Body posture sensing method based on intelligent wearable watch for children, intelligent watch for children, storage medium and computer program product

Abstract

The invention discloses a body posture sensing method based on a smart wearable watch for children, the smart watch for children, a storage medium and a computer program product, and relates to the technical field of smart watches, and the method comprises the following steps: collecting original data generated by at least one sensor on the smart watch; collecting external environment conditions and physiological parameters related to children; training based on the child behavior data and the corresponding time to obtain a scene classification model; based on the collected child behavior data, in combination with current network time and a scene classification model, analyzing a scene in which a child is currently located; and calculating a posture deviation angle in real time, sending the action data to a preset child posture evaluation model in combination with the current scene of the child, classifying the current action of the child, outputting a corresponding judgment result, and responding to the judgment result. The body posture of the child is accurately evaluated and effectively intervened, the poor body posture is corrected, and use is convenient.

Description

Technical Field

[0001] The present invention relates to the field of smart wearables, and particularly to a body posture perception method for children's smart wear watches, a children's smart watch, a storage medium, and a computer program product. Background Art

[0002] In today's society, the healthy growth of children has attracted much attention, and the cultivation of body posture is particularly important. Poor body posture not only affects the appearance of children, but may also have long-term negative impacts on their bone development and physical health. However, due to the lack of self-discipline ability and health awareness, children tend to develop bad body posture habits easily.

[0003] The main functions of existing children's smart watches are concentrated in positioning, calling, social networking, etc., and the functions of perceiving and monitoring children's body postures are relatively weak. Some simple posture monitoring methods often lack consideration of scenarios and cannot accurately evaluate and effectively intervene in children's body postures according to different scenarios. In addition, the physiological parameters of children and external environmental conditions are not fully combined, and personalized posture management services cannot be provided for children. Therefore, a more intelligent, accurate and targeted method for perceiving children's body postures is needed to meet the needs of children's healthy growth. Summary of the Invention

[0004] The main purpose of this application is to provide a method for estimating calorie consumption data based on a children's smart watch, a children's smart watch, a storage medium, and a computer program product, aiming to solve the technical problems corresponding to the background art.

[0005] To achieve the above object, this application proposes a body posture perception method based on a children's smart wearable watch, including the following steps:

[0006] Collect the raw data generated by at least one sensor on the smart watch;

[0007] Collect external environmental conditions and physiological parameters related to children;

[0008] Based on the collected past children's behavior data and the corresponding time, train a pre-established classifier to obtain a scene classification model;

[0009] Based on the collected real-time children's behavior data, combined with the current network time and the scene classification model, analyze the current scene where the children are located;

[0010] Calculate the posture deviation angle in real time, combine the current scene where the children are located, send the action data to a preset children's posture evaluation model, classify the current actions of the children, output the corresponding determination result, and respond to the determination result.

[0011] In one embodiment, the specific training process of the scenario classification model is as follows:

[0012] Divide the time corresponding to the previous children's behavior data into school days and rest days;

[0013] Divide the children's behavior data belonging to school days into the school day cluster, and divide the children's behavior data belonging to rest days into the rest day cluster;

[0014] Divide a day into eight time periods, and plan the children's behavior data in the school day cluster and the rest day cluster into the corresponding sub-clusters according to the divided time periods;

[0015] Import the scenario information corresponding to the previous children's behavior data, and add scenario labels to the children's behavior data in each sub-cluster accordingly.

[0016] In one embodiment, the specific analysis process of the current scenario where the child is located is as follows:

[0017] Collect the raw data generated by at least one sensor on the smart watch to obtain the wrist movement trajectory;

[0018] Determine the current location of the child according to the collected positioning data;

[0019] Determine the sub-cluster corresponding to the time period of the collected real-time children's behavior data according to the current network time;

[0020] Based on the extracted scenario labels, output the scenario label with the most occurrences as the current scenario where the child is located.

