CN104750965A - User exercise state determination method and device - Google Patents

Abstract

Embodiments of the present invention provide a method and device for determining a user's exercise state. The method includes: the server acquires the user's exercise data collected by the collection device within a preset first time period; according to the exercise steps in the acquired exercise data, Select a piece of motion data from the acquired motion data, and process the selected motion data through variable length segment combination, match with the preset motion data, and set the motion state corresponding to the preset motion data , as the motion state corresponding to a piece of motion data with the highest matching degree. In the embodiment of the present invention, the collection device, such as a portable device, only needs to report the relevant exercise data of the user, and does not need to perform relevant analysis, which reduces the power consumption of the collection device, and the server uses the preset exercise data to provide certain information to the user. The motion data in the time period is analyzed to obtain the different motion states of the user during this period, which is more convenient to operate and improves the user experience.

Description

A method and device for determining a user's motion state

technical field

The present invention relates to the field of communication technologies, in particular to a method and device for determining a user's exercise state.

Background technique

At present, if you want to know the running status of the user within a certain period of time, it is usually to use an acquisition device (such as a portable device) that is easy to carry on the user to collect the triaxial acceleration data of the user within a certain period of time, and then, the portable device Correlation calculations are performed on the three-axis acceleration data during this period of time, and then the user's exercise state during this period is obtained, for example, the exercise state is running, walking, cycling, etc.

Due to the limited power supply energy provided by the above-mentioned portable devices for users, if users frequently use this device to determine their own exercise status, this will lead to a relatively fast power consumption of the device, which is inconvenient for the user to use, and is limited by the computing power of the device. However, it can only provide the user with a specific exercise state in a short period of time, and cannot identify the user's specific exercise state in a long period of time, making the user experience poor.

Contents of the invention

Embodiments of the present invention provide a method and device for determining a user's exercise state, which are used to solve the existing problems of inconvenient operation and low user experience caused by using a portable device to identify a user's exercise state.

Based on the above problems, an embodiment of the present invention provides a method for determining a user's exercise state, including:

The server acquires the user's exercise data collected by the collection device within a preset first time period, the exercise data including the number of exercise steps of the user in each preset period;

According to the number of exercise steps in the acquired exercise data, select a piece of exercise data from the acquired exercise data, and process the selected exercise data by means of variable-length segment combination, and then match it with the preset exercise data, The exercise state corresponding to the preset exercise data is used as the exercise state corresponding to the segment of exercise data with the highest matching degree.

A device for determining a user's exercise state provided by an embodiment of the present invention includes:

An acquisition module, configured to acquire motion data of the user collected by the collection device within a preset first time period, the motion data including the number of motion steps of the user within each preset period;

The determination module is used to select a piece of exercise data from the acquired exercise data according to the number of exercise steps in the acquired exercise data, and after processing the selected exercise data by means of variable-length segment combination, it is combined with the preset The motion data is matched, and the motion state corresponding to the preset motion data is used as the motion state corresponding to the segment of motion data with the highest matching degree.

The beneficial effects of the embodiments of the present invention include:

Embodiments of the present invention provide a method and device for determining a user's exercise state. In the method, the server obtains the user's exercise data collected by the collection device within a preset first time period; Steps, select a piece of motion data from the acquired motion data, and process the selected motion data through variable length segment combination, match with the preset motion data, and match the preset motion data The motion state of is taken as the motion state corresponding to the segment of motion data with the highest matching degree. In the embodiment of the present invention, the collection device, such as a portable device, only needs to report the relevant exercise data of the user without performing relevant analysis, which reduces the power consumption of the collection device, and the server selects a section from the user's exercise data. Motion data, and after it is dynamically processed by variable-length segment combination, it is matched with the preset motion data, and then the different motion states of the user during this period are obtained, which is more convenient to operate and improves the user experience. experience.

