Optimal sleep-aiding music selection method and related equipment thereof
By building a music database and using neural networks to process the user's brainwave response characteristics, the most suitable sleep-aiding music is determined, which solves the problem of imprecise music style label classification in existing technologies and achieves more accurate sleep-aiding music selection.
Patent Information
- Application Number
- CN202510703270.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-29
- Publication Date
- 2025-09-09
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing sleep-aid music selection method is not detailed enough through music style label classification, and cannot accurately provide the most suitable sleep-aid music for different people in different environments.
By building a music database, collecting the brainwave response feature sequences and baseline feature sequences of the target user set, and using neural network online learning to construct a music feature space, the most suitable sleep-aiding music is determined based on preset search parameters.
The flexibility and accuracy of music classification have been improved, which can provide more accurate sleep-aid music selection for different users.
Smart Images
Figure CN120611062A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of sleep research, and in particular to a method for selecting optimal sleep-aiding music and related equipment. Background Art
[0002] Everyone has a set of music that suits them for sleep, but users themselves don't always know what music is most beneficial for their sleep. This is not only because users' perception of the impact of music on their sleep is relatively coarse and not necessarily accurate in terms of time, but also because the amount of relevant music users can find is limited. Furthermore, existing music tags for sleep-inducing music are simply categorized by musical style, a relatively crude classification method that doesn't take into account that different people may have different brainwave responses to the same music in different environments, and musical style classification is not necessarily very accurate or detailed.
[0003] That is, how to provide an optimal sleep-aid music selection method and related equipment to replace the existing method of classification by music style labels, so as to achieve the technical effect of improving the flexibility of music classification and the accuracy of music selection is a technical problem that urgently needs to be solved in this field. Summary of the Invention
[0004] The embodiments of the present invention provide a method for selecting optimal sleep-aiding music and related devices thereof to solve at least one of the above technical problems.
[0005] In a first aspect, the present application provides a method for selecting the most suitable sleep-aiding music, the method comprising:
[0006] Building a music database, wherein the music database stores a plurality of different music tracks;
[0007] Obtaining a brainwave response feature sequence set for each of the music tracks for a target user set, and obtaining a brainwave baseline feature sequence set for the target user set in a no-music state;
[0008] Processing the brainwave response feature sequence set and the brainwave reference feature sequence set according to neural network online learning to obtain a music feature space based on the music database;
[0009] Searching the initial sleep-aiding music in the music feature space according to preset search parameters, and determining the most suitable sleep-aiding music based on the search results;
[0010] The target user set includes a number of target users of different ages and genders, and the initial sleep-aiding music is any one or more music tracks in the music database.
[0011] Preferably, the step of obtaining a brainwave response feature sequence set for each music track for a target user set includes:
[0012] Selecting a current music track from the music database in sequence, and selecting a specific time to play the current music track to the target user set;
[0013] The brainwave response time sequence of each target user in the target user set based on the current music track within a preset time period is collected, and the brainwave response time sequence is preprocessed to obtain a brainwave response feature sequence set.
[0014] Preferably, the preprocessing of the brain wave response time series includes:
[0015] The brain wave response time series is subjected to filtering processing, artifact removal processing and feature sequence extraction processing.
[0016] Preferably, the step of obtaining a reference feature sequence set of brainwaves of the target user set in a non-music state comprises:
[0017] A reference brainwave time sequence of each target user in the target user set in a non-music playing state is collected according to the specific time, and the reference brainwave time sequence is preprocessed to obtain a reference brainwave feature sequence set.
[0018] Preferably, preprocessing the brainwave reference time series includes performing filtering processing, artifact removal processing, and feature sequence extraction processing on the brainwave reference time series.
[0019] Preferably, searching based on the initial sleep-aiding music in the music feature space according to preset search parameters, and determining the most suitable sleep-aiding music based on the search results, includes:
[0020] Obtaining initial sleep-aiding music, collecting current brainwave response data of the current user based on the initial sleep-aiding music, and estimating the sleep status based on the current brainwave response data to obtain a sleep-aiding effect coefficient for characterizing the sleep status, where a larger sleep-aiding effect coefficient indicates a better sleep status;
[0021] Searching the music feature space based on the initial sleep-aiding music according to preset search parameters, collecting brainwave response data of the current user based on the searched music tracks, and estimating the sleep-aiding effect coefficient corresponding to each searched music track based on the brainwave response data;
[0022] The music track with the largest sleep-aiding effect coefficient among the initial sleep-aiding music and the searched music tracks is determined as the most suitable sleep-aiding music.