[0021] In one embodiment, the process of classifying the current action of the child, outputting the corresponding determination result, and responding to the determination result includes:

[0022] Calculate the posture deviation angle in real time;

[0023] When the posture deviation angle exceeds the set angle threshold and the deviation time does not exceed the set time threshold, it is determined that the child is in a bad posture, vibration triggers a reminder, and a cartoon animation is synchronously displayed to encourage posture adjustment;

[0024] When the posture deviation angle exceeds the set angle threshold and the deviation time exceeds the set time threshold, it is determined that the child is in a dangerous posture, and the smart watch emits an alarm sound;

[0025] When the child makes a preset interesting posture action, it is determined that the child is in an interactive posture, and the smart watch plays interesting sound effects or animations for interesting interaction.

[0026] When a child makes a preset writing posture and it is a school day, it is determined that the child is in a learning state, and the social function notifications are automatically disabled.

[0027] In one embodiment, before the step of "training a pre-established classifier based on the collected historical child behavior data and the corresponding time to obtain a scene classification model", the following steps are further included:

[0028] Initialize the body posture perception module and calibrate the initial wearing position.

[0029] In one embodiment, before the step of "training a pre-established classifier based on the collected historical child behavior data and the corresponding time to obtain a scene classification model", the following steps are further included:

[0030] Perform noise filtering and time synchronization processing on the original data.

[0031] In one embodiment, the physiological parameters at least include age;

[0032] The posture evaluation model includes an age-group parameter library, and different allowable ranges of joint angles are set for children aged 5 - 8 and 9 - 12 respectively.

[0033] In addition, to achieve the above object, the present application also proposes a smart watch device for children, the device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program is configured to implement the steps of the method for estimating calorie consumption data based on a smart watch for children as described above.

[0034] In addition, to achieve the above object, the present application also proposes a storage medium, the storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, it implements the steps of the method for estimating calorie consumption data based on a smart watch for children as described above.

[0035] In addition, to achieve the above object, the present application also provides a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, it implements the steps of the method for estimating calorie consumption data based on a smart watch for children as described above.

[0036] One or more technical solutions proposed by the present application have at least the following technical effects:

[0037] In an embodiment of the present invention, by collecting the raw data on the sensor, the external environment, and the physiological parameters related to children, the current usage scenarios of children are classified in detail. It is also possible to analyze and judge the current actions of children based on the classified usage scenarios and a preset child posture evaluation model, so as to accurately evaluate and effectively intervene in the body postures of children, correct bad body postures, and facilitate use. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0039] To more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0040] Figure 1 It is a flowchart of a body posture perception method based on a smart wearable watch for children;

[0041] Figure 2 is Figure 1 a flowchart of step S30 in

[0042] Figure 3 is Figure 1 a flowchart of step S40 in

[0043] Figure 4 is Figure 1 a flowchart of step S50 in

[0044] The implementation, functional features, and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0046] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a smart watch for children, etc. that can implement the above functions. Hereinafter, a smart watch for children will be used as an example to illustrate this embodiment and the following embodiments.

[0047] Based on this, the embodiments of the present application provide a body posture perception method based on a smart wearable watch for children, including steps S10 to S50:

[0048] Step S10: Collect the raw data generated by at least one sensor on the smart watch;

[0049] It should be noted that, in one embodiment, the sensor may be an acceleration sensor and a gyroscope; among them, the acceleration sensor is used to collect the accelerations of the X, Y, and Z axes; the gyroscope is a sensor that can measure the angular velocity and angular change of an object rotating around an axis. Its principle is mainly to sense the posture and movement characteristics of the human body during movement, assist other sensors to more accurately judge the activity type, and then estimate a more accurate body posture. Specifically, when a human body performs different activities, each part of the body will have specific movement trajectories and posture changes, which contain rich rotation information, and the gyroscope can just capture these rotation data. By analyzing and processing these data, the activity type that the child is performing can be inferred, and combined with the corresponding relationship between the activity type and calorie consumption, the estimation of calorie consumption can be realized.

[0050] By collecting the acceleration of the watch and the rotation data of the gyroscope, the body posture of the child can be initially judged.

