CN109830277B - Rope skipping monitoring method, electronic device and storage medium - Google Patents
Rope skipping monitoring method, electronic device and storage medium Download PDFInfo
- Publication number
- CN109830277B CN109830277B CN201811518452.3A CN201811518452A CN109830277B CN 109830277 B CN109830277 B CN 109830277B CN 201811518452 A CN201811518452 A CN 201811518452A CN 109830277 B CN109830277 B CN 109830277B
- Authority
- CN
- China
- Prior art keywords
- rope
- skipping
- sound
- rope skipping
- ground
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 50
- 230000007613 environmental effect Effects 0.000 claims abstract description 15
- 238000012360 testing method Methods 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 8
- 230000001133 acceleration Effects 0.000 claims description 20
- 238000009826 distribution Methods 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000007704 transition Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 4
- 229920002430 Fibre-reinforced plastic Polymers 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 239000002131 composite material Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000011151 fibre-reinforced plastic Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000004217 heart function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004199 lung function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
The invention relates to artificial intelligence, and provides a rope skipping monitoring method, a device and a storage medium, wherein the method comprises the following steps: respectively collecting a plurality of sound samples in the environment, extracting one part of the collected data as a training set, and the other part as a test set; extracting characteristic parameters capable of reflecting important characteristics of environmental sounds; establishing an HMM model corresponding to each sound category; training each HMM model by using an open source acoustic model trainer, training the HMM models by using a training set, adding labels to each sound in the training set, inputting data into each HMM model, and training to obtain parameters of each HMM model; and acquiring environmental sound, calculating the probability of classifying the sound into each class by utilizing a forward algorithm, counting the rope skipping at the highest probability of rope skipping and ground slapping the sound class, and accumulating the rope skipping counts. The invention adopts a voice recognition technology to recognize the sound of the rope skipping slapping the ground, accumulates the rope skipping times, monitors the frequency and heat consumption of the rope skipping, and the like.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a rope skipping monitoring method, an electronic device and a storage medium.
Background
The skipping rope is an excellent body building exercise, can effectively train coordination capacity of limbs and heart and lung functions, and is beneficial to keeping the physical state of a person so as to achieve the aim of building up the body; rope skipping can train mathematical ideas of people, improve memory capacity, cultivate rhythm balance sense and cultivate azimuth perception. However, most of current market rope skipping APP is in a fixed counting or fixed timing mode, dead plates and cannot monitor the frequency and heat consumption of the rope skipping in real time, and cannot be separated from a mobile phone, and the mobile phone needs to be clicked for resetting at intervals.
Disclosure of Invention
In order to solve the above technical problems, the present invention provides a rope skipping monitoring method, which is applied to an electronic device, and includes: respectively collecting a plurality of sound samples in the environment, extracting one part of the collected data as a training set, and the other part as a test set; extracting characteristic parameters capable of reflecting important characteristics of environmental sounds; establishing an HMM model corresponding to each sound category; training each HMM model by using an open source acoustic model trainer, training the HMM models by using a training set, adding labels to each sound in the training set, inputting data into each HMM model, and training to obtain parameters of each HMM model; and acquiring environmental sound, calculating the probability of classifying the sound into each class by utilizing a forward algorithm, counting the rope skipping at the highest probability of the rope skipping and the sound class of the ground slapping, and accumulating the rope skipping counts.
Preferably, the HMM models are represented as l (A, B, p), where A is the transition probability matrix of states Si to Sj, B is the observed output probability density of states, and p is the initial distribution probability of states, for each HMM model l i Defining a forward probability variable alpha t (i) The method comprises the following steps In a certain HMM model l i Under the condition that the t time is in the state S i Outputting the front part observed value sequence o=o 1 ,O 2 …O t Probability of (2):
α t (i)＝P(O 1 ,O 2 …O t ，q t ＝S i |l i )，1≤t≤T，1≤i≤N
solving for forward probability variable alpha t (i) And the step of outputting the probability P (o|l) is as follows:
(1) For i is more than or equal to 1 and less than or equal to N, for the state S i And an initial viewing sequence of O 1 Initializing joint probabilities under conditions alpha t
(2) For T-1 with T being equal to or more than 1 and N with j being equal to or more than 1, there are
the iteration relation at the time t represents: state S at time t 1 And state S at time t+1 j Conversion relation between the two.
(3) Obtaining the forward probability variable value alpha through the recursion of the step (2) t (i) A. The invention relates to a method for producing a fibre-reinforced plastic composite From the forward probability variable value alpha t (i) The final probability distribution is found and the probability distribution is calculated,
wherein N is the number of sound categories;
i is the current sound category, i.e., the current state;
o is the observation sequence;
p is the initial distribution probability of the state;
a is a transition probability matrix of states Si to Sj;
b is the observed output probability density of the state;
t is the rope skipping time period;
t is the current time.
Through each HMM model, the observation value sequence O is the probability that the recognition sound corresponds to each HMM model, and if the highest probability is the type of the collision sound between the rope skipping and the ground, the recognition is carried out once.
