CN106681997B - Information processing method and device - Google Patents
Information processing method and device Download PDFInfo
- Publication number
- CN106681997B CN106681997B CN201510746856.8A CN201510746856A CN106681997B CN 106681997 B CN106681997 B CN 106681997B CN 201510746856 A CN201510746856 A CN 201510746856A CN 106681997 B CN106681997 B CN 106681997B
- Authority
- CN
- China
- Prior art keywords
- multimedia information
- user
- state
- body state
- vital sign
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/635—Filtering based on additional data, e.g. user or group profiles
- G06F16/636—Filtering based on additional data, e.g. user or group profiles by using biological or physiological data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/435—Filtering based on additional data, e.g. user or group profiles
- G06F16/436—Filtering based on additional data, e.g. user or group profiles using biological or physiological data of a human being, e.g. blood pressure, facial expression, gestures
Abstract
The invention discloses an information processing method, which comprises the following steps: monitoring vital sign parameters of a user in the exercise process; determining the current body state of the user in the motion process by utilizing the monitored vital sign parameters and based on a Support Vector Machine (SVM) algorithm; selecting multimedia information equivalent to the first reference multimedia information characteristic value; the first reference multimedia information is reference multimedia information corresponding to the current body state of the user; outputting the selected multimedia information to the user. The invention also discloses an information processing transpose.
Description
Technical Field
The present invention relates to electronic technologies, and in particular, to an information processing method and apparatus.
Background
In the existing APPlication program (APP) products, such as QQ music, certain types of songs are automatically divided into song libraries according to scenes, such as "running" and "driving", and the music inside the APP is basically fixed and similar in style. The user clicks on the theme while running and a series of songs are automatically played. That is, the user can only listen to the songs in the song library corresponding to the theme, and the played songs are basically unchanged and do not reflect the physical state of the user, so that the user can often encounter the songs that the user does not want to hear when running, and the running effect is affected.
There is also a scheme of determining the current exercise intensity level of the user by acquiring acceleration information output from the acceleration sensor and then searching for music matching the determined exercise intensity level. However, the actual exercise state of the user cannot be accurately reflected only by playing the corresponding music through the acceleration information, and accordingly, the played music cannot really play a role in increasing the exercise effect for the user.
Disclosure of Invention
In order to solve the existing technical problem, embodiments of the present invention provide an information processing method and apparatus.
In order to achieve the above purpose, the technical solution of the embodiment of the present invention is realized as follows:
the embodiment of the invention provides an information processing method, which comprises the following steps:
monitoring vital sign parameters of a user in the exercise process;
determining the current body state of the user in the movement process by using the monitored vital sign parameters and based on a Support Vector Machine (SVM) algorithm;
selecting multimedia information equivalent to the first reference multimedia information characteristic value; the first reference multimedia information is reference multimedia information corresponding to the current body state of the user;
outputting the selected multimedia information to the user.
In the above scheme, after determining the current physical state of the user, the method further includes:
and when the current physical state of the user is the limit state of the user, stopping outputting the selected multimedia information to the user, or outputting the multimedia information for warning to the user.
In the above scheme, the first reference multimedia information characteristic value is more than two different characteristic values;
correspondingly, the selecting the multimedia information equivalent to the first reference multimedia information characteristic value is as follows:
searching a multimedia information set corresponding to more than two characteristic values of the first reference multimedia information in a multimedia information base, wherein the number of the more than two characteristic values of each multimedia information in the multimedia information set, which is the same as the corresponding characteristic values of the first reference multimedia information, is within a preset range;
and taking each piece of multimedia information in the searched multimedia information set as the selected multimedia information.
In the foregoing solution, before comparing two or more feature values of each piece of multimedia information in the multimedia information library with corresponding feature values of the first reference multimedia information, the method further includes:
and counting more than two characteristic values of each piece of multimedia information in the multimedia information base and storing the characteristic values in the multimedia information base.
In the above scheme, when counting more than two feature values of each piece of multimedia information in the multimedia information base, the method further includes:
analyzing the disliked multimedia information types of the user in each body state according to the favorite habits of the user, and identifying in the multimedia information library;
accordingly, the selected multimedia information is the multimedia information according with the favorite habit of the user.
In the above scheme, the determining, by using the monitored vital sign parameters and based on an SVM algorithm, the current body state of the user in the exercise process includes:
determining the current body state of the user in the motion process by utilizing the monitored vital sign parameters based on a body state model; the body state model is a corresponding relation model of the body state of the user and the vital sign parameters, which is established based on an SVM algorithm.
In the above solution, before monitoring the vital sign parameters and the motion parameters of the user, the method further includes:
and establishing the body state model based on an SVM algorithm.
An embodiment of the present invention further provides an information processing apparatus, including: the device comprises a monitoring unit, a determining unit, a selecting unit and an output unit; wherein the content of the first and second substances,
the monitoring unit is used for monitoring vital sign parameters of the user in the exercise process;
the determination unit is used for determining the current body state of the user in the exercise process by utilizing the monitored vital sign parameters and based on an SVM algorithm;
the selection unit is used for selecting the multimedia information equivalent to the first reference multimedia information characteristic value; the first reference multimedia information is reference multimedia information corresponding to the current body state of the user;
and the output unit is used for outputting the selected multimedia information to the user.
In the above scheme, the output unit is further configured to stop outputting the selected multimedia information to the user or output the multimedia information for warning to the user when the current physical state of the user is the limit state of the user.
In the above scheme, the first reference multimedia information characteristic value is more than two different characteristic values; the selection unit includes: a searching module and a selecting module; wherein the content of the first and second substances,
the searching module is used for searching a multimedia information set corresponding to more than two characteristic values of the first reference multimedia information in a multimedia information base, and the number of the more than two characteristic values of each multimedia information in the multimedia information set, which is the same as the corresponding characteristic values of the first reference multimedia information, is within a preset range;
and the selection module is used for taking each piece of multimedia information in the searched multimedia information set as the selected multimedia information.
In the above scheme, the apparatus further comprises: and the counting unit is used for counting more than two characteristic values of each piece of multimedia information in the multimedia information base and storing the characteristic values into the multimedia information base.
In the above scheme, the statistical unit is further configured to analyze a type of the multimedia information that is disliked by the user in each body state according to the favorite habit of the user, and identify the type in the multimedia information library;
accordingly, the selected multimedia information is the multimedia information according with the favorite habit of the user.
