Music generation method, device, computer equipment and storage medium

Abstract

This application relates to a music generation method, apparatus, computer device, storage medium, and computer program product. The method includes: acquiring historical sleep data and original music from a target user, the historical sleep data reflecting the target user's sleep habits; generating at least one music production parameter for the target user based on the historical sleep data; adjusting the original music according to the at least one music production parameter to obtain target music that matches the target user's sleep habits; adjusting the music playback parameters of the target music according to the target user's current sleep process while the target music is played, obtaining adjusted music playback parameters; and controlling the playback of the target music using the adjusted music playback parameters. This method can improve the music generation effect.

Description

Technical Field

[0001] This application relates to the field of music generation technology, and in particular to a music generation method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] With the improvement of living standards, sleep-aid music has gradually become a focus of attention in people's daily lives. As a type of functional music, sleep-aid music differs from traditional music; it mainly serves as supplementary music to help users relax their mind and body and fall asleep.

[0003] Currently, users can customize sleep-aid music according to their needs through music apps. However, existing sleep-aid music customization methods are usually generated by overlaying music and white noise, and most sleep-aid music customization technologies only provide interfaces for music playback time and music playback scenarios. Although they can provide users with the function of customizing sleep-aid music, they cannot meet users' more refined customization needs. The generated sleep-aid music cannot closely match the user's actual needs and cannot accurately provide sleep assistance.

[0004] Therefore, traditional techniques suffer from poor music generation results. Summary of the Invention

[0005] Therefore, it is necessary to provide a music generation method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the music generation effect in response to the above-mentioned technical problems.

[0006] A music generation method, comprising:

[0007] Acquire the target user's historical sleep data and original music; the historical sleep data is used to reflect the target user's sleep habits.

[0008] Based on historical sleep data, generate at least one music production parameter for the target user; the music production parameter includes at least one of the following: music structure information, note density, white noise mixing ratio, and music tempo.

[0009] The original music is adjusted according to at least one music production parameter to obtain target music that matches the sleep habits of the target user;

[0010] During the process of playing target music in accordance with the target user's current sleep process, the music playback parameters of the target music are adjusted according to the target user's current sleep data to obtain the adjusted music playback parameters, which include at least one of note density, low-pass filter cutoff frequency, and music tempo; and the playback of the target music is controlled using the adjusted music playback parameters.

[0011] In one exemplary embodiment, historical sleep data includes sleep onset time, which characterizes the time required for a target user to transition from the waking phase of a sleep cycle to the core sleep phase. Based on the historical sleep data, at least one music production parameter is generated for the target user, including:

[0012] Obtain the musical structure information of the original music; the musical structure information includes the number of units in the prelude, the number of units in the main body, and the number of units in the coda.

[0013] The number of units in the prelude of the original music is determined as the number of units in the prelude of the target music. The number of units in the coda of the original music is determined as the number of units in the coda of the target music. The number of units in the main body of the original music is adjusted according to the time of falling asleep to obtain the number of units in the main body of the target music.

[0014] The number of musical phrases in the prelude, the main body, and the coda of the target music are used to represent the musical structure information of the target music.

[0015] In one exemplary embodiment, the number of musical phrases corresponding to the main section of the original music is adjusted according to the sleep time to obtain the number of musical phrases per musical phrase of the main section of the target music, including:

[0016] Determine the duration of the prelude and the duration of the coda in the original music; subtract the duration of the prelude and the duration of the coda from the time you fall asleep to obtain the duration of the main section of the target music.

[0017] The number of musical phrases in the main section of the target music is determined based on the musical duration of the main section and the preset unit phrase duration.

[0018] In one exemplary embodiment, historical sleep data includes the proportion of deep sleep in the target user's sleep cycles; based on the historical sleep data, at least one music production parameter is generated for the target user, including:

[0019] Based on the preset mapping relationship between the proportion of deep sleep and the initial density of musical notes, the proportion of deep sleep in the target user's sleep cycle is mapped to the note density of the target music.

[0020] In one exemplary embodiment, historical sleep data includes the proportion of REM (Rapid Eye Movement) time during the target user's sleep cycles; based on the historical sleep data, at least one music production parameter is generated for the target user, including:

[0021] Based on the preset mapping relationship between the REM time ratio and the white noise mixing ratio, the REM time ratio in the target user's sleep cycle is mapped to the white noise mixing ratio of the target music.

[0022] In one exemplary embodiment, historical sleep data includes the target user's heart rate and respiratory rate signals during historical sleep onset processes, which are the target user's transition from the waking phase to the core sleep phase of the sleep cycle.

[0023] Based on historical sleep data, generate at least one music production parameter for the target user, including:

[0024] Based on the target user's heart rate and respiratory rate signals during historical sleep processes, music speed adjustment information is determined, including the adjustment amplitude and direction.

[0025] The tempo of the original music is adjusted based on the tempo adjustment information to obtain the tempo of the target music.

[0026] In an exemplary embodiment, the current sleep data includes the current playback time of the target music; adjusting the music playback parameters of the target music based on the target user's current sleep data to obtain the adjusted playback parameters includes:

[0027] Obtain the curve showing the relationship between note density and music playback time, where the curve is a decreasing function.

[0028] Substitute the current playback time of the target music and the note density of the target music into the change relationship curve to obtain the adjusted note density of the target music.