Preferably, the height of the rope skipping person from the ground is measured through a sensor, the amplitude of the arm swing is detected through an acceleration sensor on an intelligent device worn on the arm, the relation between the heat consumption and the height of the single rope skipping from the ground and the amplitude of the arm swing are counted corresponding to each rope skipping, a heat consumption statistical list is built, and then the heat consumption value of the single rope skipping is obtained in the rope skipping process by searching the heat consumption statistical list.
Preferably, the dead time is also calculated, if the user interrupt time is less than or equal to a preset threshold value, the counter continues to count up, and if the user interrupt time is greater than the preset threshold value, the counter is cleared.
Preferably, the length of the rope skipping is intelligently adjusted according to the sound of the rope skipping slapping the ground, the micro motors are arranged at the two ends of the rope skipping, the two ends of the rope skipping are respectively wound on the output shafts of the corresponding micro motors, the length of the rope skipping is adjusted according to the sound of the rope skipping slapping the ground and the amplitude of arm swinging detected by the acceleration sensor on the arm, wherein: according to the condition that the tangent of the skipping rope and the ground is critical during skipping, dividing the length of the skipping rope into three conditions of long, tangent and short, recognizing the sounds of the skipping rope and the ground slapping under the three conditions by using the tangent as a standard length through an HMM sound recognition model, and combining the detection condition of an acceleration sensor on an arm to serve as the basis for adjusting the length of the skipping rope: if the length of the skipping rope is long, the voice recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates, and the two ends of the skipping rope are wound on a part of the output shaft until the length of the skipping rope meets the standard length; if the length of the skipping rope is short, the arm swings to enable the acceleration sensor on the arm to act, but no sound of the skipping rope slapping on the ground is recognized, the sound recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates reversely, and two ends of the skipping rope are rotated out of the output shaft until the length of the skipping rope meets the standard length.
Preferably, the heart rate of the rope skipping person is also monitored, and the rope skipping frequency is intelligently prompted in combination with the fat burning heart rate interval of the rope skipping person, wherein: the fat burning heart rate interval is between (220-E) x 60% and (220-E) x 70%, if the heart rate of the rope skipping person is not in the fat burning heart rate interval, the rope skipping person is prompted to accelerate or slow down the rope skipping frequency until the heart rate of the rope skipping person is in the fat burning heart rate interval, wherein E is the age of the rope skipping person.
The invention also provides an electronic device, which comprises: the device comprises a memory and a processor, wherein a rope skipping monitoring program is stored in the memory, and the following steps are realized when the rope skipping monitoring program is executed by the processor: respectively collecting a plurality of sound samples in the environment, extracting one part of the collected data as a training set, and the other part as a test set; extracting characteristic parameters capable of reflecting important characteristics of environmental sounds; establishing an HMM model corresponding to each sound category; training each HMM model by using an open source acoustic model trainer, training the HMM models by using a training set, adding labels to each sound in the training set, inputting data into each HMM model, and training to obtain parameters of each HMM model; and acquiring environmental sound, calculating the probability of classifying the sound into each class by utilizing a forward algorithm, counting the rope skipping at the highest probability of the rope skipping and the sound class of the ground slapping, and accumulating the rope skipping counts.
Preferably, the length of the rope skipping is intelligently adjusted according to the sound of the rope skipping slapping the ground, the micro motors are arranged at the two ends of the rope skipping, the two ends of the rope skipping are respectively wound on the output shafts of the corresponding micro motors, the length of the rope skipping is adjusted according to the sound of the rope skipping slapping the ground and the amplitude of arm swinging detected by the acceleration sensor on the arm, wherein: according to the condition that the tangent of the skipping rope and the ground is critical during skipping, dividing the length of the skipping rope into three conditions of long, tangent and short, recognizing the sounds of the skipping rope and the ground slapping under the three conditions by using the tangent as a standard length through an HMM sound recognition model, and combining the detection condition of an acceleration sensor on an arm to serve as the basis for adjusting the length of the skipping rope: if the length of the skipping rope is long, the voice recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates, and the two ends of the skipping rope are wound on a part of the output shaft until the length of the skipping rope meets the standard length; if the length of the skipping rope is short, the arm swings to enable the acceleration sensor on the arm to act, but no sound of the skipping rope slapping on the ground is recognized, the sound recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates reversely, and two ends of the skipping rope are rotated out of the output shaft until the length of the skipping rope meets the standard length.
Preferably, the heart rate of the rope skipping person is also monitored, and the rope skipping frequency is intelligently prompted in combination with the fat burning heart rate interval of the rope skipping person, wherein: the fat burning heart rate interval is between (220-E) x 60% and (220-E) x 70%, if the heart rate of the rope skipping person is not in the fat burning heart rate interval, the rope skipping person is prompted to accelerate or slow down the rope skipping frequency until the heart rate of the rope skipping person is in the fat burning heart rate interval, wherein E is the age of the rope skipping person.
The present invention also provides a computer readable storage medium storing a computer program comprising program instructions which, when executed by a processor, implement a rope jump monitoring method as described above.
