CN110584675B - Information triggering method and device and wearable device - Google Patents
Information triggering method and device and wearable device Download PDFInfo
- Publication number
- CN110584675B CN110584675B CN201910944557.3A CN201910944557A CN110584675B CN 110584675 B CN110584675 B CN 110584675B CN 201910944557 A CN201910944557 A CN 201910944557A CN 110584675 B CN110584675 B CN 110584675B
- Authority
- CN
- China
- Prior art keywords
- activity
- data
- state
- detection
- detection sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1118—Determining activity level
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1123—Discriminating type of movement, e.g. walking or running
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/681—Wristwatch-type devices
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
Abstract
The invention discloses an information triggering method and device and wearable equipment. Wherein, the method comprises the following steps: acquiring activity detection data of a target user by a preset sensor, wherein the preset sensor is worn on a preset body part of the target user; dividing the activity detection data to obtain a plurality of detection sub-window data, wherein each detection sub-window data corresponds to an activity state identifier; determining the activity duration of the target user in the active state based on the plurality of detection sub-window data; and if the activity duration is lower than a preset duration threshold, determining that the target user is in an inactive state, and sending out reminding information, wherein the reminding information is used for reminding the target user of an activity action. The invention solves the technical problems that wearable equipment in the related art needs a heart rate sensor with higher precision when sending motion reminding information, the requirement on the working environment is higher, and the use satisfaction degree of a user is reduced.
Description
Technical Field
The invention relates to the technical field of equipment information processing, in particular to an information triggering method and device and wearable equipment.
Background
In the related art, many users pay attention to physical health and do physical exercises, and in order to ensure physical health, many users do exercises outdoors after finishing work or on holidays; however, this exercise method requires a large amount of idle time, and does not ensure the reasonableness of exercise. Especially to the inactive state such as sitting for a long time in office or the learning process, do not have good equipment among the correlation technique and can make the motion and remind, at present, the function of reminding of standing of intelligent wearable products such as most bracelet wrist-watches relies on rhythm of the heart and triaxial acceleration sensor, some of them can be comparatively accurate send the motion at the right moment with combining together the two and remind, but adopt this kind of method to have higher requirement to rhythm of the heart sensor's precision, and intelligent wearable product needs to operate all day, and this also has certain challenge to its time of endurance.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides an information triggering method and device and wearable equipment, and aims to at least solve the technical problems that the wearable equipment in the related art needs a heart rate sensor with higher precision when sending motion reminding information, the working environment requirement is higher, and the use satisfaction of a user is reduced.
According to an aspect of the embodiments of the present invention, there is provided an information triggering method applied to a wearable device, including: acquiring activity detection data of a target user by a preset sensor, wherein the preset sensor is worn on a preset body part of the target user; dividing the activity detection data to obtain a plurality of detection sub-window data, wherein each detection sub-window data corresponds to an activity state identifier; determining an activity duration of the target user in an active state based on the plurality of detection sub-window data; and if the activity duration is lower than a preset duration threshold, determining that the target user is in an inactive state, and sending out reminding information, wherein the reminding information is used for reminding the target user of an activity action required to be performed.
Optionally, the step of segmenting the activity detection data to obtain a plurality of detection sub-window data includes: determining the interception duration of each sub-window data; and sequentially dividing the activity detection data according to the intercepting duration to obtain a plurality of detection sub-window data.
Optionally, after segmenting the activity detection data to obtain a plurality of detection sub-window data, the information triggering method further includes: for each of the detection sub-window data, determining a data size and a user activity orientation; comparing the data size of the data of the two adjacent detection sub-windows with the user activity direction, and determining the initial activity state of the user; and endowing the activity state identification corresponding to the initial activity state to the corresponding detection sub-window data.
Optionally, after segmenting the activity detection data to obtain a plurality of detection sub-window data, the information triggering method further includes: performing waveform synthesis processing on the active acceleration based on the active acceleration in each detection sub-window data to calculate a combined acceleration value; an acceleration differential increment or an increment normalization value is calculated based on the resultant acceleration values to uniformly limit the resultant acceleration values around a target speed value.
Optionally, after uniformly limiting the resultant acceleration value around the target speed value, the information triggering method further includes: and carrying out filtering processing on the resultant acceleration numerical value to obtain a smooth resultant acceleration numerical value, wherein the filtering processing mode at least comprises the following steps: bessel filters, chebyshev filters, butterworth filters.
Optionally, the active state comprises at least: after obtaining data of a plurality of detection sub-windows, the information triggering method further comprises the following steps: determining a starting sub-window of the target user in an active state based on the active state identification of each detection sub-window data; starting from the starting sub-window, if the active state identifications of a plurality of continuous detection sub-window data indicate that the target user is in an active state, starting to detect the periodic point position of the synthesized waveform; and if the periodic point location indication meets the preset point location condition, starting to perform continuous active state verification processing.