[0029] In one exemplary embodiment, the current sleep data includes the current playback time of the target music; adjusting the music playback parameters of the target music based on the target user's current sleep data to obtain the adjusted music playback parameters includes:

[0030] Obtain the curve showing the relationship between the cutoff frequency of the low-pass filter and the music playback time, where the curve is a decreasing function curve.

[0031] Substitute the current playback time of the target music and the low-pass filter cutoff frequency of the target music into the change relationship curve to obtain the adjusted low-pass filter cutoff frequency of the target music.

[0032] In an exemplary embodiment, the current sleep data includes the current playback time of the target music, the target user's heart rate signal, and respiratory rate signal at the current playback time; adjusting the music playback parameters of the target music based on the target user's current sleep data to obtain the adjusted playback parameters includes:

[0033] Based on the target user's heart rate and respiratory rate signals at the current playback time, music speed adjustment information is determined, including the adjustment magnitude and direction.

[0034] The tempo of the target music is adjusted based on the tempo adjustment information to obtain the adjusted tempo of the target music.

[0035] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0036] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described above.

[0037] A computer program product includes a computer program that, when executed by a processor, implements the steps of the method described above.

[0038] The aforementioned music generation method, apparatus, computer equipment, storage medium, and computer program product acquire the target user's historical sleep data and original music, with the historical sleep data reflecting the target user's sleep habits. Based on the historical sleep data, at least one music production parameter is generated for the target user. The original music is adjusted according to the at least one music production parameter to obtain target music that matches the target user's sleep habits. During the playback of the target music following the target user's current sleep process, the music playback parameters of the target music are adjusted according to the target user's current sleep data to obtain the adjusted music playback parameters. In this way, by combining the target user's historical sleep data and controlling each music production parameter, a large number of diverse and personalized music can be created compared to the limited types of music created manually. This achieves the adaptive generation of target music with a music playback effect that matches the target user's sleep habits before music playback. Furthermore, after adaptively generating the target music based on the user's historical sleep data, the music playback parameters of the target music can be adjusted in real time based on the target user's current sleep data during the current sleep process. This achieves the adaptive adjustment of the target music to music with a music playback effect that matches the target user's current sleep state after music playback, which can accurately and efficiently improve the music generation effect of sleep-aid music. Attached Figure Description

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 This is a diagram illustrating the application environment of a music generation method in one embodiment.

[0041] Figure 2 This is a flowchart illustrating a music generation method in one embodiment;

[0042] Figure 3 This is a schematic diagram of a data interaction control technology framework for a music production parameter during the generation process, as described in one embodiment.

[0043] Figure 4 This is a schematic diagram of an overall framework for music generation in one embodiment;

[0044] Figure 5 This is a schematic diagram of the processing logic of a sleep time control module in one embodiment;

[0045] Figure 6 This is a schematic diagram illustrating the generation of a sleep-time control music structure in one embodiment.

[0046] Figure 7 This is a schematic diagram of a sleep structure in one embodiment;

[0047] Figure 8 This is a schematic diagram of the processing logic of a sleep structure processing module in one embodiment;

[0048] Figure 9 This is a schematic diagram of the processing logic of a human rhythm processing module in one embodiment;

[0049] Figure 10 This is a schematic diagram of the processing logic of an automation control module in one embodiment;

[0050] Figure 11 This is a flowchart illustrating a music generation method in another embodiment;

[0051] Figure 12 This is a structural block diagram of a music generation device in one embodiment;

[0052] Figure 13 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0053] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0054] The music generation method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 acquires the target user's historical sleep data and original music. The historical sleep data reflects the target user's sleep habits. Based on the historical sleep data, terminal 102 generates at least one music production parameter for the target user, including at least one of music structure information, note density, white noise mixing ratio, and music tempo. Terminal 102 adjusts the original music according to the at least one music production parameter to obtain target music that matches the target user's sleep habits. While the target music plays according to the target user's current sleep process, terminal 102 adjusts the music playback parameters of the target music according to the target user's current sleep data to obtain adjusted music playback parameters, including at least one of note density, low-pass filter cutoff frequency, and music tempo. The adjusted music playback parameters are then used to control the playback of the target music. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc.

[0055] In an exemplary embodiment, Figure 2 As shown, a music generation method is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 202 to 206. Wherein:

[0056] Step 202: Obtain the target user's historical sleep data and original music. The historical sleep data is used to reflect the target user's sleep habits.

[0057] The target users can be those who require customized music generation. Historical sleep data reflects a user's historical sleep habits; therefore, it is obtained by collecting and analyzing various data points from multiple sleep episodes throughout the user's history. One way the terminal obtains historical sleep data is by collecting and analyzing data from multiple sleep episodes; another way is by acquiring it from the user's wearable device; yet another way is by obtaining historical sleep data input by the user. The original music can be sleep-inducing music with unadjusted music production parameters.

[0058] Step 204: Based on historical sleep data, generate at least one music production parameter for the target user.

[0059] Among these, music production parameters can be used to generate target music with playback effects that match the sleep habits of the target user. Music production parameters refer to the parameters used to control music generation. For example, music production parameters may include music structure information, music duration, sound effects, playback speed, white noise mixing ratio, note density, and other parameters.

[0060] Step 206: Adjust the original music according to at least one music production parameter to obtain target music that matches the sleep habits of the target user.

[0061] Among them, target music can be used to play during the target user's sleep. Target music refers to music that is finally customized by the target user according to their own music customization needs.

[0062] Step 208: While the target music is playing in accordance with the target user's current sleep process, adjust the music playback parameters of the target music according to the target user's current sleep data to obtain the adjusted music playback parameters; and use the adjusted music playback parameters to control the playback of the target music.