The invention adopts the voice recognition technology to recognize the sound of the rope skipping slapping the ground, can accumulate the rope skipping times, monitor the frequency and the heat consumption of the rope skipping in real time, and intelligently recommend rest time for a user, and the like. And according to the difference of rope skipping and ground slapping sound, the rope skipping can be adjusted to a proper length, and the experience of rope skipping people is enhanced. And according to a relation list between the heat consumption and the jump-off height of the single rope skipping and the arm swing amplitude, acquiring the heat consumption value of the single rope skipping by searching the relation list in the rope skipping process.
Drawings
The above-mentioned features and technical advantages of the present invention will become more apparent and readily appreciated from the following description of the embodiments thereof, taken in conjunction with the accompanying drawings.
FIG. 1 is a flow chart of a rope skipping monitoring method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a hardware architecture of an electronic device according to an embodiment of the invention;
fig. 3 is a block diagram of a rope skipping monitoring program according to an embodiment of the present invention.
Detailed Description
Embodiments of a rope jump monitoring method, an electronic device, and a computer-readable storage medium according to the present invention will be described below with reference to the accompanying drawings. Those skilled in the art will recognize that the described embodiments may be modified in various different ways, or combinations thereof, without departing from the spirit and scope of the invention. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive in scope. Furthermore, in the present specification, the drawings are not drawn to scale, and like reference numerals denote like parts.
Fig. 1 is a schematic flow chart of a rope skipping monitoring method according to an embodiment of the present invention. The method comprises the following steps:
a rope skipping monitoring method is applied to an electronic device and comprises the following steps:
step S10, respectively collecting a plurality of sound samples in the environment, and extracting one part of the collected data as a training set and the other part as a test set. For example, if in a room, there may be, for example, a door impact sound, a sound of an article falling to the ground, a sound of a rope jump hitting the ground, a speaking sound, or the like. And extracting one part of the acquired data as a training set and the other part as a test set.
And step S20, extracting characteristic parameters which can represent important characteristics of the environmental sound.
In step S30, an HMM model is built for each sound class.
Step S40, training each HMM model by using a SphinxTrain (a speech recognition system developed by university of calycarhizome, usa), training the HMM model by using a training set, adding a tag to each sound in the training set (i.e., noting which class the sound belongs to), and inputting data into each HMM model to train to obtain parameters of each HMM model.
And S50, calculating the probability of classifying the sound into each class by utilizing a forward algorithm, counting the number of the rope skipping at the highest probability of the class of the sound of the rope skipping and the ground slapping, and accumulating the rope skipping count. After the training of the HMM classifier, each class in the training set corresponds to one classifier HMM. And acquiring the environment sound, wherein the highest probability of each category is represented that the sound accords with the characteristics of the sound category. When the probability of the sound class of the rope skipping and the ground slapping is highest, the rope skipping is indicated to be performed once. When the HMM model recognizes the sound of a jump rope collision with the ground, 1 time is accumulated. Therefore, the number of the rope skipping can be intelligently prompted, such as the number of voice reports.
Further, the HMM model is represented as l (A, B, p), where A is the transition probability matrix of states Si to Sj, B is the observed output probability density of states, and p is the initial distribution probability of states, if there are five sound classes, an HMM model is built for each sound class, respectively l 1 、l 2、 l 3 、l 4 、l 5 . The state refers to a classification item of environmental sounds such as a door impact sound, a sound of an article falling to the ground, a sound of a rope jump hitting the ground. The states Si to Sj may be, for example, the impact sound state of the doorThe transition probability matrix to the sound state of the rope skipping colliding with the ground may be a transition probability matrix from the sound state of the article falling to the ground to the sound state of the door.
For each HMM model l i Defining a forward probability variable alpha t (i) The method comprises the following steps In a certain HMM model l i Under the condition that the t time is in the state S i Outputting the front part observed value sequence o=o 1 ,O 2 …O t Probability of (2):
α t (i)＝P(O 1 ,O 2 …O t ，q t ＝S i |l i )，1≤t≤T，1≤i≤N
solving for forward probability variable alpha t (i) And the step of outputting the probability P (o|l) is as follows:
(1) For i is more than or equal to 1 and less than or equal to N, for the state S i And an initial viewing sequence of O 1 Initializing joint probabilities under conditions alpha t
(2) For T-1 with T being equal to or more than 1 and N with j being equal to or more than 1, there are
the iteration relation at the time t represents: state S at time t 1 And state S at time t+1 j Conversion relation between the two.
(3) Obtaining the forward probability variable value alpha through the recursion of the step (2) t (i) A. The invention relates to a method for producing a fibre-reinforced plastic composite From the forward probability variable value alpha t (i) The final probability distribution is found and the probability distribution is calculated,
wherein N is the number of sound categories;
i is the current sound category, i.e., the current state;
o is the observation sequence;
p is the initial distribution probability of the state;
a is a transition probability matrix of states Si to Sj;
b is the observed output probability density of the state;
t is the rope skipping time period;
t is the current time.
Through each HMM model, the observation value sequence O is the probability that the recognition sound corresponds to each HMM model, and if the highest probability is the type of the collision sound between the rope skipping and the ground, the recognition is carried out once.