Optionally, the step of determining the activity duration of the target user in the active state based on the plurality of detection sub-window data includes: inputting each detection sub-window data into a state detection model, wherein the state detection model is a state recognition model obtained by off-line training according to a plurality of groups of user activity state data and activity state judgment results, and the model structure of the state detection model at least comprises: a decision tree model, a support vector machine model, a neural network model and an ensemble learning model; and receiving an activity starting point and an activity ending point output by the state detection model to obtain the activity duration of the target user in the activity state.
Optionally, the step of inputting each detection sub-window data into the state detection model includes: extracting direct features and indirect features in each detection sub-window data, wherein the direct features comprise: raw activity detection pose data, the indirect features including at least one of: the activity amplitude, the activity discrete degree and the amplitude difference value of adjacent detection sub-windows; combining the direct features and the indirect features into an active feature vector, and inputting the active feature vector to the state detection model.
Optionally, the preset sensor is a three-axis acceleration sensor.
According to another aspect of the embodiments of the present invention, there is also provided an information triggering apparatus applied to a wearable device, including: the device comprises an acquisition unit, a display unit and a control unit, wherein the acquisition unit is used for acquiring activity detection data of a target user by a preset sensor, and the preset sensor is worn on a preset body part of the target user; the segmentation unit is used for segmenting the activity detection data to obtain a plurality of detection sub-window data, wherein each detection sub-window data corresponds to an activity state identifier; a determining unit, configured to determine, based on the plurality of detection sub-window data, an activity duration of the target user in an active state; and the sending unit is used for determining that the target user is in an inactive state and sending out reminding information when the activity duration is lower than a preset duration threshold, wherein the reminding information is used for reminding the target user of an activity action.
Optionally, the segmentation unit includes: the first determining module is used for determining the interception duration of each sub-window data; and the first segmentation module is used for sequentially segmenting the activity detection data according to the interception duration to obtain a plurality of detection sub-window data.
Optionally, the information triggering apparatus further includes: a second determining module, configured to determine, for each detection sub-window data, a data size and a user activity direction after the activity detection data is segmented to obtain a plurality of detection sub-window data; the comparison module is used for comparing the data size of the data of the two adjacent detection sub-windows with the activity direction of the user and determining the initial activity state of the user; and the giving module is used for giving the activity state identification corresponding to the initial activity state to the corresponding detection sub-window data.
Optionally, the information triggering apparatus further includes: a synthesizing unit, configured to, after the activity detection data is divided to obtain a plurality of detection sub-window data, perform waveform synthesis processing on the activity acceleration based on the activity acceleration in each of the detection sub-window data to calculate a resultant acceleration value; and the calculating unit is used for calculating an acceleration difference increment or an increment normalization value based on the combined acceleration numerical value so as to uniformly limit the combined acceleration numerical value around the target speed value.
Optionally, the information triggering apparatus further includes: a filtering unit, configured to perform filtering processing on the combined acceleration value after the combined acceleration value is uniformly limited around a target velocity value, so as to obtain a smooth combined acceleration value, where the filtering processing manner at least includes: bessel filters, chebyshev filters, butterworth filters.
Optionally, the active state comprises at least: standing state, walking state, information trigger device still includes: the second determining module is used for determining a starting sub-window of the target user in an active state based on the active state identifier of each detection sub-window data after the plurality of detection sub-window data are obtained; a synthesis module, configured to start from the initial sub-window, and if it is detected that the active state identifiers of the consecutive detection sub-window data all indicate that the target user is in an active state, start to detect a cycle point location of a synthesized waveform; and the verification module is used for starting to carry out continuous active state verification processing when the periodic point location indication meets a preset point location condition.
Optionally, the determining unit includes: an input module, configured to input each detection sub-window data into a state detection model, where the state detection model is a state recognition model obtained by performing offline training according to multiple sets of user activity state data and activity state determination results, and a model structure of the state detection model at least includes: a decision tree model, a support vector machine model, a neural network model and an ensemble learning model; and the receiving module is used for receiving the activity starting point and the activity ending point output by the state detection model so as to obtain the activity duration of the target user in the activity state.
Optionally, the input module comprises: a first extraction sub-module, configured to extract direct features and indirect features in each detection sub-window data, where the direct features include: raw activity detection pose data, the indirect features including at least one of: the activity amplitude, the activity discrete degree and the amplitude difference value of adjacent detection sub-windows; a first combining sub-module for combining the direct features and the indirect features into an active feature vector and inputting the active feature vector to the state detection model.
Optionally, the preset sensor is a three-axis acceleration sensor.
According to another aspect of the embodiments of the present invention, there is also provided a wearable device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any of the information-triggered methods described above via execution of the executable instructions.