In the foregoing solution, the determining unit is specifically configured to: determining the current body state of the user in the motion process by utilizing the monitored vital sign parameters based on a body state model; the body state model is a corresponding relation model of the body state of the user and the vital sign parameters, which is established based on an SVM algorithm.
In the above scheme, the apparatus further comprises: and the model establishing unit is used for establishing the body state model based on an SVM algorithm.
According to the information processing method and device provided by the embodiment of the invention, the vital sign parameters of the user are monitored in the movement process; determining the current body state of the user in the movement process by using the monitored vital sign parameters and based on an SVM algorithm; selecting multimedia information equivalent to the first reference multimedia information characteristic value; the first reference multimedia information is reference multimedia information corresponding to the current body state of the user; and outputting the selected multimedia information to the user, and identifying the body state of the user based on the vital sign parameters of the user, wherein the identification result is accurate. Meanwhile, corresponding multimedia information is output according to the current body state of the user which is accurately identified, so that the exercise effect of the user can be promoted, and the user experience is improved.
Drawings
In the drawings, which are not necessarily drawn to scale, like reference numerals may describe similar components in different views. Like reference numerals having different letter suffixes may represent different examples of similar components. The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments discussed herein.
FIG. 1 is a flow chart illustrating a method of processing information according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for recommending music to a user according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a result of identifying a music type corresponding to a music tempo according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating a second information processing apparatus according to a second embodiment of the present invention;
FIG. 5 is a diagram illustrating a second information processing apparatus according to a second embodiment of the present invention;
FIG. 6 is a diagram illustrating a second information processing apparatus according to a third embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
Before describing the embodiment of the present invention, a detailed understanding of the present technical solution for playing multimedia information such as music to a user during a sports process will be given.
1) There are several kinds of APPs, such as QQ music, etc., which automatically (or based on public recognition) divide a certain type of song into song libraries according to scenes, and a user can select the song library corresponding to a running scene during running to play the song, but the method has the following defects: if the user does not manually switch the played songs, only the songs in the song library can be listened to, so that the user often encounters the songs which the user does not want to hear during running, and the running effect is influenced.
2) The current exercise intensity level of the user is identified through the acceleration information output by the acceleration sensor, and the song corresponding to the exercise intensity level is searched. However, the actual exercise state of the user cannot be accurately reflected only by playing the corresponding music through the acceleration information, for example, if the method is used on a treadmill (if the mode is not manually switched), the speed is consistent throughout the whole course, the acceleration sensor cannot detect the fatigue and discomfort condition of the user during running, so that the body state of the user during exercise cannot be accurately reflected, and the played music cannot really play a role in increasing the exercise effect for the user.
In addition, in the prior art, the state of the user during training can be sensed through physiological indexes (pulse, body temperature, blood pressure, hydration degree, heart rate, Electrocardiogram (EKG), and the like), but the technology only directly displays the sensed physiological data, so that the existing training mode is changed through the existing display result, and how to classify the body state of the user according to the physiological data is not involved, and corresponding music is played to the user.
Based on this, in various embodiments of the invention: monitoring vital sign parameters of a user in the exercise process; determining the current body state of the user in the movement process by using the monitored vital sign parameters and based on an SVM algorithm; selecting multimedia information equivalent to the first reference multimedia information characteristic value; the first reference multimedia information is reference multimedia information corresponding to the current body state of the user; outputting the selected multimedia information to the user.
Example one
The information processing method of the embodiment, as shown in fig. 1, includes the following steps:
step 101: monitoring vital sign parameters of a user in the exercise process;
here, the vital sign parameters may include: pulse, body temperature, blood pressure, galvanic skin response, etc. Wherein the galvanic skin response is: skin resistance or conductance changes with changes in skin sweat gland function, called the galvanic skin response.
When the system is actually applied, the vital sign parameters of the user can be monitored in real time. Accordingly, vital sign parameters of the user can be detected in real time by the respective acquisition device. For example, a collecting device (wearable device) integrated with a photoelectric sensor, a skin electric reaction sensor, a skin temperature sensor, etc. may be used to detect vital sign parameters of a user in real time.
Wherein, the photoplethysmogram of the user can be obtained through the photoelectric sensor. The photoplethysmography is a waveform signal obtained by monitoring blood volume change in living tissue by means of a photoelectric technology, and the signal characteristics of the photoplethysmography include many physiological and pathological information such as a human body circulatory system, a respiratory system and the like. The photoplethysmography has a wide application prospect in noninvasive monitoring of physiological parameters such as blood oxygen saturation, pulse, heart rate, respiratory volume, blood pressure, hemoglobin, hemodynamics, circulation function, anesthesia stress, arteriosclerosis and the like.
In practical applications, the breathing frequency and decibel data of the user can be monitored by a microphone, so as to obtain the breathing frequency and intensity.
Before performing this step, the method may further include:
and establishing the body state model based on an SVM algorithm.
The body state model is a corresponding relation model of the body state of the user and the vital sign parameters, which is established based on an SVM algorithm.
The established physical state model is a physical state model related to the physical state of the user.
For how to establish a body state model, for example, as shown in fig. 2, assuming that the exercise type of the user is running, monitoring vital sign parameters of the user, such as pulse, body temperature, blood pressure, and skin conductance, during the running process by using wearable devices (such as exercise bracelets) integrated with the vital sign parameters, and monitoring respiratory frequency and decibel data of the user during the running process by using a microphone; after running is finished, marking the corresponding time of each body state (including states of relaxation, fatigue, stability (recovery), limitation and the like) in the running process by the user in the monitored various data; and then, establishing a corresponding relation model of the body state and the vital sign parameters of the user by adopting the marked monitoring data and based on an SVM classification algorithm.
Specifically, first, through a large amount of personal monitoring data, according to the marked exercise state in the running process, four state samples are obtained, which are respectively relaxation, fatigue, steady (recovery), and extreme:
label state class 1: relaxed state-the body feels natural, and the spirit is relaxed and pleasant;
flag state 2 class: fatigue-feeling exhausted with obvious dyspnea;
flag state 3 type: smooth (recovery) -breathing is normal;
flag state 4 class: extreme effort in breathing, rapid and violent panting, and uncomfortable feeling of the body.