Description of drawings

FIG. 1 is a flowchart of a method for identifying a user's motion state provided by an embodiment of the present invention;

Fig. 2 is the flowchart that the server that the embodiment of the present invention provides handles the motion data that obtains;

FIG. 3(a) is a schematic waveform diagram of motion segments included in preset motion data provided by an embodiment of the present invention;

FIG. 3(b) is a schematic waveform diagram of motion segments included in the motion data within the second time period provided by the embodiment of the present invention;

Figure 3(c) to Figure 3(g) are schematic diagrams of the waveforms of each group of motion data to be matched provided by the embodiment of the present invention;

FIG. 4 is a flow chart of determining a user's exercise state within a certain day by a server provided by an embodiment of the present invention;

FIG. 5 is a structural diagram of an apparatus for identifying a user's exercise state provided by an embodiment of the present invention.

Detailed ways

The specific implementation manners of a method and an apparatus for determining a user's exercise state provided by embodiments of the present invention will be described below with reference to the accompanying drawings in the description.

A method for determining a user's exercise state provided by an embodiment of the present invention, as shown in FIG. 1 , specifically includes the following steps:

S11: The server acquires the motion data of the user collected by the collection device within the preset first time period;

Here, the above exercise data includes the number of exercise steps of the user in each preset cycle;

S12: According to the number of exercise steps in the acquired exercise data, select a piece of exercise data from the acquired exercise data, and process the selected exercise data by means of variable-length segment combination, and perform a process with the preset exercise data. For matching, the motion state corresponding to the preset motion data is used as the motion state corresponding to a piece of motion data with the highest matching degree.

Specifically, in the above step S11, when the acquisition device is a portable device that is easy for the user to carry on the body, it only needs to upload the relevant exercise data, and there is no need to analyze the exercise data, which saves a lot of power. It is more convenient for users to use, that is, the user experience is improved.

It should be noted that the above preset first time period and the above preset cycle can be determined according to the actual demand for user motion recognition, for example, the preset first time period is from 0:00 to 24:00, that is, one day Time; for example, the preset period is 5 minutes. In this case, the above exercise data is actually the number of exercise steps generated by a user every 5 minutes during the period from 0:00 to 24:00 of a certain day .

Preferably, in the above step S12, for the server, as shown in FIG. 2, the acquired motion data can be processed through the following steps:

S21: Select the exercise data within the preset second time period from the acquired exercise data, and among the selected exercise data, select the exercise data whose number of exercise steps in consecutive multiple preset periods is greater than the set value The resulting motion segment;

S22: According to the number of motion segments included in the preset motion data, combine the selected motion segments to obtain each group of motion data to be matched in the second time period;

Here, the above-mentioned second time period includes the time period corresponding to the preset motion data;

S23: Match the obtained sets of motion data to be matched with the preset motion data respectively.

Preferably, in the above-mentioned step S21, the above-mentioned second preset time period can also be determined according to the actual situation of the user's exercise. One or more sets of exercise data are defined, each corresponding to a time period. These exercise data are obtained by sampling the exercise data of multiple users and after correlation analysis. Usually, each second time period needs to include preset exercise data. The time period corresponding to the data, so that the user's exercise state can be accurately determined later. For example, when the time period corresponding to a certain set of preset exercise data is from 8:00 to 9:00, the second time period It can be set from 7:30 to 9:30.

Further, in the above-mentioned step S21, the above-mentioned set value can be determined according to the actual exercise situation of the user, for example, it is usually set to 0, that is, an exercise is formed by the exercise data with the number of steps greater than 0 in a plurality of consecutive preset periods. Fragments, other parts of motion data make up non-motion fragments. Of course, the above-mentioned set numerical values may also be set to other numerical values.

For example, taking the above-mentioned second time period of 7:30 to 9:30 as an example, assuming that the above-mentioned setting value is 0, assume that the user's exercise data from 7:30 to 8:00 is shown in Table 1 below:

Table 1

cycle Step count 7:30—7:35 0

7:35—7:40 0 7:40—7:45 15 7:45—7:50 17 7:50—7:55 0 7:55-8:00 0 8:00—8:05 20 8:05—8:10 15 8:15-8:20 18 8:20-8:25 0

In the above Table 1, the above motion data can form two motion segments, that is, the time period from 7:40 to 7:50 constitutes one motion segment, and the time period from 8:00 to 8:20 constitutes another motion segment, The motion data of other parts forms a non-motion segment, that is, the time period from 7:30 to 7:40 forms a non-motion segment, the time period from 7:50 to 8:00 forms a non-motion segment, and the time period from 8:20 to 8 :25 This period of time constitutes a non-motion segment.