According to another aspect of the embodiments of the present invention, there is also provided a storage medium, where the storage medium includes a stored program, and when the program runs, a device on which the storage medium is located is controlled to execute any one of the above information triggering methods.
In the embodiment of the invention, the activity detection data of a target user is obtained by a preset sensor, wherein the preset sensor is worn on a preset body part of the target user, then the activity detection data is segmented to obtain a plurality of detection sub-window data, each detection sub-window data corresponds to an activity state identifier, then the activity duration of the target user in an activity state can be determined based on the plurality of detection sub-window data, if the activity duration is lower than a preset duration threshold, the target user is determined to be in an inactive state, and a reminding message is sent, wherein the reminding message is used for reminding the target user of the activity action required. In this embodiment, the accessible detects user's activity data, judge the duration that the user is in the active state (if the activity of standing), in order to send the activity at the right moment and remind, the user only need wear wearable equipment can send the warning of standing at the right time, thereby reduce the health risk that is in the inactive state (if the state of sitting for a long time) and bring, this wearable equipment need not to be connected work with heart rate sensor, it is lower to operational environment requirement, can improve user's use satisfaction, thereby solve among the correlation technique wearable equipment and need rely on the higher heart rate sensor of precision in sending the motion warning information, operational environment requirement is higher, reduce the technical problem that user used satisfaction.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of an alternative information triggering method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an alternative information triggering apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In accordance with an embodiment of the present invention, there is provided an information-triggered method embodiment, it is noted that the steps illustrated in the flowchart of the figure may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
The information triggering method in the embodiment of the invention is applied to wearable equipment, and the wearable equipment comprises but is not limited to: smart watch, smart bracelet, smart belt, etc. A three-axis acceleration sensor may be provided on the wearable device, through which user activity data is detected.
Fig. 1 is a flowchart of an alternative information triggering method according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S102, acquiring activity detection data of a target user by a preset sensor, wherein the preset sensor is worn on a preset body part of the target user;
step S104, dividing the activity detection data to obtain a plurality of detection sub-window data, wherein each detection sub-window data corresponds to an activity state identifier;
step S106, determining the activity duration of the target user in the activity state based on the data of the plurality of detection sub-windows;
and S108, if the activity duration is lower than a preset duration threshold, determining that the target user is in an inactive state, and sending out reminding information, wherein the reminding information is used for reminding the target user of an activity action required to be performed.
Through the steps, the activity detection data of the target user by the preset sensor can be obtained, wherein the preset sensor is worn on the preset body part of the target user, then the activity detection data is segmented to obtain a plurality of detection sub-window data, each detection sub-window data corresponds to an activity state identifier, then the activity duration of the target user in the activity state can be determined based on the plurality of detection sub-window data, if the activity duration is lower than a preset duration threshold, the target user is determined to be in the non-activity state, and the reminding information is sent, wherein the reminding information is used for reminding the target user of the activity action required to be carried out. In this embodiment, the accessible detects user's activity data, judge the duration that the user is in the active state (if the activity of standing), in order to send the activity at the right moment and remind, the user only need wear wearable equipment can send the warning of standing at the right time, thereby reduce the health risk that is in the inactive state (if the state of sitting for a long time) and bring, this wearable equipment need not to be connected work with heart rate sensor, it is lower to operational environment requirement, can improve user's use satisfaction, thereby solve among the correlation technique wearable equipment and need rely on the higher heart rate sensor of precision in sending the motion warning information, operational environment requirement is higher, reduce the technical problem that user used satisfaction.
The embodiment of the invention relates to an information triggering method based on wearable equipment, which can also be understood as an activity reminding method, for example, sending a standing activity reminding; when a user is in an active state (for example, standing still, walking or running) in daily life, the wearable device automatically detects the starting point of the user in the active state, counts the active time length, and judges that the user is in the active state or in the non-sedentary state if the duration of standing activity in a certain period meets a certain threshold; if the duration of the standing activity in a certain period is less than a certain threshold, the user is determined to be in an inactive state or a sedentary state (including waking sitting, reclining or lying down and the like), and the user is reminded of the activity action to reduce the health risk brought by sedentary.
The following describes embodiments of the present invention in detail with reference to the respective steps.
Step S102, acquiring activity detection data of a target user by a preset sensor, wherein the preset sensor is worn on a preset body part of the target user.
The preset sensor can be worn on the body of the user, such as on the wrist, arm, waist, etc., and preferably, the preset sensor is a three-axis acceleration sensor.
And acquiring user activity data point by using a preset sensor, and recording the activity data in real time, such as recording acceleration data. After the activity detection data is obtained, the data may be analyzed.
Step S104, dividing the activity detection data to obtain a plurality of detection sub-window data, wherein each detection sub-window data corresponds to an activity state identifier.