[0063] The current sleep data reflects the user's current sleep state; therefore, it is collected in real-time from various data points during the target user's current sleep process. The music playback parameters refer to the parameters used to control music playback; for example, these parameters may include note density, low-pass filter cutoff frequency, and tempo.

[0064] In the aforementioned music generation method, the historical sleep data of the target user and the original music are obtained, with the historical sleep data reflecting the target user's sleep habits. Based on the historical sleep data, at least one music production parameter is generated for the target user. The original music is adjusted according to the at least one music production parameter to obtain target music that matches the target user's sleep habits. During the playback of the target music following the target user's current sleep process, the music playback parameters of the target music are adjusted according to the target user's current sleep data to obtain the adjusted music playback parameters. In this way, the music production parameters can be controlled by combining the target user's historical sleep data. Compared with the limited types of music created manually, a large number of diverse and personalized music can be created. This achieves the adaptive generation of target music with a music playback effect that matches the target user's sleep habits before music playback. Furthermore, after adaptively generating the target music based on the user's historical sleep data, the music playback parameters of the target music can be adjusted in real time based on the target user's current sleep data during the current sleep process. This achieves the adaptive adjustment of the target music to a music playback effect that matches the target user's current sleep state after music playback, which can accurately and efficiently improve the music generation effect of sleep-aid music.

[0065] Figure 3 An exemplary data interaction control technology framework for sleep-aid music is provided. This framework involves inputting the target user's historical sleep data (e.g., sleep onset time, deep sleep percentage, REM sleep duration percentage, historical heart rate, historical respiratory rate) and current sleep data (e.g., current heart rate, current respiratory rate, music playback time) into a sleep-aid music generation model (comprising four modules: sleep onset time control, circadian rhythm control, sleep structure control, and automation control). Based on the historical sleep data, music production parameters tailored to the target user can be generated, thus producing sleep-aid music (target music). Furthermore, the music playback parameters can be adjusted during playback based on the current sleep data. This solution adaptively generates sleep-aid music based on the target user's sleep structure and circadian rhythm information, ensuring diversity in the generated music. It also incorporates sleep science principles into the music generation logic, making the generated music more aligned with the user's sleep habits and thus better aiding sleep. Moreover, the generation of music production parameters across multiple modules ensures that the generated target music can be adjusted in real-time according to user needs, improving the user experience. The generation logic of music production parameters in each module of the sleep-aid music generation model will be explained in detail in the following embodiments.

[0066] In an exemplary embodiment, historical sleep data includes sleep onset time, which characterizes the time required for a target user to transition from the waking phase to the core sleep phase of their sleep cycle. Based on the historical sleep data, at least one music production parameter is generated for the target user, including: obtaining the music structure information of the original music; wherein the music structure information includes the number of units in the intro, the number of units in the main body, and the number of units in the outro; determining the number of units in the intro of the original music as the number of units in the intro of the target music, determining the number of units in the outro of the original music as the number of units in the outro of the target music, and adjusting the number of units in the main body of the original music according to the sleep onset time to obtain the number of units in the main body of the target music; wherein the number of units in the intro, the main body, and the outro of the target music are used to represent the music structure information of the target music.

[0067] Musical structure information refers to the composition of music. In practical applications, it can refer to the duration of the intro, main bodies, and outro sections, as well as the number of musical units corresponding to each section. A musical unit can be represented as a phase, and a musical unit as a section. The number of musical units refers to the number of sections that make up a phase. Each musical unit has the same duration (which can be a preset duration), therefore, the duration of each musical unit is determined by the number of musical units it contains.

[0068] In practical applications, the duration of different musical sections can be adjusted by determining the number of musical phrases per section, thereby adjusting the duration of the entire piece of music. In one embodiment, since the prelude and coda of the target music and the original music have the same duration, the number of musical phrases per section of the main body of the target music can be used to control the duration of the target music.

[0069] In this embodiment, by acquiring the musical structure information of the original music, the number of units per phrase in the intro, the main body, and the outro of the original music is determined. Then, keeping the number of units per phrase in the intro and outro unchanged, only the number of units per phrase in the main body of the original music is adjusted based on the sleep time to obtain the number of units per phrase in the main body of the target music. The adjusted number of units per phrase in the main body is used to adjust the duration of the main body of the target music. By using this musical structure information—the number of units per phrase in the main body of the target music—as a music production parameter, the duration of the generated target music can be controlled. It can be seen that this embodiment can adaptively generate the musical structure of the target music by combining the target user's sleep process and the musical structure information of the original music, thus assisting in the subsequent generation of the target music.

[0070] In an exemplary embodiment, the number of unit phrases corresponding to the main section of the original music is adjusted according to the sleep time to obtain the number of unit phrases of the main section of the target music, including: determining the music duration of the intro section and the music duration of the outro section in the original music; subtracting the music duration of the intro section and the music duration of the outro section from the sleep time to obtain the music duration of the main section of the target music; and determining the number of unit phrases of the main section of the target music based on the music duration of the main section of the target music and the preset unit phrase duration.

[0071] In practical applications, the length of the intro section is obtained by multiplying the number of units in the intro section by the preset unit length of the intro section. The length of the intro section in the original music is obtained by multiplying the number of units in the outro section by the preset unit length of the outro section. The length of the outro section in the original music is obtained by subtracting the length of the intro section and the length of the outro section from the time the music falls asleep. The remaining length is determined as the length of the main section in the target music. The length of the main section in the target music is divided by the preset unit length of the main section to obtain the music production parameter of the number of units in the main section of the target music.