[0023] Preferably, one or more brainwave response feature sequence sets corresponding to the initial sleep-aiding music are updated according to current brainwave response data collected based on the initial sleep-aiding music.
[0024] In a second aspect, the present application provides an optimal sleep-aiding music selection device, the optimal sleep-aiding music selection device comprising:
[0025] A database construction module is used to construct a music database, wherein the music database stores a plurality of different music tracks;
[0026] a feature acquisition module for acquiring a brainwave response feature sequence set for each of the music tracks for a target user set, and acquiring a baseline brainwave feature sequence set for the target user set in a no-music state;
[0027] a processing module, configured to process the brainwave response feature sequence set and the brainwave reference feature sequence set according to neural network online learning to obtain a music feature space based on the music database;
[0028] a determination module, configured to search the music feature space based on the initial sleep-aiding music according to preset search parameters, and determine the most suitable sleep-aiding music based on the search results;
[0029] The target user set includes a number of target users of different ages and genders, and the initial sleep-aiding music is any one or more music tracks in the music database.
[0030] In a third aspect, the present application also provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the optimal sleep-aid music selection method described in any one of the first aspects when executing the computer program stored in the memory.
[0031] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the optimal sleep-aid music selection method described in any one of the first aspects.
[0032] Specifically, the optimal sleep-aiding music selection method provided by the present invention first constructs a music database, which stores a plurality of different music tracks; then obtains a brainwave response feature sequence set for each music track in the music database for a target user set and obtains a brainwave baseline feature sequence set for the target user set in a no-music state, wherein the target user set includes a plurality of target users of different ages and genders; secondly, the brainwave response feature sequence set and the brainwave baseline feature sequence set are processed based on neural network online learning to obtain a music feature space based on the music database; finally, a search is performed in the music feature space based on the initial sleep-aiding music according to preset search parameters, and the optimal sleep-aiding music is determined based on the search results. The optimal sleep-aiding music selection method provided by the present application is a music classification based on the brain wave responses generated by music in the brains of different users, and the presentation form of the music classification is to form a music feature space for searching the optimal sleep-aiding music, thereby replacing the method of classification by music style labels in the existing technology, improving the flexibility and accuracy of music classification, and taking into account the differences in the EEG responses of different music to different users, the present application collects brain wave responses for each target user in the target user set respectively to adapt to different users, thereby providing more accurate sleep-aiding music selection for different users. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. 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 these drawings without paying any creative work.
[0034] Figure 1 A flowchart of the method for selecting the most suitable sleep-aiding music provided in this application;
[0035] Figure 2 A schematic diagram of the structure of the optimal sleep-aiding music selection device provided in this application;
[0036] Figure 3 A schematic diagram of the structure of an electronic device provided in this application;
[0037] Figure 4 A schematic diagram of the structure of the computer-readable storage medium provided in this application. DETAILED DESCRIPTION
[0038] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.
[0039] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products or devices. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can be changed in the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.
[0040] The division of modules in this application is a logical division. In actual application, there may be other division methods. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between modules can be electrical or other similar forms, which are not limited in this application. Moreover, the modules or submodules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed into multiple circuit modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this application.
[0041] See also Figure 1 , Figure 1 1 is a flow chart of a method for selecting the most suitable sleep-aiding music according to an embodiment of the present invention. As an embodiment of the method for selecting the most suitable sleep-aiding music provided by the present invention, the method for selecting the most suitable sleep-aiding music specifically includes the following steps S110 to S140:
[0042] Step S110: constructing a music database, wherein the music database stores a plurality of different music tracks;
[0043] Step S120: Obtain a brainwave response feature sequence set for each music track for the target user set, and obtain a baseline brainwave feature sequence set for the target user set in a no-music state;
[0044] As an exemplary implementation, the step S120 of obtaining the brainwave response feature sequence set for each music track for the target user set specifically includes the following:
[0045] Select a current music track from the music database in sequence, and select a specific time to play the current music track for the target user set;
[0046] The brainwave response time series of each target user in the target user set based on the current music track within a preset time period is collected, and the brainwave response time series is preprocessed to obtain a brainwave response feature sequence set.
[0047] The method of simply using music styles for label classification and directly applying it to certain specific brain waves is relatively rough, because it does not take into account that different people may have different brain wave responses to the same music in different environments, and music style classification is not necessarily very accurate and detailed.