In an alternative embodiment, the height of the rope skipping person from the ground can be measured through a sensor, the amplitude of the arm swinging is detected through an acceleration sensor on the intelligent device worn on the arm, the relation between the heat consumption and the height of the rope skipping from the ground and the arm swinging amplitude of a single rope skipping are counted corresponding to each rope skipping, a heat consumption statistical list is established, and then the heat consumption value of the rope skipping is obtained by searching the heat consumption statistical list in the rope skipping process.
In an alternative embodiment, the dead time may also be calculated, and if the user interrupt time is less than or equal to a preset threshold, the counter continues to count up, and if the user interrupt time is greater than the preset threshold, the count is cleared.
In an alternative embodiment, the length of the rope skipping can be intelligently adjusted according to the sound of the rope skipping slapping the ground, the micro motors are arranged at the two ends of the rope skipping, the two ends of the rope skipping are respectively wound on the output shafts of the corresponding micro motors, the length of the rope skipping is adjusted according to the sound of the rope skipping slapping the ground and the amplitude of the swing of the arm detected by the acceleration sensor on the arm, wherein:
dividing the length of the skipping rope into three conditions of long, tangent and short according to the condition that the tangency of the skipping rope and the ground is critical, and recognizing the sounds of the skipping rope slapping the ground under the three conditions by using the tangency as a standard length through an HMM sound recognition model as the basis for adjusting the length of the skipping rope:
if the length of the skipping rope is long, the voice recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates, and the two ends of the skipping rope are wound on a part of the output shaft until the length of the skipping rope meets the standard length;
if the length of the skipping rope is short, the arm swings to enable the acceleration sensor on the arm to act, but no sound of the skipping rope slapping on the ground is recognized, the sound recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates reversely, and two ends of the skipping rope are rotated out of the output shaft until the length of the skipping rope meets the standard length.
In an alternative embodiment, the heart rate of the rope skipping person can also be monitored, and the rope skipping frequency is intelligently prompted in combination with the fat burning heart rate interval of the rope skipping person, wherein:
the fat burning heart rate interval is between (220-E) x 60% and (220-E) x 70%, if the heart rate of the rope skipping person is not in the fat burning heart rate interval, the rope skipping person is prompted to accelerate or slow down the rope skipping frequency until the heart rate of the rope skipping person is in the fat burning heart rate interval, wherein E is the age of the rope skipping person.
Fig. 2 is a schematic diagram of a hardware architecture of an electronic device according to an embodiment of the invention. In this embodiment, the electronic device 2 is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction. For example, it may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server, or a rack server (including a stand-alone server or a server cluster composed of a plurality of servers), etc. As shown in fig. 2, the electronic device 2 includes at least, but is not limited to, a memory 21, a processor 22, and a network interface 23, which are communicatively connected to each other via a system bus. Wherein: the memory 21 includes at least one type of computer-readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 21 may be an internal storage unit of the electronic device 2, such as a hard disk or a memory of the electronic device 2. In other embodiments, the memory 21 may also be an external storage device of the electronic apparatus 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a flash Card (FlashCard) or the like, which are provided on the electronic apparatus 2. Of course, the memory 21 may also comprise both an internal memory unit of the electronic device 2 and an external memory means thereof. In this embodiment, the memory 21 is generally used for storing an operating system and various application software installed in the electronic device 2, such as the rope jump monitoring program code. Further, the memory 21 may be used to temporarily store various types of data that have been output or are to be output.
The processor 22 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 22 is typically used to control the overall operation of the electronic device 2, such as performing control and processing related to data interaction or communication with the electronic device 2. In this embodiment, the processor 22 is configured to execute the program code or process data stored in the memory 21, for example, execute the rope jump monitoring program.
The network interface 23 may comprise a wireless network interface or a wired network interface, which network interface 23 is typically used for establishing a communication connection between the electronic device 2 and other electronic devices. For example, the network interface 23 is configured to connect the electronic device 2 to a push platform through a network, and establish a data transmission channel and a communication connection between the electronic device 2 and the push platform. The network may be an Intranet (Intranet), the Internet (Internet), a global system for mobile communications (Global System of Mobile communication, GSM), wideband code division multiple access (Wideband CodeDivision Multiple Access, WCDMA), a 4G network, a 5G network, bluetooth (Bluetooth), wi-Fi, or other wireless or wired network.
Alternatively, the electronic apparatus 2 may further include a user interface, which may include an input unit such as a microphone (microphone) or the like having a voice recognition function, a voice output device such as a sound box, an earphone, or the like.
Optionally, the user interface may also include a standard wired interface, a wireless interface.
Optionally, the electronic device 2 may also comprise a display, which may also be referred to as a display screen or display unit. In some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) display, or the like. The display is used for displaying information processed in the electronic device 2 and for displaying a visualized user interface.
It is noted that fig. 2 only shows an electronic device 2 having components 21-23, but it is understood that not all of the illustrated components are required to be implemented, and that more or fewer components may alternatively be implemented.