[0051] It can be understood that, in one embodiment of the present invention, in addition to the conventional motion sensors, the smart watch may also be added with a GPS module and a skin temperature sensor. By monitoring these additional physiological parameters and geographical locations, the system can more accurately capture the subtle differences of the child in different activity states, thereby improving the accuracy of posture measurement.

[0052] Step S20: Collect external environmental conditions and physiological parameters related to the child;

[0053] Among them, the external environmental conditions can be collected by the environmental sensors built in the watch, such as temperature sensors, humidity sensors, etc., to obtain current temperature, humidity and other information. The physiological parameters related to the child at least include age, and may also include information such as height and weight. These information can be input by the child or the parent in the watch settings.

[0054] Step S30: Based on the collected past child behavior data and the corresponding time, train a pre-established classifier to obtain a scene classification model;

[0055] Step S40: Based on the collected real-time child behavior data, combined with the current network time and the scene classification model, analyze the current scene where the child is located;

[0056] Step S50: Calculate the posture deviation angle in real time, combined with the current scene where the child is located, send the action data to a preset child posture evaluation model, classify the current action of the child, output the corresponding determination result, and respond to the determination result.

[0057] In an embodiment of the present invention, by collecting the original data on the sensor, the external environment, and the physiological parameters related to children, the current usage scenarios of children are classified in detail. It is also possible to analyze and judge the current actions of children according to the classified usage scenarios and the preset child posture evaluation model, so as to accurately evaluate and effectively intervene in the body postures of children, correct bad body postures, and facilitate use.

[0058] In a feasible embodiment, the specific training of the scenario classification model includes steps S31 to S34:

[0059] Step S31: Divide the time corresponding to the previous children's behavior data into learning days and rest days;

[0060] Step S32: Divide the children's behavior data belonging to learning days into the learning day cluster, and divide the children's behavior data belonging to rest days into the rest day cluster;

[0061] Step S33: Divide a day into eight time periods, and plan the children's behavior data in the learning day cluster and the rest day cluster into the corresponding sub-clusters according to the divided time periods;

[0062] Step S34: Import the scenario information corresponding to the previous children's behavior data, and add scenario labels to the children's behavior data in each sub-cluster accordingly.

[0063] Divide the time corresponding to the previous children's behavior data into learning days and rest days; divide the children's behavior data belonging to learning days into the learning day cluster, and divide the children's behavior data belonging to rest days into the rest day cluster; divide a day into eight time periods, and plan the children's behavior data in the learning day cluster and the rest day cluster into the corresponding sub-clusters according to the divided time periods; import the scenario information corresponding to the previous children's behavior data (the children's behavior data corresponding to different scenarios is different. For example, in the exercise scenario and the sleep scenario, the children's behavior data varies greatly, and the imported scenario information is the children's own import of the AI analysis platform through the children's smart wearable watches after experiencing the previous scenario), and add scenario labels to the children's behavior data in each sub-cluster accordingly. Each child has its own work and rest pattern, which usually doesn't vary much during learning days, but there are usually some differences on rest days. In this application, the children's behavior data is classified according to learning days and rest days, and corresponding scenario labels are added to each children's behavior data to enrich the database and complete the training.

[0064] In a feasible embodiment, the specific analysis process of the current scenario where the child is located includes steps S41 to S44:

[0065] Step S41: Collect the raw data generated by at least one sensor on the smartwatch to obtain the wrist movement trajectory;

[0066] Step S42: Determine the current location of the child based on the collected positioning data;

[0067] Step S43: Determine the sub-cluster corresponding to the time period of the collected real-time child behavior data according to the current network time;

[0068] Step S44: Based on the extracted scene labels, output the scene label with the most occurrences as the current scene where the child is located.

