Digital media processing method and device, audio playing equipment and storage medium

Abstract

The invention provides a digital media processing method and device, audio playing equipment and a storage medium, and belongs to the technical field of audio processing, the method comprises the following steps: extracting audio parameters corresponding to each audio file, the audio files being files acquired from different channels; obtaining preference vectors of the user for different audio parameters based on the playing characteristics of the audio file corresponding to the audio parameters, and determining a target preference vector of the user based on the preference vectors and the basic characteristics of the user; determining a to-be-recommended audio file list based on the target preference vector of the user; playing the audio file list according to a preset time list; the preset time list is obtained according to the audio file. According to the method, the personalized audio file recommendation list can be generated according to the requirements of the user.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of audio processing, and more specifically, relates to a digital media processing method and device, an audio playback device, and a storage medium. Background Art

[0002] With the rapid development of digital media technology, the production, editing, transmission and playback of audio content have undergone profound changes. Traditional audio processing mainly relies on analog signal processing, while modern audio processing relies more on digital signal processing technology, which greatly improves the quality, flexibility and editability of audio.

[0003] During audio playback, users may want to obtain a more personalized and intelligent experience. However, this condition cannot be met in the existing technology. Therefore, there is an urgent need for a digital media processing method and device, an audio playback device, and a storage medium. Summary of the invention

[0004] The purpose of the present disclosure is to provide a digital media processing method and device, an audio playback device, and a storage medium to enhance the personalized and intelligent experience of users.

[0005] A first aspect of the embodiments of the present disclosure provides a digital media processing method, including: Extracting audio parameters corresponding to each audio file, wherein the audio files are files obtained from different channels; Obtaining a user's preference vector for different audio parameters based on the playback characteristics of the audio file corresponding to the audio parameter, and determining the user's target preference vector based on the preference vector and the user's basic characteristics; Determining a list of audio files to be recommended based on the user's target preference vector; The audio file list is played according to a preset time list; the preset time list is obtained according to the audio file.

[0006] A second aspect of the embodiments of the present disclosure provides a digital media processing device, including: A parameter acquisition module, used to extract audio parameters corresponding to each audio file, wherein the audio files are files acquired from different channels; A vector acquisition module, used to obtain the user's preference vectors for different audio parameters based on the playback characteristics of the audio file corresponding to the audio parameter, and determine the user's target preference vector based on the preference vector and the user's basic characteristics; A list determination module, used to determine a list of audio files to be recommended based on the user's target preference vector; The playing module is used to play the audio file list according to a preset time list; the preset time list is obtained according to the audio file.

[0007] According to a third aspect of an embodiment of the present disclosure, an audio playback device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned digital media processing method when executing the computer program.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned digital media processing method are implemented.

[0009] The digital media processing method and device, audio playback device, and storage medium provided by the embodiments of the present disclosure have the following beneficial effects: First, the present disclosure can accurately capture the user's preference for different audio parameters by extracting audio parameters, and then generate a personalized audio file recommendation list. This recommendation method is more in line with user needs and can improve user experience.

[0010] Secondly, the disclosure generates a list of recommended audio files based on the user's preferences and target preference vectors, and a preset time list based on the characteristics of the audio files, making the playback more intelligent and orderly. This not only improves the user's auditory enjoyment, but also optimizes time management, allowing users to arrange their time more efficiently while enjoying audio content.

[0011] Finally, the digital media processing method provided by the present invention can update the user's target preference vector in real time according to the dynamic changes of the user's basic characteristics and preferences, so that the target preference vector can dynamically adapt to the changes of the user and maintain the accuracy and timeliness of the audio recommendation content. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A flowchart of a digital media processing method provided by an embodiment of the present disclosure; Figure 2 A structural block diagram of a digital media processing device provided by an embodiment of the present disclosure; Figure 3A schematic block diagram of an audio playback device provided in one embodiment of the present disclosure. DETAILED DESCRIPTION

[0014] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0015] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0016] Please refer to Figure 1 , Figure 1 A flowchart of a digital media processing method provided by an embodiment of the present disclosure is provided, and the method includes: S101: extracting audio parameters corresponding to each audio file, where the audio files are files obtained from different channels.

[0017] In this embodiment, the audio file is a file obtained by the audio playback device from different channels, including but not limited to online music platforms, radio broadcasts, TV programs, movies, user uploads, professional audio libraries, social media libraries, etc. Audio files can be of various types, including but not limited to MP3, WAV, MP4, etc.

[0018] Each audio file played by an audio playback device has corresponding audio parameters, including frequency-related parameters (frequency range, low-frequency response, high-frequency response), amplitude-related parameters (amplitude, volume, signal-to-noise ratio), time-related parameters (phase, delay time), and other parameters (harmonic distortion, number of channels, sampling rate).