As an alternative embodiment of the present invention, the step of segmenting the activity detection data to obtain a plurality of detection sub-window data includes: determining the interception duration of each sub-window data; and sequentially dividing the activity detection data according to the intercepting duration to obtain a plurality of detection sub-window data.
The above-mentioned embodiment indicates that the motion detection data is subjected to sliding window input processing, the intercepting duration is automatically adjusted according to the average amount of motion of each user per day, for example, 1 second, 2 seconds, 5 seconds, and the like, and the motion detection data is divided by the intercepting duration, so that the input and state prejudgment of the motion detection data with a fixed length can be realized, for example, the triaxial acceleration data with the fixed intercepting duration is intercepted as a processing unit.
Optionally, after the activity detection data is segmented to obtain a plurality of detection sub-window data, the information triggering method further includes: for each detection sub-window data, determining a data size and a user activity orientation; comparing the data size of the data of the two adjacent detection sub-windows with the user activity direction, and determining the initial activity state of the user; and endowing the activity state identification corresponding to the initial activity state to the corresponding detection sub-window data.
In other words, in the embodiment of the invention, the user activity state prejudgment can be realized, the user activity state of the user is estimated, the state prejudgment refers to the simple judgment of the size and the direction of the triaxial acceleration data, and each detection sub-window is endowed with a simple state identifier (active or inactive) so as to reduce unnecessary calculation of a subsequent algorithm.
After the state anticipation is completed, a waveform synthesis process may be performed on each detection sub-window data. Optionally, after the activity detection data is segmented to obtain a plurality of detection sub-window data, the information triggering method further includes: performing waveform synthesis processing on the activity acceleration based on the activity acceleration in each detection sub-window data to calculate a combined acceleration value; an acceleration differential increment or an increment normalization value is calculated based on the resultant acceleration value to uniformly limit the resultant acceleration value around the target speed value.
In the embodiment of the invention, the combined acceleration value can be calculated through the preset sensor, and then the difference increment or the increment normalization value is calculated on the basis, so that the combined acceleration is uniformly limited to be close to the target speed value (such as 0 or 1) so as to improve the accuracy and the universality of the subsequent activity state detection.
In this embodiment of the present invention, the low-pass filtering may be further performed on the transformed combined acceleration data, and as an optional embodiment of the present invention, after the combined acceleration value is uniformly limited around the target velocity value, the information triggering method further includes: and carrying out filtering processing on the combined acceleration value to obtain a smooth combined acceleration value, wherein the filtering processing mode at least comprises the following steps: bessel filters, chebyshev filters, butterworth filters. The embodiment of the present invention does not limit the filtering processing method used, and any one of the above filtering methods may be selected, or another filtering method may be selected.
By filtering the composite acceleration value, the data can be smoother, and the data processing speed can be improved during subsequent data input and data processing.
Optionally, the active state at least includes: standing state, walking state, running state.
After the active state identification, the data synthesis processing and the data filtering processing are completed, the active state detection, the active state judgment and the active duration statistics processing can be performed on each detection sub-window data.
As an alternative embodiment of the present invention, when performing active state detection, after obtaining a plurality of detection sub-window data, the method includes: determining a starting sub-window of a target user in an active state based on the active state identification of each detection sub-window data; starting from the initial sub-window, if the active state identifications of a plurality of continuous detection sub-window data indicate that the target user is in an active state, starting to detect the periodic point position of the synthesized waveform; and if the periodic point location indication meets the preset point location condition, starting to perform continuous active state verification processing.
The active state detection is to enter a corresponding detection process according to the state identifier of each detection sub-window so as to detect the initial sub-window of the active state, if the state identifiers of a plurality of continuous detection sub-windows (sliding windows) belong to the active state and the current detection sub-window also belongs to the active state, the detection of the cycle point of the synthesized waveform is started, and when the cycle point meets a certain condition, the subsequent continuous active state judgment is entered; otherwise, continuously receiving the data of the detection sub-window and re-detecting.
When the activity state is judged, intelligent judgment can be achieved by means of the trained state detection model, the activity state can be judged by the server, namely the wearable device can send the detection sub-window data to the server, and the activity state of the user can be judged by the state detection model. The state detection model is a machine learning model and can judge the activity state corresponding to the currently detected sub-window data.
As an alternative embodiment of the present invention, the step of determining the activity duration of the target user in the active state based on the data of the plurality of detection sub-windows includes: inputting each detection sub-window data into a state detection model, wherein the state detection model is a state recognition model obtained by off-line training according to a plurality of groups of user activity state data and activity state judgment results, and the model structure of the state detection model at least comprises: a decision tree model, a support vector machine model, a neural network model and an ensemble learning model; and receiving the activity starting point and the activity ending point output by the state detection model to obtain the activity duration of the target user in the activity state. The model structure of the state detection model selected in the embodiment of the present invention is not limited to the above schematic description, and may be other applicable model structures.