[0048] Because specific music will produce specific brainwave responses in specific groups of people, this application uses the corresponding brainwave responses generated by the music to classify the music. Specifically, each music track in the music database is played to each target user in the target user set, and the brainwave response data of all target users under the music track are collected through the brain-computer interface to collect the brainwaves of a large number of users hearing specific music tracks. The target users in the target user set can include any users of different ages and genders.
[0049] After selecting a music track A from the music library, you can choose a suitable time to play the music before the user goes to work and when he or she is sleeping, and stop after a preset time period, which can be 30 minutes. Collect brain wave information within the preset time period, select other music tracks, and repeat the above process to collect brain wave information corresponding to other music tracks within the preset time period.
[0050] As an exemplary implementation, the pre-processing of the brain wave response time series involved in the above steps specifically includes: filtering processing, artifact removal processing and feature sequence extraction processing on the brain wave response time series.
[0051] As an exemplary implementation method, the acquisition of the brainwave baseline feature sequence set of the target user set in the non-music state involved in the above-mentioned step S120 specifically includes the following contents: collecting the brainwave baseline time series of each target user in the target user set in the non-music playing state according to a specific time, preprocessing the brainwave baseline time series, and obtaining the brainwave baseline feature sequence set.
[0052] Specifically, by obtaining brainwave information of the target user set without music stimulation, the effect of subsequent model training can be improved.
[0053] As an exemplary implementation, the pre-processing of the brain wave reference time series involved in the above steps includes: filtering processing, artifact removal processing and feature sequence extraction processing on the brain wave reference time series.
[0054] As you can understand, filtering and artifact removal remove noise and interference, ensuring the signal reflects true brain activity. Feature sequence extraction transforms complex signals into interpretable features to support subsequent processing. This processing makes the data more robust, reduces interference from individual differences and environmental factors, and improves application accuracy.
[0055] Step S130: Processing the brainwave response feature sequence set and the brainwave reference feature sequence set based on neural network online learning to obtain a music feature space based on the music database;
[0056] That is, traditional machine learning methods, such as support vector machines or deep learning methods, can be used to classify and cluster the music database according to brainwave responses based on neural networks to obtain a feature space based on brainwave response characteristics.
[0057] As an exemplary implementation, the above-mentioned step S130 involves processing the brainwave response feature sequence set and the brainwave reference feature sequence set based on the neural network online learning to obtain the music feature space based on the music database, which may specifically include the following contents:
[0058] A neural network model is constructed based on neural network online learning, and the neural network model is trained based on a response feature sequence set and a benchmark feature sequence set marked with similarity results to obtain a similarity recognition model;
[0059] Inputting the response feature sequence set corresponding to all music tracks into the similarity recognition model to obtain the similarity between any two music tracks in all music tracks;
[0060] A music feature space based on a music database is constructed according to the similarity. The greater the similarity between any two music tracks, the closer their relative distance in the music feature space.
[0061] It is understandable that since there are differences between the brainwave responses when listening to music and when not listening to music, the similarity between the two can be set to a constant, generally set to 0.5 or adjusted according to actual conditions. In other words, the similarity between any response feature sequence set and the baseline feature sequence set is the same and a constant. By training the neural network model based on the response feature sequence set and the baseline feature sequence set labeled with the similarity result (i.e., the above constant), a similarity recognition model can be obtained. This similarity recognition model can identify the response differences between two musical surfaces.
[0062] As an alternative implementation, the above-mentioned step S130 involves processing the brainwave response feature sequence set and the brainwave reference feature sequence set based on the neural network online learning to obtain the music feature space based on the music database, which may specifically include the following contents:
[0063] A neural network model is constructed for each music track based on online neural network learning. The corresponding neural network model is then trained based on a response feature sequence set and a reference feature sequence set labeled with preset similarity results to obtain a recognition model corresponding to each music track. The recognition model is used to identify the similarity between other music tracks and the current music track, and the similarity between any two music tracks among all music tracks can be obtained.
[0064] A music feature space based on a music database is constructed based on the similarity between any two music tracks obtained by recognition. The greater the similarity between any two music tracks, the closer their relative distance in the music feature space.
[0065] It can be understood that there is an inverse relationship between similarity and relative distance.