An operating system, a rope jump monitoring program 50, etc. may be included in the memory 21 containing the readable storage medium. The processor 22 performs the following steps when executing the rope jump monitoring program 50 in the memory 21:
step S10, respectively collecting a plurality of sound samples in the environment, and extracting one part of the collected data as a training set and the other part as a test set. For example, if in a room, there may be, for example, a door impact sound, a sound of an article falling to the ground, a sound of a rope jump hitting the ground, a speaking sound, or the like. And extracting one part of the acquired data as a training set and the other part as a test set.
And step S20, extracting characteristic parameters which can represent important characteristics of the environmental sound.
In step S30, an HMM model is built for each sound class.
Step S40, training each HMM model by using a SphinxTrain (a speech recognition system developed by university of calycarhizome, usa), training the HMM model by using a training set, adding a tag to each sound in the training set (i.e., noting which class the sound belongs to), and inputting data into each HMM model to train to obtain parameters of each HMM model.
And S50, calculating the probability of classifying the sound into each class by utilizing a forward algorithm, counting the number of the rope skipping at the highest probability of the class of the sound of the rope skipping and the ground slapping, and accumulating the rope skipping count.
In this embodiment, the rope jump monitoring program stored in the memory 21 may be divided into one or more program modules, which are stored in the memory 21 and executed by one or more processors (the processor 22 in this embodiment) to complete the present invention. For example, fig. 3 shows a schematic program module of the rope jump monitoring program, and in this embodiment, the rope jump monitoring program 50 may be divided into a sound collection module 501, a feature extraction module 502, an HMM model building module 503, an HMM model training module 504, a sound capturing module 505, and a counting module 506. The program modules referred to herein are defined as a series of computer program instruction segments capable of performing a specific function, more suitable than a program for describing the execution of the rope jump monitoring program in the electronic device 2. The following description will specifically introduce specific functions of the program modules.
The sound collection module 501 collects various sound samples in the environment, and extracts one part of the collected data as a training set and the other part as a test set. For example, if in a room, there may be, for example, a door impact sound, a sound of an article falling to the ground, a sound of a rope jump hitting the ground, a speaking sound, or the like. And extracting one part of the acquired data as a training set and the other part as a test set.
The feature extraction module 502 extracts feature parameters that can represent important characteristics of the environmental sound.
The HMM model creation module 503 creates an HMM model for each sound category.
The HMM model training module 504 trains each HMM model using SphinxTrain (a speech recognition system developed by the university of california, U.S. a), trains the HMM model using a training set, adds a tag to each sound in the training set (i.e., notes which class the sound belongs to), and then inputs data into each HMM model to train the parameters of each HMM model.
The sound capturing module 505 is configured to capture various sounds in the rope skipping environment, each HMM model calculates the probability of classifying the sounds into each class by using a forward algorithm, and counts the rope skipping at the highest probability of the class of the sounds of the rope skipping and the ground slapping, and the counting module 506 counts the rope skipping.
Further, the HMM model is represented as l (A, B, p), where A is the transition probability matrix of states Si to Sj, B is the observed output probability density of states, and p is the initial distribution probability of states, if there are five sound classes, an HMM model is built for each sound class, respectively l 1 、l 2 、l 3 、l 4 、l 5 . The state refers to a classification item of environmental sounds such as a door impact sound, a sound of an article falling to the ground, a sound of a rope jump hitting the ground. The states Si to Sj may be, for example, a transition probability matrix of the impact sound state of the door to the state of the rope-jump collision sound with the ground, or may be a transition probability matrix of the sound state of the article falling to the ground to the impact sound state of the door.
For each HMM model l i Defining a forward probability variable alpha t (i) The method comprises the following steps In a certain HMM model l i Under the condition that the t time is in the state S i Outputting the front part observed value sequence o=o 1 ,O 2 …Q t Probability of (2):
α t (i)＝P(O 1 ,O 2 …O t ，q t ＝S i |l i )，1≤t≤T，1≤i≤N
solving for forward probability variable alpha t (i) And the step of outputting the probability P (o|l) is as follows:
(1) For i is more than or equal to 1 and less than or equal to N, for the state S i And an initial viewing sequence of O 1 Initializing joint probabilities under conditions alpha t
(2) For T-1 with T being equal to or more than 1 and N with j being equal to or more than 1, there are
the iteration relation at the time t represents: state S at time t 1 And state S at time t+1 j Conversion relation between the two.
(3) Obtaining the forward probability variable value alpha through the recursion of the step (2) t (i) A. The invention relates to a method for producing a fibre-reinforced plastic composite From the forward probability variable value alpha t (i) The final probability distribution is found and the probability distribution is calculated,
wherein N is the number of sound categories;
i is the current sound category, i.e., the current state;
o is the observation sequence;
p is the initial distribution probability of the state;
a is a transition probability matrix of states Si to Sj;
b is the observed output probability density of the state;
t is the rope skipping time period;
t is the current time.
Through each HMM model, the observation value sequence O is the probability that the recognition sound corresponds to each HMM model, and if the highest probability is the type of the collision sound between the rope skipping and the ground, the recognition is carried out once.
In an alternative embodiment, the device further comprises a heat consumption relation list building module 507, wherein the height of the rope skipping person from the ground can be measured through a sensor, the amplitude of the arm swing is detected through an acceleration sensor on an intelligent device worn on the arm, the relation between the heat consumption and the height of the rope skipping person from the ground and the amplitude of the arm swing are counted by the heat consumption relation list building module 507 corresponding to each rope skipping, a heat consumption statistical list is built, and further the heat consumption value of the rope skipping is obtained in the rope skipping process by searching the heat consumption statistical list.
In an alternative embodiment, the method further includes a zero clearing module 508, where the zero clearing module 508 may calculate the dead time, and if the user interrupt time is less than or equal to a preset threshold, the counter continues to count up, and if the user interrupt time is greater than the preset threshold, the counter is zero cleared.
In an alternative embodiment, the device further comprises a rope skipping length adjusting module 509, which can intelligently adjust the length of the rope skipping according to the sound of the rope skipping to the ground, wherein the two ends of the rope skipping are provided with micro motors, the two ends of the rope skipping are respectively wound on the output shafts of the corresponding micro motors, and the length of the rope skipping is adjusted according to the sound of the rope skipping to the ground and the amplitude of the arm swing detected by the acceleration sensor on the arm, wherein:
dividing the length of the skipping rope into three conditions of long, tangent and short according to the condition that the tangency of the skipping rope and the ground is critical, and recognizing the sounds of the skipping rope slapping the ground under the three conditions by using the tangency as a standard length through an HMM sound recognition model as the basis for adjusting the length of the skipping rope:
if the length of the skipping rope is long, the voice recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates, and the two ends of the skipping rope are wound on a part of the output shaft until the length of the skipping rope meets the standard length;
if the length of the skipping rope is short, the arm swings to enable the acceleration sensor on the arm to act, but no sound of the skipping rope slapping on the ground is recognized, the sound recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates reversely, and two ends of the skipping rope are rotated out of the output shaft until the length of the skipping rope meets the standard length.
In an alternative embodiment, the rope skipping device further comprises a fat burning interval prompting module 510 for intelligently prompting the rope skipping person to change the rope skipping frequency by monitoring the heart rate of the rope skipping person and combining the fat burning heart rate interval of the rope skipping person, wherein:
the fat burning heart rate interval is between (220-E) x 60% and (220-E) x 70%, if the heart rate of the rope skipping person is not in the fat burning heart rate interval, the rope skipping person is prompted to accelerate or slow down the rope skipping frequency until the heart rate of the rope skipping person is in the fat burning heart rate interval, wherein E is the age of the rope skipping person.
In addition, the embodiment of the invention also provides a computer readable storage medium, which can be any one or any combination of a plurality of hard disk, a multimedia card, an SD card, a flash memory card, an SMC, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory and the like. The embodiment of the computer readable storage medium of the present invention is substantially the same as the above-mentioned rope skipping monitoring method and the embodiment of the electronic device 2, and will not be repeated here.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The rope skipping monitoring method is applied to an electronic device and is characterized by comprising the following steps of:
respectively collecting a plurality of sound samples in the environment, extracting one part of the collected data as a training set, and the other part as a test set;
extracting characteristic parameters capable of reflecting important characteristics of environmental sounds;
establishing an HMM model corresponding to each sound category;
training each HMM model by using an open source acoustic model trainer, training the HMM models by using a training set, adding labels to each sound in the training set, inputting data into each HMM model, and training to obtain parameters of each HMM model;
and acquiring environmental sound, calculating the probability of classifying the sound into each class by utilizing a forward algorithm, counting the rope skipping at the highest probability of the rope skipping and the sound class of the ground slapping, and accumulating the rope skipping counts.
2. The rope jump monitoring method according to claim 1, characterized in that the HMM model is represented as i (a, B, p), where a is the transition probability matrix of states Si to Sj, B is the observed output probability density of states, p is the initial distribution probability of states, for each HMM model i i Fixed, fixedSense forward probability variable alpha t (i) The method comprises the following steps In a certain HMM model l i Under the condition that the t time is in the state S i Outputting the front part observed value sequence o=o 1 ,O 2 ....O t Probability of (2):
α t (i)＝P(O 1 ,O 2 ....O t ，q t ＝Si|l i )，1≤t≤T，1≤i≤N
solving for forward probability variable alpha t (i) And the step of outputting the probability P (o|l) is as follows:
(1) For i is more than or equal to 1 and less than or equal to N, for the state S i And an initial observation sequence of O 1 Initialization of joint probabilities under conditions
(2) For T-1 with T being equal to or more than 1 and N with j being equal to or more than 1, there are
the iteration relation at the time t represents: state S at time t 1 And state S at time t+1 j A conversion relationship between the two;
(3) Obtaining the forward probability variable value alpha through the recursion of the step (2) t (i) From the forward probability variable value alpha t (i) The final probability distribution is found and the probability distribution is calculated,wherein:
n is the number of sound categories;
i is the current sound category, i.e., the current state;
o is the observation sequence;
p is the initial distribution probability of the state;
a is a transition probability matrix of states Si to Sj;
b is the observed output probability density of the state;
t is the rope skipping time period;
t is the current moment;
through each HMM model, the observation value sequence O is the probability that the recognition sound corresponds to each HMM model, and if the highest probability is the type of the collision sound between the rope skipping and the ground, the recognition is carried out once.