[0069] Collect the raw data generated by at least one sensor on the smartwatch to obtain the wrist movement trajectory: Collect the real-time data of the sensor again. By analyzing and processing the acceleration and angular velocity data, calculate the movement trajectory of the wrist to understand the current hand movement state of the child. Determine the current location of the child based on the collected positioning data: The smartwatch is usually equipped with a GPS positioning module. By obtaining the current positioning data, the geographical location where the child is located can be determined. Combining with map information, it can be judged whether the child is at home, at school, in the mall or other specific locations. Determine the sub-cluster corresponding to the time period of the collected real-time child behavior data according to the current network time: Obtain the current network time. According to the previously divided time periods, determine the sub-cluster to which the current time belongs, so as to filter out relevant scene information from the scene classification model. Based on the extracted scene labels, output the scene label with the most occurrences as the current scene where the child is located: Extract the scene labels from the corresponding sub-cluster, count the occurrences of each scene label, and use the scene label with the most occurrences as the current scene where the child is located.

[0070] In a feasible implementation manner, the process of classifying the current action of the child, outputting the corresponding determination result, and responding to the determination result includes steps S51 - S55:

[0071] Step S51: Calculate the posture deviation angle in real time;

[0072] Step S52: When the posture deviation angle exceeds the set angle threshold and the deviation time does not exceed the set time threshold, determine that the child is in a bad posture, trigger a vibration reminder, and synchronously display a cartoon animation to encourage posture adjustment;

[0073] Step S53: When the posture deviation angle exceeds the set angle threshold and the deviation time exceeds the set time threshold, determine that the child is in a dangerous posture, and the smartwatch emits an alarm sound;

[0074] Step S54: When the child makes a preset interesting gesture, it is determined that the child is in an interactive posture, and the smartwatch plays interesting sound effects or animations for interesting interaction.

[0075] Step S55: When the child makes a preset writing posture and it is a study day, it is determined that the child is in a learning state, and the social function notifications are automatically disabled.

[0076] When the deviation angle of the posture exceeds the set angle threshold and the deviation time does not exceed the set time threshold, it is determined that the child is in a bad posture, and vibration is triggered to give a reminder, and a cartoon animation is synchronously displayed to encourage posture adjustment. For example, the set angle threshold is 15° and the time threshold is 3 minutes. When the deviation angle of the child's posture exceeds 15° but the duration does not exceed 3 minutes, the watch will vibrate slightly and display a cute cartoon animation on the screen to remind the child to adjust the posture.

[0077] In addition, the smartwatch for children may further include a parental supervision function. When the deviation angle of the posture exceeds the set angle threshold and the deviation time exceeds the set time threshold, it is determined that the child is in a dangerous posture, and the smartwatch emits an alarm sound and sends a danger prompt message to the associated parental device. For example, when the deviation angle of the posture exceeds 15° and the duration exceeds 3 minutes, the watch will emit a loud alarm sound, and at the same time send a danger prompt to the parent's mobile phone by means of text message or APP message, informing the parent that the current posture of the child may pose a health risk.

[0078] When the child makes a preset interesting gesture, it is determined that the child is in an interactive posture, and the smartwatch plays interesting sound effects or animations for interesting interaction. For example, some specific gestures or actions are preset as interesting gesture actions. When the child makes these actions, the watch will play cheerful sound effects or display interesting animations to increase the interactivity with the child.

[0079] When the child makes a preset writing posture and it is a study day, it is determined that the child is in a learning state, and the social function notifications are automatically disabled. This can avoid being disturbed by social messages when the child is studying and improve the learning efficiency.

[0080] In addition, if the child adjusts the posture after receiving the reminder, or performs specific operations on the watch, such as turning off the alarm, clicking on the animation, etc., the current posture information of the child can be updated according to these operations, so as to perform more accurate posture evaluation and scenario analysis subsequently.

[0081] In a feasible embodiment, before the step of "training a pre-established classifier based on the collected previous child behavior data and the corresponding time to obtain a scene classification model", the following steps are further included:

[0082] Initialize the body posture perception module and calibrate the initial wearing position;

[0083] By initializing the body posture perception module before starting to train the scene classification model, ensure that each sensor works properly. At the same time, calibrate the initial wearing position to eliminate the errors caused by different wearing positions and ensure the accuracy of subsequent data collection.

[0084] In a feasible embodiment, before the step of "determining the current activity type of the child according to the preprocessed data", the following steps are further included:

[0085] Preprocess the data obtained from the original data of the steps, including but not limited to noise filtering and time synchronization.

