Method for monitoring swimming state by means of wearable device, and wearable device

1. A method for monitoring a swimming state by using a wearable device, comprising:

providing a swimming mode in the wearable device, and storing standard swimming stroke data that has been collected in advance as corresponding template data,

when a monitoring process starts, activating the swimming mode according to an instruction given by a user who will immediately enter water, and after the swimming mode has been activated, controlling a sensor to collect swimming stroke data of the user;

obtaining test data from the swimming stroke data for identifying a swimming state of the user; and

matching the test data with each template data, and when the test data that is successfully matched to the template data exist, identifying the swimming state of the user to be the swimming state that corresponds to the template data associated with the test data that is successfully matched,

wherein the controlling of the sensor to collect swimming stroke data comprises controlling the sensor to collect three-axis acceleration data of the swimming stroke of the user by using a three-axis acceleration sensor, and obtaining the test data,

wherein the matching of the test data with each template data comprises, for a group of test data, matching data of each axis direction of the three axis directions respectively with data of corresponding axis direction in the template data, and obtaining a matching result of the group of test data according to matching results of the three axis directions, and

wherein the matching data of each axis direction of the three axis directions respectively with data of corresponding axis direction in the template data, and obtaining the matching result of the group of test data according to the matching results of the three axis directions comprises, by using dynamic time warping DTW, calculating a shortest DTW distance between the data of each axis direction of the group of test data that have been normalized and the data of the corresponding axis direction of each template data respectively, summating shortest DTW distances of the axis directions, and using template data that have a minimum summation value as the template data associated with the group of test data.

2. The method according to claim 1 , wherein the step of storing standard swimming stroke data that have been collected in advance as corresponding template data comprises:

collecting standard swimming stroke data in advance, generating the template data according to the collected standard swimming stroke data and storing the template data in the wearable device, wherein the standard swimming stroke data comprise at least breaststroke data, freestyle data, butterfly stroke data and backstroke data; and

the step of identifying the swimming state of the user to be the swimming state that corresponds to the template data associated with the test data that are successfully matched comprises:

identifying the swimming stroke of the user to be breaststroke, freestyle, butterfly stroke or backstroke that corresponds to the template data associated with the test data that are successfully matched.

3. The method according to claim 1 , wherein the step of controlling a sensor to collect swimming stroke data of the user comprises:

controlling the sensor to collect and obtain swimming stroke data of a swimming lap of the user; and

selecting swimming stroke data of a stroke cycle from the swimming stroke data of the swimming lap of the user as the test data.

4. The method according to claim 3 , wherein the step of selecting swimming stroke data of a stroke cycle from the swimming stroke data of the swimming lap of the user as the test data comprises:

acquiring a total number of stroke cycles in the swimming lap of the user, and selecting the swimming stroke data of any stroke cycle other than a first stroke cycle and a last stroke cycle as the test data; or

acquiring a total number N of stroke cycles in the swimming lap of the user, and when N is an even number, selecting the swimming stroke data of the N/2 stroke cycle or the N/2+1 stroke cycle as the test data, and when N is an odd number, selecting the swimming stroke data of the (N+1)/2 stroke cycle as the test data.

5. The method according to claim 3 , wherein the step of selecting swimming stroke data of a stroke cycle from the swimming stroke data of the swimming lap of the user as the test data comprises:

in axis direction data that correspond to a forward direction of swimming, selecting data between two neighboring waveform peak values which are used as end points as the swimming stroke data of a stroke cycle.

6. The method according to claim 3 , further comprising:

conducting smoothing filtering processing on the selected swimming stroke data of a stroke cycle by using K time-nearest neighbor mean filtering, to filter out noise interference; and

conducting data normalization processing on the filtered swimming stroke data, to normalize the filtered swimming stroke data into a range of ±10.

7. A wearable device comprising:

a three-axis acceleration sensor;

a memory; and

a processor configured to:

store, in the memory, standard swimming stroke data that has been collected in advance as corresponding template data;

when a monitoring process starts, activate the swimming mode according to an instruction given by a user who will immediately enter water, control the sensor to collect swimming stroke data of the user, obtain test data from the swimming stroke data for identifying a swimming state of the user, control the three-axis acceleration sensor to collect three-axis acceleration data of the swimming stroke of the user, and obtain the test data;

match the test data with each template data, and when the test data that is successfully matched to the template data exist, identify the swimming state of the user to be the swimming state that corresponds to the template data associated with the test data that is successfully matched;

for a group of test data, match data of each axis direction of the three axis directions respectively with data of corresponding axis direction in the template data; and

obtain a matching result of the group of test data according to the matching results of the three axis directions, by using dynamic time warping DTW, calculating a shortest DTW distance between the data of each axis direction of the group of test data that has been normalized and the data of the corresponding axis direction of each template data respectively, summating shortest DTW distances of the axis directions, and using template data that has a minimum summation value as the template data associated with the group of test data.

8. The wearable device according to claim 7 , wherein the processor is further configured to:

collect standard swimming stroke data in advance, generating the template data according to the collected standard swimming stroke data and storing the template data in the wearable device, wherein the standard swimming stroke data comprise at least breaststroke data, freestyle data, butterfly stroke data and backstroke data; and

identify the swimming stroke of the user to be breaststroke, freestyle, butterfly stroke or backstroke that corresponds to the template data associated with the test data that are successfully matched.

9. The wearable device according to claim 7 , wherein the processor is further configured to control the sensor to collect swimming stroke data of a swimming lap of the user; and selecting swimming stroke data of a stroke cycle from the swimming stroke data of the swimming lap of the user as the test data.

10. The wearable device according to claim 9 , wherein the processor is further configured to acquire a total number of stroke cycles in the swimming lap of the user, and select the swimming stroke data of any stroke cycle other than a first stroke cycle and a last stroke cycle as the test data; or

acquire a total number N of stroke cycles in the swimming lap of the user, and when N is an even number, select the swimming stroke data of the N/2 stroke cycle or the N/2+1 stroke cycle as the test data, and when N is an odd number, select the swimming stroke data of the (N+1)/2 stroke cycle as the test data.

11. The wearable device according to claim 9 , wherein the processor is further configured, in axis direction data that correspond to a forward direction of swimming, to select data between two neighboring waveform peak values which are used as end points as the swimming stroke data of a stroke cycle.

12. The wearable device according to claim 9 , wherein the processor is further configured to conduct a smoothing filtering processing on the selected swimming stroke data of a stroke cycle by using K time-nearest neighbor mean filtering, to filter out noise interference; and conduct data normalization processing on the filtered swimming stroke data, to normalize the filtered swimming stroke data into a range of ±10.