Preferably, in the above step S22, for the server, each group of motion data to be matched in the second time period can be obtained specifically through the following process: for the selected motion segments adjacent to N-1 and N Combine with N+1 motion segments to obtain the combined groups of motion segments in the second time period; and combine each group of motion segments after the combination with the non-motion segments between each group of motion segments to obtain Each group of motion data to be matched in the second time period. Here, N is the number of motion segments included in the preset motion data, and N is an integer greater than 2;

That is to say, assume that the time period corresponding to the preset motion data is from 8:00 to 9:00, and the included motion segments are the two motion segments A and B (the waveform segment shown in Figure 3(a)); Assuming that the motion segments of the second time period (7:30 to 9:30) are the four motion segments C, D, E and F (the waveform segment shown in Figure 3(b)), then the second In the four motion segments in the time period, the adjacent 2 and adjacent 3 motion segments can be combined to obtain each group of motion data to be matched in the second time segment, specifically: the to-be-matched motion data formed after the combination of C and D Match motion data (wave segment as shown in Figure 3(c)), motion data to be matched formed after combination of D and E (wave segment as shown in Figure 3(d)), combination of E and F to form Match motion data (wave segment as shown in Figure 3(e)), C, D and E combined to form the data to be matched (wave segment as shown in Figure 3(f)) and D, E and F (as shown in The waveform segment shown in Fig. 3(g)) these 5 sets of motion data to be matched.

Preferably, in the above step S23, the server usually adopts a Dynamic Time Warping algorithm (DynamicTime Warping, DTW) to respectively match each set of motion data to be matched with the preset motion model data. The specific matching process is as follows: The prior art will not be described in detail here.

For example, still taking the time period mentioned in the previous paragraph as an example, it is actually the motion data to be matched formed by the combination of C and D, the motion data to be matched formed by the combination of D and E, and the motion data to be matched formed by the combination of E and F. The five sets of motion data to be matched, the motion data to be matched formed by the combination of C, D, and E, and the motion data to be matched formed by the combination of D, E, and F, are matched with the preset motion data one by one. Assuming that the dynamic time rounding algorithm is used to match the motion data to be matched after the combination of C, D, and E (the waveform segment shown in Figure 3(f)) is the motion data with the highest matching degree, then C, D, and E The exercise state of the exercise data to be matched formed after the combination is the exercise state corresponding to the preset exercise data, for example, the exercise state corresponding to the preset exercise data is early commuting.

In the embodiment of the present invention, for the server, after taking the exercise state corresponding to the preset exercise data as the exercise state corresponding to the exercise data with the highest matching degree, divide the first period of time by dividing the exercise state with the highest matching degree The exercise state corresponding to other time periods other than the time period corresponding to the exercise data is set as the preset exercise state, and each exercise state of the user in the first time period can be obtained.

That is to say, after using the above-mentioned determination process to obtain the motion state of certain specific time periods, within the above-mentioned first time period, the motion states corresponding to time periods other than these specific time periods are all set in advance, so that , users can log in to the server to check their specific exercise status in a certain day, which improves the user experience.

The method for determining the above-mentioned user's motion state will be described in detail below in conjunction with the following specific embodiments:

Assume that the server obtains the exercise data of a certain user collected by the portable device on a certain day (0:00 to 24:00), and pre-sets 3 sets of exercise data, corresponding to 3 different time periods (that is, 8: 00-9:00, 11:00-12:00 and 17:00-18:00), the corresponding exercise states are morning commuting, lunch and late commuting; assuming the preset period is 5 minutes, the set value is 0 , then, as shown in Figure 4, the server needs to perform the following steps to complete the determination of the user's exercise state:

S41: Select the exercise data in the current second time period (for example, 7:30-9:30, including the time period of 8:00-9:00) from the acquired exercise data, and then select the exercise data from the selected period of exercise data Select the motion segment formed by the motion data with multiple consecutive 5-minute motion steps greater than 0;