[0086] Specifically, for the noise filtering, median filtering is used to remove impulse noise from the accelerometer and gyroscope data, and the window size is set to 3. Taking the accelerometer X-axis data as an example, the processing process is as follows: for the first two data points, keep the original values unchanged. Starting from the third data point, sort the current point and the points before and after it, and take the median value as the processed value. For the heart rate monitor data, sliding average filtering is used with a window size of 5 to smooth the heart rate fluctuations. The time synchronization ensures that the data of the accelerometer, gyroscope, and heart rate monitor correspond on the same time series. If there are slight deviations in the acquisition time, time alignment is performed through linear interpolation. In this way, noise filtering can remove the interference signals in the data and ensure the reliability of the data; time synchronization ensures the consistency of different sensor data in the time dimension, improves the data quality, provides a reliable data basis for accurately judging the activity type, and further improves the accuracy of calorie consumption estimation.

[0087] It can be understood that children are in a period of rapid physical development, and there are significant physical differences at different ages, and the range of body posture changes is also large. Therefore, in a feasible embodiment, the physiological parameters at least include age; the posture evaluation model includes an age-segmented parameter library, and different allowable ranges of joint angles are set for children aged 5-8 and 9-12 respectively. In this way, the smart watch can more accurately judge the body posture of children and avoid misjudgment caused by body type differences among children of different ages.

[0088] This application provides a smart watch for children. The smart watch for children includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the calorie consumption data estimation method based on the smart watch for children in the first embodiment above.

[0089] The smart watch for children in the embodiments of the present application may include, but are not limited to, children's devices such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions: tablet computers), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The illustrated smart watch for children is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present application.

[0090] The smart watch for children may include a processing device (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) or a program loaded from a storage device into a random access memory (RAM: Random Access Memory). In the RAM, various programs and data required for the operation of the smart watch for children are also stored. The processing device, the ROM, and the RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus. Generally, the following systems may be connected to the I / O interface: input devices including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an acceleration sensor, a gyroscope, etc.; output devices including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; storage devices including, for example, a magnetic tape, a hard disk, etc.; and a communication device. The communication device may allow the smart watch for children to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a smart watch for children having various systems, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems may be alternatively implemented or had.

[0091] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication device, or installed from a storage device, or installed from the ROM. When the computer program is executed by the processing device, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0092] The smart watch for children provided by the present application adopts the method for estimating calorie consumption data based on the smart watch for children in the above embodiment, and can solve the technical problem of calorie consumption data. Compared with the prior art, the beneficial effects of the smart watch for children provided by the present application are the same as those of the method for estimating calorie consumption data based on the smart watch for children provided in the above embodiment, and other technical features in the smart watch for children are the same as the features disclosed in the method of the previous embodiment, which will not be elaborated here.

[0093] It should be understood that each part disclosed in the present application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0094] As mentioned above, the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0095] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the method for estimating calorie consumption data based on the smart watch for children in the above embodiment.

[0096] The computer-readable storage medium provided by the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or combined with an instruction execution system, device, or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0097] The above computer-readable storage medium may be included in a smart watch for children; or it may exist independently without being assembled into the smart watch for children.

[0098] The above computer-readable storage medium carries one or more programs, which, when executed by the smart watch for children, cause the smart watch for children to: estimate calorie consumption data.

[0099] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the children's computer, partially on the children's computer, executed as a stand-alone software package, partially on the children's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the children's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0101] The modules described in the embodiments of this application can be implemented in software or in hardware. In some cases, the name of the module does not constitute a limitation on the unit itself.

[0102] The readable storage medium provided by this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for estimating calorie consumption data based on a smart watch for children, and can solve the technical problem of estimating calorie consumption data. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by this application are the same as those of the method for estimating calorie consumption data based on a smart watch for children provided in the above embodiments, and will not be elaborated here.

[0103] This application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps of the method for estimating calorie consumption data based on a smart watch for children as described above.

