Delivering a chemical compound based on a measure of trust dynamics

Patent metadata

Field	Value
Publication number	US-11557398-B2
Application number	US-201815986617-A
Country	US
Kind code	B2
Filing date	May 22, 2018
Priority date	May 22, 2018
Publication date	Jan 17, 2023
Grant date	Jan 17, 2023

Abstract

Techniques regarding autonomously controlling the delivery of one or more chemical compounds are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a compound component can identify a chemical compound mixture to be distributed to an entity based on a trust disposition value. The trust disposition value can be determined using machine learning technology and is indicative of an expected effectiveness of the chemical compound mixture with regards to the entity.

First claim

What is claimed is:

1. A system, comprising:
a memory that stores computer executable components;
a processor, operably coupled to the memory, and that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
a data analysis component that trains a machine learning model, using features extracted from data associated with patients, to determine trust disposition values of chemical compound mixtures with respect to the patients; and
a compound component that identifies, using the machine learning model on a dataset associated with a patient, a chemical compound mixture to be distributed to the patient based on a trust disposition value, wherein the trust disposition value is indicative of an expected effectiveness of the chemical compound mixture with respect to the patient based on one or more factors defining trust perceived by the patient of a treatment process.

2. The system of claim 1 , further comprising:
a data collection component that generates the dataset, wherein the dataset comprises a plurality of features extracted from a communication regarding the patient; and
an evaluation component that determines, using the machine learning model, the trust disposition value associated with the patient by analyzing the dataset.

3. The system of claim 2 , wherein the communication is between the patient and an artificial intelligence chatbot.

4. The system of claim 2 , wherein the evaluation component further determines the trust disposition value based on a trust graph, and wherein the trust graph represents a plurality of trust disposition values associated with a plurality of patients.

5. The system of claim 2 , wherein the communication regards a commitment regarding the patient, and wherein the plurality of features delineates whether the commitment was fulfilled.

6. The system of claim 1 , wherein the chemical compound mixture comprises compounds selected from a group consisting of a medicine and a placebo.

7. The system of claim 6 , wherein the compound component further controls a medical device to administer the chemical compound mixture to the patient.

8. The system of claim 1 , further comprising:
a composition component that determines a composition of the chemical compound mixture based on the trust disposition value.

9. The system of claim 8 , wherein the composition component further controls a medical device to prepare the composition of the chemical compound mixture.

10. A computer-implemented method, comprising:
training, by a system operatively coupled to a processor, a machine learning model, using features extracted from data associated with patients, to determine trust disposition values of chemical compounds with respect to the patients; and
determining, by the system, using the machine learning model on a dataset associated with a patient, how a chemical compound is to be distributed to the patient based on a trust disposition value, wherein the trust disposition value is indicative of an effectiveness of the chemical compound with respect to the patient based on one or more factors defining trust perceived by the patient of a treatment process.

11. The computer-implemented method of claim 10 , further comprising:
generating, by the system, the dataset, wherein the dataset comprises a plurality of features extracted from a communication regarding the patient; and
determining, by the system, using the machine learning model, the trust disposition value associated with the patient by analyzing the dataset.

12. The computer-implemented method of claim 11 , wherein the communication is between the patient and an artificial intelligence chatbot.

13. The computer-implemented method of claim 10 , wherein the determining comprises determining a dosage of the chemical compound to be distributed to the patient.

14. The computer-implemented method of claim 10 , wherein the determining comprises determining a frequency at which to distribute the chemical compound to the patient.

15. The computer-implemented method of claim 10 , further comprising:
identifying, by the system, using the machine learning model, the chemical compound based on the trust disposition value.

16. A computer program product for chemical compound delivery, the computer program product comprising a non-transitory computer readable medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
train a machine learning model, using features extracted from data associated with patients, to determine trust disposition values of chemical compounds with respect to the patients; and
control, using the machine learning model on a dataset associated with a patient, a delivery of a chemical compound to the patient based on a trust disposition value, wherein the trust disposition value is indicative of an effectiveness of the chemical compound with respect to the patient based on one or more factors defining trust perceived by the patient of a treatment process.

17. The computer program product of claim 16 , wherein the program instructions further cause the processor to:
generate, by the system, the dataset, wherein the dataset comprises a plurality of features extracted from a communication regarding the patient; and
determine, by the system, using the machine learning model, the trust disposition value associated with the patient by analyzing the dataset.

18. The computer program product of claim 17 , wherein the communication is between the patient and an artificial intelligence chatbot.

19. The computer program product of claim 16 , wherein the program instructions further cause the processor to:
select, using the machine learning model, the chemical compound from a group consisting of a medicine and a placebo.

20. The computer program product of claim 16 , wherein the trust disposition value is determined in a cloud computing environment.

Assignees

• IBM

Inventors

• Kozloski James R
• Kalia Anup
• Rogers Jeffrey L
• Berger Sara

Classifications

• G06N5/00

  Computing arrangements using knowledge-based models · CPC title

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• G06N20/00

  Machine learning · CPC title

• G16H20/10

  relating to drugs or medications, e.g. for ensuring correct administration to patients · CPC title

• G16H50/20 Primary

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title