[0019] Audio parameters are data that describe the characteristics of an audio file. The purpose of extracting audio parameters is to enable audio playback devices to obtain audio features and implement personalized recommendations. Different audio files differ in frequency range, amplitude, dynamic range, etc. By extracting audio parameters, the device can use specific values ​​to describe the characteristics of the audio. For example, a piece of classical music has a wider frequency range and a more balanced amplitude, while a piece of rock music has a higher amplitude and a more prominent low-frequency response. By extracting audio parameters from the user's playback history, the device can also understand the user's preferences for different audio features.

[0020] S102: Obtaining a user's preference vector for different audio parameters based on playback characteristics of the audio file corresponding to the audio parameters, and determining a target preference vector of the user based on the preference vector and basic characteristics of the user.

[0021] In this embodiment, the playback characteristics of the audio file refer to the number of times each audio file is played, the playback duration, the playback time node, etc.

[0022] The preference vectors of different audio parameters represent the quantitative representation of the user's preference for different audio parameters. It can be a multidimensional vector, where each dimension represents a specific audio parameter, and the value in the vector represents the user's preference for the parameter. For example, if the user prefers high-volume audio, then the value in the preference vector will be relatively large in the corresponding volume parameter dimension. Basic features refer to some basic information and characteristics of the user himself, including but not limited to the user's age, gender, occupation, cultural background, music preference type, etc. These basic features will affect the user's preference for audio parameters. For example, young people may prefer audio with a strong rhythm and loud volume, while older people may prefer soft and soothing audio.

[0023] The target preference vector is a preference vector that the audio playback device adjusts and optimizes according to the basic characteristics of the user, so that the target preference vector is more in line with the actual needs and preferences of the user.

[0024] In this embodiment, the audio playback device first obtains the user's preference vector for specific audio parameters (such as volume, frequency, etc.) by analyzing the user's behavior and feedback when playing different audio files; secondly, the user's preference vector and basic features are combined to further refine or adjust the user's preferences and generate a more specific target preference vector. The target preference vector more accurately reflects the user's personalized needs and can be used to recommend audio content that better suits the user's preferences.

[0025] S103: Determine a list of audio files to be recommended based on the user's target preference vector.

[0026] In this embodiment, based on the user's target preference vector, the audio playback device can generate a personalized audio file list using a variety of matching, screening algorithms or deep learning models. In this way, users can more easily discover and enjoy their favorite audio content, and the audio playback device can also improve user satisfaction and participation.

[0027] For example, the audio playback device can first extract the audio parameters of the audio files that the user Xiaohong has listened to. For example, it can find that the audio Xiaohong likes usually has a slightly higher rhythm intensity, a warm timbre, and a moderate volume. Based on these playback characteristics, Xiaohong's preference vector for different audio parameters is obtained (the preference vector is L={[r,50],[t,70],[v,40]}). Based on the above preference vector and the basic feature that Xiaohong is a young woman who likes reading, her target preference vector is determined (LL={[r,30],[t,70],[v,40]}). Then, the device inputs the target preference vector into the deep learning model to obtain a list of audio files to be recommended.

[0028] S104: Play the audio file list according to the preset time list; the preset time list is obtained according to the audio file.

[0029] In this embodiment, the audio playback device can arrange the list of audio files to be recommended for playback in a specific order and time. For example, the audio files arranged at the front in the list of audio files to be recommended have a longer playback time, while the audio files arranged at the back have a shorter playback time. When the user listens to audio content during the working day, the audio files with a shorter playback time can be arranged for playback first; when the user listens to audio content on weekends, the audio files with a longer playback time can be arranged for playback first. This playback strategy can both meet the needs of users and improve user satisfaction.

[0030] The preset time list is obtained based on the audio file, indicating that the preset time list is generated based on some characteristics of the audio file itself or other related factors. For example, the specific time point at which each audio file is played in the preset time list can be determined based on factors such as the duration, style, and importance of the audio file.

[0031] From the above, it can be concluded that, firstly, the present disclosure can accurately capture the user's preference for different audio parameters by extracting audio parameters, and then generate a personalized audio file recommendation list. This recommendation method is more in line with user needs and can improve user experience.

[0032] Secondly, the disclosure generates a list of recommended audio files based on the user's preferences and target preference vectors, and a preset time list based on the characteristics of the audio files, making the playback more intelligent and orderly. This not only improves the user's auditory enjoyment, but also optimizes time management, allowing users to arrange their time more efficiently while enjoying audio content.

[0033] Finally, the digital media processing method provided by the present invention can update the user's target preference vector in real time according to the dynamic changes of the user's basic characteristics and preferences, so that the target preference vector can dynamically adapt to the changes of the user and maintain the accuracy and timeliness of the audio recommendation content.

[0034] In one embodiment of the present disclosure, obtaining a user preference vector for different audio parameters based on the playback characteristics of the audio file corresponding to the audio parameter includes: Count the number of times and duration of playback of the audio file containing each audio parameter; The user's preference vector for different audio parameters is constructed based on the number of times the audio file is played and the duration of the playback.

[0035] In this embodiment, the number of plays refers to the number of times the audio file is played by the user. A large number of plays means that the user has a high interest or preference for the audio file or the audio parameters contained therein.

[0036] Playing time refers to the total time that a user plays an audio file. By counting the playing time, we can understand the user's level of involvement and preference for different audio files. A longer playing time means that the user is more interested in the content of the audio. For example, the length of time that an audio file is played each time may be different, but by adding up these playing times, we can get the playing time of the audio file.

[0037] The user's preference vector for different audio parameters is constructed based on the number of times the audio file is played and the length of time it is played. The preference vector is a way to quantify user preferences, which can express the user's preference for various audio parameters with numerical values. If an audio parameter appears frequently in audio files that are played many times and for a long time, it can be considered that the user has a high preference for this audio parameter. For example, if the user often plays audio files with a brisk pace and a long playing time, then when constructing the preference vector, the value corresponding to the audio parameter of brisk pace will be higher, reflecting the user's preference for fast-paced audio.

[0038] It can be concluded from the above that this embodiment constructs a preference vector by counting the number of times an audio file is played and the length of time it is played, which can accurately reflect the actual preferences of the user. A large number of plays indicates that the user has a high interest in a specific audio parameter, and a long play time indicates that the user is highly invested in the parameter. The preference vector constructed in this way can provide users with more accurate audio recommendations, improve user experience, and meet personalized needs.

[0039] In one embodiment of the present disclosure, a user preference vector for different audio parameters is constructed according to the number of times an audio file is played and the duration of the audio file, including: Assign a weight value to each audio parameter based on the number of times the audio file is played and the duration of the play; Taking the audio parameter as the dimension and the weight value corresponding to each audio parameter as the vector element, a user preference vector for different audio parameters is constructed.

[0040] In this embodiment, the audio playback device may assign a weight value to each audio parameter according to the number of times the audio file is played and the duration of the audio file. The specific assignment principle is as follows: First, consider the weight distribution of the number of plays separately: assign an initial weight value to each audio parameter according to the number of times the audio file is played. You can use a proportional distribution method, that is, assign a higher weight to parameters with more plays and a lower weight to parameters with fewer plays. You can also assign an initial weight value to each audio parameter based on the average number of plays corresponding to each audio parameter.

[0041] Secondly, adjust the weights based on the playback duration: Considering the impact of playback duration on the weight value, adjust the initial weight value assigned according to the number of playbacks to obtain a modified weight value. If an audio file corresponding to an audio parameter has not only a large number of playbacks but also a long playback duration, then the weight value of the parameter can be increased; if an audio file corresponding to an audio parameter has a small number of playbacks and a short playback duration, then the weight value of the parameter can be reduced.

[0042] Finally, the weight values ​​of all audio parameters are normalized to obtain a normalized weight value corresponding to each audio parameter.

[0043] Taking the audio parameter as the dimension and the weight value corresponding to each audio parameter as the vector element, the user's preference vector for different audio parameters is constructed. It can be understood as: taking the audio parameter as the dimension, the normalized weight value corresponding to each audio parameter is used as the element of the preference vector, and filled into the corresponding dimension to obtain the user's preference vector for different audio parameters.

[0044] For example, if there are n audio parameters, then the preference vector is an n-dimensional vector. The normalized weight values ​​corresponding to these n audio parameters are , ,……, , .

[0045] It can be concluded from the above that, in this embodiment, by allocating weight values ​​based on the number of play times and the play duration to the audio parameters, the preference vector can more accurately reflect the user's real preference.

[0046] In one embodiment of the present disclosure, a weight value is assigned to each audio parameter according to the number of times the audio file is played and the duration of the play, including: Calculate the average number of playbacks and average playback duration of the audio files containing each audio parameter; Assign an initial playback count weight value to each audio parameter according to the average playback count corresponding to each audio parameter; Assigning an initial playback duration weight value to each audio parameter according to the average playback duration corresponding to each audio parameter; The initial playback times weight value and the initial playback duration weight value of each parameter are processed to obtain a weight value corresponding to each audio parameter.

[0047] In this embodiment, for each audio file containing a specific audio parameter, its play count and play duration can be recorded by the log recording function of the audio playback software or platform. For the audio file set corresponding to each audio parameter, the play counts of all audio files are added up and then divided by the total number of files to obtain the average play count of the audio parameter.

