Somatosensory dance game method capable of customizing lyrics

Abstract

The invention discloses a somatosensory dance game method and device for customizing lyrics and a computer readable storage medium. The method comprises the steps that keywords input by a user and used for customizing the lyrics are obtained; extracting basic music features associated with lyric generation in the currently selected accompaniment; generating lyric requirements according to the basic music features and the keywords; according to the lyric demand, generating lyrics matched with the accompaniment through a preset natural language model; and combining the generated lyrics with the accompaniment to complete the self-definition of the lyrics. The somatosensory dance game method capable of customizing lyrics has the advantages of meeting individual requirements of users and improving game interactivity.

Description

Technical Field

[0001] The present invention relates to the technical field of somatosensory dance games, and in particular to a somatosensory dance game method and device with customized lyrics, and a computer-readable storage medium. Background Art

[0002] With the rapid development of technology, motion-sensing dance games have become one of the important ways for people to relax and have fun. Such games usually use motion-sensing devices, such as motion capture cameras and motion-sensing controllers, to allow users to interact with the game through body movements. Players can follow the instructions on the screen and imitate the preset dance moves, achieving the dual purpose of entertainment and exercise.

[0003] However, existing somatosensory dance games mainly rely on preset songs and dance moves. Game developers design a fixed list of songs and corresponding dance choreography in advance, and players can only choose from these preset contents. Since the song content is pre-set, users cannot customize the game content according to their personal preferences, their own level or specific occasions. This lack of personalized design limits the appeal of the game and reduces the enthusiasm of users to participate. In addition, the fixed nature of the game content may make players feel bored after multiple experiences. This limitation not only affects the user experience, but also limits the market expansion of the game.

[0004] Therefore, it is urgent to provide a kind of dance game to meet the personalized needs of users. Summary of the invention

[0005] The embodiment of the present application aims to meet the personalized needs of users and enhance the user's gaming experience by providing a somatosensory dance game method with customized lyrics.

[0006] To achieve the above purpose, the embodiment of the present application provides a somatosensory dance game method with customized lyrics, comprising:

[0007] Get the keywords entered by the user for customizing lyrics;

[0008] Extracting basic musical features in the currently selected accompaniment that are associated with lyrics generation;

[0009] Generate lyrics requirements according to the basic music features and the keywords;

[0010] According to the lyrics requirement, lyrics matching the accompaniment are generated through a preset natural language model;

[0011] The generated lyrics are combined with the accompaniment to complete the customization of the lyrics.

[0012] In one embodiment, generating lyrics requirements according to the basic music features and the keywords includes:

[0013] determining the emotional tone and stylistic type of said accompaniment;

[0014] Performing sentiment analysis and style classification on the keywords input by the user to determine the sentiment tone and style type of the keywords;

[0015] Performing compatibility analysis on the emotional tone and style type of the keyword and the emotional tone and style type of the accompaniment;

[0016] Generate lyrics requirements based on compatibility analysis results.

[0017] In one embodiment, the compatibility analysis of the emotional tone and style type of the keyword and the emotional tone and style type of the accompaniment includes:

[0018] Calculating the emotional similarity between the keyword and the accompaniment based on the emotional tone of the accompaniment and the emotional tone of the keyword;

[0019] Calculating the style similarity between the keyword and the accompaniment based on the style type of the accompaniment and the style type of the keyword;

[0020] The compatibility of the keyword and the accompaniment is determined according to the emotion similarity and the style similarity.

[0021] In one embodiment, generating lyrics requirements according to the compatibility analysis results includes:

[0022] When the emotional similarity is lower than a first preset threshold, calculating the influence coefficient of the emotional tone of the keyword on the basic music feature;

[0023] When the style similarity is lower than a second preset threshold, calculating the influence coefficient of the style type of the keyword on the basic music feature;

[0024] Adjusting the basic music features according to the influence coefficient of the emotional tone and / or style type of the keyword;

[0025] Lyrics requirements are generated based on the adjusted basic music features and the keywords.

[0026] In one embodiment, the basic music features are adjusted according to the influence coefficient based on the following formula:

[0027] T final =T initial +(T max -T min )×α;

[0028] Among them, T final is the eigenvalue of the adjusted basic music feature;

[0029] Tinitial is the initial feature value of the basic music feature;

[0030] T max and T min Preset maximum and minimum values ​​for basic music characteristics;

[0031] α is the influence coefficient of emotional tone or style type.

[0032] In one embodiment, generating lyrics requirements according to the compatibility analysis result further includes:

[0033] When the emotion similarity is higher than a first preset threshold, and the style similarity is higher than a second preset threshold, lyrics requirements are generated according to the basic music features and the keywords.

[0034] In one embodiment, generating lyrics requirements based on basic music features and keywords includes:

[0035] Determining the structural requirements of the lyrics according to the basic characteristics of the music, wherein the structural requirements include at least one of sentence pattern, rhythm, segmentation, and emotional progression;

[0036] Determining the content requirements of the lyrics based on the keywords;

[0037] The lyrics requirement is generated according to the structural requirement and the content requirement.

[0038] In one embodiment, determining the content requirements of lyrics based on the keywords includes:

[0039] Performing semantic expansion and sentiment optimization on the keywords to generate an expanded keyword set;

[0040] Determining the priority of keywords in the keyword set;

[0041] Determining the position distribution of the keywords in the lyrics according to the music structure of the accompaniment and the priority of the keywords;

[0042] Based on the keyword set and the position distribution, the content requirements of the lyrics are generated.

[0043] To achieve the above objectives, an embodiment of the present application also proposes a somatosensory dance game device with customized lyrics, comprising a memory, a processor, and a somatosensory dance game program with customized lyrics stored in the memory and executable on the processor, wherein the processor implements the somatosensory dance game method with customized lyrics as described in any one of the above items when executing the somatosensory dance game program with customized lyrics.

[0044] To achieve the above objectives, an embodiment of the present application also proposes a computer-readable storage medium, on which a somatosensory dance game program with custom lyrics is stored. When the somatosensory dance game program with custom lyrics is executed by a processor, the somatosensory dance game method with custom lyrics as described in any of the above items is implemented.

[0045] The somatosensory dance game method of the technical solution of the present application generates lyrics requirements that match the accompaniment based on the keywords input by the user and the basic music features of the currently selected accompaniment, and then generates lyrics requirements that match the accompaniment based on the lyrics requirements, thereby not only ensuring that the lyrics content meets the user's expectations, but also ensuring that the lyrics and the accompaniment remain harmonious. In this way, the personalized customization of the lyrics in the dance song is achieved, and the personalized needs of the user are met. This helps to improve the personalization and interactivity of the somatosensory dance game. It can be seen that compared with the traditional somatosensory dance game method, the somatosensory dance game method of the technical solution of the present application has the advantages of meeting the personalized needs of users and improving the interactivity of the game. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] 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 described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0047] Figure 1 A module structure diagram of an embodiment of a somatosensory dance game device with customized lyrics according to the present invention;

[0048] Figure 2 The figure is a flow chart of an embodiment of a method for playing a somatosensory dance game with customized lyrics according to the present invention.

[0049] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0051] In order to better understand the above technical solution, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0052] It should be noted that in the claims, any reference symbols placed between brackets shall not be constructed as limitations to the claims. The presence of "comprising" in the text does not exclude the presence of components or steps not listed in the claims. The quantifier "one" or "an" preceding a component does not exclude the presence of a plurality of such components. The present invention can be implemented by means of hardware comprising several different components and by means of appropriately programmed computers. In a unit claim that lists several means, several of these means may be embodied by the same hardware item. The use of "first", "second", and "third" etc. does not indicate any order, and these words may be interpreted as names.

[0053] like Figure 1 As shown, Figure 1 It is a structural diagram of a server 1 (also called a somatosensory dance game device with customized lyrics) of a hardware operating environment involved in an embodiment of the present invention.

[0054] The server of the embodiment of the present invention is a device with display function, such as "Internet of Things devices", smart air conditioners, smart lights, smart power supplies with networking functions, AR / VR devices with networking functions, smart speakers, self-driving cars, PCs, smart phones, tablet computers, e-book readers, portable computers, etc.

[0055] like Figure 1 As shown, the server 1 includes: a memory 11, a processor 12 and a network interface 13.

[0056] The memory 11 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the server 1, such as a hard disk of the server 1. In other embodiments, the memory 11 may also be an external storage device of the server 1, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc., equipped on the server 1.

[0057] Furthermore, the memory 11 may include an internal storage unit of the server 1 as well as an external storage device. The memory 11 may be used not only to store application software and various data installed on the server 1, such as the code of the somatosensory dance game program 10 with customized lyrics, but also to temporarily store data that has been output or is to be output.

[0058] In some embodiments, the processor 12 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, which is used to run the program code or process data stored in the memory 11, such as executing the somatosensory dance game program 10 with customized lyrics.

[0059] The network interface 13 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), and is generally used to establish a communication connection between the server 1 and other electronic devices.

[0060] The network may be the Internet, a cloud network, a wireless fidelity (Wi-Fi) network, a personal area network (PAN), a local area network (LAN), and / or a metropolitan area network (MAN). Various devices in the network environment may be configured to connect to the communication network according to various wired and wireless communication protocols. Examples of such wired and wireless communication protocols may include, but are not limited to, at least one of the following: Transmission Control Protocol and Internet Protocol (TCP / IP), User Datagram Protocol (UDP), Hypertext Transfer Protocol (HTTP), File Transfer Protocol (FTP), ZigBee, EDGE, IEEE 802.11, Light Fidelity (Li-Fi), 802.16, IEEE 802.11s, IEEE 802.11g, multi-hop communication, wireless access point (AP), device-to-device communication, cellular communication protocol, and / or Bluetooth (Blue Tooth) communication protocol or a combination thereof.

[0061] Optionally, the server may further include a user interface, which may include a display, an input unit such as a keyboard, and an optional user interface may further include a standard wired interface and a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device, etc. The display may also be referred to as a display screen or a display unit, which is used to display information processed in the server 1 and to display a visual user interface.

[0062] Figure 1 Only the server 1 having components 11-13 and a somatosensory dance game program 10 with customized lyrics is shown. It can be understood by those skilled in the art that Figure 1 The structure shown does not constitute a limitation on the server 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0063] In this embodiment, the processor 12 can be used to call the somatosensory dance game program with customized lyrics stored in the memory 11, and perform the following operations:

[0064] Get the keywords entered by the user for customizing lyrics;

[0065] Extracting basic musical features in the currently selected accompaniment that are associated with lyrics generation;

[0066] Generate lyrics requirements according to the basic music features and the keywords;

[0067] According to the lyrics requirement, lyrics matching the accompaniment are generated through a preset natural language model;

[0068] The generated lyrics are combined with the accompaniment to complete the customization of the lyrics.

[0069] In one embodiment, the processor 12 may be used to call a somatosensory dance game program with customized lyrics stored in the memory 11, and perform the following operations:

[0070] determining the emotional tone and stylistic type of said accompaniment;

[0071] Performing sentiment analysis and style classification on the keywords input by the user to determine the sentiment tone and style type of the keywords;

[0072] Performing compatibility analysis on the emotional tone and style type of the keyword and the emotional tone and style type of the accompaniment;

[0073] Generate lyrics requirements based on compatibility analysis results.

[0074] In one embodiment, the processor 12 may be used to call a somatosensory dance game program with customized lyrics stored in the memory 11, and perform the following operations:

[0075] Calculating the emotional similarity between the keyword and the accompaniment based on the emotional tone of the accompaniment and the emotional tone of the keyword;

[0076] Calculating the style similarity between the keyword and the accompaniment based on the style type of the accompaniment and the style type of the keyword;

[0077] The compatibility of the keyword and the accompaniment is determined according to the emotion similarity and the style similarity.

[0078] In one embodiment, the processor 12 may be used to call a somatosensory dance game program with customized lyrics stored in the memory 11, and perform the following operations:

[0079] When the emotional similarity is lower than a first preset threshold, calculating the influence coefficient of the emotional tone of the keyword on the basic music feature;

[0080] When the style similarity is lower than a second preset threshold, calculating the influence coefficient of the style type of the keyword on the basic music feature;

[0081] Adjusting the basic music features according to the influence coefficient of the emotional tone and / or style type of the keyword;

[0082] Lyrics requirements are generated based on the adjusted basic music features and the keywords.

[0083] In one embodiment, the processor 12 may be used to call a somatosensory dance game program with customized lyrics stored in the memory 11, and perform the following operations:

[0084] When the emotion similarity is higher than a first preset threshold, and the style similarity is higher than a second preset threshold, lyrics requirements are generated according to the basic music features and the keywords.

[0085] In one embodiment, the processor 12 may be used to call a somatosensory dance game program with customized lyrics stored in the memory 11, and perform the following operations:

[0086] Determining the structural requirements of the lyrics according to the basic characteristics of the music, wherein the structural requirements include at least one of sentence pattern, rhythm, segmentation, and emotional progression;

[0087] Determining the content requirements of the lyrics based on the keywords;

[0088] The lyrics requirement is generated according to the structural requirement and the content requirement.

[0089] In one embodiment, the processor 12 may be used to call a somatosensory dance game program with customized lyrics stored in the memory 11, and perform the following operations:

[0090] Performing semantic expansion and sentiment optimization on the keywords to generate an expanded keyword set;

[0091] Determining the priority of keywords in the keyword set;

[0092] Determining the position distribution of the keywords in the lyrics according to the music structure of the accompaniment and the priority of the keywords;

[0093] Based on the keyword set and the position distribution, the content requirements of the lyrics are generated.

[0094] Based on the hardware architecture of the above-mentioned somatosensory dance game device with customized lyrics, an embodiment of the somatosensory dance game method with customized lyrics of the present invention is proposed. The somatosensory dance game method with customized lyrics of the present invention is intended to meet the personalized needs of users and enhance the user's game experience.

[0095] Reference Figure 2 , Figure 2 This is an embodiment of a somatosensory dance game method with customized lyrics of the present invention, and the somatosensory dance game method with customized lyrics comprises the following steps:

[0096] S10: Obtain keywords input by the user for customizing lyrics.

[0097] Among these, keywords refer to words entered by users based on personal preferences, emotions or themes, such as emotional keywords (such as "happy", "sad"), thematic keywords (such as "dream", "freedom"), etc.

[0098] Specifically, the system accepts keywords input by users through the input module or voice recognition module of the game interface. These keywords represent the main emotions or themes that users want to express in the lyrics. The system will perform semantic analysis on the keywords to ensure that the subsequently generated lyrics can accurately reflect the needs of users. For example, when a user enters the keyword "dream", the system will use the emotion and theme of the keyword as the core basis for the creation of lyrics.

[0099] S20, extracting basic music features associated with lyrics generation in the currently selected accompaniment.

[0100] Among them, the currently selected accompaniment refers to the corresponding accompaniment music when the user is playing a somatosensory dance game. It is the soundtrack for dance movements and game interactions.

[0101] Basic music features refer to features related to the overall structure of music, including rhythm, pitch, harmony, dynamics, instrument configuration, chords, beat type, etc.

[0102] Specifically, the system analyzes the accompaniment through audio processing algorithms to extract the basic features of the music.

[0103] For example, the system can extract pitch information through fast Fourier transform (FFT) and identify the rhythm (BPM) through beat detection algorithm. At the same time, harmony analysis will identify the chord progression in the accompaniment, and dynamic analysis will determine the change pattern of the accompaniment volume. These extracted music features will serve as an important basis for generating lyrics to ensure that the lyrics content matches the emotion and style of the accompaniment.

[0104] S30: Generate lyrics requirements according to the basic music features and the keywords.

[0105] Among them, lyrics requirements refer to the structural and content requirements determined to generate lyrics that meet the accompaniment characteristics and user input requirements. Lyrics requirements may include structural requirements (such as sentence pattern, rhythm, length, segmentation, emotional progression, etc.) and content requirements (such as emotional expression, theme, etc.).

[0106] Specifically, the system first analyzes the keywords input by the user to determine their emotional tone and theme characteristics. Then, the system performs a compatibility analysis on the emotional tone of the keywords and the basic musical characteristics of the accompaniment to determine the matching degree between the two.

[0107] For example, when the keyword "happy" is consistent with the fast rhythm (high BPM) of the accompaniment, the system will generate lyrics requirements with positive emotions as the main focus. The system also determines the sentence pattern, rhythm and paragraph structure of the lyrics to ensure that the lyrics are consistent with the rhythm, tone and other characteristics of the music. The lyrics requirements finally generated include not only the structure of the lyrics, but also the emotional expression and theme requirements corresponding to the keywords.

[0108] S40: Generate lyrics matching the accompaniment through a preset natural language model according to the lyrics requirement.

[0109] Among them, the natural language generation model refers to a text generation model trained based on deep learning technology, such as GPT (generative pre-training model), which is used to generate coherent lyrics based on the input text or needs.

[0110] Specifically, the system takes the lyrics requirements generated in step S30 as input and passes it to the preset natural language generation model. The model generates lyrics text that meets the requirements based on the input structure requirements (such as rhythm, sentence structure) and content requirements (such as emotion, theme) combined with the basic music features of the accompaniment.

[0111] For example, the keyword "dream" may generate a lyric about "chasing dreams", while ensuring that the lyrics are consistent with the emotion and style of the music based on the rhythm and tone of the accompaniment. The generated lyrics will have a certain rhyme, fluency, and fit naturally with the accompaniment.

[0112] S50: combining the generated lyrics with the accompaniment to complete the customization of the lyrics.

[0113] Among them, the combination of lyrics and accompaniment refers to playing the generated lyrics and accompaniment synchronously, so that the lyrics can present a complete song effect with the coordination of the rhythm, harmony, tone and other characteristics of the accompaniment.

[0114] Specifically, the system adjusts the time synchronization between the generated lyrics and the accompaniment based on the basic musical features of the accompaniment, such as the beat, pitch, and harmony, to ensure that the lyrics and the accompaniment blend naturally. By combining the generated lyrics with the accompaniment, users can experience song content customized according to their input during the game. This customized lyrics not only maintains harmony with the accompaniment, but also reflects the user's personalized input, improving the game's interactivity and user experience.

[0115] It can be understood that the somatosensory dance game method of the technical solution of the present application generates lyrics requirements that match the accompaniment based on the keywords input by the user and the basic music characteristics of the currently selected accompaniment, and then generates lyrics requirements that match the accompaniment based on the lyrics requirements, thereby not only ensuring that the lyrics content meets the user's expectations, but also ensuring that the lyrics and the accompaniment remain harmonious. In this way, the personalized customization of the lyrics in the dance song is achieved, and the personalized needs of the user are met. This helps to improve the personalization and interactivity of the somatosensory dance game. It can be seen that compared with the traditional somatosensory dance game method, the somatosensory dance game method of the technical solution of the present application has the advantages of meeting the personalized needs of users and improving the interactivity of the game.

[0116] In some embodiments, generating lyrics requirements according to the basic music features and the keywords includes:

[0117] S31, determining the emotional tone and style type of the accompaniment.

[0118] Among them, emotional tone refers to the main emotional characteristics conveyed by the accompaniment, such as positive, sad, cheerful, lyrical, etc. The system determines the emotional expression of the accompaniment by analyzing the musical characteristics of the accompaniment, such as the tone (such as major or minor), rhythm, dynamic changes, etc.

[0119] Style type refers to the musical style characteristics of the accompaniment, such as pop, rock, jazz, electronic, etc. Accompaniments of different styles have obvious differences in instrumentation, rhythmic patterns, and harmony complexity.

[0120] Specifically, the system extracts the musical features of the accompaniment through audio analysis technology, and performs emotion and style analysis based on these features. For example, the system can identify the tonality of the accompaniment through pitch wheel analysis and chord progression detection, thereby determining whether the accompaniment expresses a happy or sad emotion. At the same time, the system can determine the style type of the accompaniment through rhythm pattern and instrumentation analysis, ensuring that the subsequently generated lyrics conform to the style characteristics of the accompaniment.

[0121] S32: Perform sentiment analysis and style classification on the keywords input by the user to determine the sentiment tone and style type of the keywords.

[0122] Among these, sentiment analysis refers to the system using natural language processing technology to analyze the sentiment characteristics of keywords input by users and determine the emotional attributes expressed by the keywords.

[0123] The emotional tone of a keyword refers to the emotional characteristics represented by the keyword entered by the user, for example, "happy" represents positive emotion and "sad" represents negative emotion.

[0124] Style classification refers to determining the corresponding music style based on the semantic features of keywords.

[0125] The style type of a keyword refers to the music style preference reflected by the keyword. For example, the keyword "rock" may correspond to fast-paced, strong drum beats and electric guitar accompaniment, while the keyword "lyrical" may correspond to slow-paced, soft piano accompaniment.

[0126] Specifically, the system first performs sentiment analysis on the keywords input by the user, and determines the emotional tone of the keywords through a sentiment classification model (such as a sentiment dictionary or a deep learning-based sentiment classifier). For example, the input keyword "freedom" may be associated with the emotions of "positive" and "relaxed".

[0127] Next, the system performs style classification on the semantics of the keyword to determine the style type of the keyword. For example, "jazz" corresponds to more complex harmony and soft rhythm, while "rock" is characterized by strong rhythm and prominent tone changes.

[0128] S33, performing compatibility analysis on the emotional tone and style type of the keyword and the emotional tone and style type of the accompaniment.

[0129] Among them, compatibility analysis refers to comparing the similarity between the emotion and style of the keywords and the emotion and style of the accompaniment to determine the degree of their matching.

[0130] Specifically, the system first calculates the similarity between the keyword and the accompaniment in terms of emotional tone. For example, if the keyword "happy" entered by the user matches the emotional tone of the accompaniment (such as major key and fast tempo), the matching degree is high. Then, the system calculates the style similarity based on the style type of the accompaniment and the style classification of the keyword. For example, if the keyword style entered by the user is "rock", and the accompaniment also has rock style characteristics (such as strong rhythm and prominent guitar sound effects), the matching degree between the two is high.

[0131] By integrating sentiment similarity and style similarity, the system generates a matching score for subsequent lyric demand generation.

[0132] S34. Generate lyrics requirements based on the compatibility analysis results.

[0133] Specifically, when the match between the keyword and the accompaniment is high, the system will generate lyrics that are highly consistent with the emotional tone and style type of the accompaniment. For example, when the keyword "dream" matches the fast rhythm and positive emotion of the accompaniment, the system will emphasize positive emotional expression when generating lyrics.

[0134] If the match is low, the system will make appropriate adjustments to ensure that the lyrics are in harmony with the accompaniment. For example, when the user's keywords differ from the emotional tone of the accompaniment, the system may generate a progressive lyric structure to gradually transition the emotional expression of the two, so that the lyrics and accompaniment are unified in expression.

[0135] It can be understood that by determining the emotional tone and style type of the accompaniment and the user's keywords, and then performing a compatibility analysis on the emotional tone and style types of the two, the system can accurately judge the adaptability of the keywords and the accompaniment, so as to generate lyrics that are more in line with the accompaniment and user intentions, and ensure the integration of the lyrics with the accompaniment in terms of content and structure, thereby enhancing the interactivity and user experience of the game.

[0136] In some embodiments, performing compatibility analysis on the emotional tone and style type of the keyword and the emotional tone and style type of the accompaniment includes:

[0137] S331. Calculate the emotional similarity between the keyword and the accompaniment based on the emotional tone of the accompaniment and the emotional tone of the keyword.

[0138] Specifically, the sentiment similarity between the keyword and the accompaniment can be calculated through a sentiment classification model (such as a word vector model). If the sentiment tone of the accompaniment is the same as the sentiment tone of the keyword, the sentiment similarity is high; if the sentiment tone is different, the similarity is low.

[0139] Exemplarily, the system compares the emotional tone of the accompaniment with the emotional tone of the keyword. If the two are the same, the emotional similarity is 1; if the two are different, the similarity is 0.5 or lower.

[0140] S332: Calculate the style similarity between the keyword and the accompaniment based on the style type of the accompaniment and the style type of the keyword.

[0141] Specifically, the style similarity calculation model can be used to measure the style matching degree between keywords and accompaniment. For example, if the keyword "jazz" and the style type of the accompaniment are both "jazz music", the style similarity is high; if the style type of the keyword and the accompaniment is very different (such as rock and lyric), the style similarity is low.

[0142] S333: Determine the compatibility between the keyword and the accompaniment according to the emotion similarity and the style similarity.

[0143] Compatibility refers to the overall fit between keywords and accompaniment in terms of emotion and style. The higher the compatibility, the more harmonious the keywords and accompaniment are in terms of emotion and style.

[0144] Optionally, the system can combine sentiment similarity and style similarity through a weighted algorithm to generate an overall compatibility score. The calculation formula for the compatibility score can be expressed as follows:

[0145] Compatibility score = w1*emotional similarity + w2*style similarity;

[0146] Among them, w1 and w2 are weight coefficients, which are adjusted according to the importance of emotion and style. For example, if emotion has a greater impact on lyric generation, the weight of w1 will be higher.

[0147] Based on the compatibility score, the system determines the compatibility of the keyword with the accompaniment. If the compatibility score is high, the system will generate lyrics requirements that are highly consistent with the accompaniment. If the compatibility score is low, the system may generate adjusted lyrics requirements to ensure that the lyrics content is consistent with the emotion and style of the accompaniment. For example, when the keyword "happy" entered by the user highly matches the emotion and style of the accompaniment, the system will generate lyrics that closely match the accompaniment; if the compatibility is low, the system may adjust the emotion or style of the lyrics to adapt to the accompaniment.

[0148] It can be understood that by calculating the emotional similarity and style similarity between keywords and accompaniment, and then determining the compatibility of keywords and accompaniment based on the emotional similarity and style similarity, the emotional expression and style type of the generated lyrics can be made consistent with the accompaniment to generate high-quality lyrics, thereby improving the harmony between the lyrics and accompaniment, which helps to improve the user experience.

[0149] In some embodiments, generating lyrics requirements according to the compatibility analysis results includes:

[0150] S341. When the emotional similarity is lower than a first preset threshold, calculate the influence coefficient of the emotional tone of the keyword on the basic music feature.

[0151] The first preset threshold is used to measure the emotional similarity, that is, the matching degree between the emotional tone of the keyword input by the user and the emotional tone of the accompaniment.

[0152] The influence coefficient refers to the degree to which the emotional tone of the keyword adjusts the characteristics of the accompaniment music (such as rhythm, pitch, harmony, etc.). The size of the influence coefficient reflects the extent of the adjustment required.

[0153] Specifically, when the emotional similarity is lower than the first preset threshold, it indicates that the emotional fit between the keyword and the accompaniment is low. For example, the emotional tone of the keyword input by the user is "positive", while the emotional tone of the accompaniment is "negative".

[0154] Specifically, when the emotional similarity is lower than the preset threshold, the system calculates the difference between the emotional tone of the keyword and the emotional tone of the accompaniment, and generates a corresponding emotional impact coefficient. If the emotional tone of the keyword is very different from the emotional tone of the accompaniment (such as "happy" and "sad"), the impact coefficient will be higher, which means that the musical characteristics of the accompaniment need to be adjusted significantly. The system will adjust the rhythm, tone or harmony in the accompaniment according to the impact coefficient to reduce emotional disharmony. For example, when the accompaniment is in a minor key (negative emotion), the input keyword is "happy" (positive emotion), the system will appropriately adjust the tone and rhythm of the accompaniment according to the impact coefficient to make it closer to the emotional expression of the keyword.

[0155] S342: When the style similarity is lower than a second preset threshold, calculate the influence coefficient of the style type of the keyword on the basic music feature.

[0156] The second preset threshold is used to measure the style similarity, that is, the matching degree between the style type of the keyword input by the user and the style type of the accompaniment.

[0157] The influence coefficient of the keyword style type on the basic music characteristics refers to the degree of adjustment of the keyword style type on the accompaniment music characteristics (such as rhythm, orchestration, harmony, etc.).

[0158] Specifically, when the style similarity is lower than the second preset threshold, the style of the keyword is inconsistent with the accompaniment style. For example, the keyword "rock" corresponds to a fast-paced, strong sound effect style, while the accompaniment is a soft lyrical style.

[0159] Specifically, when the style type of the keyword is significantly different from the style type of the accompaniment, the system generates an influence coefficient based on the keyword style type. For example, if the keyword entered by the user is "rock" and the accompaniment style is lyrical music, in this case, the system will calculate a higher influence coefficient and adjust the rhythm, instrumentation or dynamics of the accompaniment based on this coefficient to make it more in line with the style requirements of "rock". If the style difference between the keyword and the accompaniment is small, the influence coefficient will be lower and the adjustment of the accompaniment will be relatively small.

[0160] S343: Adjust the basic music features according to the influence coefficient of the emotional tone and / or style type of the keyword.

[0161] Among these, adjusting the basic music characteristics means: adjusting the rhythm, pitch, harmony and other characteristics of the accompaniment according to the influence of the emotional tone and style type of the keywords to make it more in line with the requirements of the lyrics.

[0162] Specifically, the system dynamically adjusts the musical features of the accompaniment based on the influence coefficient of the keyword's emotional tone and style type. For example, when the emotional tone of the keyword is quite different from the emotion of the accompaniment, the system can adjust the pitch of the accompaniment from a minor key to a major key, or increase the rhythm speed (increase the BPM) to enhance the positive emotional expression of the accompaniment. Similarly, if the style type of the keyword does not match the style of the accompaniment, the system can adjust the instrumentation or rhythm pattern of the accompaniment to make it more in line with the style requirements of the keyword. Through such adjustments, the system ensures that the basic musical features of the accompaniment can be coordinated with the keywords entered by the user.

[0163] It is worth noting that when the emotional similarity is higher than the first preset threshold, the influence of the emotional tone of the keyword on the basic music features is not calculated. Similarly, when the style similarity is higher than the second preset threshold, the influence of the style type of the keyword on the basic music features is not calculated.

[0164] S344: Generate lyrics requirements based on the adjusted basic music features and the keywords.

[0165] Specifically, the system combines the adjusted music features with the keywords input by the user to generate lyrics requirements that match the emotion and style. For example, if the keyword "dream" is highly matched with the rhythm and tone of the accompaniment after adjustment, the system will generate lyrics requirements with positive emotions as the main focus, ensuring that the rhythm and rhyme of the lyrics are consistent with the accompaniment, and the content can reflect the theme of "chasing dreams". In the end, the lyrics requirements generated by the system not only conform to the musical characteristics of the accompaniment in structure, but also keep in line with the accompaniment in emotion and style.

[0166] It can be understood that by calculating the influence coefficient of the emotional tone and style type of the keyword on the accompaniment music characteristics, the influence coefficient can be used to ensure that the music characteristics of the accompaniment can be adaptively adjusted according to the requirements of the keyword, so that the emotional tone and style type of the accompaniment match the keyword input by the user. In this way, the lyrics requirements are generated based on the adjusted music characteristics, which can ensure that the generated lyrics are consistent with the accompaniment in terms of emotion and style, thereby enhancing the user's personalized experience in the somatosensory dance game.

[0167] In some embodiments, the basic music features are adjusted according to the influence coefficient based on the following formula:

[0168] T final =T initial +(T max -T min )×α;

[0169] Among them, T final is the eigenvalue of the adjusted basic music feature;

[0170] T initial is the initial feature value of the basic music feature;

[0171] T max and T min Preset maximum and minimum values ​​for basic music characteristics;

[0172] α is the influence coefficient of emotional tone or style type.

[0173] Specifically, the system first extracts the basic music features in the current accompaniment and determines the feature values ​​of these basic music features. At the same time, the system determines the preset maximum value Tmax and minimum value Tmin of the music feature. For example, the system extracts the initial rhythm Tinitial of the current accompaniment through audio analysis technology, assuming that the rhythm is 80BPM (a slower rhythm, representing a negative emotional tone). The preset range of the rhythm is 40BPM (Tmin) to 160BPM (Tmax).

[0174] Furthermore, when the system detects that the keyword and the accompaniment do not match well in terms of emotional tone or style type, the system calculates the influence coefficient α based on the compatibility analysis results. The influence coefficient usually ranges from 0 to 1. The larger α is, the stronger the influence on the accompaniment and the larger the adjustment. For example, suppose the keyword is "happy", which represents a positive emotional tone, while the accompaniment is a negative emotion (minor key, slow tempo). The system calculates that the emotional similarity is low, so the accompaniment needs to be adjusted. The influence coefficient α of the emotional tone is set to 0.7, indicating that a larger adjustment is required.

[0175] Finally, after determining the influence coefficient, the system will calculate the characteristic value of the adjusted music feature according to the above formula. For example, assuming that the current accompaniment rhythm Tinitial is 80BPM, the system hopes to adjust the rhythm to better match the positive emotion conveyed by the keyword "happy". According to the preset maximum value Tmax of the rhythm is 160BPM, the minimum value Tmin is 40BPM, and the influence coefficient α is 0.7. Through the formula calculation, the adjusted rhythm Tfinal is:

[0176] Tfinal=80+(160-40)×0.7=80+120×0.7=80+84=164BPM

[0177] Therefore, the adjusted tempo is 164BPM, which represents a faster tempo and is consistent with the emotional expression of the keyword “happy”.

[0178] It is worth adding that for non-numerical basic music features, the system will first quantify these features into computable numerical forms when making adjustments, apply the influence coefficient of the emotional tone or style type to calculate, and then dequantize the calculation results into corresponding music features.

[0179] For example, non-numerical basic musical features such as pitch (such as C major, A minor), harmonic complexity (simple harmony, complex harmony), instrumentation (such as piano, guitar, synthesizer, etc.), etc., can be converted into numerical values ​​through preset rules.

[0180] For example, for pitch quantization, the pitch (Key) can be quantized according to the tonality of the scale. For example, the major key has a more positive emotion, while the minor key has a more negative emotion, so corresponding values ​​can be assigned to different tonality. The major key can be quantized as a positive value (e.g., +1), while the minor key can be quantized as a negative value (e.g., -1).

[0181] After the calculation of the quantized value is completed, the system will convert the adjusted quantized value back to the actual music feature. This process is called dequantization, which converts the numerical value back to the corresponding non-numerical feature.

[0182] For example, for pitch inverse quantization, when the pitch quantization value is adjusted from -1 (minor) to 0.5 after calculation, the system will convert it into a pitch closer to the major key, such as C major, representing a more positive emotional expression.

[0183] By quantizing and dequantizing the non-numerical basic musical features, it can be ensured that the non-numerical features in the accompaniment (such as pitch, harmonic complexity, orchestration, etc.) can be reasonably adjusted according to the influence coefficients of the emotional tone and style type.

[0184] In some embodiments, generating lyrics requirements based on the compatibility analysis results also includes: when the emotional similarity is higher than a first preset threshold and the style similarity is higher than a second preset threshold, generating lyrics requirements based on the basic music features and the keywords.

[0185] Specifically, when the emotional similarity is higher than the first preset threshold and the style similarity is higher than the second preset threshold, it means that the user's keywords and the accompaniment are highly consistent in terms of emotion and style, so there is no need to adjust the musical features of the accompaniment. The system will directly generate a lyric structure suitable for the music based on the rhythm of the accompaniment.

[0186] This operation can simplify the processing flow to increase the rate of lyric generation and help save computing resources while ensuring that the generated lyrics are highly consistent with the accompaniment in terms of emotion and style.

[0187] In some embodiments, generating lyrics requirements based on basic music features and keywords includes:

[0188] S110, determining structural requirements of the lyrics according to the basic characteristics of the music, wherein the structural requirements include at least one of sentence pattern, rhythm, segmentation, and emotional progression.

[0189] Among them, sentence pattern refers to the sentence structure of the lyrics, whether it is a short sentence or a long sentence.

[0190] Rhythm refers to the way the lyrics rhyme, and whether a strong sense of rhyme is required.

[0191] Segmentation refers to whether the lyrics require multiple segments, such as the difference between a chorus and a verse.

[0192] Emotional progression refers to the way the emotions in the lyrics are advanced, whether it needs to progress gradually or remain steady.

[0193] Specifically, the system generates appropriate lyrics structure requirements based on the rhythm, tone and other musical features of the accompaniment. For example:

[0194] If the accompaniment has a faster tempo (such as 120BPM), the system may choose a shorter sentence pattern to generate lyrics with more vitality and rhythm; if the tempo is slower (such as 60BPM), a longer sentence pattern will be selected to make the lyrics more lyrical.

[0195] If the accompaniment is in a major key, the lyrics structure may tend to be positive and bright in rhythm; if the accompaniment is in a minor key, the system will choose an emotionally progressive lyrics structure to convey more introspective or sentimental emotions.

[0196] For accompaniment with complex harmonies, the system may introduce segmentation requirements in the lyrics, such as a more narrative verse and a more emotional climax in the chorus.

[0197] S120: Determine the content requirements of the lyrics based on the keywords.

[0198] Among these, content requirements refer to the requirements of lyrics in terms of emotional expression, theme and language style.

[0199] Specifically, the system uses natural language processing technology to perform semantic analysis on keywords and generate content requirements related to the keywords. For example:

[0200] Enter the keyword "happy", and the system will generate lyrics with positive emotions, such as "sunshine", "smile", "hope" and other words;

[0201] By inputting the keyword "freedom", the system may generate lyrics that express the pursuit of freedom and breaking free from constraints, highlighting the core theme of "freedom".

[0202] S130: Generate the lyrics requirement according to the structure requirement and the content requirement.

[0203] Specifically, structural requirements determine the form of the lyrics, such as short sentences, rhymes, paragraphs, etc. Content requirements determine the emotions and themes of the lyrics, such as positivity, negativity, freedom, dreams, etc.

[0204] By combining the structural requirements with the content requirements, the lyrics requirements suitable for the accompaniment can be generated. For example:

[0205] If the accompaniment is fast-paced, major-key music with positive emotions, and the keyword entered by the user is "happiness", the system will generate a short, strongly rhymed lyric structure, and the lyrics will revolve around the theme of "happiness", such as "Run towards the sun and embrace dreams."

[0206] If the accompaniment is slow-tempo, minor-key, lyrical music, and the keyword entered by the user is "freedom", the system may generate a lyric structure with long sentences and progressive emotions to express the user's desire for freedom and inner struggle.

[0207] It can be understood that by determining the structural requirements of lyrics based on the basic characteristics of music, it can be ensured that the form of the lyrics matches the rhythm, tone and other characteristics of the accompaniment; by determining the content requirements of lyrics based on keywords, the system can generate lyrics content that meets the user's intentions and reflects the emotions and themes input by the user; further, by combining structural requirements with content requirements, the perfect combination of content and form of lyrics can be achieved, thereby ensuring a high degree of consistency in the lyrics in terms of emotional expression and musical fit.

[0208] In some embodiments, determining the content requirements of lyrics based on the keywords includes:

[0209] S121, performing semantic expansion and sentiment optimization on the keywords to generate an expanded keyword set.

[0210] Semantic expansion refers to generating words that are close to or related to the meaning of keywords by performing semantic analysis on keywords. For example, the keyword "dream" can be expanded to "hope", "pursuit", etc.; "freedom" can be expanded to "liberation", "unrestrained", etc.

[0211] Emotional optimization refers to the emotional adjustment and screening of the expanded vocabulary according to the emotional tone of the accompaniment to ensure that the emotion of the expanded vocabulary matches the accompaniment. For example, if the emotional tone of the accompaniment is positive, the system will select positive words in the expanded vocabulary, such as "bright" and "hope".

[0212] Specifically, the system first expands the keywords through semantic analysis algorithms (such as word vector-based models) to generate a set of related words. Then, the system screens and optimizes the words based on the emotional tone of the accompaniment to generate the final set of expanded keywords. For example, after entering "dream", the system generates an expanded set of words including "pursuit", "hope", "goal", etc., and selects the words based on the emotional tone of the accompaniment.

[0213] S122: Determine the priority of the keywords in the keyword set.

[0214] Among them, keyword priority refers to the system sorting the frequency and importance of keywords in lyrics according to their importance, emotional intensity and fit with the accompaniment.

[0215] Specifically, the system prioritizes keywords based on the following criteria:

[0216] Relevance of keywords to original input: Original keywords are directly related to the user’s input and therefore have a higher priority.

[0217] Emotional intensity: Expanded keywords that express stronger emotions (such as "pursuit" and "desire") have a higher priority, while words with weaker emotions have a lower priority.

[0218] Compatibility with the accompaniment: Keywords that are more consistent with the emotional tone and style of the accompaniment will have a higher priority. For example, when the accompaniment is positive, the keyword "hope" has a higher priority than "struggle".

[0219] Specifically, the system uses a sentiment analysis algorithm to combine the keywords entered by the user and their extended words to determine the priority of each keyword. For example, the keywords "pursuit", "hope" and "dream" in the extended set have a high degree of fit with the original keyword "dream", so they have a higher priority, while "goal" may have a lower sentiment intensity and therefore a lower priority.

[0220] S123, determining the position distribution of the keywords in the lyrics according to the music structure of the accompaniment and the priorities of the keywords.

[0221] Among them, the musical structure refers to the overall arrangement of the accompaniment, such as being divided into the main song, bridge, chorus and other parts. The emotional intensity of each part may be different, and the musical structure directly affects the arrangement of keywords in the lyrics.

[0222] Keyword position distribution refers to the specific position of each keyword in the extended keyword set in the lyrics according to the rhythm and paragraph structure of the music. For example, a higher priority keyword may appear in the chorus or climax, while a lower priority keyword may appear in the verse or introduction.

[0223] Specifically, the system first analyzes the structure of the accompaniment and identifies the emotional intensity and rhythmic pattern of each part. Then, according to the priority of the keywords, the important keywords are arranged in the emotional climax of the lyrics (such as the chorus), while the secondary keywords are distributed in the more gentle passages (such as the verse). For example, for an extended set of "dream", "pursuit", and "hope", the system may place "dream" in the climax of the chorus, and "hope" or "pursuit" in the verse part to create an emotional progression effect.

[0224] S124: Generate content requirements of lyrics based on the keyword set and the position distribution.

[0225] Specifically, after arranging the position distribution of keywords, the system will generate the core content of the lyrics based on the keywords and their distribution, ensuring that the lyrics are consistent with the rhythm and style of the accompaniment in terms of emotional expression and structure. In this way, the natural language model will combine the emotional expression and position distribution of keywords based on the content requirements, so that the lyrics can convey different levels of emotions in different paragraphs.

[0226] For example, for the extended set of "dream", "pursuit", and "hope", the system may generate lyrics with "dream" as the core in the chorus, such as "pursue dreams and welcome the light"; and in the main song, generate more narrative lyrics, such as "longing for the road to freedom".

[0227] It can be understood that by semantically expanding and emotionally optimizing keywords, a richer keyword set can be generated to enhance the expressive depth of lyrics; in addition, by sorting keywords according to their priority in the keyword set, it can be ensured that keywords with higher emotional intensity are better presented in the lyrics; and by determining the position distribution of keywords in the lyrics according to the musical structure of the accompaniment and the keyword priority, it can be ensured that the content of the lyrics is consistent with the rhythm and emotional progression of the accompaniment; finally, by generating the content requirements of the lyrics based on the expanded keyword set and position distribution, it can be ensured that the content of the lyrics perfectly matches the accompaniment in form and emotion, thereby enhancing the user's personalized experience and the flexibility of lyrics generation.

[0228] In addition, the embodiment of the present invention also proposes a computer-readable storage medium, which can be any one or any combination of a hard disk, a multimedia card, an SD card, a flash memory card, an SMC, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk read-only memory (CD-ROM), a USB memory, etc. The computer-readable storage medium includes a somatosensory dance game program 10 with customized lyrics. The specific implementation of the computer-readable storage medium of the present invention is roughly the same as the specific implementation of the somatosensory dance game method with customized lyrics and the server 1, which will not be repeated here.

[0229] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0230] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0231] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0232] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0233] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0234] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A somatosensory dance game method with customized lyrics, characterized in that: include: Get the keywords entered by the user for customizing lyrics; Extracting basic musical features in the currently selected accompaniment that are associated with lyrics generation; Generate lyrics requirements according to the basic music features and the keywords; According to the lyrics requirement, lyrics matching the accompaniment are generated through a preset natural language model; The generated lyrics are combined with the accompaniment to complete the customization of the lyrics.

2. The somatosensory dance game method with customized lyrics as claimed in claim 1, characterized in that: Generating lyrics requirements according to the basic music features and the keywords includes: determining the emotional tone and stylistic type of said accompaniment; Performing sentiment analysis and style classification on the keywords input by the user to determine the sentiment tone and style type of the keywords; Performing compatibility analysis on the emotional tone and style type of the keyword and the emotional tone and style type of the accompaniment; Generate lyrics requirements based on compatibility analysis results.

3. The somatosensory dance game method with customized lyrics as claimed in claim 2, characterized in that: The compatibility analysis of the emotional tone and style type of the keyword and the emotional tone and style type of the accompaniment includes: Calculating the emotional similarity between the keyword and the accompaniment based on the emotional tone of the accompaniment and the emotional tone of the keyword; Calculating the style similarity between the keyword and the accompaniment based on the style type of the accompaniment and the style type of the keyword; The compatibility of the keyword and the accompaniment is determined according to the emotion similarity and the style similarity.

4. The method for playing a somatosensory dance game with customized lyrics as claimed in claim 3, characterized in that: Generate lyrics requirements based on compatibility analysis results, including: When the emotional similarity is lower than a first preset threshold, calculating the influence coefficient of the emotional tone of the keyword on the basic music feature; When the style similarity is lower than a second preset threshold, calculating the influence coefficient of the style type of the keyword on the basic music feature; Adjusting the basic music features according to the influence coefficient of the emotional tone and / or style type of the keyword; Lyrics requirements are generated based on the adjusted basic music features and the keywords.

5. The somatosensory dance game method with customized lyrics as claimed in claim 4, characterized in that: The basic music features are adjusted according to the influence coefficient based on the following formula: T final =T initial +(T max -T min )×α; Among them, T final is the eigenvalue of the adjusted basic music feature; T initial is the initial feature value of the basic music feature; T max and T min Preset maximum and minimum values ​​for basic music characteristics; α is the influence coefficient of emotional tone or style type.

6. The method for playing a somatosensory dance game with customized lyrics as claimed in claim 4, characterized in that: Generate lyrics requirements based on compatibility analysis results, including: When the emotion similarity is higher than a first preset threshold, and the style similarity is higher than a second preset threshold, lyrics requirements are generated according to the basic music features and the keywords.

7. The somatosensory dance game method with customized lyrics according to any one of claims 4 to 6, characterized in that: Generate lyrics requirements based on basic music features and keywords, including: Determining the structural requirements of the lyrics according to the basic characteristics of the music, wherein the structural requirements include at least one of sentence pattern, rhythm, segmentation, and emotional progression; Determining the content requirements of the lyrics based on the keywords; The lyrics requirement is generated according to the structural requirement and the content requirement.

8. The method for playing a somatosensory dance game with customized lyrics as claimed in claim 7, characterized in that: Determining the content requirements of the lyrics based on the keywords includes: Performing semantic expansion and sentiment optimization on the keywords to generate an expanded keyword set; Determining the priority of keywords in the keyword set; Determining the position distribution of the keywords in the lyrics according to the music structure of the accompaniment and the priority of the keywords; Based on the keyword set and the position distribution, the content requirements of the lyrics are generated.

9. A somatosensory dance game device with customized lyrics, characterized in that: The invention comprises a memory, a processor and a somatosensory dance game program with custom lyrics stored in the memory and executable on the processor, wherein the processor implements the somatosensory dance game method with custom lyrics as described in any one of claims 1 to 8 when executing the somatosensory dance game program with custom lyrics.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a somatosensory dance game program with customized lyrics, and when the somatosensory dance game program with customized lyrics is executed by a processor, the somatosensory dance game method with customized lyrics as described in any one of claims 1-8 is implemented.

Images