S42: respectively combine N-1, N and N+1 adjacent motion segments among the selected motion segments to obtain each group of combined motion segments, and combine each group of combined motion segments with After the non-motion segments between each group of motion segments are combined, each group of motion data to be matched in the time period of the current second time period (for example, 7:30-9:30) is obtained;

Here, N is the number of motion segments included in the preset motion sequence, and N is an integer greater than 2;

S43: Match the exercise data to be matched with the preset exercise data in the preset matching library (for example, the preset exercise data corresponding to the time period of 8:00-9:00), and match the preset exercise data corresponding to Exercise state (such as early commuting corresponding to the time period of 8:00-9:00), as the exercise state corresponding to the most matching segment of exercise data;

S44: Determine whether the acquired motion data matches all the preset motion data; if so, execute step S45, otherwise, set the next second time period (for example, 10:30-12:30, including 11:00-12: 00 this time period) as the current second time period, return to above-mentioned step S41;

S45: Set the exercise states corresponding to other time periods in the first time period except the time period corresponding to the movement data with the highest matching degree as the preset exercise states, and obtain the user's exercise states in the first time period .

In the above process, the server needs to execute the above process three times before it can match the above three sets of preset exercise data. For example, after the server executes the above process, it determines the user's exercise status from 0:00 to 24:00 as shown in the following table 2.

Table 2

period User's motion state

0:00 to 8:00 (default) sleep 8:00 to 9:00 commute early 9:00 to 11:00 (default) office 11:00 to 12:00 Lunch 12:00 to 17:00 (default) office 17:00 to 18:00 late commute 18:00 to 24:00 (Default) Evening sports

Based on the same inventive concept, the embodiment of the present invention also provides a device for determining the user's exercise state. Since the principle of the problem solved by the device is similar to the aforementioned method for determining the user's exercise state, the implementation of the device can refer to the implementation of the aforementioned method. , the repetitions will not be repeated.

A device for determining a user's exercise state provided by an embodiment of the present invention, as shown in FIG. 5 , specifically includes:

An acquisition module 51, configured to acquire motion data of the user collected by the collection device within a preset first time period;

Here, the above exercise data includes the number of exercise steps of the user in each preset cycle;

The determining module 52 is used to select a segment of exercise data from the acquired exercise data according to the number of exercise steps in the acquired exercise data, and after processing the selected exercise data by means of variable-length segment combinations, it is combined with the preset Assuming that the motion data matches the motion data, the motion state corresponding to the preset motion data is used as the motion state corresponding to the segment of motion data with the highest matching degree.

Preferably, the above-mentioned determining module 52 is specifically configured to select motion data within a preset second time period from the acquired motion data, and select motion data within a plurality of consecutive preset periods among the selected motion data. Motion segments formed by motion data whose steps are greater than a set value; according to the number of motion segments included in the preset motion data, the selected motion segments are combined to obtain each group of motion data to be matched in the second time period; and The obtained sets of exercise data to be matched are respectively matched with the preset exercise data, and the second time period includes a time period corresponding to the preset exercise data.

Preferably, the above-mentioned determination module 52 is specifically configured to combine the N-1, N and N+1 adjacent motion segments among the selected motion segments to obtain the combined groups in the second time period motion segments; and combining each group of combined motion segments with non-motion segments between each group of motion segments to obtain each group of motion data to be matched in the second time period. Here, N is the number of motion segments included in the preset motion sequence, and N is an integer greater than 2.

Preferably, the determination module 52 is specifically configured to use a dynamic time rounding algorithm to respectively match the obtained sets of motion data to be matched with the preset motion model data.

Preferably, the above-mentioned determination module 52 is further configured to, after taking the motion state corresponding to the preset motion data as the motion state corresponding to a segment of motion data with the highest degree of matching, divide the segment of motion data with the highest degree of matching within the first time period The exercise states corresponding to other time periods other than the corresponding time period are set as preset exercise states, and the user's exercise states in the first time period are obtained.

Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and equivalent technologies thereof, the present invention also intends to include these modifications and variations.

Claims (10)

1. A method for determining a user's motion state, comprising: The server acquires the user's exercise data collected by the collection device within a preset first time period, the exercise data including the number of exercise steps of the user in each preset period; According to the number of motion steps in the acquired motion data, a piece of motion data is selected from the acquired motion data, and the selected motion data is processed by a variable-length segment combination, and then matched with the preset motion data, The motion state corresponding to the preset motion data is used as the motion state corresponding to a piece of motion data with the highest matching degree. 2. The method according to claim 1, wherein the server selects a section of motion data from the motion data obtained according to the number of motion steps in the motion data obtained, and performs a variable-length segmentation to After it is processed, it is matched with preset motion data, including: Select motion data within a preset second time period from the acquired motion data, and among the selected motion data, select motion data whose number of motion steps in a plurality of consecutive preset periods is greater than a set value The resulting motion segment; According to the number of motion segments included in the preset motion data, the selected motion segments are combined to obtain each group of motion data to be matched in the second time period, the second time period includes the preset motion The time period corresponding to the data; The obtained sets of motion data to be matched are respectively matched with the preset motion data. 3. The method according to claim 2, wherein the server obtains each group of motion data to be matched in the second time period in the following manner: The server respectively combines N-1, N and N+1 adjacent motion segments among the selected motion segments to obtain groups of combined motion segments in the second time period, wherein N is the number of motion segments included in the preset motion data, and N is an integer greater than 2; Each group of combined motion segments is combined with the non-motion segments between each group of motion segments to obtain each group of motion data to be matched in the second time period. 4. The method according to claim 2, wherein the server uses a dynamic time rounding algorithm to respectively match the obtained sets of motion data to be matched with the preset motion model data. 5. The method according to any one of claims 1-4, further comprising: After the server takes the motion state corresponding to the preset motion data as the motion state corresponding to a segment of motion data with the highest degree of matching, the server divides the time range corresponding to the segment of motion data with the highest degree of matching within the first time period. The exercise states corresponding to other time periods are set as preset exercise states, and each exercise state of the user in the first time period is obtained. 6. A device for determining a user's exercise state, comprising: An acquisition module, configured to acquire motion data of the user collected by the collection device within a preset first time period, the motion data including the number of motion steps of the user within each preset period; The determination module is used to select a piece of exercise data from the acquired exercise data according to the number of exercise steps in the acquired exercise data, and after processing the selected exercise data by means of variable-length segment combination, it is combined with the preset The motion data is matched, and the motion state corresponding to the preset motion data is used as the motion state corresponding to the segment of motion data with the highest matching degree. 7. The device according to claim 6, wherein the determination module is specifically configured to select exercise data within a preset second time period from the acquired exercise data, and select the exercise data in the selected exercise data , selecting a motion segment formed by motion data whose number of motion steps in a plurality of consecutive preset periods is greater than a set value; performing the selected motion segment according to the number of motion segments included in the preset motion data Combine to obtain each group of motion data to be matched in the second time period; and match each group of motion data to be matched with the preset motion data respectively, and the second time period includes the preset The time period corresponding to the motion data. 8. The device according to claim 7, wherein the determining module is specifically configured to respectively combine N-1, N and N+1 adjacent motion segments among the selected motion segments , to obtain the combined groups of motion segments in the second time period; and combine each group of motion segments after the combination with the non-motion segments between each group of motion segments to obtain the second time period Each set of motion data to be matched, wherein, N is the number of motion segments included in the preset motion data, and N is an integer greater than 2. 9. The device according to claim 7, wherein the determining module is specifically configured to use a dynamic time rounding algorithm to combine the obtained sets of motion data to be matched with the preset motion model data to match. 10. The device according to any one of claims 6-9, wherein the determining module is further configured to use the motion state corresponding to the preset motion data as a segment of motion data corresponding to the highest degree of matching After the exercise state, set the exercise states corresponding to other time periods in the first time period except the time period corresponding to the most matching period of exercise data as the preset exercise state, and obtain the user’s Each motion state in the first time period is described.