Background music regulation and control system and method based on gait recognition analysis

Abstract

The invention relates to the technical field of intelligent regulation and control, and discloses a background music regulation and control system and method based on gait recognition analysis, and the system comprises a data collection module which is used for collecting the gait data and facial feature data of a target object in a target region, and collecting the behavior data of the target object through a preset time period; the gait recognition module is used for determining the gender, the age group and the occupation of the target object according to the gait data; the emotion recognition module is used for determining the real-time emotion of the target object according to the facial feature data; the music adjusting module is used for determining a background music track according to the gender, the age group, the occupation and the real-time emotion of the target object, and adjusting a current playlist; and the analysis and correction module is used for judging whether the target object performs the target behavior or not according to the behavior data and correcting the adjusted playlist. The background music can be automatically selected and adjusted according to the gait characteristics of the user, so that the requirements of different users are met, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a background music control system and method based on gait recognition and analysis. Background Art

[0002] In modern life, background music has become an indispensable part of many occasions. Whether it is a shopping mall, restaurant, gym or home environment, background music can bring people a pleasant atmosphere. However, traditional background music control systems often lack intelligence and cannot be dynamically adjusted according to the actual environment and user needs. For example, in shopping malls, background music is usually selected and played manually, and it is impossible to make personalized adjustments based on the gait characteristics and emotional state of customers, resulting in the frequent mismatch between music and the environment and user needs.

[0003] In the prior art, although there are some music control systems based on biometrics, most of these systems rely on physiological signals such as facial expressions and heart rate, while ignoring the important behavioral characteristics of gait. Gait can not only reflect a person's emotional state, but also reveal their physical condition and psychological characteristics. Therefore, there is an urgent need for a background music control system and method based on gait recognition and analysis, which can automatically select and adjust background music according to the user's gait characteristics to meet the needs of different users and improve user experience. Summary of the invention

[0004] The purpose of the present invention is to provide a background music control system and method based on gait recognition and analysis, so as to solve the problem that background music is usually selected and played manually, and cannot be personalized according to the customer's gait characteristics and emotional state, or only relies on physiological signals such as facial expressions and heart rate, while ignoring the behavioral characteristics of gait.

[0005] The present invention provides a background music control system based on gait recognition analysis, comprising:

[0006] A data acquisition module, wherein a target area is set in the data acquisition module, and the data acquisition module is used to collect gait data and facial feature data of a target object in the target area, wherein the gait data includes cadence data, step length data, and motion acceleration data; the data acquisition module is also used to collect behavior data of the target object after a preset time period after the playlist is adjusted;

[0007] A gait recognition module, used to determine the gender, age group and occupation of the target object according to the gait data based on a gait recognition model;

[0008] An emotion recognition module, used to determine the real-time emotion of the target object according to the facial feature data based on a facial emotion recognition model;

[0009] The music adjustment module is used to determine the background music tracks according to the gender, age group, occupation and real-time mood of the target object, and adjust the current playlist according to the background music tracks to obtain the adjusted playlist, and play the background music;

[0010] The analysis and correction module is used to determine whether the target object performs the target behavior according to the behavior data of the target object, and determine whether to correct the adjusted play list according to the judgment result.

[0011] Preferably, when the data acquisition module is used to collect gait data of a target object in a target area, it includes:

[0012] Performing face recognition scanning on the moving target in the target area, if it is determined that there are face features, setting the moving target corresponding to the face features as the target object;

[0013] The target object is tracked and analyzed to determine the gait data of the target object.

[0014] Preferably, the gait recognition module, when used to determine the gender, age group and occupation of the target object according to the gait data based on the gait recognition model, includes:

[0015] The gait data also includes the body shape and movement posture of the target object;

[0016] Preprocessing the gait data, wherein the preprocessing includes denoising, outlier processing and standardization;

[0017] The preprocessed gait data is input into the gait recognition model to obtain the age group and occupation of the target object output by the gait recognition model, and the gender of the target object is determined according to the movement posture.

[0018] Preferably, the facial feature data includes mouth shape, eye opening degree, eyebrow changes and facial muscle tightness.