[0072] For the convenience of those skilled in the art, Figure 4 A schematic diagram of the overall framework for music generation is provided, in which the entire piece of music includes a prelude (Intro), main bodies, and an outro. Each body includes several phases, and each phase includes several sections.

[0073] In practical applications, a mapping relationship can be established between the cycle of sleep-aiding music and the time it takes to fall asleep, thus enabling the creation of music loop processing logic (such as...). Figure 5 This means that the music loop processing logic (corresponding to the sleep time control module) adaptively generates the structure information of sleep-aid music based on the sleep time and the structure information of the original music, thereby assisting in the generation of sleep-aid music. Figure 6 This provides an exemplary schematic diagram of generating a music structure for controlling sleep time. Figure 6 This example shows two target music tracks generated when the target user sets a total music playback duration of 20 minutes. The two target music tracks are 15 minutes and 5 minutes long respectively. Both tracks have a one-strand intro and a two-strand outro. Comparing the two tracks reveals that the intro and outro are of fixed length, and the overall music duration depends only on the number of strides in the main body. Because the intro and outro are highly functional and each consists of only one phase (a phase may include multiple sections), they are typically set to fixed length by default in target music. In other words, for different sleep durations, only the length of the main body changes. Assuming the duration of a section (the length of a unit section) is Section_duration and the sleep time is LoopTime, the number of sections in the main body is calculated as follows: main_body.section_num = (LoopTime - (Intro.section_num + Outros.section_num) * Section_duration) / Section_duration; where main_body.section_num is the number of sections in the main body, LoopTime is the sleep time, Intro.section_num is the number of sections in the intro section, and Outros.section_num is the number of sections in the outro section.

[0074] In this embodiment, the duration of the intro and outro in the original music is used as the duration of the intro and outro in the target music. Then, the duration of the intro and outro is subtracted from the time of falling asleep to obtain the duration of the main section of the target music. The duration of the main section of the target music is then divided by the number of units of musical phrases to accurately determine the number of units of musical phrases in the main section of the target music, which is used as a music production parameter, thereby facilitating accurate control of the duration of the target music.

[0075] For the convenience of those skilled in the art, Figure 7 An exemplary sleep cycle diagram is provided, wherein the sleep cycle includes four stages: wakefulness, deep sleep, core sleep (i.e., light sleep), and REM sleep. This embodiment selects the deep sleep ratio and the REM sleep time ratio to generate music production parameters. The deep sleep ratio is the ratio of deep sleep time to total sleep time, and the REM sleep time ratio is the ratio of REM sleep time to total sleep time. In practical applications, the wakefulness ratio and the core sleep ratio can also be used as the basis for generating music production parameters. The wakefulness ratio is the ratio of wakefulness time to total sleep time in the sleep cycle, and the core sleep ratio is the ratio of light sleep time to total sleep time in the sleep cycle. Figure 8 As shown, this embodiment of the application determines the note density and white noise ratio based on the deep sleep ratio (DSleepRatio) and the rapid eye movement time ratio (DreamRatio) using a sleep structure processing module. This embodiment selects two sleep data points: the deep sleep ratio (DSleepRatio) and the rapid eye movement time ratio (DreamRatio). Since a low deep sleep ratio or a high rapid eye movement time ratio indicates poor sleep quality, some music-related parameters are adjusted accordingly. The process of generating music production parameters based on the deep sleep ratio (DSleepRatio) and the rapid eye movement time ratio (DreamRatio) can be seen in the following two embodiments.

[0076] In an exemplary embodiment, historical sleep data includes the proportion of deep sleep in the target user's sleep cycles. Based on the historical sleep data, at least one music production parameter is generated for the target user, including: mapping the proportion of deep sleep in the target user's sleep cycles to the note density of the target music based on a preset mapping relationship between the proportion of deep sleep and note density. Note density is used to characterize the density of notes in the target music. The note density in this embodiment can be called the starting note density, i.e., the note density used to generate the target music, or it can be understood as the note density included in the music production parameters.

[0077] Among them, the preset mapping relationship between the deep sleep ratio and the note density can characterize the numerical correlation between the deep sleep ratio and the note density. The deep sleep ratio can be the ratio of deep sleep to sleep duration.

[0078] In one embodiment, the preset mapping relationship between the deep sleep ratio and the note density can be expressed as: DensityStart = k1 * DSleepRatio + b; where k1 > 0, which is a ratio coefficient that controls the preset mapping relationship between the deep sleep ratio and the note density, DensityStart is the note density, and DSleepRatio is the deep sleep ratio.

[0079] In practical applications, if the proportion of deep sleep is too low, it's necessary to reduce the "density" of the music, meaning the generated musical notes should be less dense and the sound field less full. Therefore, the performance effect of the target music is controlled by adjusting the note density (DensityStart). For example, the formula for calculating the note density of the target music is: DensityStart = k1*DSleepRatio+b; where k1 > 0, serving as a proportional coefficient to control the mapping relationship. This formula represents a positive relationship between the proportion of deep sleep and note density. The specific calculation formula depends on the actual situation; the lower the proportion of deep sleep, the lower the note density. If DensityStart exceeds the standard range, the indicator is considered invalid and adjusted to the default value.

[0080] This embodiment uses a preset mapping relationship between the proportion of deep sleep and the density of musical notes to obtain the corresponding musical note density for the target user, and then uses this musical note density to generate the target music for the target user. This preset mapping relationship is a positive relationship. It can be understood that if the proportion of deep sleep of the target user is too low, music with less dense musical notes can be generated, so that the sound field of the generated target music is not too full, thereby generating target music with a music playback effect that matches the sleep quality of the target user.

[0081] To provide a better sleep aid effect, the note density of the target music can be adaptively adjusted as the playback duration changes while playing the target user's current sleep process. See the next embodiment for a specific method.

[0082] In an exemplary embodiment, the current sleep data includes the current playback time of the target music; adjusting the music playback parameters of the target music according to the current sleep data of the target user to obtain the adjusted playback parameters includes: obtaining the change relationship curve between note density and music playback time, wherein the change relationship curve is a decreasing function curve; substituting the current playback time of the target music and the note density of the target music into the change relationship curve to obtain the adjusted note density of the target music.

[0083] The current playback time can refer to any moment when the target music is being played.

[0084] In practical applications, the note density of the target music should gradually decrease as sleep deepens. Therefore, one way to adjust the note density of the target music is to use a decreasing function (corresponding to the curve showing the change in note density versus music playback time). In one specific implementation, the relationship between the adjusted note density and the original note density is: Density = DensityStart * e^(-k4t); where Density is the adjusted note density, DensityStart is the music density of the target music (obtained from the deep sleep ratio), k4 is the control parameter of the curve, and t is the music playback time. It can be understood that Density = DensityStart * e^(-k4t) is a decreasing function; as the music playback time increases, the adjusted note density Density decreases.

[0085] In this embodiment, the note density decreases as the playback duration increases to accommodate the user's sleep process.

[0086] In an exemplary embodiment, historical sleep data includes the proportion of REM (Rapid Eye Movement) time in the sleep cycle of the target user; based on the historical sleep data, at least one music production parameter is generated for the target user, including: mapping the proportion of REM time in the sleep cycle of the target user to the white noise mixing ratio of the target music based on a preset mapping relationship between REM time and white noise mixing ratio.

[0087] The preset mapping relationship between the rapid eye movement time ratio and the white noise mixing ratio represents the numerical correlation between the rapid eye movement time ratio and the white noise mixing ratio.

[0088] The white noise mixing ratio can be the proportion of white noise (natural soundscape) in the target music.

[0089] In one embodiment, the preset mapping relationship between the rapid eye movement time ratio and the white noise mixing ratio can be expressed as: NoiseRatio = DreamRatio * k2 + b; where k2 > 0, serving as a scaling factor to control the second mapping relationship, NoiseRatio is the white noise mixing ratio, and DreamRatio is the rapid eye movement time ratio. This calculation formula represents a positive relationship between the rapid eye movement time ratio and the white noise mixing ratio. The specific calculation formula depends on the actual situation; when the rapid eye movement time ratio is higher, the white noise mixing ratio is higher.

[0090] In practical applications, a high REM (Rapid Eye Movement) ratio indicates that the user is dreaming more, which can negatively impact sleep quality. Therefore, the ratio of target music to white noise will be controlled in the final mixing stage. The parameter controlling the white noise mixing ratio is called NoiseRatio, which corresponds to the mixing ratio of white noise (natural soundscape). For example, the calculation method for the white noise mixing ratio of the target music is: NoiseRatio = DreamRatio * k2 + b, where k2 > 0, serving as a ratio coefficient to control the mapping relationship. If NoiseRatio exceeds the standard range, the indicator is considered invalid and adjusted to the default value.

[0091] This embodiment uses a preset mapping relationship between the REM (Rapid Eye Movement Time) ratio and the white noise mixing ratio to obtain the white noise mixing ratio corresponding to the target user, and then uses this white noise mixing ratio to generate the target music for the target user. This preset mapping relationship is positive; that is, if the target user has a high REM ratio or experiences frequent dreaming, the proportion of white noise in the target music can be increased, making the generated target music sound stream more stable and peaceful, thus generating target music with a playback effect that better matches the target user's sleep quality.

[0092] In an exemplary embodiment, historical sleep data includes the target user's heart rate and respiratory rate signals during historical sleep onset, the historical sleep onset being the target user's transition from the wakefulness phase to the core sleep phase of the sleep cycle; based on the historical sleep data, at least one music production parameter is generated for the target user, including: determining music tempo adjustment information based on the target user's heart rate and respiratory rate signals during historical sleep onset, the music tempo adjustment information including adjustment magnitude and adjustment direction; adjusting the tempo of the original music based on the music tempo adjustment information to obtain the tempo of the target music.

[0093] The heart rate signal can be heart rate curve data from the user's historical sleep onset process. The respiratory rate signal can be respiratory rate curve data from the user's historical sleep onset process. The sleep onset process refers to the time from the onset of sleep to entering core sleep (light sleep). The music tempo adjustment information refers to the magnitude and direction of the adjustment to the original music tempo.

[0094] like Figure 9 As shown, the human rhythm processing module can generate a new playback speed based on heart rate, respiratory rate, and playback tempo. This module's processing logic is applicable to two scenarios: generating music tempo in music production parameters (i.e., generating the target music's tempo), and adjusting the target music's tempo.