Optionally, the step of inputting the data of each detection sub-window into the state detection model includes: extracting direct features and indirect features in each detection sub-window data, wherein the direct features comprise: raw activity detection pose data, indirect features including at least one of: the activity amplitude, the activity discrete degree and the amplitude difference value of adjacent detection sub-windows; the direct features and the indirect features are combined into an active feature vector, and the active feature vector is input to a state detection model.
According to the embodiment of the invention, a state detection model is utilized, and according to the data entering the detected sub-window, a feature vector consisting of direct features (original data) and indirect features (activity amplitude, activity discrete degree, amplitude difference of front and rear windows and the like) is extracted, and the feature vector is input into the selected state detection model to obtain a corresponding activity state. The selected state detection model is a model trained by offline data, the feature types of the model training are consistent with those described above, the offline training data includes but is not limited to manually collected data, empirical data and the like, and the model structure includes but is not limited to a decision tree model, a support vector machine model, a neural network model, an ensemble learning model and the like.
In the embodiment of the invention, the three-axis acceleration sensor can be used for respectively detecting various activity states such as a standing state, a sedentary state, a walking state, a running state and the like.
After the activity detection and the activity state judgment are completed, the operation of activity duration statistics can be carried out.
And step S106, determining the activity duration of the target user in the active state based on the data of the plurality of detection sub-windows.
The activity duration statistics is a step of performing activity duration statistics according to the judgment result of the user activity state within a certain time. And counting and judging the total activity state including standing still, walking, sitting for a long time and the like according to the activity state judgment result in the continuous time, and setting the reminding mark to be in a corresponding state according to the duration when the total activity state is in the activities of standing, walking, running and the like.
And S108, if the activity duration is lower than a preset duration threshold, determining that the target user is in an inactive state, and sending out reminding information, wherein the reminding information is used for reminding the target user of an activity action required to be performed.
As an optional embodiment of the present invention, when sending out the reminding message, the method includes: fixed period reminders and variable period reminders. Wherein, the fixed period reminding refers to setting the reminding interval duration or setting the fixed reminding time point to send out reminding information; the variable period reminding is that according to the analysis result of the activity detection data, when the reminding condition is met, reminding information is directly sent out.
Optionally, the types of the reminder information include, but are not limited to: voice prompt, mail prompt, short message prompt and instant communication message prompt.
In the embodiment of the invention, the activity detection data of the user can be processed, the starting point and the activity duration of the activity state of the user are determined, the duration of the user in the non-activity state is further judged, and the reminding information is sent out after the non-activity duration exceeds the preset duration threshold, so that the user can stand for activities (such as standing still, walking and the like) in time, the duration of the user in the non-activity state is reduced, the physical health of the user is improved, and the satisfaction degree of the user in using the wearable device is improved.
Fig. 2 is a schematic diagram of an alternative information triggering apparatus according to an embodiment of the present invention, applied to a wearable device, as shown in fig. 2, the information triggering apparatus includes: an acquisition unit 21, a segmentation unit 23, a determination unit 25, an issuing unit 27, wherein,
the acquisition unit 21 is configured to acquire activity detection data of a target user from a preset sensor, where the preset sensor is worn on a preset body part of the target user;
a dividing unit 23, configured to divide the activity detection data to obtain multiple detection sub-window data, where each detection sub-window data corresponds to an activity status identifier;
a determining unit 25, configured to determine an activity duration of the target user in an active state based on the plurality of detection sub-window data;
and the sending unit 27 is configured to determine that the target user is in an inactive state when the activity duration is lower than the preset duration threshold, and send out the reminding information, where the reminding information is used to remind the target user of an activity action required.
The above information triggering device may acquire activity detection data of a preset sensor to a target user through the acquisition unit 21, where the preset sensor is worn on a preset body part of the target user, and then the activity detection data is segmented through the segmentation unit 23 to obtain a plurality of detection sub-window data, where each detection sub-window data corresponds to an activity status identifier, and then an activity duration of the target user in an activity status may be determined based on the plurality of detection sub-window data through the determination unit 25, and finally, when the activity duration is lower than a preset duration threshold, the target user is determined to be in an inactive status through the sending unit 27, and a reminding information is sent, where the reminding information is used to remind the target user of an activity action. In this embodiment, the accessible detects user's activity data, judge the duration that the user is in the active state (if the activity of standing), in order to send the activity at the right moment and remind, the user only need wear wearable equipment can send the warning of standing at the right time, thereby reduce the health risk that is in the inactive state (if the state of sitting for a long time) and bring, this wearable equipment need not to be connected work with heart rate sensor, it is lower to operational environment requirement, can improve user's use satisfaction, thereby solve among the correlation technique wearable equipment and need rely on the higher heart rate sensor of precision in sending the motion warning information, operational environment requirement is higher, reduce the technical problem that user used satisfaction.