[0066] Step S140: searching the initial sleep-aiding music in the music feature space according to preset search parameters, and determining the most suitable sleep-aiding music based on the search results;
[0067] As an exemplary implementation, the above step S140 involves searching for the initial sleep-aiding music in the music feature space according to the preset search parameters, and determining the most suitable sleep-aiding music based on the search results, specifically including the following sub-steps (a) to (c):
[0068] Sub-step (a): obtaining initial sleep-aiding music, collecting the current brainwave response data of the current user based on the initial sleep-aiding music, and estimating the sleep status based on the current brainwave response data to obtain a sleep-aiding effect coefficient used to characterize the sleep status. A larger sleep-aiding effect coefficient indicates a better sleep status.
[0069] The initial sleep-aiding music is any one or more music tracks in the music database, and the initial sleep-aiding music can be one or more music tracks manually selected by the user from the music database or set by the system as a default.
[0070] Sub-step (b): searching in the music feature space based on the initial sleep-aiding music according to preset search parameters, collecting the brainwave response data of the current user based on the searched music tracks, and estimating the sleep-aiding effect coefficient corresponding to each searched music track based on the brainwave response data;
[0071] The search parameters include a search temperature parameter and a search frequency parameter. The search temperature parameter is related to the search jump distance in the music feature space. Generally speaking, the search temperature parameter is proportional to the search jump distance. By using the pre-set search temperature and search frequency parameters, a diffusion search is performed with the initial sleep-inducing music as the center, and multiple music tracks can be found.
[0072] Sub-step (c): The music track with the highest sleep-inducing effect coefficient among the initial sleep-inducing music and the searched music tracks is determined as the optimal sleep-inducing music track. The optimal sleep-inducing music track is then played as the current music track. The optimal sleep-inducing music track can be a single music track or a series of music tracks.
[0073] As an exemplary implementation, one or more brainwave response feature sequence sets corresponding to the initial sleep-aiding music are updated based on the current brainwave response data collected based on the initial sleep-aiding music. Simultaneously, the corresponding music feature space is also updated accordingly.
[0074] Specifically, the optimal sleep-aiding music selection method provided by the present invention first constructs a music database, which stores a plurality of different music tracks; then obtains a brainwave response feature sequence set for each music track in the music database for a target user set and obtains a brainwave baseline feature sequence set for the target user set in a no-music state, wherein the target user set includes a plurality of target users of different ages and genders; secondly, the brainwave response feature sequence set and the brainwave baseline feature sequence set are processed based on neural network online learning to obtain a music feature space based on the music database; finally, a search is performed in the music feature space based on the initial sleep-aiding music according to preset search parameters, and the optimal sleep-aiding music is determined based on the search results. The optimal sleep-aiding music selection method provided by the present application is a music classification based on the brain wave responses generated by music in the brains of different users, and the presentation form of the music classification is to form a music feature space for searching the optimal sleep-aiding music, thereby replacing the method of classification by music style labels in the existing technology, improving the flexibility and accuracy of music classification, and taking into account the differences in the EEG responses of different music to different users, the present application collects brain wave responses for each target user in the target user set respectively to adapt to different users, thereby providing more accurate sleep-aiding music selection for different users.
[0075] The following describes an embodiment of the optimal sleep-aiding music selection device according to the present invention. Figure 2 , Figure 2 This is a schematic diagram of an embodiment of a device for selecting the most suitable sleep-aiding music according to an embodiment of the present invention. The sleep-aiding music selection device 200 includes:
[0076] A database construction module 201 is used to construct a music database, wherein the music database stores a plurality of different music tracks;
[0077] The feature acquisition module 202 is used to obtain a brainwave response feature sequence set for each music track for a target user set, and obtain a baseline brainwave feature sequence set for the target user set in a no-music state;
[0078] a processing module 203 for processing the brainwave response feature sequence set and the brainwave reference feature sequence set according to neural network online learning to obtain a music feature space based on the music database;
[0079] A determination module 204 is configured to search the music feature space based on the initial sleep-aiding music according to preset search parameters, and determine the most suitable sleep-aiding music based on the search results;
[0080] The target user set includes several target users of different ages and genders, and the initial sleep-aiding music is any one or more music tracks in the music database.
[0081] As an exemplary implementation, the feature acquisition module 202 specifically includes:
[0082] a first selection unit, configured to sequentially select a current music track from the music database and select a specific time to play the current music track for the target user set;
[0083] The first processing unit is configured to pre-process the brainwave response time series of each target user in the target user set based on the current music track collected within a preset time period to obtain a brainwave response feature sequence set.