Secondly, establishing a body state model based on an SVM classification algorithm;
specifically, the input is the number of pulses (X) in each physical state1) Body temperature (X)2) Blood pressure value (X)3) Picowatt value (X)4) Respiratory rate (X)5) Decibel data (X)6) Six parameters. Based on the four body states of the markers, a set-up is made
And (4) modeling. The output is two kinds of body states marked arbitrarily. Using an SVM algorithm, classification model parameters are determined.
The SVM classification algorithm is specifically realized as follows:
step 1: normalization:
normalizing the physiological indexes in the running process, and recording the maximum value X of the physiological indexes Xi in the running process of the userimaxAnd minimum value XiminCalculating new Xi'＝(Xi-Ximin)/(Ximax-Ximin)。
Step 2: reducing vitamin
In order to reduce redundancy contained in data, a Principal Component Analysis (PCA) algorithm is adopted to map a six-dimensional vector into a smaller-dimensional vector, and a covariance matrix C and a dimension N are stored for use after physiological index data in a subsequent user running process are input.
And step 3: grid optimization of classification parameters
An SVM classification model using a radial basis function RBF kernel function relates to two parameters of c and gamma. Through cross validation, the training data is divided into 6 classes, and the best c and gamma are determined.
And 4, step 4: classification model establishment
And (3) carrying out two classes of classification by using an RBF kernel function, substituting the optimal c and gamma values, setting probability estimation, and finally determining model parameters (model).
How to build the body state model is explained in detail below.
The user running process contains a large amount of data of physical physiological indexes, and the physiological indexes of the user in the running process are assumed to comprise: pulse rate (X)1) Body temperature (X)2) Blood pressure value (X)3) Picowatt value (X)4)、Respiratory rate (X)5) Decibel data (X)6)). A total of n recordings, i.e. n samples, are made as shown in table 1.
| Serial number | Number of pulses | Body temperature | Blood pressure value | Pear-to-peak value | Respiratory rate | Decibel | State classification |
| 1 | X11 | X21 | X31 | X41 | X51 | X61 | State 1 |
| 2 | X12 | X22 | X32 | X42 | X52 | X62 | State 2 |
| 3 | X13 | X23 | X33 | X43 | X53 | X63 | State 1 |
| 4 | X14 | X24 | X34 | X44 | X54 | X64 | State 3 |
| 5 | X15 | X25 | X35 | X45 | X55 | X65 | State 4 |
| … | … | … | … | … | … | … | … |
| n | X1n | X1n | X3n | X4n | X5n | X6n | State 2 |
TABLE 1
And designing an SVM between any two types of samples. The example shown in fig. 2 includes four body states, and therefore, the total number of the body states is four
The method specifically comprises the following steps: state 1 and state 2, state 1 and state 3, state 1 and state 4, state 2 and state 3, state 2 and state 4, state 3 and state. In particular toSVM1 (State 1 and State 2) (see Table 2)
| Serial number | Number of pulses | Body temperature | Blood pressure value | Pear-to-peak value | Respiratory rate | Decibel | State classification |
| 1 | X11 | X21 | X31 | X41 | X51 | X61 | State 1 |
| 2 | X12 | X22 | X32 | X42 | X52 | X62 | State 2 |
| 3 | X13 | X23 | X33 | X43 | X53 | X63 | State 1 |
| … | X1n3 | X2n3 | X3n3 | X4n3 | X5n3 | X6n3 | State 2 |
| n | X1n | X1n | X3n | X4n | X5n | X6n | State 2 |
TABLE 2
SVM2 (State 1 and State 3) (shown in Table 3)
| Serial number | Number of pulses | Body temperature | Blood pressure value | Pear-to-peak value | Respiratory rate | Decibel | State classification |
| 1 | X11 | X21 | X31 | X41 | X51 | X61 | State 1 |
| 3 | X13 | X23 | X33 | X43 | X53 | X63 | State 1 |
| 4 | X14 | X24 | X34 | X44 | X54 | X64 | State 3 |
| … | X1n1 | X2n1 | X3n1 | X4n1 | X5n1 | X6n1 | State 3 |
TABLE 3
SVM3 (State 1 and State 4) (shown in Table 4)
| Serial number | Number of pulses | Body temperature | Blood pressure value | Pear-to-peak value | Respiratory rate | Decibel | State classification |
| 1 | X11 | X21 | X31 | X41 | X51 | X61 | State 1 |
| 3 | X13 | X23 | X33 | X43 | X53 | X63 | State 1 |
| 5 | X15 | X25 | X35 | X45 | X55 | X65 | State 4 |
| … | X1n2 | X2n2 | X3n2 | X4n2 | X5n2 | X6n2 | State 4 |
TABLE 4
SVM4 (State 2 and State 3) (shown in Table 5)
| Serial number | Number of pulses | Body temperature | Blood pressure value | Pear-to-peak value | Respiratory rate | Decibel | State classification |
| 2 | X12 | X22 | X32 | X42 | X52 | X62 | State 2 |
| 4 | X14 | X24 | X34 | X44 | X54 | X64 | State 3 |
| … | X1n1 | X2n1 | X3n1 | X4n1 | X5n1 | X6n1 | State 3 |
| … | X1n3 | X2n3 | X3n3 | X4n3 | X5n3 | X6n3 | State 2 |
| n | X1n | X1n | X3n | X4n | X5n | X6n | State 2 |
TABLE 5
SVM5 (State 2 and State 4) (shown in Table 6)
| Serial number | Number of pulses | Body temperature | Blood pressure value | Pear-to-peak value | Respiratory rate | Decibel | State classification |
| 2 | X12 | X22 | X32 | X42 | X52 | X62 | State 2 |
| 5 | X15 | X25 | X35 | X45 | X55 | X65 | State 4 |
| … | X1n2 | X2n2 | X3n2 | X4n2 | X5n2 | X6n2 | State 4 |
| … | X1n3 | X2n3 | X3n3 | X4n3 | X5n3 | X6n3 | State 2 |
| n | X1n | X1n | X3n | X4n | X5n | X6n | State 2 |
TABLE 6
SVM6 (State 3 and State 4) (shown in Table 7)
| Serial number | Number of pulses | Body temperature | Blood pressure value | Pear-to-peak value | Respiratory rate | Decibel | State classification |
| 4 | X14 | X24 | X34 | X44 | X54 | X64 | State 3 |
| 5 | X15 | X25 | X35 | X45 | X55 | X65 | State 4 |
| … | X1n1 | X2n1 | X3n1 | X4n1 | X5n1 | X6n1 | State 3 |
| … | X1n2 | X2n2 | X3n2 | X4n2 | X5n2 | X6n2 | State 4 |
TABLE 7
And respectively carrying out normalization and dimensionality reduction on the data of the six groups of SVM so as to form a corresponding relation model of the body state and the vital sign parameters.
