Control unit and control method for controlling an output unit from information in the context of medical diagnostics and therapy

1. A method for creating a controller for controlling an output device from information in a context of medical diagnostics and therapy, the method comprising:

recognizing, via a learning processing apparatus, spoken words spoken by a plurality of actors, the learning processing apparatus including an algorithm for recognizing spoken words; and

training an untrained controller, via machine learning, to predict a subsequent action performed by the plurality of actors following a captured keyword by

providing a number of speech recordings, each speech recording of the number of speech recordings including a communication during a medical procedure, wherein the number of speech recordings concern comparable medical procedures,

performing a speech analysis of the speech recordings, and

training the untrained controller according to a machine learning principle based upon the speech analysis of the speech recordings,

wherein the untrained controller is on, or in, the learning processing apparatus.

2. The method of claim 1 ,

wherein the performing the speech analysis includes capturing keywords in the speech recordings,

wherein the training the untrained controller includes, for the captured keyword or an action linked to the captured keyword, training the controller on the subsequent action, the subsequent action including at least one of an equipment adjustment, a display of a sequence of activities for personnel or a patient, or a display of X-ray images.

3. The method of claim 2 , further comprising at least one of:

analyzing the speech recordings systematically to capture repetitions and chronological sequences; or

performing the speech analysis for each actor.

4. The method of claim 1 , wherein the training the untrained controller includes

linking the speech analysis of the speech recordings to at least one of an activity analysis or an action analysis based on film images of the medical procedure, and

computationally linking timings of keywords to actions by actors performed at least one of on a system or in a room, the actions taken from the film images.

5. The method of claim 1 , further comprising:

performing a comparative speech analysis of a multiplicity of identical procedures,

wherein the training the controller includes optimizing the controller based on the comparative speech analysis.

6. The method of claim 5 , wherein the training the controller includes optimizing the controller with regard to duration of the procedure, a frequency and number of keywords, and a duration of speech communication.

7. A non-transitory computer-readable medium, storing program segments downloadable and executable by a processor, to perform the method of claim 1 , when the program segments are executed by the processor.

8. A controller for controlling an output device from information in a context of medical diagnostics and therapy, the controller comprising:

circuitry configured to cause the controller to

recognize, via an algorithm for recognizing spoken words, spoken words spoken by a plurality of actors; and

train an untrained controller, via machine learning, to predict a subsequent action performed by the plurality of actors following a captured keyword by

providing a number of speech recordings, each speech recording of the number of speech recordings including a communication during a medical procedure, wherein the number of speech recordings concern comparable medical procedures,

performing a speech analysis of the speech recordings, and

training the untrained controller according to a machine learning principle based upon the speech analysis of the speech recordings.

9. The controller of claim 8 , wherein the circuitry is further configured to cause the controller to,

create a speech recording during a medical procedure;

process the speech recording while continuing to create the speech recording;

determine the captured keywords in the speech recording;

generate result output data based on the captured keywords; and

control the output device with the result output data.

10. The controller of claim 9 , wherein circuitry is further configured to cause the controller to:

create the speech recording from the communication in an examination room captured using a plurality of microphones;

analyze the speech recording to determine a best way to capture by different microphones of the plurality of microphones; and

generate result output data based on at least one of keywords linked to an optical capture for the captured keyword, or an action linked to the captured keyword, the optical capture being an optical recording of areas of the examination room performed via number of cameras, the result output data including the subsequent action learned by the controller,

wherein the subsequent action includes at least one of an equipment adjustment, a display of a sequence of activities for personnel or a patient, or a display of X-ray images.

11. The controller of claim 10 , wherein the circuitry is further configured to cause the controller to:

generate, from keywords included in questions asked during the medical procedure through the microphones, answers as the result output data.

12. The controller of claim 11 , wherein the circuitry is further configured to cause the controller to:

generate the output data to produce a synthetic speech; and

output the synthetic speech through a proximate loudspeaker, of a plurality of loudspeakers included in the output device, such that specific information is output to an actor in the examination room via the proximate loudspeaker.

13. The controller of claim 10 , wherein the circuitry is further configured to cause the controller to:

generate the output data to produce a synthetic speech; and

output the synthetic speech through a proximate loudspeaker, of a plurality of loudspeakers included in the output device, such that specific information is output to an actor in the examination room via the proximate loudspeaker.

14. The controller of claim 9 , wherein the circuitry is further configured to cause the controller to:

generate the output data to produce a synthetic speech; and

output the synthetic speech through a proximate loudspeaker, of a plurality of loudspeakers included in the output device, such that specific information is output to an actor in an examination room via the proximate loudspeaker.

15. The controller of claim 9 , wherein the circuitry is further configured to cause the controller to,

output result output data including film data for documentation purposes in response to a request for help, the request for help requested via voice control.

16. The controller of claim 9 , wherein the result output data includes data for an output, and the circuitry is further configured to cause the controller to activate an output for dedicated actors.

17. The controller of claim 9 , wherein circuitry is further configured to cause the controller to systematically analyze the output produced via the result output data at least one of during or after output, with regard to acceptance by actors.

18. An information system for the output of information in the context of medical diagnostics and therapy, comprising:

the controller of claim 8 ;

an output device; and

a speech recording

wherein the circuitry is further configured to cause the information system to

process the speech recording while continuing to create the speech recording,

determine the captured keywords in the speech recording,

generate result output data based on the captured keywords, and

control the output device with the result output data.

19. A non-transitory computer program product, storing a computer program, directly loadable into a memory device of a computing system or an information system, for output of information in a context of medical diagnostics and therapy, the computer program including program segments, to perform a control method, when the computer program is executed in the computing system or the information system, the control method comprising:

recognizing, via an algorithm for recognizing spoken words, spoken words spoken by a plurality of actors;

training an untrained controller, via machine learning, to predict a subsequent action performed by the plurality of actors following a captured keyword by

providing a number of speech recordings, each speech recording of the number of speech recordings including a communication during a medical procedure, wherein the number of speech recordings concern comparable medical procedures,

performing a speech analysis of the speech recordings, and

training the untrained controller according to a machine learning principle based upon the speech analysis of the speech recordings;

creating a speech recording during a medical procedure;

processing the speech recording while continuing to create the speech recording;

determining the captured keywords in the speech recording;

generating result output data based on the captured keywords; and

controlling an output device with the result output data.