[0084] As an exemplary implementation, the first processing unit is further configured to perform the following steps:
[0085] The brain wave response time series is subjected to filtering processing, artifact removal processing and feature sequence extraction processing.
[0086] As an exemplary implementation, the feature acquisition module 202 further includes:
[0087] The second processing unit is configured to pre-process the reference brainwave time series of each target user in the target user set in a non-music playing state collected at the specific time to obtain a reference brainwave feature sequence set.
[0088] As an exemplary implementation, the second processing unit is further configured to perform the following steps:
[0089] The brain wave reference time series is subjected to filtering processing, artifact removal processing and feature sequence extraction processing.
[0090] As an exemplary implementation, the processing module 203 specifically includes:
[0091] A model construction unit is used to construct a neural network model based on neural network online learning, and train the neural network model based on a response feature sequence set and a reference feature sequence set marked with similarity results to obtain a similarity recognition model;
[0092] An input-output unit, configured to input the response feature sequence sets corresponding to all music tracks into a similarity recognition model to obtain the similarity between any two music tracks among all music tracks;
[0093] The feature space construction unit is used to construct a music feature space based on the music database according to similarity. The greater the similarity between any two music tracks, the closer their relative distance in the music feature space.
[0094] As an exemplary implementation, the determining module 204 specifically includes:
[0095] an information acquisition unit, configured to acquire initial sleep-aiding music and collect current brainwave response data of the current user based on the initial sleep-aiding music;
[0096] an estimating unit, configured to estimate a sleep condition based on the current brain wave response data, and obtain a sleep-aiding effect coefficient for characterizing the sleep condition, wherein a larger sleep-aiding effect coefficient indicates a better sleep condition;
[0097] The search determination unit is used to search in the music feature space based on preset search parameters based on the initial sleep-aid music, collect brain wave response data of the current user based on the searched music tracks, and estimate the sleep-aid effect coefficient corresponding to each searched music track based on the brain wave response data; and determine the music track with the largest sleep-aid effect coefficient between the initial sleep-aid music and the searched music tracks as the most suitable sleep-aid music.
[0098] As an exemplary implementation, the optimal sleep-aiding music selection device further includes:
[0099] An updating module is configured to update one or more brainwave response feature sequence sets corresponding to the initial sleep-aiding music according to current brainwave response data collected based on the initial sleep-aiding music.
[0100] Specifically, the optimal sleep-aid music selection device provided by the present invention first constructs a music database through a database construction module 201, and the music database stores a plurality of different music tracks; then, the feature acquisition module 202 obtains a brainwave response feature sequence set for each music track in the music database for a target user set, and obtains a brainwave baseline feature sequence set for the target user set in a no-music state, wherein the target user set includes a plurality of target users of different ages and genders; secondly, the processing module 203 processes the brainwave response feature sequence set and the brainwave baseline feature sequence set based on neural network online learning to obtain a music feature space based on the music database; finally, the determination module 204 searches for the initial sleep-aid music in the music feature space based on preset search parameters and determines the optimal sleep-aid music based on the search results. This application realizes music classification based on the brain wave response generated by music in the brains of different users, and the presentation form of music classification is to form a music feature space for searching the most suitable sleep-aid music, thereby replacing the method of classification by music style labels in the existing technology, improving the flexibility and accuracy of music classification. In addition, considering that different music has different EEG responses for different users, this application collects brain wave responses for each target user in the target user set to adapt to different users, and thus can provide more accurate sleep-aid music selection for different users.
[0101] An electronic device is also provided in the embodiment of the present invention. Figure 3 , Figure 3 The following is a schematic diagram of an electronic device according to an embodiment of the present invention, including:
[0102] A memory 301, a processor 302, and a computer program 303 stored in the memory and executable on the processor, wherein the processor implements the above-mentioned optimal sleep-aiding music selection method when executing the computer program 303 stored in the memory.
[0103] For ease of explanation, only the portions relevant to the embodiments of the present invention are shown. For specific technical details not disclosed, please refer to the section on the optimal sleep-aid music selection method of the embodiments of the present invention. Memory 301 can be used to store computer program 303, which includes software programs, modules, and data. Processor 302 executes computer program 303 stored in memory 301 to perform various functional applications and data processing of the electronic device.
[0104] The present invention also provides a computer-readable storage medium. Figure 4 , Figure 4 1 is a schematic diagram of an embodiment of a computer-readable storage medium in an embodiment of the present invention, wherein the computer-readable storage medium may store a computer program, which, when executed, includes some or all of the steps of the optimal sleep-aid music selection method described in the above method embodiment.
[0105] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described device, electronic device, and computer-readable storage medium can refer to the corresponding process of the optimal sleep-aid music selection method in the aforementioned method embodiment, and will not be repeated here.
[0106] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.
[0107] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.
[0108] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.
[0109] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the optimal sleep-aiding music selection method of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and other media that can store program codes.
[0110] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for selecting the most suitable sleep-aiding music, characterized in that: The method comprises: Building a music database, wherein the music database stores a plurality of different music tracks; Obtaining a brainwave response feature sequence set for each of the music tracks for a target user set, and obtaining a brainwave baseline feature sequence set for the target user set in a no-music state; Processing the brainwave response feature sequence set and the brainwave reference feature sequence set according to neural network online learning to obtain a music feature space based on the music database; Searching the initial sleep-aiding music in the music feature space according to preset search parameters, and determining the most suitable sleep-aiding music based on the search results; The target user set includes a number of target users of different ages and genders, and the initial sleep-aiding music is any one or more music tracks in the music database.
2. The method for selecting the most suitable sleep-aiding music according to claim 1, wherein: The step of obtaining a brainwave response feature sequence set for each music track for a target user set includes: Selecting a current music track from the music database in sequence, and selecting a specific time to play the current music track to the target user set; The brainwave response time sequence of each target user in the target user set based on the current music track within a preset time period is collected, and the brainwave response time sequence is preprocessed to obtain a brainwave response feature sequence set.
3. The method for selecting the most suitable sleep-aiding music according to claim 2, characterized in that: The preprocessing of the brain wave response time series includes: The brain wave response time series is subjected to filtering processing, artifact removal processing and feature sequence extraction processing.
4. The method for selecting the most suitable sleep-aiding music according to claim 1, wherein: The step of obtaining a reference feature sequence set of brainwaves of the target user set in a non-music state comprises: A reference brainwave time sequence of each target user in the target user set in a non-music playing state is collected according to the specific time, and the reference brainwave time sequence is preprocessed to obtain a reference brainwave feature sequence set.
5. The method for selecting the most suitable sleep-aiding music according to claim 4, characterized in that: The preprocessing of the brain wave reference time series includes filtering, artifact removal and feature sequence extraction on the brain wave reference time series.
6. The method for selecting the most suitable sleep-aiding music according to claim 1, wherein: The searching based on the initial sleep-aiding music in the music feature space according to the preset search parameters and determining the most suitable sleep-aiding music based on the search results includes: Obtaining initial sleep-aiding music, collecting current brainwave response data of the current user based on the initial sleep-aiding music, and estimating the sleep status based on the current brainwave response data to obtain a sleep-aiding effect coefficient for characterizing the sleep status, where a larger sleep-aiding effect coefficient indicates a better sleep status; Searching the music feature space based on the initial sleep-aiding music according to preset search parameters, collecting brainwave response data of the current user based on the searched music tracks, and estimating the sleep-aiding effect coefficient corresponding to each searched music track based on the brainwave response data; The music track with the largest sleep-aiding effect coefficient among the initial sleep-aiding music and the searched music tracks is determined as the most suitable sleep-aiding music.
7. The method for selecting the most suitable sleep-aiding music according to claim 6, characterized in that: One or more brainwave response feature sequence sets corresponding to the initial sleep-aiding music are updated according to the current brainwave response data collected based on the initial sleep-aiding music.
8. An optimal sleep-aiding music selection device, characterized in that: The optimal sleep-aiding music selection device comprises: A database construction module is used to construct a music database, wherein the music database stores a plurality of different music tracks; a feature acquisition module for acquiring a brainwave response feature sequence set for each of the music tracks for a target user set, and acquiring a baseline brainwave feature sequence set for the target user set in a no-music state; a processing module, configured to process the brainwave response feature sequence set and the brainwave reference feature sequence set according to neural network online learning to obtain a music feature space based on the music database; a determination module, configured to search the music feature space based on the initial sleep-aiding music according to preset search parameters, and determine the most suitable sleep-aiding music based on the search results; The target user set includes a number of target users of different ages and genders, and the initial sleep-aiding music is any one or more music tracks in the music database.
9. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the optimal sleep-aid music selection method according to any one of claims 1 to 7 when executing the computer program stored in the memory.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for selecting the optimal sleep-aiding music according to any one of claims 1 to 7 is implemented.