[0095] In the first scenario, where the heart rate and respiratory rate are the same as those during the historical sleep process, and the playback speed is the original music's playback speed, the resulting new playback speed will be the playback speed included in the music production parameters. Specifically, human circadian rhythms include heart rate (HeartRate) and respiratory rate (BreathFreq). In the control logic of the rhythm processing module, both heart rate and respiratory rate can control the tempo of the generated target music. In simpler terms, when heart rate and respiratory rate decrease, people need more soothing music to aid sleep; therefore, the bpm of the music should decrease accordingly. The playback speed is calculated as follows: relative_bpm = BreathFreq - DefaultBreathFreq + HeartRate – DefaultHeartRate, new_bpm = bpm + relative_bpm; relative_bpm is the music speed adjustment information, BreathFreq is the breathing frequency, DefaultBreathFreq is the default breathing frequency, HeartRate is the heart rate, DefaultHeartRate is the default heart rate, new_bpm is the music speed of the target music, and bpm is the music speed of the original music.

[0096] In the second scenario, where the heart rate and respiratory rate are the same as during the current sleep process, and the playback speed is the same as the target music's playback speed, then the resulting new playback speed is the adjusted playback speed of the target music. See the next embodiment for details.

[0097] In an exemplary embodiment, the current sleep data includes the current playback time of the target music, the target user's heart rate signal and respiratory rate signal at the current playback time; adjusting the music playback parameters of the target music based on the target user's current sleep data to obtain the adjusted playback parameters includes: determining music speed adjustment information based on the target user's heart rate signal and respiratory rate signal at the current playback time, the music speed adjustment information including adjustment magnitude and adjustment direction; adjusting the music speed of the target music based on the music speed adjustment information to obtain the adjusted music speed of the target music.

[0098] In the previous embodiment, music speed adjustment information was determined based on the heart rate and respiratory rate signals of the target user during historical sleep processes. The music speed adjustment information was then used to adjust the speed of the original music, thus obtaining the music speed of the target music as a music production parameter. This enabled the music speed of the target music to be adaptively determined according to the target user's body rhythm, which is beneficial for obtaining more soothing target music and for more accurately assisting the target user's sleep.

[0099] Based on the previous embodiment, this embodiment determines the music speed adjustment information at the current playback time by using the heart rate and respiratory rate signals of the target user during the current sleep process. The music speed adjustment information at the current playback time is then used to adjust the music speed of the target music. The adjusted music speed is then used as the music speed of the target music at the current playback time. This enables the music speed of the target music to be adaptively adjusted in real time according to the target user's current body rhythm, thus providing real-time and precise sleep assistance to the target user.

[0100] In an exemplary embodiment, the current sleep data includes the current playback time of the target music; adjusting the music playback parameters of the target music according to the current sleep data of the target user to obtain the adjusted music playback parameters includes: obtaining the change relationship curve between the low-pass filter cutoff frequency and the music playback time, wherein the change relationship curve is a decreasing function curve; substituting the current playback time of the target music and the low-pass filter cutoff frequency of the target music into the change relationship curve to obtain the adjusted low-pass filter cutoff frequency of the target music.

[0101] The music playback time can be any moment during music playback. The low-pass filter cutoff frequency can refer to a pre-set cutoff frequency for the low-pass filter. By setting the cutoff frequency, high-frequency signals exceeding the cutoff frequency can be filtered out, thus generating a deeper, more resonant sound.

[0102] In practical applications, for music creation, automation control in music production typically refers to the automatic adjustment and control of various parameters (such as volume, sound balance, effects, etc.) within a digital audio workstation (DAW). Automation control allows music producers to precisely adjust these parameters across the entire track or specific sections, enabling more complex and refined music production. For the music generation system in this solution, two particularly effective control parameters are the cutoff frequency (CutFreq) of the low-pass filter in the mixing section and the note density (Density), such as... Figure 10 As shown, the cutoff frequency (CutFreq) and note density of the low-pass filter in the mixing section can be processed by the automated control module to generate the sound effects and note density of the target music. It should be noted that the automated control module is used to determine the note density as it changes over time. Specifically:

[0103] Regarding the cutoff frequency, it should gradually decrease as sleep progresses. The lower the cutoff frequency of the low-pass filter (a type of audio effect), the fewer high-frequency frequencies are output. The relationship between cutoff frequencies is: CutFreq = startCutFreq * e^(-k3t); where startCutFreq and k3 are control parameters of the curve, and t is the music playback time. CutFreq = startCutFreq * e^(-k3t) is a decreasing function; the longer the time, the lower the cutoff frequency CutFreq becomes.

[0104] This embodiment can gradually reduce the cutoff frequency of the low-pass filter according to the target user's sleep time, thereby achieving precise and automated control of the sound effects of the target music, making the target music more suitable for the target user's sleep-aid scenario.

[0105] In an exemplary embodiment, the method further includes: in response to a target user's selection operation for a music genre, obtaining candidate music that matches the music genre selected by the selection operation; and in response to a selection operation for the candidate music, obtaining the candidate music selected by the selection operation as the original music.

[0106] The music genre can refer to subcategories of sleep-aid music, such as high-density, low-density, more natural sounds, less natural sounds, etc. The candidate music can refer to pre-configured default music that matches the music genre.

[0107] In practical applications, the target user selects a music genre, and the terminal can match candidate music based on the selected genre and display it to the target user. The target user then selects one song from the candidate songs, and the terminal uses the selected song as the original music.

[0108] This embodiment can accurately determine the music type that matches the user's preferences by using the interactive information when the user selects the music type. This is beneficial for subsequent optimization of the original music using various music production parameters to generate target music that matches the user's preferences.

