Information
-
Patent Application
-
20230298752
-
Publication Number
20230298752
-
Date Filed
July 23, 20204 years ago
-
Date Published
September 21, 202311 months ago
-
Inventors
-
Original Assignees
-
CPC
-
-
International Classifications
Abstract
Disclosed are a method and a system for providing a customized diagnosis system. A method for providing a diagnosis system, which is to achieve the technical task, comprises the steps wherein: a reference diagnosis system transmits, to a first diagnostic subject system, M (M is an integer of 2 or larger) pieces of unannotated learning data for customization; the reference diagnosis system receives the M pieces of learning data for customization, which are annotated by a first diagnostic subject side, from the first diagnostic subject system; and the received annotated M pieces of learning data for customization are reflected in the reference diagnosis system, wherein the M pieces of learning data for customization, which have been annotated by the first diagnostic subject side, are reflected in a neural network for the reference diagnosis system under a condition that a predetermined price is to be paid.
Claims
- 1. A method for providing a customized diagnosis system, the method comprising:
transmitting, by a reference diagnosis system, M (M is an integer of 2 or more) pieces of unannotated training data for customization to a first diagnoser system;receiving, by the reference diagnosis system, the M pieces of training data for customization annotated by a first diagnoser side from the first diagnoser system; andreflecting the received M pieces of annotated training data for customization in the reference diagnosis system,wherein the M pieces of training data for customization annotated by the first diagnoser side are reflected in a neural network for the reference diagnosis system under a condition that a predetermined price is paid.
- 2. The method of claim 1, comprising:
receiving diagnosis data from the first diagnoser system, generating a diagnosis result, and transmitting the diagnosis result to the first diagnoser system, by the reference diagnosis system in which the M pieces of annotated training data for customization are reflected.
- 3. The method of claim 1, wherein the reference diagnosis system sets the price to be larger as the M is larger or according to a ratio of the M to the number of training data learned by the reference diagnosis system.
- 4. The method of claim 1, wherein the reference diagnosis system is a system that comprises an individual diagnosis system set comprising a plurality of individual diagnosis systems and performs diagnosis through consensus based on individual diagnosis results output by the plurality of individual diagnosis systems.
- 5. The method of claim 4, wherein the reflecting of the received M pieces of annotated training data for customization in the reference diagnosis system comprises retraining at least some of the plurality of individual diagnosis systems using the M pieces of annotated training data for customization.
- 6. The method of claim 4, wherein the M pieces of training data for customization comprises data in which at least two of the individual diagnosis systems included in the individual diagnosis system set output different diagnosis results.
- 7. A method for providing a customized diagnosis system, comprising:
transmitting, by a reference diagnosis system, M (M is an integer of 2 or more) pieces of unannotated training data for customization to a first diagnoser system, the reference diagnosis system comprising an individual diagnosis system set comprising a plurality of individual diagnosis systems;receiving, by the reference diagnosis system, the M pieces of training data for customization annotated by a first diagnoser side from the first diagnoser system;reflecting the received M pieces of annotated training data for customization in any one first individual diagnosis system included in the reference diagnosis system set;receiving a diagnosis request comprising diagnosis data to be diagnosed by the reference diagnosis system from a predetermined diagnosis request system; anddetermining, according to the received diagnosis request, a type of diagnosis result corresponding to the diagnosis request as a first individual diagnosis result of the first individual diagnosis system, and transmitting a diagnosis result comprising the first individual diagnosis result output by the first individual diagnosis system receiving input data to the diagnosis request system.
- 8. A computer program stored in a non-transitory computer readable recording medium installed in a data processing device and for performing the method of claim 1.
- 9. A data processing system, comprising:
a processor; anda storage device in which a program is stored,wherein the method of claim 1 is performed by the program executed by the processor.
- 10. A customized diagnosis system, comprising:
a processor;a storage device in which a program executed by the processor is stored,wherein the storage device comprises at least one neural network, andthe program is configured to:
transmit M (M is an integer of 2 or more) pieces of unannotated training data for customization to a first diagnoser system, receive the M pieces of training data for customization annotated by a first diagnoser side from the first diagnoser system, and reflect the received M pieces of annotated training data for customization in a reference diagnosis system, andwherein the M pieces of training data for customization annotated by the first diagnoser side are reflected in the neural network under a condition that a predetermined price is paid.
- 11. A customized diagnosis system, comprising:
a processor; anda storage device in which a program executed by the processor is stored,wherein the storage device comprises a neural network corresponding to a plurality of individual diagnosis systems, andwherein the program is configured to:
transmit M (M is an integer of 2 or more) pieces of unannotated training data for customization to a first diagnoser system, and when receiving the M pieces of training data for customization annotated by a first diagnoser side from the first diagnoser system, reflect the received M pieces of annotated training data for customization to a first neural network corresponding to a first individual diagnosis system among the plurality of individual diagnosis systems, andwhen receiving a diagnosis request comprising diagnosis data to be diagnosed from a predetermined diagnosis request system, determine, according to the received diagnosis request, a type of diagnosis result corresponding to the diagnosis request as a first individual diagnosis result of a first individual diagnosis system, and transmit a diagnosis result comprising the first individual diagnosis result output by the first individual diagnosis system receiving input data to the diagnosis request system.
PCT Information
Filing Document |
Filing Date |
Country |
Kind |
PCT/KR2020/009719 |
7/23/2020 |
WO |
|