In practical application, the corresponding relation model of the body state and the vital sign parameters of the user can be established by adopting the above mode according to different motion types.
Step 102: determining the current body state of the user in the movement process by using the monitored vital sign parameters and based on an SVM algorithm;
specifically, based on a body state model, the current body state of the user in the motion process is determined by using the monitored vital sign parameters.
For the example shown in fig. 2, the physical state is classified based on the above-mentioned established physical state model and brought into the new physiological index data of the user during running.
Specifically, the physiological index data of the user in the running process is brought into the body state model to generate a prediction result:
step 1: normalization:
normalizing the physiological index in the running process of the user, wherein the new physiological index in the running process of the user is X'i＝(Xi-Ximin)/(Ximax-Ximin)；
Step 2: and (3) reducing the dimensionality:
and mapping the six-dimensional parameters into new parameters according to the covariance matrix C stored during modeling (after subtracting respective mean values from each dimension and multiplying the mean values by the covariance matrix, taking the former N-dimensional parameters).
And step 3: model prediction:
and substituting the data into the model, setting the needed probability estimation, and outputting the category and the probability. When an unknown sample is classified, vectors are brought into the six SVM models, and the category with the largest number of votes is the category of the unknown sample.
Wherein, six groups of corresponding vectors are used as a training set, then six training results are obtained, and during testing, the corresponding vector (X) is used1a、X2a、X3a、X4a、X5a、X6a) The six results are tested separately and then taken in the form of a vote. The category with the most votes is the category of the unknown sample.
Here, the voting process and the result are illustrated as:
(state 1, state 2): if the number of votes in the state 1 is more, the state 1 is equal to the state 1+ 1; otherwise, state 2 is state 2+ 1;
(state 1, state 3): if the number of votes in the state 1 is more, the state 1 is equal to the state 1+ 1; otherwise, state 3 is state 3+ 1;
...
(state 3, state 4): if the number of votes in the state 3 is more, the state 3 is equal to the state 3+ 1; otherwise, state 4 is equal to state 4+ 1.
And finally, the physical state results corresponding to the six physiological indexes in the certain movement process of the user are Max (state 1, state 2, state 3 and state 4).
Step 103: selecting multimedia information equivalent to the first reference multimedia information characteristic value; the first reference multimedia information is reference multimedia information corresponding to the current body state of the user;
here, the multimedia information may be music, songs, etc. in actual use.
For the example shown in fig. 2, similarly, the same processing method as the body state determination method is adopted, and the music type corresponding to a certain music is Max (music1, music2, music3, music 4).
After the physical state and the music type are associated (i.e., music1 corresponding to state 1, music2 corresponding to state 2, music3 corresponding to state 3, and music4 corresponding to state 4), the media player recommends a music song suitable for the user in the current state to the user.
Specifically, if the current physical state of the user is easy, the first reference multimedia information is corresponding music (music with a moderate tempo) in an easy state. And if the current physical state of the user is fatigue, the first reference multimedia information is corresponding music (music with strong rhythm sense) in the fatigue state. If the current body state of the user is steady (recovery), the first reference multimedia information is corresponding music (music with relaxed rhythm) in a steady state.
In other words, when the above-described process of determining the physical state of the user is used, if it is determined that the physical state is state 1 (easy state), music with moderate rhythm is pushed from the media player (music 1);
if the body state is determined to be state 2 (fatigue state), music with strong rhythmic sense is pushed from the media player (music 2);
if the body state is determined to be state 3 (smooth resume), music with a relaxed rhythm is pushed from the media player (music 3);
if the body state is determined to be state 4 (extreme state), alert music is pushed from the media player or music is stopped (music 4).
Here, it should be noted that: the music classification method is to extract rhythm indexes in music and classify music1, music2, music3 and music4 by an SVM algorithm, and the method is similar.
For the reference multimedia information, in practical application, the user can select the multimedia information most conforming to each body state (the light, fatigue and steady state of the body) as the reference multimedia information corresponding to each body state.
For example, assuming that the multimedia information is music, the user may select music that best meets various physical conditions (relaxed, tired, and steady), and obtain a corresponding score as the reference multimedia information corresponding to each physical condition. Then, the number of feature values (such as the length of a sound) of each piece of music is counted, including: note mark, number of rest symbols, punctuated notes, punctuated rest symbols, continuous sound line, and continuous sound division of notes; and counting the number of different beats, rhythms and the like in the music so as to obtain a plurality of characteristic values. Here, in actual application, the number of statistics is allowed to have a certain range of error.
Based on this, in practical application, the first reference multimedia information characteristic value may be more than two different characteristic values;
correspondingly, the selecting the multimedia information equivalent to the first reference multimedia information feature value specifically includes:
searching a multimedia information set corresponding to more than two characteristic values of the first reference multimedia information in a multimedia information base, wherein the number of the more than two characteristic values of each multimedia information in the multimedia information set, which is the same as the corresponding characteristic values of the first reference multimedia information, is within a preset range;
and taking each piece of multimedia information in the searched multimedia information set as the selected multimedia information.
Wherein, the preset range can be set according to the requirement.
And comparing by adopting more than two different characteristic values, and further improving the accuracy of the selected type of the multimedia information and the first reference multimedia information type.
Before searching the multimedia information base for the multimedia information set corresponding to the two or more feature values of the first reference multimedia information, the method may further include:
and counting more than two characteristic values of each piece of multimedia information in the multimedia information base, and storing the characteristic values into the multimedia information base to form the multimedia information set.
Here, in practical application, when more than two feature values of each piece of multimedia information in the multimedia information base are counted, the type of the multimedia information that the user dislikes in the corresponding body state can be analyzed based on the favorite habit of the user, so that the user is not output the disliked multimedia information.