[0109] In another embodiment, such as Figure 11 As shown, a music generation method is provided, which can be applied to... Figure 1 Taking the terminal 102 in FIG. 1 as an example, the method includes the following steps:

[0110] Step S1102: Obtain the target user's historical sleep data and original music. The historical sleep data is used to reflect the target user's sleep habits.

[0111] Step S1104: Based on historical sleep data, generate at least one music production parameter for the target user; wherein the music production parameter includes at least one of music structure information, note density, white noise mixing ratio, and music tempo.

[0112] Step S1106: Adjust the original music according to at least one music production parameter to obtain target music that matches the sleep habits of the target user.

[0113] Step S1108: During the process of playing the target music following the target user's current sleep process, music speed adjustment information is determined based on the target user's heart rate signal and respiratory rate signal at the current playback time. The music speed adjustment information includes the adjustment amplitude and adjustment direction.

[0114] Step S1110: Adjust the speed of the target music based on the music speed adjustment information to obtain the adjusted speed of the target music; and use the adjusted speed to control the playback of the target music.

[0115] It should be noted that the specific limitations of the above steps can be found in the specific limitations of a music generation method described above.

[0116] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0117] Based on the same inventive concept, this application also provides a music generation apparatus for implementing the music generation method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more music generation apparatus embodiments provided below can be found in the limitations of the music generation method described above, and will not be repeated here.

[0118] In an exemplary embodiment, Figure 12 As shown, a music generation device is provided, including: an acquisition module 1202, a generation module 1204, an adjustment module 1206, and a control module 1208, wherein:

[0119] Module 1202 acquires the target user's historical sleep data and original music. The historical sleep data is used to reflect the target user's sleep habits.

[0120] The generation module 1204 generates at least one music production parameter for the target user based on historical sleep data; wherein the music production parameter includes at least one of the following: music structure information, note density, white noise mixing ratio, and music tempo.

[0121] The adjustment module 1206 adjusts the original music according to at least one music production parameter to obtain target music that matches the sleep habits of the target user.

[0122] The control module 1208 adjusts the music playback parameters of the target music based on the target user's current sleep data during the playback of the target music. The music playback parameters include at least one of note density, low-pass filter cutoff frequency, and music tempo. The control module 1208 also controls the playback of the target music using the adjusted music playback parameters.

[0123] In an exemplary embodiment, historical sleep data includes sleep onset time, which represents the time required for a target user to transition from the waking phase to the core sleep phase of their sleep cycle. The generation module 1204 is specifically used to acquire the musical structure information of the original music. This musical structure information includes the number of units in the intro, the number of units in the main body, and the number of units in the outro. The number of units in the intro of the original music is determined as the number of units in the intro of the target music, the number of units in the outro of the original music is determined as the number of units in the outro of the target music, and the number of units in the main body of the original music is adjusted according to the sleep onset time to obtain the number of units in the main body of the target music. The number of units in the intro, the main body, and the outro of the target music represent the musical structure information of the target music.

[0124] In an exemplary embodiment, the generation module 1204 is specifically used to determine the music duration of the prelude and the coda in the original music; subtract the music duration of the prelude and the coda from the sleep time to obtain the music duration of the main section of the target music; and determine the number of units of the main section of the target music based on the music duration of the main section and the preset unit length.

[0125] In an exemplary embodiment, the historical sleep data includes the proportion of deep sleep in the sleep cycle of the target user. The generation module 1204 is specifically used to map the proportion of deep sleep in the sleep cycle of the target user to the note density of the target music based on a preset mapping relationship between the proportion of deep sleep and the note density.

[0126] In an exemplary embodiment, the historical sleep data includes the proportion of rapid eye movement (REM) time in the sleep cycle of the target user. The generation module 1204 is specifically used to map the proportion of REM time in the sleep cycle of the target user to the proportion of white noise mixing of the target music based on a preset mapping relationship between the proportion of REM time and the proportion of white noise mixing.

[0127] In an exemplary embodiment, historical sleep data includes the target user's heart rate and respiratory rate signals during historical sleep onset. The historical sleep onset process is from the target user's awake stage to the core sleep stage of the sleep cycle. The generation module 1204 is specifically used to determine music tempo adjustment information based on the target user's heart rate and respiratory rate signals during historical sleep onset. The music tempo adjustment information includes the adjustment magnitude and adjustment direction. Based on the music tempo adjustment information, the music tempo of the original music is adjusted to obtain the music tempo of the target music.

[0128] In an exemplary embodiment, the current sleep data includes the current playback time of the target music. The control module 1208 is specifically used to obtain the change relationship curve between note density and music playback time, wherein the change relationship curve is a decreasing function curve; and to substitute the current playback time of the target music and the note density of the target music into the change relationship curve to obtain the adjusted note density of the target music.

[0129] In an exemplary embodiment, the current sleep data includes a target music current playback time control module 1208, which is specifically used to obtain the change relationship curve between the low-pass filter cutoff frequency and the music playback time, wherein the change relationship curve is a decreasing function curve; the target music current playback time and the target music low-pass filter cutoff frequency are substituted into the change relationship curve to obtain the adjusted low-pass filter cutoff frequency of the target music.

[0130] In an exemplary embodiment, the current sleep data includes the current playback time of the target music, the target user's heart rate signal and respiratory rate signal at the current playback time, and the control module 1208 is specifically used to determine music speed adjustment information based on the target user's heart rate signal and respiratory rate signal at the current playback time. The music speed adjustment information includes the adjustment magnitude and adjustment direction. The music speed is adjusted based on the music speed adjustment information to obtain the adjusted music speed of the target music.