Optionally, the segmentation unit includes: the first determining module is used for determining the interception duration of each sub-window data; and the first segmentation module is used for sequentially segmenting the activity detection data according to the interception duration to obtain a plurality of detection sub-window data.
Optionally, the information triggering apparatus further includes: the second determining module is used for determining the data size and the user activity direction for each detection sub-window data after the activity detection data are segmented to obtain a plurality of detection sub-window data; the comparison module is used for comparing the data size of the data of the two adjacent detection sub-windows with the activity direction of the user and determining the initial activity state of the user; and the giving module is used for giving the activity state identification corresponding to the initial activity state to the corresponding detection sub-window data.
Another optional, the information triggering apparatus further includes: a synthesis unit, configured to perform waveform synthesis processing on the activity acceleration based on the activity acceleration in each detection sub-window data after the activity detection data is divided to obtain a plurality of detection sub-window data, so as to calculate a resultant acceleration value; and the computing unit is used for computing an acceleration difference increment or an increment normalization value based on the combined acceleration numerical value so as to uniformly limit the combined acceleration numerical value around the target speed value.
As an optional embodiment of the present invention, the information triggering apparatus further includes: the filtering unit is used for performing filtering processing on the combined acceleration value after the combined acceleration value is uniformly limited around the target speed value to obtain a smooth combined acceleration value, wherein the filtering processing mode at least comprises the following steps: bessel filters, chebyshev filters, butterworth filters.
Optionally, the active state at least includes: standing state, walking state, information trigger device still includes: the second determining module is used for determining a starting sub-window of the target user in an active state based on the active state identifier of each detection sub-window data after the plurality of detection sub-window data are obtained; the synthesis module is used for starting from the initial sub-window, and if the active state identifications of the continuous detection sub-window data indicate that the target user is in an active state, starting to detect the periodic point position of the synthesized waveform; and the verification module is used for starting to carry out continuous active state verification processing when the periodic point location indication meets the preset point location condition.
In an alternative embodiment of the present invention, the determining unit includes: the input module is used for inputting the data of each detection sub-window into the state detection model, wherein the state detection model is a state recognition model obtained by off-line training according to a plurality of groups of user activity state data and activity state judgment results, and the model structure of the state detection model at least comprises: a decision tree model, a support vector machine model, a neural network model and an ensemble learning model; and the receiving module is used for receiving the activity starting point and the activity ending point output by the state detection model so as to obtain the activity duration of the target user in the activity state.
Optionally, the input module includes: a first extraction sub-module, configured to extract direct features and indirect features in each detection sub-window data, where the direct features include: raw activity detection pose data, the indirect features including at least one of: the activity amplitude, the activity discrete degree and the amplitude difference value of adjacent detection sub-windows; and the first combination submodule is used for combining the direct features and the indirect features into an activity feature vector and inputting the activity feature vector to the state detection model.
Alternatively, the predetermined sensor is a three-axis acceleration sensor.
The information triggering device may further include a processor and a memory, and the acquiring unit 21, the dividing unit 23, the determining unit 25, the issuing unit 27, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.
The processor comprises a kernel, and the kernel calls a corresponding program unit from the memory. The kernel can be set to be one or more, the user activity state is detected by adjusting kernel parameters, and the reminding information is sent when the duration of the user in the inactive state is determined to exceed a preset duration threshold.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
According to another aspect of the embodiments of the present invention, there is also provided a wearable device, including: a processor; and a memory for storing executable instructions for the processor; wherein the processor is configured to perform any of the above-described information-triggered methods via execution of executable instructions.
According to another aspect of the embodiments of the present invention, there is also provided a storage medium, where the storage medium includes a stored program, and when the program runs, a device on which the storage medium is located is controlled to execute any one of the information triggering methods described above.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: acquiring activity detection data of a target user by a preset sensor, wherein the preset sensor is worn on a preset body part of the target user; dividing the activity detection data to obtain a plurality of detection sub-window data, wherein each detection sub-window data corresponds to an activity state identifier; determining the activity duration of the target user in the active state based on the plurality of detection sub-window data; and if the activity duration is lower than a preset duration threshold, determining that the target user is in an inactive state, and sending out reminding information, wherein the reminding information is used for reminding the target user of an activity action.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. An information triggering method is applied to a wearable device and comprises the following steps:
acquiring activity detection data of a target user by a preset sensor, wherein the preset sensor is worn on a preset body part of the target user;
dividing the activity detection data to obtain a plurality of detection sub-window data, and determining the data size and the user activity direction of each detection sub-window data; comparing the data size of the data of the two adjacent detection sub-windows with the user activity direction, and determining the initial activity state of the user; assigning an activity state identifier corresponding to the initial activity state to first detection sub-window data and second detection sub-window data in two adjacent detection sub-window data, so that each detection sub-window data corresponds to an activity state identifier;
inputting each detection sub-window data into a state detection model to obtain the activity duration of the target user in an active state, wherein the step of inputting each detection sub-window data into the state detection model comprises the following steps: extracting direct features and indirect features in each of the detection sub-window data, the direct features including: raw activity detection pose data, the indirect features including at least one of: the activity amplitude, the activity discrete degree and the amplitude difference value of adjacent detection sub-windows; combining the direct features and the indirect features into an active feature vector and inputting the active feature vector to the state detection model;
and if the activity duration is lower than a preset duration threshold, determining that the target user is in an inactive state, and sending out reminding information, wherein the reminding information is used for reminding the target user of an activity action required to be performed.