Based on this, the method may further comprise:
analyzing the disliked multimedia information types of the user in each body state according to the favorite habits of the user, and identifying in the multimedia information library;
accordingly, the selected multimedia information is the multimedia information according with the favorite habit of the user.
For example, for the example shown in fig. 2, the number of music switching times of the user during running can be counted, and the type of music that the user dislikes in a certain physical state can be analyzed, so as to obtain the result of the identifier shown in fig. 3.
Step 104: outputting the selected multimedia information to the user.
In practical application, according to various body states during the movement of the user, the same number of multimedia information within a preset range as the corresponding eigenvalue of the first reference multimedia information is output to the user, through multiple times of movement training, the multimedia information in each body state forms a multimedia information set, and the output times of the multimedia information in each set and the number of eigenvalues of the multimedia information are recorded. And continuously correcting the number of the characteristic values representing the multimedia types under the physical state and the range of the characteristic values until the characteristic values are stable, thereby forming a stable multimedia information base.
With the example shown in fig. 2, music having a similar number of feature values to the reference music in the running state may be pushed according to the running state while the user is running. After running training for many times, music under each physical state forms a music library (set), and the playing times of each type of music and the number of characteristic values of the music are recorded. The number of the music characteristics and the interval range representing the music type under the physical state are continuously corrected until the music characteristics and the interval range are stable.
In practical application, when the current physical state of the user is the limit state of the user, the output of the selected multimedia information to the user may be stopped, or the multimedia information for warning may be output to the user, so as to prompt the user to gradually stop or slow down the movement speed.
Wherein the limit state is: a very poor physical condition.
Accordingly, for the example shown in fig. 2, when the current physical state of the user is the limit state of the user, music may be stopped from being played to the user, or warning music may be played to the user to indicate that the user should gradually stop running or slow down running speed.
In the information processing method provided by the embodiment, the vital sign parameters of the user are monitored in the exercise process; determining the current body state of the user in the movement process by using the monitored vital sign parameters and based on an SVM algorithm; selecting multimedia information equivalent to the first reference multimedia information characteristic value; the first reference multimedia information is reference multimedia information corresponding to the current body state of the user; and outputting the selected multimedia information to the user, and identifying the body state of the user based on the vital sign parameters of the user, wherein the identification result is accurate. Meanwhile, corresponding multimedia information is output according to the current body state of the user which is accurately identified, so that the exercise effect of the user can be promoted, and the user experience is improved.
In addition, when the current physical state of the user is the limit state of the user, the output of the selected multimedia information to the user is stopped, or the multimedia information for warning is output to the user, so that the user is prompted to gradually stop the movement or slow down the movement speed, and thus, the user experience can be further improved.
Example two
To implement the method of the embodiment of the present invention, the embodiment provides an information processing apparatus, as shown in fig. 4, the apparatus including: a monitoring unit 41, a determination unit 42, a selection unit 43, and an output unit 44; wherein the content of the first and second substances,
the monitoring unit 41 is configured to monitor vital sign parameters of the user during exercise;
the determining unit 42 is configured to determine, by using the monitored vital sign parameters and based on an SVM algorithm, a current body state of the user during the exercise process;
the selecting unit 43 is configured to select multimedia information equivalent to the first reference multimedia information feature value; the first reference multimedia information is reference multimedia information corresponding to the current body state of the user;
the output unit 44 is configured to output the selected multimedia information to the user.
Wherein the vital sign parameters may include: pulse, body temperature, blood pressure, galvanic skin response, etc. Wherein the galvanic skin response is: skin resistance or conductance changes with changes in skin sweat gland function, called the galvanic skin response.
In practical application, the monitoring unit 44 can monitor the vital sign parameters of the user in real time. Accordingly, vital sign parameters of the user can be detected in real time by the respective acquisition device. For example, a collecting device (wearable device) integrated with a photoelectric sensor, a skin electric reaction sensor, a skin temperature sensor, etc. may be used to detect vital sign parameters of a user in real time.
Wherein, the photoplethysmogram of the user can be obtained through the photoelectric sensor. The photoplethysmography is a waveform signal obtained by monitoring blood volume change in living tissue by means of a photoelectric technology, and the signal characteristics of the photoplethysmography include many physiological and pathological information such as a human body circulatory system, a respiratory system and the like. The photoplethysmography has a wide application prospect in noninvasive monitoring of physiological parameters such as blood oxygen saturation, pulse, heart rate, respiratory volume, blood pressure, hemoglobin, hemodynamics, circulation function, anesthesia stress, arteriosclerosis and the like.
In practical applications, the breathing frequency and decibel data of the user can be monitored by a microphone, so as to obtain the breathing frequency and intensity.
In one embodiment, as shown in fig. 5, the apparatus may further include: a model establishing unit 45, configured to establish the body state model based on an SVM algorithm.
The body state model is a corresponding relation model of the body state of the user and the vital sign parameters, which is established based on an SVM algorithm.
The established physical state model is a physical state model related to the physical state of the user.
For how to establish a body state model, for example, as shown in fig. 2, assuming that the exercise type of the user is running, monitoring vital sign parameters of the user, such as pulse, body temperature, blood pressure, and skin conductance, during the running process by using wearable devices (such as exercise bracelets) integrated with the vital sign parameters, and monitoring respiratory frequency and decibel data of the user during the running process by using a microphone; after running is finished, marking the corresponding time of each body state (including states of relaxation, fatigue, stability (recovery), limitation and the like) in the running process by the user in the monitored various data; then, the model establishing unit 45 establishes a corresponding relationship model between the body state of the user and the vital sign parameters based on an SVM classification algorithm by using the labeled monitoring data.
In practical application, the corresponding relation model of the body state and the vital sign parameters of the user can be established by adopting the above mode according to different motion types.
The determining unit 42 is specifically configured to: and determining the current body state of the user in the motion process by utilizing the monitored vital sign parameters based on the body state model.
Here, the multimedia information may be music, songs, etc. in actual use.
For the example shown in fig. 2, if the current physical state of the user is easy, the first reference multimedia information is corresponding music (music with moderate tempo) in an easy state. And if the current physical state of the user is fatigue, the first reference multimedia information is corresponding music (music with strong rhythm sense) in the fatigue state. If the current body state of the user is steady (recovery), the first reference multimedia information is corresponding music (music with relaxed rhythm) in a steady state.
For the reference multimedia information, in practical application, the user can select the multimedia information most conforming to each body state (the light, fatigue and steady state of the body) as the reference multimedia information corresponding to each body state.
For example, assuming that the multimedia information is music, the user may select music that best meets various physical conditions (relaxed, tired, and steady), and obtain a corresponding score as the reference multimedia information corresponding to each physical condition. Then, the number of feature values (such as the length of a sound) of each piece of music is counted, including: note mark, number of rest symbols, punctuated notes, punctuated rest symbols, continuous sound line, and continuous sound division of notes; and counting the number of different beats, rhythms and the like in the music so as to obtain a plurality of characteristic values. Here, in actual application, the number of statistics is allowed to have a certain range of error.
Based on this, in practical application, the first reference multimedia information characteristic value may be more than two different characteristic values; the selection unit 43 includes: a searching module and a selecting module; wherein the content of the first and second substances,
the searching module is used for searching a multimedia information set corresponding to more than two characteristic values of the first reference multimedia information in a multimedia information base, and the number of the more than two characteristic values of each multimedia information in the multimedia information set, which is the same as the corresponding characteristic values of the first reference multimedia information, is within a preset range;
and the selection module is used for taking each piece of multimedia information in the searched multimedia information set as the selected multimedia information.
Wherein, the preset range can be set according to the requirement.
And comparing by adopting more than two different characteristic values, and further improving the accuracy of the selected type of the multimedia information and the first reference multimedia information type.
As shown in fig. 6, the apparatus may further include: the statistical unit 46 is configured to perform statistics on more than two feature values of each piece of multimedia information in the multimedia information base, and store the feature values in the multimedia information base to form the multimedia information set.
Here, in practical application, when more than two feature values of each piece of multimedia information in the multimedia information base are counted, the type of the multimedia information that the user dislikes in the corresponding body state can be analyzed based on the favorite habit of the user, so that the user is not output the disliked multimedia information.
Based on this, the statistical unit 46 is further configured to analyze the type of the multimedia information that is disliked in each physical state of the user according to the favorite habit of the user, and identify the type in the multimedia information library;
accordingly, the selected multimedia information is the multimedia information according with the favorite habit of the user.
For example, for the example shown in fig. 2, the number of music switching times of the user during running can be counted, and the type of music that the user dislikes in a certain physical state can be analyzed, so as to obtain the result of the identifier shown in fig. 3.
In practical application, according to various body states during the movement of the user, the multimedia information with the same number as the corresponding eigenvalue of the first reference multimedia information within a preset range can be output to the user, through multiple times of movement training, the multimedia information in each body state forms a multimedia information set, and the statistical unit 46 records the output times of the multimedia information in each set and the number of eigenvalues of the multimedia information. And continuously correcting the number of the characteristic values representing the multimedia types under the physical state and the range of the characteristic values until the characteristic values are stable, thereby forming a stable multimedia information base.
With the example shown in fig. 2, music having a similar number of feature values to the reference music in the running state may be pushed according to the running state while the user is running. After a plurality of running exercises, music in each physical state forms a music library (collection), and the statistical unit 46 records the number of times of playing each type of music and the number of eigenvalues of the music. The number of the music characteristics and the interval range representing the music type under the physical state are continuously corrected until the music characteristics and the interval range are stable.
In practical applications, the output unit 44 is further configured to stop outputting the selected multimedia information to the user or output the multimedia information for warning to the user when the current physical state of the user is the limit state of the user.
Wherein the limit state is: a very poor physical condition.
Accordingly, for the example shown in fig. 2, when the current physical state of the user is the user's extreme state, the output unit 44 may stop playing music to the user or play warning music to the user to prompt the user that the running should be gradually stopped or slowed down.
In practical applications, the monitoring unit 41 may be implemented by various sensors in the information processing device; the determining Unit 42, the selecting Unit 43, the model establishing Unit 45, the searching module, the selecting module, and the statistical Unit 46 may be implemented by a Central Processing Unit (CPU), a Microprocessor (MCU), a Digital Signal Processor (DSP), or a Programmable logic Array (FPGA) in the information Processing apparatus; the output unit 44 may be implemented by a handset in the information processing apparatus.
In the information processing apparatus provided in this embodiment, the monitoring unit 41 monitors vital sign parameters of the user during the exercise process; the determination unit 42 determines the current body state of the user in the exercise process by using the monitored vital sign parameters and based on an SVM algorithm; the selection unit 43 selects multimedia information equivalent to the first reference multimedia information feature value; the first reference multimedia information is reference multimedia information corresponding to the current body state of the user; the output unit 44 outputs the selected multimedia information to the user, and identifies the physical state of the user based on the vital sign parameters of the user, so that the identification result is accurate. Meanwhile, corresponding multimedia information is output according to the current body state of the user which is accurately identified, so that the exercise effect of the user can be promoted, and the user experience is improved.
In addition, when the current physical state of the user is the limit state of the user, the output unit 44 stops outputting the selected multimedia information to the user, or outputs multimedia information for warning to the user, so as to prompt the user to gradually stop the exercise or slow down the exercise speed, thus further improving the user experience.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (14)
1. An information processing method, characterized in that the method comprises:
monitoring vital sign parameters of a user in the exercise process;
determining the current body state of the user in the motion process by using the monitored vital sign parameters and based on a Support Vector Machine (SVM) algorithm; the physical state is one of: ease, fatigue, stability, extreme;
selecting multimedia information equivalent to the first reference multimedia information characteristic value; the first reference multimedia information is reference multimedia information corresponding to the current body state of the user; the characteristic value is obtained by counting the number of different beats and rhythms in the first reference multimedia information;
outputting the selected multimedia information to the user;
the method further comprises the following steps:
acquiring four state samples; the four state samples include one of: ease, fatigue, stability, extreme;
determining an SVM model according to any two state samples in the four state samples to obtain six SVM models;
and determining the category with the most votes by using the monitored vital sign parameters and combining the six SVM models, and taking the body state corresponding to the category with the most votes as the current body state of the user in the exercise process.
2. The method of claim 1, wherein upon determining the user's current physical state, the method further comprises:
and when the current physical state of the user is the limit state of the user, stopping outputting the selected multimedia information to the user, or outputting the multimedia information for warning to the user.
3. The method of claim 1, wherein the first reference multimedia information characteristic value is two or more different characteristic values;
correspondingly, the selecting the multimedia information equivalent to the first reference multimedia information characteristic value is as follows:
searching a multimedia information set corresponding to more than two characteristic values of the first reference multimedia information in a multimedia information base, wherein the number of the more than two characteristic values of each multimedia information in the multimedia information set, which is the same as the corresponding characteristic values of the first reference multimedia information, is within a preset range;
and taking each piece of multimedia information in the searched multimedia information set as the selected multimedia information.
4. The method of claim 3, wherein before comparing the two or more feature values of each piece of multimedia information in the multimedia information library with the corresponding feature values of the first reference multimedia information, the method further comprises:
and counting more than two characteristic values of each piece of multimedia information in the multimedia information base and storing the characteristic values in the multimedia information base.
5. The method of claim 4, wherein when counting more than two feature values of each piece of multimedia information in the multimedia information library, the method further comprises:
analyzing the disliked multimedia information types of the user in each body state according to the favorite habits of the user, and identifying in the multimedia information library;
accordingly, the selected multimedia information is the multimedia information according with the favorite habit of the user.
6. The method according to any one of claims 1 to 5, wherein the determining a current body state of the user during exercise using the monitored vital sign parameters and based on an SVM algorithm comprises:
determining the current body state of the user in the motion process by utilizing the monitored vital sign parameters based on a body state model; the body state model is a corresponding relation model of the body state of the user and the vital sign parameters, which is established based on an SVM algorithm.
7. The method of claim 6, wherein prior to monitoring vital sign parameters and motion parameters of the user, the method further comprises:
and establishing the body state model based on an SVM algorithm.
8. An information processing apparatus characterized in that the apparatus comprises: the device comprises a monitoring unit, a determining unit, a selecting unit and an output unit; wherein the content of the first and second substances,
the monitoring unit is used for monitoring vital sign parameters of the user in the exercise process;
the determination unit is used for determining the current body state of the user in the exercise process by utilizing the monitored vital sign parameters and based on an SVM algorithm; the physical state is one of: ease, fatigue, stability, extreme;
the selection unit is used for selecting the multimedia information equivalent to the first reference multimedia information characteristic value; the first reference multimedia information is reference multimedia information corresponding to the current body state of the user; the characteristic value is obtained by counting the number of different beats and rhythms in the first reference multimedia information;
the output unit is used for outputting the selected multimedia information to the user;
the determining unit is specifically configured to:
acquiring four state samples; the four state samples include one of: ease, fatigue, stability, extreme; determining an SVM model according to any two state samples in the four state samples to obtain six SVM models; and determining the category with the most votes by using the monitored vital sign parameters and combining the six SVM models, and taking the body state corresponding to the category with the most votes as the current body state of the user in the exercise process.
9. The apparatus of claim 8, wherein the output unit is further configured to stop outputting the selected multimedia information to the user or outputting the multimedia information for warning to the user when the current physical state of the user is an extreme state of the user.
10. The apparatus according to claim 8, wherein the first reference multimedia information characteristic value is two or more different characteristic values; the selection unit includes: a searching module and a selecting module; wherein the content of the first and second substances,
the searching module is used for searching a multimedia information set corresponding to more than two characteristic values of the first reference multimedia information in a multimedia information base, and the number of the more than two characteristic values of each multimedia information in the multimedia information set, which is the same as the corresponding characteristic values of the first reference multimedia information, is within a preset range;
and the selection module is used for taking each piece of multimedia information in the searched multimedia information set as the selected multimedia information.
11. The apparatus of claim 10, further comprising: and the counting unit is used for counting more than two characteristic values of each piece of multimedia information in the multimedia information base and storing the characteristic values into the multimedia information base.
12. The apparatus according to claim 11, wherein the statistical unit is further configured to analyze a type of the multimedia information that is disliked in each physical state of the user according to the favorite habit of the user, and identify the type in the multimedia information base;
accordingly, the selected multimedia information is the multimedia information according with the favorite habit of the user.
13. The apparatus according to any one of claims 8 to 12, wherein the determining unit is specifically configured to: determining the current body state of the user in the motion process by utilizing the monitored vital sign parameters based on a body state model; the body state model is a corresponding relation model of the body state of the user and the vital sign parameters, which is established based on an SVM algorithm.
14. The apparatus of claim 13, further comprising: and the model establishing unit is used for establishing the body state model based on an SVM algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510746856.8A CN106681997B (en) | 2015-11-05 | 2015-11-05 | Information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510746856.8A CN106681997B (en) | 2015-11-05 | 2015-11-05 | Information processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106681997A CN106681997A (en) | 2017-05-17 |
| CN106681997B true CN106681997B (en) | 2020-09-08 |
Family
ID=58857422
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510746856.8A Active CN106681997B (en) | 2015-11-05 | 2015-11-05 | Information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106681997B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108903911B (en) * | 2018-05-23 | 2021-04-23 | 江西格律丝科技有限公司 | Remote acquisition and processing method for traditional Chinese medicine pulse condition information |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101108125A (en) * | 2007-08-02 | 2008-01-23 | 张志强 | Dynamic monitoring system of body sign |
| CN101287214A (en) * | 2008-05-13 | 2008-10-15 | 王海燕 | Method and system for acquiring information by mobile terminal and applying the same |
| CN101485562A (en) * | 2009-02-05 | 2009-07-22 | 薛萍 | Fat-reducing device and control method thereof |
| CN101499301A (en) * | 2008-02-03 | 2009-08-05 | 幻音科技(深圳)有限公司 | Multimedia device and method capable of real-time regulating output according to vital sign parameter |
| CN103402118A (en) * | 2013-07-05 | 2013-11-20 | Tcl集团股份有限公司 | Media program interaction method and system |
| CN103514302A (en) * | 2013-10-28 | 2014-01-15 | 深圳先进技术研究院 | Human body gait database and establishment method thereof |
| CN103530426A (en) * | 2013-11-01 | 2014-01-22 | 深圳市金立通信设备有限公司 | Music search method, music search device and terminal equipment |
| CN103577805A (en) * | 2013-10-28 | 2014-02-12 | 汕头大学 | Gender identification method based on continuous gait images |
| CN103729406A (en) * | 2013-12-09 | 2014-04-16 | 宇龙计算机通信科技(深圳)有限公司 | Searching method and system for environmental information |
| CN103823898A (en) * | 2014-03-14 | 2014-05-28 | 联想(北京)有限公司 | Data processing method, device and electronic equipment |
| CN104040547A (en) * | 2011-12-21 | 2014-09-10 | 皇家飞利浦有限公司 | Method and system to predict physiologic and clinical status changes |
| CN104123355A (en) * | 2014-07-17 | 2014-10-29 | 深圳市明康迈软件有限公司 | Music recommendation method and system |
| CN104361016A (en) * | 2014-10-15 | 2015-02-18 | 广东小天才科技有限公司 | Method and device for adjusting music play effect according to sport state |
| CN104407766A (en) * | 2014-08-28 | 2015-03-11 | 联想(北京)有限公司 | Information processing method and wearable electronic equipment |
| CN104720783A (en) * | 2013-12-24 | 2015-06-24 | 中国移动通信集团公司 | Exercise heart rate monitoring method and apparatus |
| CN104750965A (en) * | 2013-12-31 | 2015-07-01 | 中国移动通信集团公司 | User exercise state determination method and device |
| CN104810025A (en) * | 2015-03-31 | 2015-07-29 | 天翼爱音乐文化科技有限公司 | Audio similarity detecting method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004090724A (en) * | 2002-08-30 | 2004-03-25 | Pioneer Electronic Corp | Play back control system for moving body, its method, and its program and recording medium recording it |
-
2015
- 2015-11-05 CN CN201510746856.8A patent/CN106681997B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101108125A (en) * | 2007-08-02 | 2008-01-23 | 张志强 | Dynamic monitoring system of body sign |
| CN101499301A (en) * | 2008-02-03 | 2009-08-05 | 幻音科技(深圳)有限公司 | Multimedia device and method capable of real-time regulating output according to vital sign parameter |
| CN101287214A (en) * | 2008-05-13 | 2008-10-15 | 王海燕 | Method and system for acquiring information by mobile terminal and applying the same |
| CN101485562A (en) * | 2009-02-05 | 2009-07-22 | 薛萍 | Fat-reducing device and control method thereof |
| CN104040547A (en) * | 2011-12-21 | 2014-09-10 | 皇家飞利浦有限公司 | Method and system to predict physiologic and clinical status changes |
| CN103402118A (en) * | 2013-07-05 | 2013-11-20 | Tcl集团股份有限公司 | Media program interaction method and system |
| CN103514302A (en) * | 2013-10-28 | 2014-01-15 | 深圳先进技术研究院 | Human body gait database and establishment method thereof |
| CN103577805A (en) * | 2013-10-28 | 2014-02-12 | 汕头大学 | Gender identification method based on continuous gait images |
| CN103530426A (en) * | 2013-11-01 | 2014-01-22 | 深圳市金立通信设备有限公司 | Music search method, music search device and terminal equipment |
| CN103729406A (en) * | 2013-12-09 | 2014-04-16 | 宇龙计算机通信科技(深圳)有限公司 | Searching method and system for environmental information |
| CN104720783A (en) * | 2013-12-24 | 2015-06-24 | 中国移动通信集团公司 | Exercise heart rate monitoring method and apparatus |
| CN104750965A (en) * | 2013-12-31 | 2015-07-01 | 中国移动通信集团公司 | User exercise state determination method and device |
| CN103823898A (en) * | 2014-03-14 | 2014-05-28 | 联想(北京)有限公司 | Data processing method, device and electronic equipment |
| CN104123355A (en) * | 2014-07-17 | 2014-10-29 | 深圳市明康迈软件有限公司 | Music recommendation method and system |
| CN104407766A (en) * | 2014-08-28 | 2015-03-11 | 联想(北京)有限公司 | Information processing method and wearable electronic equipment |
| CN104361016A (en) * | 2014-10-15 | 2015-02-18 | 广东小天才科技有限公司 | Method and device for adjusting music play effect according to sport state |
| CN104810025A (en) * | 2015-03-31 | 2015-07-29 | 天翼爱音乐文化科技有限公司 | Audio similarity detecting method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106681997A (en) | 2017-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Real-time fractal-based valence level recognition from EEG | |
| Janssen et al. | Tune in to your emotions: a robust personalized affective music player | |
| Daly et al. | Music-induced emotions can be predicted from a combination of brain activity and acoustic features | |
| van der Zwaag et al. | Directing physiology and mood through music: Validation of an affective music player | |
| US11324436B2 (en) | Knowledge discovery based on brainwave response to external stimulation | |
| Jaimovich et al. | Emotion in motion: A study of music and affective response | |
| CN107106028A (en) | The system and method classified for cardiopulmonary sleep stage | |
| Giraldo et al. | Brain-activity-driven real-time music emotive control | |
| KR101170208B1 (en) | System and method for music recommendation | |
| CN107174209B (en) | Sleep stage staging method based on nonlinear dynamics | |
| Mijić et al. | MMOD-COG: A database for multimodal cognitive load classification | |
| CN106611028A (en) | Personalized music recommendation method and system | |
| van den Broek et al. | Unobtrusive sensing of emotions (USE) | |
| AU2021101097A4 (en) | A system and method for automatic playlist generation by analysing human emotions through physiological signals | |
| Engin et al. | Extraction of low-dimensional features for single-channel common lung sound classification | |
| CN106681997B (en) | Information processing method and device | |
| US20210259616A1 (en) | Knowledge, interest and experience discovery by psychophysiologic response to external stimulation | |
| Cui et al. | A review: Music-emotion recognition and analysis based on EEG signals | |
| JP6469242B2 (en) | System and method for controlling information to be presented to user browsing content | |
| An et al. | Mental health detection from speech signal: A convolution neural networks approach | |
| Kim et al. | Development of person-independent emotion recognition system based on multiple physiological signals | |
| Eggert et al. | Recognizing mental stress in chess players using vital sign data | |
| Kathiravan et al. | Efficient Intensity Bedded Sonata Wiles System using IoT | |
| Koike et al. | Transferring cross-corpus knowledge: an investigation on data augmentation for heart sound classification | |
| Nguyen et al. | Snore detection using convolution neural networks and data augmentation |
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 |