3. The rope skipping monitoring method according to claim 1, wherein the height of a rope skipping person from the ground is measured through a sensor, the amplitude of arm swinging is detected through an acceleration sensor worn on an arm, the relation between heat consumption and the height of a single rope skipping from the ground and the amplitude of arm swinging is counted corresponding to each rope skipping, a heat consumption statistical list is established, and further the heat consumption value of the single rope skipping is obtained by searching the heat consumption statistical list in the rope skipping process.
4. The rope-skipping monitoring method of claim 1 wherein the dead time is also calculated, the counter continues to count if the user interrupt time is less than or equal to a preset threshold, and the counter is cleared if the user interrupt time is greater than the preset threshold.
5. The rope skipping monitoring method according to claim 1, wherein the length of the rope skipping is intelligently adjusted according to the sound of the rope skipping slapping the ground, miniature motors are arranged at two ends of the rope skipping, the two ends of the rope skipping are respectively wound on the output shafts of the corresponding miniature motors, and the length of the rope skipping is adjusted according to the sound of the rope skipping slapping the ground and the amplitude of the arm swing detected by an acceleration sensor on the arm, wherein:
according to the condition that the tangent of the skipping rope and the ground is critical during skipping, dividing the length of the skipping rope into three conditions of long, tangent and short, recognizing the sounds of the skipping rope and the ground slapping under the three conditions by using the tangent as a standard length through an HMM sound recognition model, and combining the detection condition of an acceleration sensor on an arm to serve as the basis for adjusting the length of the skipping rope:
if the length of the skipping rope is long, the voice recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates, and the two ends of the skipping rope are wound on a part of the output shaft until the length of the skipping rope meets the standard length;
if the length of the skipping rope is short, the arm swings to enable the acceleration sensor on the arm to act, but no sound of the skipping rope slapping on the ground is recognized, the sound recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates reversely, and two ends of the skipping rope are rotated out of the output shaft until the length of the skipping rope meets the standard length.
6. The rope skipping monitoring method of claim 1, further monitoring the heart rate of the rope skipping person and intelligently prompting the rope skipping frequency in conjunction with the fat burning heart rate interval of the rope skipping person, wherein:
the fat burning heart rate interval is between (220-E) x 60% and (220-E) x 70%, if the heart rate of the rope skipping person is not in the fat burning heart rate interval, the rope skipping person is prompted to accelerate or slow down the rope skipping frequency until the heart rate of the rope skipping person is in the fat burning heart rate interval, wherein E is the age of the rope skipping person.
7. An electronic device, comprising: the device comprises a memory and a processor, wherein a rope skipping monitoring program is stored in the memory, and the following steps are realized when the rope skipping monitoring program is executed by the processor:
respectively collecting a plurality of sound samples in the environment, extracting one part of the collected data as a training set, and the other part as a test set;
extracting characteristic parameters capable of reflecting important characteristics of environmental sounds;
establishing an HMM model corresponding to each sound category;
training each HMM model by using an open source acoustic model trainer, training the HMM models by using a training set, adding labels to each sound in the training set, inputting data into each HMM model, and training to obtain parameters of each HMM model;
and acquiring environmental sound, calculating the probability of classifying the sound into each class by utilizing a forward algorithm, counting the rope skipping at the highest probability of the rope skipping and the sound class of the ground slapping, and accumulating the rope skipping counts.
8. The electronic device of claim 7, wherein the length of the jump rope is intelligently adjusted according to the sound of the jump rope slapping the ground, the two ends of the jump rope are respectively wound on the output shafts of the corresponding micro motors, and the length of the jump rope is adjusted according to the sound of the jump rope slapping the ground and the amplitude of the swing of the arm detected by the acceleration sensor on the arm, wherein:
according to the condition that the tangent of the skipping rope and the ground is critical during skipping, dividing the length of the skipping rope into three conditions of long, tangent and short, recognizing the sounds of the skipping rope and the ground slapping under the three conditions by using the tangent as a standard length through an HMM sound recognition model, and combining the detection condition of an acceleration sensor on an arm to serve as the basis for adjusting the length of the skipping rope:
if the length of the skipping rope is long, the voice recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates, and the two ends of the skipping rope are wound on a part of the output shaft until the length of the skipping rope meets the standard length;
if the length of the skipping rope is short, the arm swings to enable the acceleration sensor on the arm to act, but no sound of the skipping rope slapping on the ground is recognized, the sound recognition system sends a signal to the micro motor, the output shaft of the micro motor rotates reversely, and two ends of the skipping rope are rotated out of the output shaft until the length of the skipping rope meets the standard length.