[0019] Preferably, the music adjustment module, when used to determine the background music track according to the gender, age group, occupation and real-time emotion of the target object, includes:

[0020] A music comparison table is preset, and the music comparison table includes a number of music tracks, and the music tracks are provided with corresponding emotional expression characteristics, age group preference, occupation preference and gender preference;

[0021] Based on the gender, age group and occupation of the target object, the music comparison table is screened to obtain initial music tracks;

[0022] The initial music tracks are screened for a second time according to the real-time emotions of the target object, the music tracks with the real-time emotions and the emotional expression characteristics are retained, and the retained music tracks are set as background music tracks.

[0023] Preferably, the music adjustment module, when used to adjust the current playlist according to the background music tracks to obtain the adjusted playlist and play the background music, includes:

[0024] Determine the music tracks in the current playlist;

[0025] Compare the music tracks in the current playlist with the background music tracks, and if the music tracks in the current playlist are consistent with the background music tracks, retain the music tracks in the current playlist;

[0026] If the music tracks in the current playlist are inconsistent with the background music tracks, the background music tracks are added to the current playlist, and the added background music tracks are pinned to the top to obtain an adjusted playlist, and the background music is immediately switched according to the adjusted playlist.

[0027] Preferably, the analysis and correction module, when used to judge whether the target object performs the target behavior according to the behavior data of the target object, and determine whether to correct the adjusted playlist according to the judgment result, includes:

[0028] determining the adjustment behavior of the target object according to the behavior data, comparing the adjustment behavior with the target behavior, and if the adjustment behavior is consistent with the target behavior, determining that the target object has performed the target behavior, and not modifying the adjustment playlist;

[0029] If the adjustment behavior is inconsistent with the target behavior, it is determined that the target object does not perform the target behavior, and the data acquisition module is controlled to acquire the adjustment facial feature data of the target object, and the adjustment playlist is modified according to the adjustment facial feature data.

[0030] Preferably, when the analysis and correction module is used to correct the adjusted playlist according to the adjusted facial feature data, it includes:

[0031] Inputting the adjusted facial feature data into the facial emotion recognition model to obtain the adjusted emotion of the target object output by the facial recognition model;

[0032] Comparing the adjusted emotion with the real-time emotion, if the positivity of the adjusted emotion is higher than the positivity of the real-time emotion, then not making a second adjustment to the playlist;

[0033] If the positivity of the adjusted emotion is lower than the positivity of the real-time emotion, an adjusted background music track is determined according to the adjusted emotion, and the playlist is adjusted a second time based on the adjusted background music track.

[0034] The present invention provides a background music control method based on gait recognition analysis, which is applied to the above-mentioned background music control system based on gait recognition analysis. The method comprises:

[0035] Determine a target area, and collect gait data of a target object in the target area, wherein the gait data includes cadence data, step length data, and motion acceleration data;

[0036] Based on the gait recognition model, determining the gender, age group and occupation of the target object according to the gait data;

[0037] Collecting facial feature data of a target object, and determining the real-time emotion of the target object according to the facial feature data based on a facial emotion recognition model;

[0038] Determine the background music track according to the gender, age group, occupation and real-time emotion of the target object, and adjust the current playlist according to the background music track;

[0039] After the playlist is adjusted, the behavior data of the target object is collected after a preset period of time, and it is determined whether the target object performs the target behavior based on the behavior data of the target object, and it is determined whether to modify the adjusted playlist based on the judgment result.

[0040] Compared with the prior art, the beneficial effect of the present invention is that, through the system and method of the present invention, background music can be automatically selected and adjusted according to the gait characteristics of the user, so as to better meet the personalized needs of the user and improve the overall user experience. The present invention selects and adjusts the background music according to the gender, age, occupation and real-time emotions of the target object, and can provide the target object with a personalized music experience that is more in line with its needs and feelings, thereby improving its satisfaction. And by collecting facial feature data and emotional information in real time and making secondary adjustments, the background music can dynamically adapt to the changes in the emotions of the target object, thereby enhancing the interactivity between music and emotions. At the same time, by using the gait recognition model and the facial emotion recognition model, the characteristics and emotions of the target object can be more accurately determined, thereby achieving precise control of the background music and improving the control effect. Realizing the selection of appropriate background music according to the characteristics and emotions of the target object helps to create a more suitable atmosphere and enhance the environmental appeal of the target area; the entire control process realizes automation and intelligence, reduces manual intervention, and improves management efficiency. In addition, the present invention also has a wide range of application prospects and can be applied to shopping centers, restaurants, gyms, home environments and other occasions. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0042] Figure 1 It is a functional block diagram of a background music control system based on gait recognition and analysis of the present invention;