2. The method of claim 1, wherein the step of segmenting the activity detection data into a plurality of detection sub-window data comprises:
determining the interception duration of each sub-window data;
and sequentially dividing the activity detection data according to the intercepting duration to obtain a plurality of detection sub-window data.
3. The method of claim 1, wherein after segmenting the activity detection data into a plurality of detection sub-window data, the information triggering method further comprises:
performing waveform synthesis processing on the active acceleration based on the active acceleration in each detection sub-window data to calculate a combined acceleration value;
an acceleration differential delta or delta normalization value is calculated based on the resultant acceleration values to uniformly constrain the resultant acceleration values around a target speed value.
4. The method of claim 3, wherein after uniformly limiting the resultant acceleration value around a target speed value, the information-triggered method further comprises:
and carrying out filtering processing on the resultant acceleration numerical value to obtain a smooth resultant acceleration numerical value, wherein the filtering processing mode at least comprises the following steps: bessel filters, chebyshev filters, butterworth filters.
5. The method according to claim 1, wherein the active state comprises at least: after obtaining data of a plurality of detection sub-windows, the information triggering method further comprises the following steps:
determining a starting sub-window of the target user in an active state based on the active state identification of each detection sub-window data;
starting from the starting sub-window, if the active state identifications of a plurality of continuous detection sub-window data indicate that the target user is in an active state, starting to detect the periodic point position of the synthesized waveform;
and if the periodic point location indication meets the preset point location condition, starting to perform continuous active state verification processing.
6. The method of claim 1, wherein the step of determining the active duration of the target user in the active state based on the plurality of detected sub-window data comprises:
inputting each detection sub-window data into a state detection model, wherein the state detection model is a state recognition model obtained by off-line training according to a plurality of groups of user activity state data and activity state judgment results, and the model structure of the state detection model at least comprises: a decision tree model, a support vector machine model, a neural network model and an ensemble learning model;
and receiving an activity starting point and an activity ending point output by the state detection model to obtain the activity duration of the target user in the activity state.
7. The method according to any one of claims 1 to 6, wherein the predetermined sensor is a three-axis acceleration sensor.
8. An information triggering device applied to a wearable device comprises:
the device comprises an acquisition unit, a display unit and a control unit, wherein the acquisition unit is used for acquiring activity detection data of a target user by a preset sensor, and the preset sensor is worn on a preset body part of the target user;
the segmentation unit is used for segmenting the activity detection data to obtain a plurality of detection sub-window data, wherein each detection sub-window data corresponds to an activity state identifier;
a determining unit, configured to determine, based on the multiple pieces of detection sub-window data, an activity duration of the target user in an active state, where the activity duration of the target user in the active state is obtained by inputting each piece of detection sub-window data into a state detection model, and the determining unit specifically includes: extracting direct features and indirect features in each of the detection sub-window data, the direct features including: raw activity detection pose data, the indirect features including at least one of: the activity amplitude, the activity discrete degree and the amplitude difference value of adjacent detection sub-windows; combining the direct features and the indirect features into an activity feature vector, and inputting the activity feature vector into the state detection model to obtain the activity duration of the target user in an active state;
the sending unit is used for determining that the target user is in an inactive state and sending reminding information when the activity duration is lower than a preset duration threshold, wherein the reminding information is used for reminding the target user of an activity action;
the information triggering apparatus further includes: a second determining module, configured to determine, for each detection sub-window data, a data size and a user activity direction after the activity detection data is segmented to obtain a plurality of detection sub-window data; the comparison module is used for comparing the data size of the data of the two adjacent detection sub-windows with the activity direction of the user and determining the initial activity state of the user; and the giving module is used for giving the activity state identifier corresponding to the initial activity state to the first detection sub-window data and the second detection sub-window data in the two adjacent detection sub-window data.
9. A wearable device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the information triggering method of any one of claims 1 to 7 via execution of the executable instructions.