[0131] Each module in the aforementioned music generation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0132] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 13As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores music generation data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a music generation method.

[0133] Those skilled in the art will understand that Figure 13 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0134] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the music generation method described above. The steps of the music generation method described here can be steps from one of the music generation methods in the various embodiments described above.

[0135] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the steps of the music generation method described above. The steps of the music generation method described here may be steps from one of the music generation methods in the various embodiments described above.

[0136] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, causes the processor to perform the steps of the music generation method described above. The steps of the music generation method described here may be steps from one of the music generation methods in the various embodiments described above.

[0137] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0138] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0139] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0140] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for generating music, characterized in that, The method includes: Obtain the target user's historical sleep data, which is used to reflect the target user's sleep habits; Based on the historical sleep data, at least one music production parameter is generated for the target user; wherein the music production parameter includes at least one of music structure information, note density, white noise mixing ratio, and music tempo. The original music is acquired and adjusted according to at least one music production parameter to obtain target music that matches the sleep habits of the target user. During the playback of the target music following the target user's current sleep process, the music playback parameters of the target music are adjusted according to the target user's current sleep data to obtain adjusted music playback parameters, wherein the music playback parameters include at least one of note density, low-pass filter cutoff frequency, and music tempo; and the playback of the target music is controlled using the adjusted music playback parameters.

2. The method according to claim 1, characterized in that, The historical sleep data includes sleep onset time, which represents the time required for the target user to transition from the waking phase to the core sleep phase of the sleep cycle. The step of generating at least one music production parameter for the target user based on the historical sleep data includes: Obtain the musical structure information of the original music; wherein the musical structure information of the original music includes the number of units of the prelude, the number of units of the main body, and the number of units of the coda. The number of units of the intro section of the original music is determined as the number of units of the intro section of the target music, the number of units of the outro section of the original music is determined as the number of units of the outro section of the target music, and the number of units of the main section of the original music is adjusted according to the sleep time to obtain the number of units of the main section of the target music. The number of musical phrases in the prelude, the number of musical phrases in the main body, and the number of musical phrases in the coda of the target music are used to represent the musical structure information of the target music.

3. The method according to claim 2, characterized in that, The step of adjusting the number of musical phrases corresponding to the main section of the original music based on the sleep time to obtain the number of musical phrases per musical phrase of the target music includes: Determine the duration of the prelude and the duration of the coda in the original music; and subtract the duration of the prelude and the duration of the coda from the time the music falls asleep to obtain the duration of the main section of the target music. The number of musical phrases in the main section of the target music is determined based on the music duration of the main section and the preset unit phrase duration.

4. The method according to claim 1, characterized in that, The historical sleep data includes the proportion of deep sleep in the target user's sleep cycles; generating at least one music production parameter for the target user based on the historical sleep data includes: Based on a preset mapping relationship between the proportion of deep sleep and the density of musical notes, the proportion of deep sleep in the sleep cycle of the target user is mapped to the density of musical notes in the target music.

5. The method according to claim 1, characterized in that, The historical sleep data includes the proportion of REM (Rapid Eye Movement) time during the target user's sleep cycles; the step of generating at least one music production parameter for the target user based on the historical sleep data includes: Based on a preset mapping relationship between the rapid eye movement (REM) time ratio and the white noise mixing ratio, the REM time ratio of the target user's sleep cycle is mapped to the white noise mixing ratio of the target music.

6. The method according to claim 1, characterized in that, The historical sleep data includes the target user's heart rate and respiratory rate signals during the historical sleep onset process, which is the target user's sleep cycle from the waking stage to the core sleep stage. The step of generating at least one music production parameter for the target user based on the historical sleep data includes: Based on the heart rate signal and respiratory rate signal of the target user during the historical sleep process, music speed adjustment information is determined, including adjustment amplitude and adjustment direction. The tempo of the original music is adjusted based on the tempo adjustment information to obtain the tempo of the target music.

7. The method according to claim 1, characterized in that, The current sleep data includes the current playback time of the target music; adjusting the music playback parameters of the target music based on the target user's current sleep data to obtain the adjusted music playback parameters includes: Obtain the curve showing the relationship between note density and music playback time, wherein the curve is a decreasing function curve; Substitute the current playback time of the target music and the note density of the target music into the change relationship curve to obtain the adjusted note density of the target music.

8. The method according to claim 1, characterized in that, The current sleep data includes the current playback time of the target music; adjusting the music playback parameters of the target music based on the target user's current sleep data to obtain the adjusted music playback parameters includes: Obtain the curve showing the relationship between the cutoff frequency of the low-pass filter and the music playback time, wherein the curve is a decreasing function curve; Substitute the current playback time of the target music and the low-pass filter cutoff frequency of the target music into the change relationship curve to obtain the adjusted low-pass filter cutoff frequency of the target music.

9. The method according to claim 1, characterized in that, The current sleep data includes the current playback time of the target music, the target user's heart rate signal, and respiratory rate signal at the current playback time; adjusting the music playback parameters of the target music based on the target user's current sleep data to obtain the adjusted music playback parameters includes: Based on the target user's heart rate and respiratory rate signals at the current playback time, music speed adjustment information is determined, including adjustment magnitude and adjustment direction. Based on the music tempo adjustment information, the music tempo of the target music is adjusted to obtain the adjusted music tempo of the target music.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images