[0043] Figure 2 It is a flow chart of a background music control method based on gait recognition analysis of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] like Figure 1 As shown, the present invention provides a background music control system based on gait recognition analysis, including: a data acquisition module, a target area is set in the data acquisition module, and the data acquisition module is used to collect gait data and facial feature data of a target object in the target area, and the gait data includes step frequency data, step length data and motion acceleration data; the data acquisition module is also used to collect behavior data of the target object after a preset time period after the playlist is adjusted.

[0046] The gait recognition module is used to determine the gender, age group and occupation of the target object according to the gait data based on the gait recognition model.

[0047] The emotion recognition module is used to determine the real-time emotion of the target object according to the facial feature data based on the facial emotion recognition model.

[0048] The music adjustment module is used to determine the background music tracks according to the gender, age group, occupation and real-time emotion of the target object, and adjust the current playlist according to the background music tracks to obtain the adjusted playlist and play the background music.

[0049] The analysis and correction module is used to determine whether the target object performs the target behavior according to the behavior data of the target object, and determine whether to correct the adjusted play list according to the judgment result.

[0050] In some embodiments of the present application, when the data acquisition module is used to collect gait data of a target object in a target area, it includes: performing facial recognition scanning on the moving targets in the target area, and if it is determined that there are facial features, setting the moving targets corresponding to the facial features as the target objects; tracking and analyzing the target objects to determine the gait data of the target objects.

[0051] In this embodiment, when the data acquisition module is used to collect the gait data of the target object in the target area, the specific steps are as follows: First, the module will perform face recognition scanning on the moving targets in the target area. Through this process, the system will detect and identify whether there are facial features. Once the system determines that there are facial features, the moving targets with these features will be set as the target objects for this collection. Next, the module will track and analyze these identified target objects, and determine and extract the gait data of the target objects by analyzing their movement patterns and behavioral characteristics.

[0052] In some embodiments of the present application, when the gait recognition module is used to determine the gender, age group and occupation of the target object according to the gait data based on a gait recognition model, it includes: the gait data also includes the body shape and movement posture of the target object; the gait data is preprocessed, and the preprocessing includes denoising, outlier processing and standardization processing; the preprocessed gait data is input into the gait recognition model, the age group and occupation of the target object output by the gait recognition model are obtained, and the gender of the target object is determined according to the body shape of the target object.

[0053] In this embodiment, the gait recognition module is used to determine the gender and age group of the target object by analyzing and processing the gait data based on the gait recognition model. Specifically, the gait data not only includes the walking method of the target object, but also covers the motion posture information of the target object. In order to ensure the accuracy and reliability of the gait data, a series of preprocessing steps need to be performed on it. These preprocessing steps include denoising to remove noise interference in the data; outlier processing to exclude abnormal data points that may affect the analysis results; and standardization to ensure that the data is analyzed on a uniform scale. After these preprocessing steps, the clean and standardized gait data obtained will be input into the gait recognition model. The gait recognition model will analyze these data and finally output the age group information of the target object. In addition, by analyzing the motion posture of the target object, the gender of the target object can be further determined. For example, certain specific motion posture features may indicate that the target object is male or female. By comprehensively considering the gait data and motion posture information, the gait recognition module can more accurately identify the gender and age group of the target object.

[0054] It is understandable that the gait recognition model is an existing model, which can be a deep learning model: such as convolutional neural network (CNN) and recurrent neural network (RNN), which can extract spatiotemporal features from video sequences. 3D convolutional neural network (3DCNN): a three-dimensional convolution operation specially designed for processing video data, which can capture the spatiotemporal features of gait. Long short-term memory network (LSTM): a special recurrent neural network suitable for processing and predicting time series data, often used for modeling gait sequences. Generative adversarial network (GAN): through the adversarial process of generator and discriminator, realistic gait images or videos can be generated for gait recognition. Spatiotemporal convolutional neural network (TCN): combines the advantages of time series analysis and convolutional neural network, and is used to extract spatiotemporal features from gait data. Skeleton-based model: recognizes gait by analyzing the motion pattern of key points of the human skeleton, usually combined with deep learning technology. Optical flow-based method: analyzes gait features by calculating the optical flow field between video frames. Fusion model based on deep learning: multiple models or features are fused to improve the accuracy and robustness of gait recognition.

[0055] In some embodiments of the present application, the facial feature data includes mouth shape, eye opening degree, eyebrow changes and facial muscle tightness.

[0056] In this embodiment, the facial feature data includes a plurality of key facial feature information. Specifically, these data cover the shape characteristics of the mouth, such as the degree of opening and closing of the mouth, the upturn or drooping of the corners of the mouth, etc. In addition, the degree of opening and closing of the eyes is also included, that is, whether the eyes are fully open, slightly squinting or fully closed. The change of eyebrows is also an important feature, including the state of raising, lowering, frowning or stretching eyebrows. Finally, the tightness of facial muscles is also a key indicator, reflecting the tension or relaxation of facial muscles, such as muscle relaxation when smiling and muscle tension when frowning.

[0057] It is understandable that the facial emotion recognition model can be an existing model, including but not limited to VGG, CNN, ResNet, and YOLOv8 / v7 / v6 / v5. These models are all based on deep learning technology and are trained with a large amount of data to achieve accurate facial expression recognition. The VGG model is based on a convolutional neural network (CNN) and extracts image features through continuous convolutional layers and pooling layers. The VGG model is widely used in image classification and facial expression recognition due to its simple structure and clear hierarchy. In facial expression recognition, VGG can handle complex image tasks and is suitable for scenarios that require high real-time performance, such as real-time monitoring systems. ResNet solves the gradient vanishing problem in deep networks by introducing residual blocks, making the model deeper and having better performance. ResNet performs well in various image tasks, especially in facial expression recognition. ResNet is widely used in facial expression recognition and is often used in scenarios that require high precision, such as mental health analysis and public safety monitoring. YOLO (You Only Look Once) is an efficient target detection algorithm suitable for fast and real-time facial expression recognition. Different versions of the YOLO model have trade-offs in performance and speed, and users can choose different versions according to their specific needs. In the application of facial expression recognition, new versions such as YOLOv8 can achieve high-precision real-time detection, support video and real-time camera input, and are suitable for expression analysis in dynamic scenes. It is understandable that a multi-person gait recognition method based on human skeleton heat map in Chinese patent CN114187665A can also be used for gait recognition.

[0058] In some embodiments of the present application, when the music adjustment module is used to determine the background music tracks according to the gender, age group, occupation and real-time emotions of the target object, it includes: a music comparison table is preset, the music comparison table includes a number of music tracks, and the music tracks are set with corresponding emotional expression characteristics, age group preference, occupation preference and gender preference; based on the gender, age group and occupation of the target object, the music comparison table is screened once to obtain the initial music tracks; according to the real-time emotions of the target object, the initial music tracks are screened twice, the music tracks whose real-time emotions are consistent with the emotional expression characteristics are retained, and the retained music tracks are set as background music tracks.

[0059] In this embodiment, the music adjustment module is used to determine the appropriate background music tracks according to the gender, age group and real-time emotions of the target object. The module contains a pre-set music comparison table, which lists a variety of different music tracks in detail. Each music track is equipped with corresponding emotional expression characteristics and liking scores for different age groups and genders. These scores reflect the preferences of different groups for music. When background music needs to be selected for the target object, the music adjustment module will first perform a preliminary screening of the music comparison table according to the gender and age group information of the target object. In this way, the system can quickly narrow down the range of music tracks and obtain an initial list of music tracks. The tracks in this list are pre-screened according to the gender and age group of the target object to ensure that these tracks meet the preferences of the target object to some extent. Next, the music adjustment module will further perform a secondary screening according to the real-time emotions of the target object. The current emotional state of the target object is analyzed and matched with the emotional expression characteristics in the music comparison table. In this way, the system can identify those music tracks whose emotional expression characteristics are consistent with the real-time emotions of the target object. Finally, the system will retain these music tracks that match the real-time emotions and set them as background music tracks. Through this dual screening mechanism, the music adjustment module can ensure that the selected background music not only meets the target audience's gender and age group preferences, but also matches the target audience's real-time emotions on an emotional level. This design enables background music to better serve the target audience and enhance their auditory experience and emotional state.

[0060] In some embodiments of the present application, when the music adjustment module is used to adjust the current playlist according to the background music track, obtain an adjusted playlist, and play background music, it includes: determining the music track of the current playlist; comparing the music track of the current playlist with the background music track, if the music track of the current playlist is consistent with the background music track, retaining the music track of the current playlist; if the music track of the current playlist is inconsistent with the background music track, adding the background music track to the current playlist, and pinning the added background music track to the top to obtain an adjusted playlist, and immediately switching the background music according to the adjusted playlist.

[0061] In this embodiment, the function of the music adjustment module is to make corresponding adjustments to the playlist according to the background music tracks. Specifically, the module first identifies and determines all the music tracks contained in the current playlist. Next, it will compare and analyze these tracks in detail with the background music tracks. If it is found that the music tracks in the current playlist are exactly the same as the background music tracks, then the module will keep the current playlist unchanged and will not make any adjustments. However, if it is found that the music tracks in the current playlist are inconsistent with the background music tracks after comparison, then the music adjustment module will take further measures. Specifically, it will add the background music tracks to the current playlist. In order to ensure that the background music tracks can be played first, the module will also perform a top operation, that is, the background music tracks are placed at the top position of the playlist, and the background music is immediately switched according to the adjustment playlist, so that when the music continues to be played, the background music tracks will be played first, thereby ensuring that the background music can be smoothly integrated into the user's auditory experience. This means that the user will be able to enjoy the music playback experience that matches the background music tracks in the next listening process. In this way, the music adjustment module not only improves the personalization of the playlist, but also enhances the user's listening experience in different scenarios.

[0062] In some embodiments of the present application, when the analysis and correction module is used to determine whether the target object performs the target behavior based on the behavior data of the target object, and determine whether to correct the adjustment playlist based on the judgment result, it includes: determining the adjustment behavior of the target object based on the behavior data, comparing the adjustment behavior with the target behavior, if the adjustment behavior is consistent with the target behavior, determining that the target object has performed the target behavior, and not correcting the adjustment playlist; if the adjustment behavior is inconsistent with the target behavior, determining that the target object has not performed the target behavior, controlling the data acquisition module to acquire the adjustment facial feature data of the target object, and correcting the adjustment playlist based on the adjustment facial feature data.

[0063] In this embodiment, the analysis and correction module is responsible for judging whether the target object has performed a specific target behavior based on the behavior data of the target object. Based on this judgment result, the system will decide whether the playlist needs to be adjusted and corrected accordingly. Specifically, the analysis and correction module will first identify the adjustment behavior of the target object based on the collected behavior data. Subsequently, this adjustment behavior will be carefully compared and analyzed with the preset target behavior (such as visiting the store). If the adjustment behavior of the target object is found to be consistent with the target behavior after comparison, the system will confirm that the target object has completed the target behavior. In this case, the system will keep the current playlist unchanged and will not make any corrections to the playlist. However, if the adjustment behavior is inconsistent with the target behavior, the system will conclude that the target object has not performed the target behavior. At this point, the system will start the data acquisition module and start collecting the adjustment facial feature data of the target object. The collected adjustment facial feature data will be used for further analysis and processing in order to make necessary corrections to the playlist. In this way, the system can ensure that the playlist is always consistent with the actual behavior of the target object, thereby providing a more personalized and accurate user experience. The entire process not only relies on precise data analysis, but also involves real-time monitoring and dynamic adjustment of the target object's behavior to ensure that the optimization of the playlist always meets the actual needs of the target object.

[0064] In some embodiments of the present application, when the analysis and correction module is used to correct the adjusted playlist according to the adjusted facial feature data, it includes: inputting the adjusted facial feature data into the facial emotion recognition model to obtain the adjusted emotion of the target object output by the facial recognition model; comparing the adjusted emotion with the real-time emotion, if the positivity of the adjusted emotion is higher than the positivity of the real-time emotion, then no secondary adjustment is made to the playlist; if the positivity of the adjusted emotion is lower than the positivity of the real-time emotion, then determining the adjusted background music track according to the adjusted emotion, and making secondary adjustments to the playlist based on the adjusted background music track.

[0065] In the present invention, the analysis and correction module is used to correct the playlist according to the adjusted facial feature data. Specifically, the workflow of the module is as follows: first, the adjusted facial feature data is input into the facial emotion recognition model, and the adjusted emotion of the target object is obtained through the processing of the model. Then, the obtained adjusted emotion is compared and analyzed with the real-time emotion. If it is found that the positivity of the adjusted emotion is higher than the positivity of the real-time emotion, it means that the emotion of the target object has improved, so in this case, no further adjustment is needed to the playlist. However, if the positivity of the adjusted emotion is lower than the positivity of the real-time emotion, it indicates that the emotion of the target object has not yet reached the ideal state, and measures need to be taken to adjust it. The specific operation is to determine the background music tracks that need to be adjusted according to the adjusted emotion, and then make a secondary adjustment to the playlist based on the selected background music tracks, in order to achieve the purpose of improving the emotion of the target object. In this way, the analysis and correction module can effectively dynamically adjust the playlist according to the facial feature data of the target object, so as to better meet the emotional needs of the target object.

[0066] The present invention also discloses a background music control method based on gait recognition analysis, which is applied to the above-mentioned background music control system based on gait recognition analysis. The method comprises:

[0067] S1, determining a target area, and collecting gait data of a target object in the target area, wherein the gait data includes cadence data, step length data, and motion acceleration data.

[0068] S2, based on a gait recognition model, determining the gender, age group and occupation of the target object according to the gait data.

[0069] S3, collecting facial feature data of the target object, and determining the real-time emotion of the target object according to the facial feature data based on a facial emotion recognition model.

[0070] S4, determining background music tracks according to the gender, age group, occupation and real-time emotions of the target object, and adjusting the current playlist according to the background music tracks.

[0071] S5, after the playlist is adjusted, the behavior data of the target object is collected after a preset period of time, and it is determined whether the target object performs the target behavior according to the behavior data of the target object, and it is determined whether to modify the adjusted playlist according to the determination result.

[0072] The present invention provides an intelligent background music control method, which can dynamically adjust the music tracks in the playlist according to the user's gait characteristics and emotional state. Specifically, by analyzing the target object's step frequency, step length and motion acceleration data, the user's gender and age group can be accurately identified, and then combined with facial emotion recognition technology, the user's emotional changes can be captured in real time. Based on this information, the system can intelligently select and adjust the background music suitable for the user's current state, thereby enhancing the user's auditory experience and emotional regulation effect. In addition, by adjusting the playlist twice, the system can continuously optimize the music selection, ensure the synchronization of music and user emotions, and provide users with a more personalized and comfortable auditory environment.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

[0074] The system provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.

[0075] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

Claims

1. A background music control system based on gait recognition and analysis, characterized in that: include: A data acquisition module, wherein a target area is set in the data acquisition module, and the data acquisition module is used to collect gait data and facial feature data of a target object in the target area, wherein the gait data includes cadence data, step length data, and motion acceleration data; the data acquisition module is also used to collect behavior data of the target object after a preset time period after the playlist is adjusted; A gait recognition module, used to determine the gender, age group and occupation of the target object according to the gait data based on a gait recognition model; An emotion recognition module, used to determine the real-time emotion of the target object according to the facial feature data based on a facial emotion recognition model; The music adjustment module is used to determine the background music tracks according to the gender, age group, occupation and real-time mood of the target object, and adjust the current playlist according to the background music tracks to obtain the adjusted playlist, and play the background music; The analysis and correction module is used to determine whether the target object performs the target behavior according to the behavior data of the target object, and determine whether to correct the adjusted play list according to the judgment result.

2. The background music control system based on gait recognition analysis according to claim 1 is characterized in that: When the data acquisition module is used to collect gait data of a target object in a target area, it includes: Performing face recognition scanning on the moving target in the target area, if it is determined that there are face features, setting the moving target corresponding to the face features as the target object; The target object is tracked and analyzed to determine the gait data of the target object.

3. The background music control system based on gait recognition analysis according to claim 1, characterized in that: The gait recognition module, when used to determine the gender, age group and occupation of the target object according to the gait data based on the gait recognition model, includes: The gait data also includes the body shape and movement posture of the target object; Preprocessing the gait data, wherein the preprocessing includes denoising, outlier processing and standardization; The preprocessed gait data is input into the gait recognition model to obtain the age group and occupation of the target object output by the gait recognition model, and the gender of the target object is determined according to the body shape of the target object.

4. The background music control system based on gait recognition analysis according to claim 1, characterized in that: The facial feature data includes mouth shape, eye opening degree, eyebrow changes and facial muscle tightness.

5. The background music control system based on gait recognition analysis according to claim 1, characterized in that: The music adjustment module, when used to determine the background music track according to the gender, age group, occupation and real-time emotion of the target object, includes: A music comparison table is preset, and the music comparison table includes a number of music tracks, and the music tracks are provided with corresponding emotional expression characteristics, age group preference, occupation preference and gender preference; Based on the gender, age group and occupation of the target object, the music comparison table is screened to obtain initial music tracks; The initial music tracks are screened for a second time according to the real-time emotions of the target object, the music tracks with the real-time emotions and the emotional expression characteristics are retained, and the retained music tracks are set as background music tracks.

6. The background music control system based on gait recognition analysis according to claim 1, characterized in that: The music adjustment module is used to adjust the current playlist according to the background music tracks to obtain the adjusted playlist and play the background music, including: Determine the music tracks in the current playlist; Compare the music tracks in the current playlist with the background music tracks, and if the music tracks in the current playlist are consistent with the background music tracks, retain the music tracks in the current playlist; If the music tracks in the current playlist are inconsistent with the background music tracks, the background music tracks are added to the current playlist, and the added background music tracks are pinned to the top to obtain an adjusted playlist, and the background music is immediately switched according to the adjusted playlist.

7. The background music control system based on gait recognition analysis according to claim 1, characterized in that: The analysis and correction module is used to judge whether the target object performs the target behavior according to the behavior data of the target object, and determine whether to correct the adjusted playlist according to the judgment result, including: determining the adjustment behavior of the target object according to the behavior data, comparing the adjustment behavior with the target behavior, and if the adjustment behavior is consistent with the target behavior, determining that the target object has performed the target behavior, and not modifying the adjustment playlist; If the adjustment behavior is inconsistent with the target behavior, it is determined that the target object does not perform the target behavior, and the data acquisition module is controlled to acquire the adjustment facial feature data of the target object, and the adjustment playlist is modified according to the adjustment facial feature data.

8. The background music control system based on gait recognition analysis according to claim 1, characterized in that: When the analysis and correction module is used to correct the adjusted playlist according to the adjusted facial feature data, it includes: Inputting the adjusted facial feature data into the facial emotion recognition model to obtain the adjusted emotion of the target object output by the facial recognition model; Comparing the adjusted emotion with the real-time emotion, if the positivity of the adjusted emotion is higher than the positivity of the real-time emotion, then not making a second adjustment to the playlist; If the positivity of the adjusted emotion is lower than the positivity of the real-time emotion, an adjusted background music track is determined according to the adjusted emotion, and the playlist is adjusted a second time based on the adjusted background music track.

9. A background music control method based on gait recognition analysis, applied to the background music control system based on gait recognition analysis as claimed in any one of claims 1 to 8, characterized in that: The method comprises: Determine a target area, and collect gait data of a target object in the target area, wherein the gait data includes cadence data, step length data, and motion acceleration data; Based on the gait recognition model, determining the gender, age group and occupation of the target object according to the gait data; Collecting facial feature data of a target object, and determining the real-time emotion of the target object according to the facial feature data based on a facial emotion recognition model; Determine the background music track according to the gender, age group, occupation and real-time emotion of the target object, and adjust the current playlist according to the background music track; After the playlist is adjusted, the behavior data of the target object is collected after a preset period of time, and it is determined whether the target object performs the target behavior based on the behavior data of the target object, and it is determined whether to modify the adjusted playlist based on the judgment result.

Images