[0104] The computer program product provided by this application can solve the technical problem of estimating calorie consumption data. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as those of the method for estimating calorie consumption data based on a smart watch for children provided in the above embodiments, and will not be elaborated here.

[0105] The above are only partial embodiments of this application, and do not limit the patent scope of this application accordingly. Any equivalent structural transformation made by using the content of the specification and drawings of this application under the technical concept of this application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of this application.

Claims

1. A body posture perception method based on a smart wearable watch for children, characterized in that: The following steps are involved: Collecting raw data generated by at least one sensor on the smart watch; Collect external environmental conditions and physiological parameters related to children; Based on the collected previous children's behavior data and the corresponding time, the pre-established classifier is trained to obtain a scene classification model; Based on the collected real-time children's behavior data, combined with the current network time and scene classification model, the current scene of the children is analyzed; The posture deviation angle is calculated in real time, and combined with the child’s current scene, the motion data is sent to the preset child posture assessment model to classify the child’s current motion, output the corresponding judgment result, and respond to the judgment result.

2. The body posture perception method based on a smart wearable watch for children as claimed in claim 1, characterized in that: The specific training process of the scene classification model is as follows: Divide the time corresponding to the previous children's behavior data into study days and rest days; The children's behavior data belonging to the study day are divided into the study day cluster, and the children's behavior data belonging to the rest day are divided into the rest day cluster; Divide a day into eight time periods, and organize the children's behavior data in the study day cluster and the rest day cluster into corresponding sub-clusters according to the divided time periods; Import the scene information corresponding to the previous children's behavior data to add scene labels to the children's behavior data in each sub-cluster.

3. The body posture perception method based on the smart wearable watch for children as claimed in claim 1, characterized in that: The specific analysis process of the scene currently in which the child is located is as follows: Collecting raw data generated by at least one sensor on the smart watch to obtain a wrist motion trajectory; Determine the child's current location based on the collected positioning data; According to the current network time, determine the sub-cluster of the time period corresponding to the collected real-time children's behavior data; Based on the extracted scene labels, the scene label with the most repetitions is output as the child’s current scene.

4. The body posture perception method based on a smart wearable watch for children as claimed in claim 1, characterized in that: The process of classifying the child's current action, outputting the corresponding judgment result, and responding to the judgment result includes: Calculate posture deviation angle in real time; When the posture deviation angle exceeds the set angle threshold, and the deviation time does not exceed the set time threshold, it is judged that the child is in a bad posture, a vibration triggers a reminder, and a cartoon animation is displayed synchronously to encourage posture adjustment; When the posture deviation angle exceeds the set angle threshold, and the deviation time exceeds the set time threshold, the child is judged to be in a dangerous posture, and the smart watch sounds an alarm; When a child makes a preset interesting gesture, the smartwatch determines that the child is in an interactive posture, and plays interesting sound effects or animations for interesting interaction; When a child makes a preset writing posture and it is a study day, it is determined that the child is in a study state and social function notifications are automatically disabled.

5. The body posture perception method based on a smart wearable watch for children as claimed in claim 1, characterized in that: The step of "training a pre-established classifier based on the collected previous children's behavior data and the corresponding time to obtain a scene classification model" also includes: Initialize the body posture perception module and calibrate the initial wearing position.

6. The body posture perception method based on a smart wearable watch for children as claimed in claim 1, characterized in that: The step of "training a pre-established classifier based on the collected previous children's behavior data and the corresponding time to obtain a scene classification model" also includes: The raw data is subjected to noise filtering and time synchronization processing.

7. The body posture perception method based on a smart wearable watch for children as claimed in claim 1, characterized in that: The physiological parameters include at least age; The posture assessment model includes a parameter library divided by age group, and sets differentiated allowable ranges of joint angles for children aged 5-8 and 9-12 respectively.

8. A smart watch for children, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of a body posture perception method based on a smart wearable watch for children as described in any one of claims 1 to 7.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the body posture perception method based on a smart wearable watch for children are implemented as described in any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product includes a computer program, which, when executed by a processor, implements the steps of the body posture perception method based on a smart wearable watch for children as described in any one of claims 1 to 7.

Images