model; and receiving text output from the second machine-learning model, wherein the text output is customized to the second recipient-user.