9. The electronic device of claim 7, further monitoring a rope jumper's heart rate and intelligently prompting rope skipping frequency in conjunction with a fat burning heart rate interval of the rope jumper, wherein:
the fat burning heart rate interval is between (220-E) x 60% and (220-E) x 70%, if the heart rate of the rope skipping person is not in the fat burning heart rate interval, the rope skipping person is prompted to accelerate or slow down the rope skipping frequency until the heart rate of the rope skipping person is in the fat burning heart rate interval, wherein E is the age of the rope skipping person.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program comprising program instructions which, when executed by a processor, implement the rope jump monitoring method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811518452.3A CN109830277B (en) | 2018-12-12 | 2018-12-12 | Rope skipping monitoring method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811518452.3A CN109830277B (en) | 2018-12-12 | 2018-12-12 | Rope skipping monitoring method, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109830277A CN109830277A (en) | 2019-05-31 |
| CN109830277B true CN109830277B (en) | 2024-03-15 |
Family
ID=66859852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811518452.3A Active CN109830277B (en) | 2018-12-12 | 2018-12-12 | Rope skipping monitoring method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109830277B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115193010B (en) * | 2021-04-09 | 2024-08-23 | 广东小天才科技有限公司 | Rope skipping frequency calculation method and wearable device |
| CN112973131A (en) * | 2021-04-16 | 2021-06-18 | 上海跳与跳信息技术合伙企业(有限合伙) | Rope skipping game control system |
| CN113627340B (en) * | 2021-08-11 | 2024-02-09 | 广东沃莱科技有限公司 | Method and equipment capable of identifying rope skipping mode |
| CN115702993B (en) * | 2021-08-12 | 2023-10-31 | 荣耀终端有限公司 | Rope skipping state detection method and electronic equipment |
| CN113627396B (en) * | 2021-09-22 | 2023-09-05 | 浙江大学 | Rope skipping counting method based on health monitoring |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWM246019U (en) * | 2003-11-13 | 2004-10-11 | Shian-Ting Huang | Structure of jumping rope with features of informing exercise status by display or voice |
| CN107331384A (en) * | 2017-06-12 | 2017-11-07 | 平安科技（深圳）有限公司 | Audio recognition method, device, computer equipment and storage medium |
| CN107680582A (en) * | 2017-07-28 | 2018-02-09 | 平安科技（深圳）有限公司 | Acoustic training model method, audio recognition method, device, equipment and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8046058B2 (en) * | 2007-08-10 | 2011-10-25 | Salutron, Inc. | Heart beat signal recognition |
-
2018
- 2018-12-12 CN CN201811518452.3A patent/CN109830277B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWM246019U (en) * | 2003-11-13 | 2004-10-11 | Shian-Ting Huang | Structure of jumping rope with features of informing exercise status by display or voice |
| CN107331384A (en) * | 2017-06-12 | 2017-11-07 | 平安科技（深圳）有限公司 | Audio recognition method, device, computer equipment and storage medium |
| CN107680582A (en) * | 2017-07-28 | 2018-02-09 | 平安科技（深圳）有限公司 | Acoustic training model method, audio recognition method, device, equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于短时平均幅度和HMM的语音识别系统研究;武志翔 等;化工自动化及仪表;20130610;40(06);779-782 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109830277A (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109830277B (en) | Rope skipping monitoring method, electronic device and storage medium | |
| CN108053838B (en) | In conjunction with fraud recognition methods, device and the storage medium of audio analysis and video analysis | |
| CN109859772B (en) | Emotion recognition method, emotion recognition device and computer-readable storage medium | |
| CN110189769B (en) | Abnormal sound detection method based on combination of multiple convolutional neural network models | |
| WO2021051579A1 (en) | Body pose recognition method, system, and apparatus, and storage medium | |
| Lester et al. | A hybrid discriminative/generative approach for modeling human activities | |
| CN110265040A (en) | Training method, device, storage medium and the electronic equipment of sound-groove model | |
| CN109889920A (en) | Network courses video clipping method, system, equipment and storage medium | |
| CN107688790B (en) | Human behavior recognition method and device, storage medium and electronic equipment | |
| CN104007822A (en) | Large database based motion recognition method and device | |
| CN113420556B (en) | Emotion recognition method, device, equipment and storage medium based on multi-mode signals | |
| CN108038413A (en) | Cheat probability analysis method, apparatus and storage medium | |
| CN102707806A (en) | Motion recognition method based on acceleration sensor | |
| CN109902582A (en) | A kind of classification of motion method, apparatus, storage medium and terminal device | |
| CN116311539B (en) | Sleep motion capturing method, device, equipment and storage medium based on millimeter waves | |
| CN109841221A (en) | Parameter adjusting method, device and body-building equipment based on speech recognition | |
| JP2009238196A (en) | Method and system for estimating moving state of portable terminal apparatus | |
| CN110491394A (en) | Wake up the acquisition methods and device of corpus | |
| CN112489628B (en) | Voice data selection method and device, electronic equipment and storage medium | |
| CN117078976A (en) | Action scoring method, action scoring device, computer equipment and storage medium | |
| CN111883174A (en) | Voice recognition method and device, storage medium and electronic device | |
| CN111860061A (en) | Identification method and device for badminton hitting action and wearable equipment | |
| US20210295184A1 (en) | Predicting And Mitigating Athlete Injury Risk | |
| CN115565639A (en) | Exercise heart rate prediction method, device and equipment | |
| CN109815806B (en) | Face recognition method and device, computer equipment and computer storage medium |
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 |