Assistance method and assistance system and assistance device using assistance method that execute processing relating to a behavior model
A driving assistance device executes processing relating to a behavior model of a vehicle. Detected information from the vehicle is input to a detected information inputter. An acquirer derives at least one of a travel difficulty level of a vehicle, a wakefulness level of a driver, and a driving proficiency level of the driver on the basis of the detected information that is input to the detected information inputter. A determiner determines whether or not to execute processing on the basis of at least one information item derived by the acquirer. If the determiner has made a determination to execute the processing, a processor executes the processing relating to the behavior model. It is assumed that the processor does not execute the processing relating to the behavior model if the determiner has made a determination to not execute the processing.
1. An assistance system that executes processing relating to a behavior model for an utterance, the assistance system comprising:
a processor; and
a memory coupled to the processor, the memory storing a program that, when executed by the processor, causes the assistance system to:
receive an input of detected information for the utterance;
acquire, as an information item affecting accuracy of the behavior model, content of the utterance on a basis of the detected information;
acquire, as the information item affecting accuracy of the behavior model, content of a position of processing for the behavior model;
determine whether or not to execute the processing relating to the behavior model on the basis of the content of the utterance;
determine to not execute the processing relating to the behavior model if the position of processing for the behavior model is not spaced apart from a position of the utterance via a network; and
execute the processing relating to the behavior model in response to determining to execute the processing relating to the behavior model, and not execute the processing relating to the behavior model in response to determining to not execute the processing,
wherein the processor, during execution of the processing relating to the behavior model, receives the content of the utterance as an input parameter, inputs the input parameter to a neural network, adjusts a weight parameter of the neural network, and performs learning of a relationship between the input parameter to the neural network and supervision data.
2. The assistance system according to claim 1 , wherein the program further causes the assistance system to:
determine to not execute the processing relating to the behavior model if the content of the utterance is unplanned.
3. The assistance system according to claim 1 , wherein the program further causes the assistance system to:
acquire, as the information item affecting accuracy of the behavior model, content of a speaker of the utterance;
recognize the speaker of the utterance; and
determine to not execute the processing relating to the behavior model if the speaker of the utterance is unplanned.
4. The assistance system according to claim 1 , further comprising:
a reporter including at least one of a display or a speaker,
wherein the program further causes the assistance system to report, by the reporter, a determination result indicating whether or not the processing relating to the behavior model is being executed.
5. The assistance system according to claim 4 ,
wherein, in response to determining to execute the processing relating to the behavior model, the reporter outputs a reason for learning indicating why the processing relating to the behavior model is being executed with the determination result indicating the processing relating to the behavior model is being executed.
6. The assistance system according to claim 4 ,
wherein, in response to determining to execute the processing relating to the behavior model, the reporter outputs an identity of a speaker of the utterance toether with the determination result indicating the processing relating to the behavior model is being executed.
7. The assistance system according to claim 1 , wherein the memory pre-stores keywords which are to be included in planned utterance content, and which are divided into first keywords to be processed at the position of processing for the behavior model spaced apart from the position of the utterance via the network and second keywords to be processed at an internal position.
8. An assistance system that executes processing relating to a behavior model for an utterance, the assistance system comprising:
a reporter including at least one of a display or a speaker;
a processor; and
a memory coupled to the processor, the memory storing a program that, when executed by the processor, causes the assistance system to:
receive an input of detected information for the utterance;
acquire, as an information item affecting accuracy of the behavior model, content of the utterance on a basis of the detected information;
determine whether or not to execute the processing relating to the behavior model on the basis of the content of the utterance;
execute the processing relating to the behavior model in response to determining to execute the processing relating to the behavior model, and not execute the processing relating to the behavior model in response to determining to not execute the processing,
wherein the processor, during execution of the processing relating to the behavior model, receives the content of the utterance as an input parameter, inputs the input parameter to a neural network, adjusts a weight parameter of the neural network, and performs learning of a relationship between the input parameter to the neural network and supervision data; and
report, by the reporter, a determination result indicating whether or not the processing relating to the behavior model is being executed,
wherein, in response to determining to execute the processing relating to the behavior model, the reporter outputs a reason for learning indicating why the processing relating to the behavior model is being executed with the determination result indicating the processing relating to the behavior model is being executed.