Granted Patent B2

US 12,454,271 · App. 18/566,244 · Granted Oct 28, 2025

Inventors: Nao Ito (Tokyo, JP); Takeshi Tanaka (Tokyo, JP); Shunsuke Minusa (Tokyo, JP); Hiroyuki Kuriyama (Tokyo, JP); Kiminori Sato (Tokyo, JP)

Assignee: LOGISTEED, LTD.

B60W40/08B60W50/0097B60W50/14B60W2050/0083B60W2050/146B60W2540/221B60W2556/20

Abstract

Claims (61)

1. An operation management aid system for reducing driver accident risk, the operation management aid system comprising:

a memory that stores a first group of associated data in which biological measurement data pertaining to a biology of a driver is associated with task state data pertaining to a respective task state among a plurality of task states of the driver, and a second group of danger determination results indicating a degree of danger of driving by the driver; and

a processor that is communicatively coupled to the memory, wherein the processor is configure to:

perform a first acquisition process that acquires for each of the plurality of task states, the associated data pertaining to a specific task state of the driver from the first group, and acquiring a specific danger determination result group in the specific task state of the driver from the second group,

perform a generation process, using an associated data group pertaining to the specific task state and a specific danger determination result group for the specific task state, which were acquired during the first acquisition process, to generate, for each of the specific task states, an estimation model that estimates an accident risk of the driver during the specific task state, and saving the estimation model in a third group,

execute an association process of associating the biological measurement data with the task state of the task state data during a same time period and for a same driver, and saving the associated data in the first group, and

executes a detection process of detecting invalid data indicating behavior irrelevant to the association process, from among the biological measurement data groups split into time segments,

wherein, during the association process, the processor does not perform association for the invalid data detected during the detection process

wherein the first acquisition process includes:

acquiring an associated data group pertaining to the specific task state of the driver from the first group in which the associated data that was associated by the association process is saved, and

wherein association process includes

splitting the biological measurement data into time segments,

for each biological measurement data group split into time segments, associating therewith the task state of the task state data during the same time period and for the same driver, and

saving the associated biological measurement data group and task state in the first group.

2. The operation management aid system according to claim 1 ,

wherein the biological measurement data is data based on a heart rate of the driver.

3. The operation management aid system according to claim 2 ,

wherein the data based on the heart rate of the driver is data pertaining to an autonomic nerve function of the driver.

4. The operation management aid system according to claim 1 ,

wherein, during the detection process, if the biological measurement data is data based on a heart rate, the processor detects the invalid data from the biological measurement data group split into time segments by a heartbeat interval.

5. The operation management aid system according to claim 1 ,

wherein, during the detection process, the processor detects the invalid data indicating behavior based on body movement noise from the biological measurement data group split into time segments.

6. The operation management aid system according to claim 1 ,

wherein:

the processor is further configured to execute a setting process of setting the task state data based on at least one of an action of the driver, recording data that records the action of the driver, and a behavior of a vehicle driven by the driver, and

wherein, during the association process, the processor associates the biological measurement data with the respective task state of the task state data during the same time period and for the same driver set by the setting process, and saves the associated biological measurement data and task state in the first group.

7. The operation management aid system according to claim 1 ,

wherein the processor is further configured to execute:

a second acquisition process of acquiring associated data for an item subject to prediction;

a selection process of selecting, from the third group, the estimation model for a same task state as a task state included in the associated data, for the item subject to the prediction, acquired during the second acquisition process;

an estimation process of inputting the associated data for an item subject to the prediction to the estimation model selected by the selection process to estimate the accident risk of the item subject to the prediction; and

an output process of outputting an estimation result from the estimation process.

8. The operation management aid system according to claim 7 ,

wherein, in the output process, the processor further outputs information for alerting the driver of the estimation result.

9. The operation management aid system according to claim 7 ,

wherein, in the output process, the processor further outputs as the estimation result a shift in the accident risk for the item subject to the prediction and the task state included in the associated data of the item subject to the prediction, in a manner enabling display thereof.

10. An operation management aid method for reducing driver accident risk, the method comprising

storing a first group of associated data in which biological measurement data pertaining to a biology of a driver is associated with task state data pertaining to a respective task state among a plurality of task states of the driver, and a second group of danger determination results indicating a degree of danger of driving by the driver,

performing a first acquisition process that acquires, for each of the plurality of task states, the associated data pertaining to a specific task state of the driver from the first group, and acquiring a specific danger determination result group in the specific task state of the driver from the second group;

performing a generation process using an associated data group pertaining to the specific task state and the specific danger determination result group for the specific task state, which were acquired during the acquisition process, to generate an estimation model that estimates an accident risk of the driver during the specific task state, and saving the estimation model in a third group;

executing an association process of associating the biological measurement data with the task state of the task state data during a same time period and for a same driver, and saving the associated data in the first group; and

executing a detection process of detecting invalid data indicating behavior irrelevant to the association process, from among the biological measurement data groups split into time segments,

wherein, during the association process, an association for the invalid data detected during the detection process is not performed,

wherein the first acquisition process includes:

acquiring an associated data group pertaining to the specific task state of the driver from the first group in which the associated data that was associated by the association process is saved, and

wherein association process includes

splitting the biological measurement data into time segments,

for each biological measurement data group split into time segments, associating therewith the task state of the task state data during the same time period and for the same driver, and

saving the associated biological measurement data group and task state in the first group.

11. A non-transitory computer readable storage medium storing instruction for reducing driver accident risk, the instructions when executed by a processor cause the processor to perform a method comprising:

storing a first group of associated data in which biological measurement data pertaining to a biology of a driver is associated with task state data pertaining to a respective task state among a plurality of task states of the driver, and a second group of danger determination results indicating a degree of danger of driving by the driver, performing a first acquisition process that acquires, for each of the plurality of task states, the associated data pertaining to a specific task state of the driver from the first group, and acquiring a specific danger determination result group in the specific task state of the driver from the second group;

performing a generation process using an associated data group pertaining to the specific task state and the specific danger determination result group for the specific task state, which were acquired during the acquisition process, to generate an estimation model that estimates an accident risk of the driver during the specific task state, and saving the estimation model in a third group;

executing an association process of associating the biological measurement data with the task state of the task state data during a same time period and for a same driver, and saving the associated data in the first group; and

executing a detection process of detecting invalid data indicating behavior irrelevant to the association process, from among the biological measurement data groups split into time segments,

wherein, during the association process, an association for the invalid data detected during the detection process is not performed,

wherein the first acquisition process includes:

acquiring an associated data group pertaining to the specific task state of the driver from the first group in which the associated data that was associated by the association process is saved, and

wherein association process includes

splitting the biological measurement data into time segments,

for each biological measurement data group split into time segments, associating therewith the task state of the task state data during the same time period and for the same driver, and

saving the associated biological measurement data group and task state in the first group.

Assignments (4)

Priority Claims (1)

Continuity (1)

References Cited (15)