10. A storage medium, characterized in that the storage medium comprises a stored program, wherein when the program runs, a device where the storage medium is located is controlled to execute the information triggering method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910944557.3A CN110584675B (en) | 2019-09-30 | 2019-09-30 | Information triggering method and device and wearable device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910944557.3A CN110584675B (en) | 2019-09-30 | 2019-09-30 | Information triggering method and device and wearable device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110584675A CN110584675A (en) | 2019-12-20 |
| CN110584675B true CN110584675B (en) | 2022-05-03 |
Family
ID=68865457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910944557.3A Active CN110584675B (en) | 2019-09-30 | 2019-09-30 | Information triggering method and device and wearable device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110584675B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113074724B (en) * | 2021-03-26 | 2023-05-02 | 歌尔股份有限公司 | Motion time calculation method, device, equipment and computer readable storage medium |
| CN114543306A (en) * | 2022-01-28 | 2022-05-27 | 青岛海尔空调器有限总公司 | Method and device for controlling air conditioner, air conditioner and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105976581A (en) * | 2016-05-11 | 2016-09-28 | 安徽华米信息科技有限公司 | Posture prompt method and device and wearable equipment |
| CN107393260A (en) * | 2017-07-31 | 2017-11-24 | 青岛真时科技有限公司 | A kind of sitting based reminding method, device and wrist type sitting reminiscences |
| CN107680649A (en) * | 2017-08-26 | 2018-02-09 | 深圳市盛路物联通讯技术有限公司 | Movable based reminding method and relevant device |
| CN109663323A (en) * | 2018-12-20 | 2019-04-23 | 出门问问信息科技有限公司 | A kind of motion state monitoring method and wearable device based on wearable device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160249832A1 (en) * | 2015-02-27 | 2016-09-01 | Amiigo, Inc. | Activity Classification Based on Classification of Repetition Regions |
-
2019
- 2019-09-30 CN CN201910944557.3A patent/CN110584675B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105976581A (en) * | 2016-05-11 | 2016-09-28 | 安徽华米信息科技有限公司 | Posture prompt method and device and wearable equipment |
| CN107393260A (en) * | 2017-07-31 | 2017-11-24 | 青岛真时科技有限公司 | A kind of sitting based reminding method, device and wrist type sitting reminiscences |
| CN107680649A (en) * | 2017-08-26 | 2018-02-09 | 深圳市盛路物联通讯技术有限公司 | Movable based reminding method and relevant device |
| CN109663323A (en) * | 2018-12-20 | 2019-04-23 | 出门问问信息科技有限公司 | A kind of motion state monitoring method and wearable device based on wearable device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110584675A (en) | 2019-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110584675B (en) | Information triggering method and device and wearable device | |
| Amft et al. | Detection of eating and drinking arm gestures using inertial body-worn sensors | |
| CN103676604B (en) | Watch and running method thereof | |
| CN106020348B (en) | Show the method, apparatus and wearable device of information | |
| CN104049761B (en) | Eye electro-detection method and eye electric detection means | |
| CN106388771B (en) | A kind of method and motion bracelet of automatic detection human body physiological state | |
| WO2019192235A1 (en) | User identity authentication method and system based on mobile device | |
| CN104142583A (en) | Intelligent glasses with blinking detection function and implementation method thereof | |
| CN103699795A (en) | Exercise behavior identification method and device and exercise intensity monitoring system | |
| CN106919913A (en) | Method for detecting fatigue driving and device based on computer vision | |
| Bhandari et al. | Non-invasive sensor based automated smoking activity detection | |
| CN112057066A (en) | Heart rate detection method, wearable device and computer storage medium | |
| CN110801216B (en) | Abnormity early warning method and related equipment | |
| CN109784178A (en) | Parameter adjusting method, device and body-building equipment based on gesture identification | |
| CN105530581A (en) | Smart wearable device based on voice recognition and control method thereof | |
| CN111089604A (en) | Body-building exercise identification method based on wearable sensor | |
| CN110710962A (en) | Sleep state detection method and device | |
| CN107393260A (en) | A kind of sitting based reminding method, device and wrist type sitting reminiscences | |
| CN105212941A (en) | A kind of human body active state recognition methods and system | |
| CN114140868A (en) | Method and device for identifying standard actions of putting-on and taking-off of protective appliance | |
| CN109044375A (en) | A kind of control system and its method of real-time tracking detection eyeball fatigue strength | |
| US20210282656A1 (en) | Blood pressure monitoring method, apparatus, and device | |
| CN111028488A (en) | Intelligent sedentary reminding method based on PSO-SVM | |
| CN111166340A (en) | Human body posture real-time identification method based on self-adaptive acceleration signal segmentation | |
| CN112274902B (en) | Swimming data acquisition method and device and control method of swimming data acquisition equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |