A dance movement prediction method and related equipment

Abstract

The present invention provides a method for predicting dance movements and related equipment, which are applied to the field of data processing technology. The present application obtains a total sample set, music information to be predicted, and target user information; processes the target user information to generate dance attribute information of the target user; pre-processes the total sample set to generate a training sample set with identification information, wherein the identification information is used to characterize that the user's dance movement is in an abnormal state; obtains an initial dance prediction model that matches the identification information, wherein the initial dance prediction model is set based on the music information to be predicted and the target user information received within a preset time period; trains the initial dance prediction model based on the training sample set with identification information to generate a target dance prediction model; processes the music information to be predicted and the dance attribute information of the target user based on the target dance prediction model to generate a target dance movement.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a dance movement prediction method and related equipment. Background Art

[0002] The artistic effect brought about by the diverse combination of music and dance is a rare audio-visual enjoyment. With the rapid development of Internet and computer technology, wonderful music and dance creation is no longer limited to artists themselves; thus, music-driven dance generation technology came into being.

[0003] At present, when generating corresponding dance movements based on music information, short dance sequences are generally generated. If a long dance sequence is to be generated, there will be overall incoordination, poor correlation of the overall dance category, and inconsistent choreography style types, resulting in poor display of dance movements.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of this application is to provide a dance movement prediction method and related equipment, which at least to a certain extent overcomes the problems existing in the prior art, takes into account the personalized needs of users, including cultural background and physical condition, to provide appropriate dance movement recommendations. During the recommendation process, user feedback is used to continuously optimize the model. Through personalized dance prediction and music feature generation, users can enjoy a richer dance experience that meets their specific needs.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present invention.

[0007] According to one aspect of the present application, a method for predicting dance movements is provided, comprising: obtaining a total sample set, music information to be predicted, and target user information, wherein the total sample set is dance types of different users received within a preset time period and music matching the dance types; processing the target user information to generate dance attribute information of the target user; preprocessing the total sample set to generate a training sample set with identification information, wherein the identification information is used to characterize that the user's dance movements are in an abnormal state; obtaining an initial dance prediction model that matches the identification information, wherein the initial dance prediction model is set based on the music information to be predicted and the target user information received within a preset time period; and preprocessing the initial dance prediction model based on the training sample set with identification information. The model is trained to generate a target dance prediction model; based on the target dance prediction model, the music information to be predicted and the dance attribute information of the target user are processed to generate target dance movements; the target user information is processed to generate the dance attribute information of the target user, including: processing the target user information to generate the dance preference information of the target user, the physical examination information of the target user and the dance usage information of the target user; processing the dance preference information of the target user and the physical examination information of the target user to generate the body movement factor of the target user; processing the body movement factor of the target user based on the dance usage information of the target user to generate the dance difficulty factor of the target user; and generating the dance attribute information of the target user based on the dance difficulty factor of the target user.

[0008] Specifically, feature extraction is performed on the total sample set to determine an original feature library.

[0009] Specifically, feature extraction is performed on the total sample set to determine an original feature library, including: obtaining a historical music data set that matches the music to be predicted, wherein the historical music data set includes dance movements generated based on different user preferences and different dance types; processing the historical music data set to obtain dance movement features and music clip correlation co-occurrence frequencies; processing the dance movement features and the music clip correlation co-occurrence frequencies to generate correlation matrix information; generating a number of dance feature data based on the correlation matrix information; and generating an original feature library based on the number of dance feature data.

[0010] Specifically, the method further comprises extracting features from the total sample set to determine the original feature library: the method comprises a calculation formula for calculating the correlation co-occurrence frequency, and the calculation formula is: ;in, Representation concept and Concept The number of times they co-occur in the report set, Representation concept The total number of occurrences, Representation concept Concept of appearance Frequency of occurrence, based on correlation co-occurrence frequency Constructing a correlation matrix :The method includes a calculation formula for calculating the correlation matrix, and the calculation formula is: ;in, is the co-occurrence frequency threshold, if Greater than or equal to the co-occurrence frequency threshold , then the concept With concept There is a correlation, otherwise there is no correlation.

[0011] Specifically, the music information to be predicted and the dance attribute information of the target user are processed based on the target dance prediction model to generate target dance movements, including: processing the music information to be predicted based on the target dance prediction model to generate musical characteristics and music duration information of the target music; processing the musical characteristics and the music duration information of the target music based on the target dance prediction model to generate a music influence factor; processing the music influence factor and the dance difficulty factor of the target user based on the target dance prediction model to generate initial dance movement information.

[0012] Specifically, the music information to be predicted and the dance attribute information of the target user are processed based on the target dance prediction model to generate target dance movements, and also includes: obtaining real-time physiological state information of the target user, wherein the real-time physiological state information of the target user is generated when the target user exercises based on the initial dance movement information; based on the target dance prediction model, the real-time physiological state information of the target user and the initial dance movement information are processed to generate a dance movement adjustment factor; based on the dance movement adjustment factor, the music information to be predicted and the initial dance movement information are processed to generate target dance movements.

[0013] Another aspect of the present application is a dance movement prediction device, characterized in that it includes: an acquisition module, used to acquire a total sample set, music information to be predicted and target user information, wherein the total sample set is dance types of different users received within a preset time period and music matching the dance types; an initial dance prediction model matching the identification information is acquired, wherein the initial dance prediction model is set based on the music information to be predicted and the target user information received within a preset time period; a processing module, used to process the target user information to generate dance attribute information of the target user; pre-processing the total sample set to generate a training sample set with identification information, wherein the identification information is used to characterize that the user's dance movement is in an abnormal state; based on the training sample set with identification information The initial dance prediction model is trained to generate a target dance prediction model; the music information to be predicted and the dance attribute information of the target user are processed based on the target dance prediction model to generate a target dance movement; the target user information is processed to generate the dance attribute information of the target user, including: processing the target user information to generate the dance preference information of the target user, the physical examination information of the target user and the dance usage information of the target user; processing the dance preference information of the target user and the physical examination information of the target user to generate a body movement factor of the target user; processing the body movement factor of the target user based on the dance usage information of the target user to generate a dance difficulty factor of the target user; and generating the dance attribute information of the target user based on the dance difficulty factor of the target user.

[0014] According to another aspect of the present application, an electronic device is characterized in that it includes: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-mentioned dance movement prediction method by executing the executable instructions.

[0015] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the above-mentioned dance movement prediction method is implemented.

[0016] According to another aspect of the present application, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a third processor, the above-mentioned dance movement prediction method is implemented.

[0017] The present application provides a method and related device for predicting dance movements, wherein a server obtains a total sample set, music information to be predicted, and target user information, wherein the total sample set is the dance types of different users received within a preset time period and the music matching the dance types; the target user information is processed to generate dance attribute information of the target user; the total sample set is preprocessed to generate a training sample set with identification information, wherein the identification information is used to characterize that the user's dance movement is in an abnormal state; an initial dance prediction model matching the identification information is obtained, wherein the initial dance prediction model is set based on the music information to be predicted and the target user information received within a preset time period; the initial dance prediction model is trained based on the training sample set with identification information to generate a target dance prediction model; the music information to be predicted and the dance attribute information of the target user are processed based on the target dance prediction model to generate a target dance movement. The personalized needs of users, including cultural background and physical conditions, are taken into account to provide appropriate dance movement recommendations. In the recommendation process, user feedback is used to continuously optimize the model. Through this personalized dance prediction and music feature generation, users can enjoy a dance experience that is richer and meets their specific needs.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flowchart showing a dance movement prediction method provided by an embodiment of the present application;

[0020] Figure 2 A schematic diagram of the structure of a dance movement prediction device provided by an embodiment of the present application is shown;

[0021] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown;

[0022] Figure 4 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0023] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0024] Combine the following Figure 1The following is a description of a dance action prediction method according to an exemplary embodiment of the present application. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the embodiments of the present application are not limited in this respect. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0025] In one implementation, the present application also proposes a dance movement prediction method and related equipment. Figure 1 The flowchart of a method for predicting dance movements according to an embodiment of the present application is schematically shown. Figure 1 As shown, the method is applied to a server, comprising:

[0026] S101, obtaining the total sample set, music information to be predicted and target user information.

[0027] In one embodiment, the dance types and matching music data of different users in a specific time period are collected by obtaining a total sample set, which is the dance types of different users and the music matching the dance types received in a preset time period. Next, the music information to be predicted is identified, including key elements such as style and rhythm, and detailed information of the target user, such as music preferences and historical interactions, is collected.

[0028] By conducting in-depth analysis of the sample set, music and user features are extracted, and these features are used to train and optimize the recommendation model to ensure that it can accurately capture the relationship between user preferences and music.

[0029] S102: Process the target user information to generate dance attribute information of the target user.

[0030] In one implementation, the target user information is processed to generate the target user's dance preference information, the target user's physical examination information, and the target user's dance usage information, collect necessary information from the target user, including his / her dance experience, preference surveys, physical examination reports, and the purpose of dance activities, and analyze the user's dance history and preferences, including favorite dance styles, rhythms, artists, and music types.

[0031] Utilize users' physical examination information, such as fitness test results, health status, flexibility and strength level, to assess users' physical condition and determine the purpose of users' participation in dance activities, including leisure, entertainment, social, competitive, fitness or rehabilitation. Integrate dance preferences, physical examination information and dance purposes to form a comprehensive user profile, and design personalized dance courses, music recommendations and health guidance based on the integrated user information. In addition, provide users with feedback channels to further refine and adjust their dance preferences and health goals, and regularly update users' dance preferences and physical examination information to respond to their changing needs and health conditions.

[0032] The target user's dance preference information and physical examination information are processed to generate the target user's body movement factor. In the process of generating body movement factors for users, the target user's dance preference and physical examination information are first integrated to evaluate their dance movement ability, analyze the user's dance style preference, rhythm preference, and physical conditions such as muscle strength and coordination, and combine these data to create body movement factors that reflect the user's movement ability. These factors include movement amplitude, speed, and complexity to ensure that the recommended dance movements are suitable for the user's health status and meet their dance skill level. At the same time, user safety is emphasized to avoid recommending movements that may cause injury. Over time, user feedback is continuously collected and the body movement factors are updated to adapt to the improvement of user skills and changes in health status.

[0033] The target user's body movement factors are processed based on the target user's dance purpose information to generate the target user's dance difficulty factor. First, the user's dance purpose is identified, such as fitness, performance, or social interaction. Then, the user's physical examination information and dance preferences are analyzed to generate body movement factors, which reflect the user's physical ability and dance skills. Combined with the user's dance purpose and body movement factors, the dance difficulty factor suitable for the user is evaluated and generated to ensure that dance activities are both safe and helpful for the improvement of user skills. Personalized dance courses are designed, and the difficulty is dynamically adjusted according to the user's progress and feedback to optimize the learning experience and meet changing needs.

[0034] The target user's dance attribute information is generated based on the target user's dance difficulty factor. In the process of generating dance attribute information for a specific user, the target user's dance difficulty factor is first analyzed. These factors reflect the user's physical condition, dance skills and personal preferences. Based on these factors, the system is able to create a detailed dance attribute profile, which includes the dance style, rhythm and movement type suitable for the user. Further, this attribute information is used to design personalized dance courses to ensure that the course content is both in line with the user's dance level and can stimulate their interest and challenge. At the same time, the system will dynamically adjust the recommended content based on the user's feedback and experience to optimize the learning process and improve user satisfaction.

[0035] S103, preprocessing the total sample set to generate a training sample set with identification information.

[0036] In one implementation, feature extraction is performed on the total sample set to determine an original feature library and generate training samples with identification information, wherein the identification information is used to characterize that the user's dance movements are in an abnormal state, that is, the current dance movement may be one that the user cannot do (possibly due to physical reasons or in conflict with the user's religious beliefs or customs).

[0037] S104: Acquire an initial dance prediction model that matches the identification information.

[0038] In one embodiment, the initial dance prediction model is set based on the music information to be predicted and the target user information received within a preset time period. The process of developing the initial dance prediction model begins with collecting the music information to be predicted and the detailed information of the target user within a specific time period, and constructing a prediction model that can reflect the user's dance tendency by extracting the key attributes of the music and analyzing the user's dance preferences, physical conditions and dance purposes. The model is first trained to identify the dance styles and music types that the user may like, and then verified and optimized through actual user feedback to improve its prediction accuracy.

[0039] Furthermore, the model will be adjusted based on user feedback to ensure the relevance and appeal of the recommended content. As user preferences evolve and new data accumulates, the model will be updated regularly to maintain its timeliness and personalization level. In this way, the initial dance prediction model can bring users a more accurate and personalized dance experience, while providing strong technical support for dance education and health activities.

[0040] S105: Training the initial dance prediction model based on the training sample set with identification information to generate a target dance prediction model.

[0041] In one embodiment, in the process of developing the target dance prediction model, the initial dance prediction model is first carefully trained based on a training sample set with identification information. These identification information critically indicates whether the user's dance movements are in an abnormal state. For example, some movements may be unsuitable for a specific user due to physical reasons or cultural or religious beliefs. Through this training, the model learns to recognize and adapt to the individual differences of users, ensuring that the recommended movements are both safe and appropriate.

[0042] Subsequently, the generated target dance prediction model can provide personalized dance moves and music recommendations based on the user's dancing ability, physical condition and cultural background. The model continuously improves its prediction accuracy and personalization level through continuous verification and optimization. At the same time, it ensures that cultural diversity and the user's personal beliefs are taken into account throughout the recommendation process, avoiding the recommendation of movements that may cause discomfort, and providing users with a dance learning experience that is both personalized and respectful of individual differences.

[0043] S106: Process the music information to be predicted and the dance attribute information of the target user based on the target dance prediction model to generate target dance movements.

[0044] In one embodiment, the music information to be predicted is processed based on the target dance prediction model to generate the musical characteristics and music duration information of the target music. The target dance prediction model can generate key music features, including musical characteristics and music duration, by processing the music information to be predicted. The model analyzes elements such as the rhythm, melody, and harmony of the music, while taking into account the overall duration of the music, providing a basis for dance choreography. By integrating these music features, the model can recommend dance moves that match the music style and rhythm to ensure the harmony between dance and music.

[0045] In addition, the model is designed to take into account the personalized needs of users, including cultural background and physical condition, in order to provide appropriate dance moves. During the recommendation process, user feedback is used to continuously optimize the model and improve its prediction accuracy and personalization, which not only improves the quality of dance choreography and user experience, but also provides a scientific basis for dance education and performance, while respecting and adapting to the individual differences of users. Through this personalized dance prediction and music feature generation, users can enjoy a richer dance experience that meets their specific needs.

[0046] The target dance prediction model is used to process the musical characteristics and music duration information of the target music to generate music influence factors. The target dance prediction model is used to analyze the target music, extract musical characteristics, including rhythm, melody, mode, harmony, etc., consider the duration of the music, evaluate its impact on dance choreography and performance, ensure that the dance movements match the music duration, and combine the musical characteristics and music duration to generate music influence factors. These factors quantify the impact of music on the selection and arrangement of dance movements. According to the music influence factors, dance movements that are suitable for the music style and rhythm are matched or arranged to achieve the harmonious unity of music and dance.

[0047] Use music influence factors to recommend dance moves suitable for different users' dancing abilities, preferences, and cultural backgrounds. Through user feedback and dance practice, continuously optimize the algorithm for generating music influence factors to improve the accuracy and personalization of recommendations. When generating music influence factors, consider the music characteristics and dance traditions of different cultural backgrounds to ensure the diversity and inclusiveness of recommended content. Encourage users to participate in the dance choreography process and adjust the music influence factors based on their feedback and experience to better meet user needs.

[0048] The music influence factor and the dance difficulty factor of the target user are processed based on the target dance prediction model to generate initial dance movement information (i.e., dance movements that are theoretically suitable for the target user). Specifically, the target dance prediction model is used to analyze the musical characteristics and duration of the music, extract key music influence factors such as rhythm intensity, melody characteristics and music style, consider the target user's dancing ability, physical condition and cultural background, determine the dance difficulty factor, ensure that the dance movements are suitable for the user's actual level, and combine the music influence factor and dance difficulty factor. The model generates initial dance movement information that matches the music and has appropriate difficulty.

[0049] The choreographed dance moves are designed to coordinate with the user's physical ability and dance preferences, while blending with the rhythm and style of the music. Based on the user's feedback and dance practice, the dance moves are dynamically adjusted and the choreography is optimized to improve the personalization and expressiveness of the dance. Users are encouraged to participate in the dance choreography process and their feedback is collected to ensure that the dance moves are both challenging and enjoyable. When generating dance moves, the user's cultural background and physical conditions are considered to ensure that the dance moves respect individual differences and are safe and feasible. Provide users with a personalized and creative dance choreography experience while ensuring the appropriateness and safety of the dance moves, so that users can enjoy the fun of dancing while also feeling the charm of the combination of music and dance.

[0050] In another embodiment, the real-time physiological state information of the target user is obtained, wherein the real-time physiological state information of the target user is generated when the target user performs exercise based on the initial dance movement information, the real-time physiological state information and the initial dance movement information of the target user are processed based on the target dance prediction model to generate a dance movement adjustment factor, and the predicted music information and the initial dance movement information are processed based on the dance movement adjustment factor to generate a target dance movement. That is, the initial dance movement information is a dance movement that is theoretically suitable for the current target user, but when the target user actually rehearses, he may not be able to perfectly master the dance movement choreographed at the beginning due to poor mastery of the dance movement or poor on-the-spot performance (such as nervousness). At this time, the dance movement choreographed at the beginning will be adjusted to be adapted to the dance movement of the current user.

[0051] Specifically, when the user exercises according to the initial dance movement information, their real-time physiological state information, such as heart rate, blood pressure, fatigue level, etc., is collected. The target dance prediction model is used to combine the user's real-time physiological state information and the initial dance movement information for comprehensive analysis. Through model processing, dance movement adjustment factors are generated. These factors reflect the user's adaptability and comfort to the movements in actual dance.

[0052] The dance movement adjustment factor is applied to the music information to be predicted and the initial dance movement information for further matching and adjustment. The adjustment factor and music characteristics are combined to generate the final target dance movement to ensure that the dance choreography is in line with the rhythm of the music and adapts to the physiological and psychological state of the user, ensuring that the target dance movement provides a personalized experience for the user. At the same time, the user's dance skills, physical condition and real-time feedback are taken into consideration. The dance movements are dynamically adjusted and the choreography is optimized according to the user's real-time physiological reactions and dance performance to enhance the fluency and expressiveness of the dance. Users are encouraged to provide feedback and participate in the adjustment process of the dance movements to ensure that the dance choreography can meet the user's expectations and needs. During the entire dance process, the user's physiological state is monitored to ensure that the dance activities are carried out within a safe range to avoid excessive fatigue or injury.

[0053] In this application, the server obtains the total sample set, the music information to be predicted and the target user information, wherein the total sample set is the dance types of different users received within a preset time period and the music matching the dance types; the target user information is processed to generate the dance attribute information of the target user; the total sample set is preprocessed to generate a training sample set with identification information, wherein the identification information is used to characterize that the user's dance movements are in an abnormal state; an initial dance prediction model matching the identification information is obtained, wherein the initial dance prediction model is set based on the music information to be predicted and the target user information received within a preset time period; the initial dance prediction model is trained based on the training sample set with identification information to generate a target dance prediction model; the music information to be predicted and the dance attribute information of the target user are processed based on the target dance prediction model to generate the target dance movement. The personalized needs of users, including cultural background and physical conditions, are taken into account to provide appropriate dance movement recommendations. In the recommendation process, user feedback is used to continuously optimize the model. Through personalized dance prediction and music feature generation, users can enjoy a richer dance experience that meets their specific needs.

[0054] Optionally, in another embodiment of the method of the present application, feature extraction is performed on the total sample set to determine an original feature library, including:

[0055] Acquire a historical music data set that matches the music to be predicted, wherein the historical music data set includes dance moves generated based on different user preferences and different dance types;

[0056] Processing the historical music data set to obtain dance movement features and music clip correlation co-occurrence frequencies;

[0057] Processing the co-occurrence frequency of the dance movement features and the music clip correlation to generate correlation matrix information;

[0058] Generate a number of dance feature data based on the correlation matrix information;

[0059] An original feature library is generated based on the plurality of dance feature data.

[0060] In one embodiment, in the process of building a dance prediction model, it is basic work to extract features from the total sample set and determine the original feature library. Collect historical music data sets that match the music to be predicted. These data sets reflect the preferences of different users and the characteristics of different dance types. Extract dance movement features from the historical music data sets, including key elements such as movement type, rhythm, style, etc., analyze the correlation co-occurrence frequency between dance movement features and music clips to identify the matching pattern between movement and music, and use dance movement features and co-occurrence frequency information to construct a correlation matrix, which quantifies the relationship between different features. Extract valuable information from the correlation matrix and generate a number of dance feature data to provide a basis for the prediction of dance movements.

[0061] The extracted dance feature data is integrated to construct an original feature library, which will serve as the basis for the dance prediction model. The original feature library is used to train and optimize the dance prediction model so that it can predict the corresponding dance movements based on the music features. The feature library and model parameters are dynamically adjusted to adapt to different dance styles and user preferences, ensuring that the dance prediction model can accurately capture the complex relationship between music and dance and provide users with a high-quality personalized dance experience.

[0062] In another embodiment, the present invention includes a calculation formula for calculating the co-occurrence frequency of correlation, and the calculation formula is: ;in, Representation concept and Concept The number of times they co-occur in the report set, Representation concept The total number of occurrences, Representation concept Concept of appearance Frequency of occurrence, based on correlation co-occurrence frequency Constructing a correlation matrix .

[0063] Suppose we have a historical music dataset that contains dance moves generated by different user preferences and different dance types. (e.g. a certain type of dance move, such as "twirl") and concepts (e.g. a specific rhythmic pattern of a piece of music, such as "syncopated rhythm"), Indicates the number of times the dance action "spin" and the music clip "syncopated rhythm" appear together in the entire report set. If "spin" and "syncopated rhythm" appear together 15 times in 100 combinations of dance actions and music clips, then =15. Indicates the total number of times the concept "syncopated rhythm" appears in the report set. Assuming that "syncopated rhythm" appears 30 times in these 100 combinations, then =30. According to the formula, , which means that when the “syncopated rhythm” appears, the frequency of the dance action “spinning” is 0.5.

[0064] The present invention includes a calculation formula for calculating the correlation matrix, which is:

[0065] ;in, is the co-occurrence frequency threshold, if Greater than or equal to the co-occurrence frequency threshold , then the concept With concept There is a correlation, otherwise there is no correlation.

[0066] Continuing with the above calculation Assume that the co-occurrence frequency threshold is 0.5. Set to 0.4. Because, according to the formula, =1, which means that in the correlation matrix, there is a correlation between the dance action "spin" and the music clip "syncopated rhythm", and the corresponding position in the matrix will be marked as 1. 0.3 (less than ),So =0, indicating that there is no correlation between the two, and the corresponding position in the matrix is ​​marked as 0. Through such calculations, a matrix reflecting the correlation between dance movement features and music clips can be constructed, providing a basis for the subsequent generation of several dance feature data based on the correlation matrix information, and then constructing the original feature library for the prediction of dance movements.

[0067] By applying the above technical solution, the server obtains a total sample set, music information to be predicted and target user information, wherein the total sample set is the dance types of different users received within a preset time period and the music matching the dance types; the target user information is processed to generate the target user's dance preference information, the target user's physical examination information and the target user's dance usage information; the target user's dance preference information and the target user's physical examination information are processed to generate the target user's body movement factor; the target user's body movement factor is processed based on the target user's dance usage information to generate the target user's dance difficulty factor; and the target user's dance attribute information is generated based on the target user's dance difficulty factor.

[0068] A historical music data set matching the music to be predicted is obtained, wherein the historical music data set includes dance movements generated based on different user preferences and different dance types; the historical music data set is processed to obtain dance movement features and music clip correlation co-occurrence frequencies; the method includes a calculation formula for calculating the correlation co-occurrence frequency, and the calculation formula is: ;in, Representation concept and Concept The number of times they co-occur in the report set, Representation concept The total number of occurrences, Representation concept Concept of appearance Frequency of occurrence, based on correlation co-occurrence frequency Constructing a correlation matrix : The co-occurrence frequency of the dance movement features and the music clip correlation is processed to generate correlation matrix information; the method includes a calculation formula for calculating the correlation matrix, and the calculation formula is: ;in, is the co-occurrence frequency threshold, if Greater than or equal to the co-occurrence frequency threshold , then the concept With concept There is correlation, otherwise there is no correlation; generating a number of dance feature data based on the correlation matrix information; generating an original feature library based on the number of dance feature data.

[0069] The invention relates to a method for obtaining an initial dance prediction model that matches the identification information, wherein the initial dance prediction model is set based on the music information to be predicted and the target user information received within a preset time period; the initial dance prediction model is trained based on the training sample set with the identification information to generate a target dance prediction model; the music information to be predicted is processed based on the target dance prediction model to generate the musical characteristics and music duration information of the target music; the musical characteristics and music duration information of the target music are processed based on the target dance prediction model to generate a music influence factor; the music influence factor and the dance difficulty factor of the target user are processed based on the target dance prediction model to generate initial dance movement information; the real-time physiological state information of the target user is obtained, wherein the real-time physiological state information of the target user is generated when the target user exercises based on the initial dance movement information; the real-time physiological state information and the initial dance movement information of the target user are processed based on the target dance prediction model to generate a dance movement adjustment factor; the music information to be predicted and the initial dance movement information are processed based on the dance movement adjustment factor to generate a target dance movement. The personalized needs of users, including cultural background and physical conditions, are taken into consideration to provide appropriate dance move recommendations. During the recommendation process, user feedback is used to continuously optimize the model. Through personalized dance prediction and music feature generation, users can enjoy a dance experience that is richer and meets their specific needs, ensuring that the dance prediction model can accurately capture the complex relationship between music and dance and provide users with high-quality personalized dance experience.

[0070] In one embodiment, if Figure 2 As shown, the present application also provides a dance movement prediction device, comprising:

[0071] The acquisition module 201 is used to acquire a total sample set, music information to be predicted and target user information, wherein the total sample set is dance types of different users received within a preset time period and music matching the dance types; acquire an initial dance prediction model matching the identification information, wherein the initial dance prediction model is set based on the music information to be predicted and target user information received within the preset time period;

[0072] The processing module 202 is used to process the target user information to generate dance attribute information of the target user; pre-process the total sample set to generate a training sample set with identification information, wherein the identification information is used to characterize that the user's dance movements are in an abnormal state; train the initial dance prediction model based on the training sample set with identification information to generate a target dance prediction model; and process the music information to be predicted and the dance attribute information of the target user based on the target dance prediction model to generate a target dance movement.

[0073] In another embodiment of the present application, the processing module 202 is configured to process the target user information to generate dance attribute information of the target user, including:

[0074] Processing the target user information to generate dance preference information of the target user, physical examination information of the target user, and dance usage information of the target user;

[0075] Processing the dance preference information of the target user and the physical examination information of the target user to generate a body movement factor of the target user;

[0076] Processing the body movement factor of the target user based on the dance usage information of the target user to generate a dance difficulty factor of the target user;

[0077] The dance attribute information of the target user is generated based on the dance difficulty factor of the target user.

[0078] In another embodiment of the present application, the processing module 202 is configured to perform feature extraction on the total sample set to determine an original feature library.

[0079] In another embodiment of the present application, the processing module 202 is configured to extract features from the total sample set to determine an original feature library, including:

[0080] Acquire a historical music data set that matches the music to be predicted, wherein the historical music data set includes dance moves generated based on different user preferences and different dance types;

[0081] Processing the historical music data set to obtain dance movement features and music clip correlation co-occurrence frequencies;

[0082] Processing the co-occurrence frequency of the dance movement features and the music clip correlation to generate correlation matrix information;

[0083] Generate a number of dance feature data based on the correlation matrix information;

[0084] An original feature library is generated based on the plurality of dance feature data.

[0085] In another embodiment of the present application, the processing module 202 is configured to extract features from the total sample set to determine an original feature library, and further includes:

[0086] The method includes a calculation formula for calculating the correlation co-occurrence frequency, and the calculation formula is:

[0087] ;in, Representation concept and Concept The number of times they co-occur in the report set, Representation concept The total number of occurrences, Representation concept Concept of appearance Frequency of occurrence, based on correlation co-occurrence frequency Constructing a correlation matrix :

[0088] The method includes a calculation formula for calculating a correlation matrix, which is:

[0089] ;in, is the co-occurrence frequency threshold, if Greater than or equal to the co-occurrence frequency threshold , then the concept With concept There is a correlation, otherwise there is no correlation.

[0090] In another embodiment of the present application, the processing module 202 is configured to process the music information to be predicted and the dance attribute information of the target user based on the target dance prediction model to generate a target dance movement, including:

[0091] Processing the music information to be predicted based on the target dance prediction model to generate musical characteristics and music duration information of the target music;

[0092] Processing the musical characteristics of the target music and the music duration information based on the target dance prediction model to generate a music influence factor;

[0093] The music influence factor and the dance difficulty factor of the target user are processed based on the target dance prediction model to generate initial dance movement information.

[0094] In another embodiment of the present application, the processing module 202 is configured to process the music information to be predicted and the dance attribute information of the target user based on the target dance prediction model to generate a target dance movement, and further includes:

[0095] Acquire real-time physiological state information of the target user, wherein the real-time physiological state information of the target user is generated when the target user performs exercise based on the initial dance movement information;

[0096] Processing the real-time physiological state information and the initial dance movement information of the target user based on the target dance prediction model to generate a dance movement adjustment factor;

[0097] The music information to be predicted and the initial dance movement information are processed based on the dance movement adjustment factor to generate a target dance movement.

[0098] The present application embodiment provides an electronic device, such as Figure 3 As shown, the electronic device 3 includes a first processor 300, a memory 301, a bus 302 and a communication interface 303, wherein the first processor 300, the communication interface 303 and the memory 301 are connected via the bus 302; the memory 301 stores a computer program that can be run on the first processor 300, and when the first processor 300 runs the computer program, the dance movement prediction method provided in any of the aforementioned embodiments of the present application is executed.

[0099] The memory 301 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 303 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0100] The bus 302 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 301 is used to store a program, and the first processor 300 executes the program after receiving an execution instruction. The dance movement prediction method disclosed in any implementation of the embodiment of the present application may be applied to the first processor 300, or implemented by the first processor 300.

[0101] The first processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the first processor 300. The above-mentioned first processor 300 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be embodied as being executed by a hardware decoding processor, or by a combination of hardware and software modules in a decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 301, and the first processor 300 reads the information in the memory 301 and completes the steps of the above method in combination with its hardware.

[0102] The electronic device provided in the above-mentioned embodiment of the present application and the dance movement prediction method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0103] The present application embodiment provides a computer-readable storage medium, such as Figure 4 As shown, the computer-readable storage medium 401 stores a computer program, and when the computer program is read and executed by the second processor 402, the dance action prediction method as described above is implemented.

[0104] The technical solution of the embodiment of the present application is essentially or the part that co-exists with the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling an electronic device (which may be an air conditioner, a refrigeration device, a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk.

[0105] The computer-readable storage medium provided in the above-mentioned embodiment of the present application and the dance movement prediction method provided in the embodiment of the present application are based on the same inventive concept, and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0106] An embodiment of the present application provides a computer program product, including a computer program, wherein the computer program is executed by a third processor to implement the method described above.

[0107] The computer program product provided by the above-mentioned embodiment of the present application and the dance movement prediction method provided by the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0108] It should be noted that, in this application, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or still includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0109] Each embodiment in the present application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the prediction method, electronic device, electronic device, and readable storage medium embodiment for evaluating dance movements, since they are basically similar to the above-mentioned dance movement prediction method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the above-mentioned dance movement prediction method embodiment.

[0110] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application shall be subject to the scope defined by the claims.

Claims

1. A dance movement prediction method, characterized in that: include: Acquire a total sample set, music information to be predicted, and target user information, wherein the total sample set is dance types of different users received within a preset time period and music matching the dance types; Processing the target user information to generate dance attribute information of the target user; Preprocessing the total sample set to generate a training sample set with identification information, wherein the identification information is used to indicate that the dance movements of the user are in an abnormal state; Acquire an initial dance prediction model that matches the identification information, wherein the initial dance prediction model is set based on the music information to be predicted and the target user information received within a preset time period; Training the initial dance prediction model based on the training sample set with identification information to generate a target dance prediction model; Processing the music information to be predicted and the dance attribute information of the target user based on the target dance prediction model to generate a target dance move; Processing the target user information to generate dance attribute information of the target user includes: processing the target user information to generate dance preference information of the target user, physical examination information of the target user, and dance usage information of the target user; processing the dance preference information of the target user and the physical examination information of the target user to generate a body movement factor of the target user; processing the body movement factor of the target user based on the dance usage information of the target user to generate a dance difficulty factor of the target user; generating dance attribute information of the target user based on the dance difficulty factor of the target user; The target dance prediction model is used to process the music information to be predicted and the dance attribute information of the target user to generate a target dance action, including: processing the music information to be predicted based on the target dance prediction model to generate the musical characteristics and music duration information of the target music; processing the musical characteristics and the music duration information of the target music based on the target dance prediction model to generate a music influence factor; processing the music influence factor and the dance difficulty factor of the target user based on the target dance prediction model to generate initial dance action information; The target dance prediction model is used to process the music information to be predicted and the dance attribute information of the target user to generate a target dance movement, and the method further includes: obtaining real-time physiological state information of the target user, wherein the real-time physiological state information of the target user is generated when the target user exercises based on the initial dance movement information; the real-time physiological state information of the target user and the initial dance movement information are processed based on the target dance prediction model to generate a dance movement adjustment factor; the music information to be predicted and the initial dance movement information are processed based on the dance movement adjustment factor to generate a target dance movement; The total sample set is preprocessed, including: obtaining a historical music data set that matches the music to be predicted, wherein the historical music data set includes dance movements generated based on different user preferences and different dance types; processing the historical music data set to obtain dance movement features and music clip correlation co-occurrence frequencies; processing the dance movement features and the music clip correlation co-occurrence frequencies to generate correlation matrix information; generating a number of dance feature data based on the correlation matrix information; and generating an original feature library based on the number of dance feature data.

2. The method according to claim 1, characterized in that The method includes a calculation formula for calculating the correlation co-occurrence frequency, and the calculation formula is: ； in, Dance movement characteristics and music clip features The number of times they co-occur in the report set, Represents the characteristics of music clips The total number of occurrences, Represents the characteristics of music clips Dance movement characteristics when appearing Frequency of occurrence, based on correlation co-occurrence frequency Constructing a correlation matrix : The method includes a calculation formula for calculating a correlation matrix, which is: ； in, Indicates based on With co-occurrence frequency threshold 0 or 1 indicates whether there is a correlation between the dance movement features and the music clip features. is the co-occurrence frequency threshold, if Greater than or equal to the co-occurrence frequency threshold , then the dance movement characteristics Features of music clips There is a correlation, otherwise there is no correlation.

3. A dance movement prediction device, characterized in that: The method for predicting dance movements according to claim 1 comprises: An acquisition module is used to acquire a total sample set, music information to be predicted and target user information, wherein the total sample set is dance types of different users received within a preset time period and music matching the dance types; acquire an initial dance prediction model matching the identification information, wherein the initial dance prediction model is set based on the music information to be predicted and target user information received within the preset time period; A processing module is used to process the target user information to generate dance attribute information of the target user; pre-process the total sample set to generate a training sample set with identification information, wherein the identification information is used to characterize that the user's dance movements are in an abnormal state; train the initial dance prediction model based on the training sample set with identification information to generate a target dance prediction model; process the music information to be predicted and the dance attribute information of the target user based on the target dance prediction model to generate a target dance movement; Processing the target user information to generate dance attribute information of the target user includes: processing the target user information to generate dance preference information of the target user, physical examination information of the target user, and dance usage information of the target user; processing the dance preference information of the target user and the physical examination information of the target user to generate a body movement factor of the target user; processing the body movement factor of the target user based on the dance usage information of the target user to generate a dance difficulty factor of the target user; generating dance attribute information of the target user based on the dance difficulty factor of the target user; The target dance prediction model is used to process the music information to be predicted and the dance attribute information of the target user to generate a target dance action, including: processing the music information to be predicted based on the target dance prediction model to generate the musical characteristics and music duration information of the target music; processing the musical characteristics and the music duration information of the target music based on the target dance prediction model to generate a music influence factor; processing the music influence factor and the dance difficulty factor of the target user based on the target dance prediction model to generate initial dance action information; The method further includes: obtaining real-time physiological state information of the target user, wherein the real-time physiological state information of the target user is generated when the target user exercises based on the initial dance movement information; processing the real-time physiological state information of the target user and the initial dance movement information based on the target dance prediction model to generate a dance movement adjustment factor; and processing the music information to be predicted and the initial dance movement information based on the dance movement adjustment factor to generate a target dance movement.

4. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; The first processor is configured to execute the dance movement prediction method according to any one of claims 1 to 2 by executing the executable instructions.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the dance movement prediction method according to any one of claims 1 to 2 is implemented.

Images