[0048] The average number of plays reflects the user's overall listening tendency to audio files containing specific audio parameters. A higher average number of plays means that the user has a stronger interest in the audio parameters.

[0049] In this embodiment, the initial weight strategy can be to allocate the initial play count weight value according to the relative size of the average play count. For example, the average play counts of all audio parameters can be sorted, and then the weights can be allocated in proportion. Or the initial weight strategy can also be to adopt segmented allocation, and determine the initial play count weight value according to the range of the average play count. For example, parameters with an average play count between 0 and 100 are allocated with a lower weight, those with an average play count between 100 and 200 are allocated with a medium weight, and those above 200 are allocated with a higher weight. Then, according to the determined weight allocation strategy, an initial play count weight value is allocated to each audio parameter.

[0050] The average playback time reflects the duration of users' listening to audio files containing specific audio parameters. A longer average playback time indicates that users have more patience and interest in the audio content with these parameters.

[0051] In this embodiment, similar to the allocation strategy of the play count weight value, the allocation of the play duration weight value can determine the initial play duration weight value according to the relative size of the average play duration. The average play duration of all audio parameters is sorted, and then the weight is allocated according to the proportion. Alternatively, the weight is allocated in sections according to the range of the average play duration. Then, according to the determined weight allocation strategy, the initial play duration weight value is allocated to each audio parameter.

[0052] Determine the importance ratio of play count and play duration based on data analysis or user surveys. For example, if the play count and play duration are considered equally important, then each can be given a 50% weight. If the play count better reflects user preferences, then a higher weight can be given to the play count, such as 60%, and the play duration can be 40%.

[0053] For each audio parameter, the initial play count weight value is multiplied by the importance ratio of the play count, and the initial play duration weight value is multiplied by the importance ratio of the play duration to obtain the comprehensive weight value of the parameter. The comprehensive weight values ​​of all audio parameters are normalized to obtain the weight value corresponding to each audio parameter.

[0054] From the above, it can be concluded that this embodiment improves the accuracy of audio analysis by comprehensively considering the number of times the audio file is played and the playback duration to accurately assign weight values ​​to each audio parameter, and also makes audio recommendations, editing or optimization more in line with the user's actual preferences, thereby enhancing the user experience.

[0055] In one embodiment of the present disclosure, determining a target preference vector of a user based on the preference vector and basic characteristics of the user includes: The basic features of the user are concatenated into the preference vector to obtain a comprehensive preference vector; Normalizing the comprehensive preference vector to obtain a normalized preference vector; A target preference vector of the user is determined based on the normalized preference vector.

[0056] In this embodiment, the basic characteristics of the user include age, gender, region, music type preference, activity preference, art preference, audio platform usage habits and consumption behavior, etc. Different basic characteristics of the user can be selected according to different scenarios.

[0057] For example, in the working scenario of a music recommendation platform: If the goal is to provide users with personalized music recommendations, we can focus on users' music genre preferences, audio platform usage habits, and consumer behavior characteristics. By analyzing users' collections, playback history, and purchase records, combined with their preferences for different music genres, we can accurately recommend audio files that suit their preferences.

[0058] In the work scenario of an audio production company: In order to create audio works that are more popular in the market, we can focus on the user's age, gender, interests and hobbies. Understanding the preferences of users of different age groups and genders, as well as their preferences in entertainment activities and cultural arts, will help to produce more targeted and attractive audio content.

[0059] In the advertising and marketing work scenario: If you want to place audio ads, you can choose the appropriate basic user characteristics based on the characteristics of the target audience. For example, if the ad is mainly targeted at young people, you can pay attention to their music type preferences and entertainment activity preferences, choose to place ads in the types of music they often listen to, or play audio ads in activity scenes related to their interests.

[0060] The basic features of the user are converted into data in the same format as that in the preference vector, and the data is directly concatenated to the front or back of the data in the preference vector to obtain a comprehensive preference vector.

[0061] In different scenarios, the splicing method is different. In response to the scenario where the user is in an interactive situation, the basic features of the user are converted into data with the same format as that in the preference vector, and the data is directly spliced ​​to the front of the data in the preference vector to obtain a comprehensive preference vector. In response to the scenario where the user is listening to music alone, the basic features of the user are converted into data with the same format as that in the preference vector, and the data is directly spliced ​​to the back of the data in the preference vector to obtain a comprehensive preference vector.

[0062] In interactive scenarios, people tend to pay more attention to each other's personality and characteristics, so the user's basic characteristics are directly spliced ​​to the front of the data in the preference vector; in the scenario of listening to music alone, the user's music preference is the primary consideration. Songs that suit the user's musical taste are recommended to the user based on the preference vector to ensure that the user can immerse himself in the music atmosphere he likes.

[0063] For example, for age, different age groups can be mapped to different values, such as 18-25 years old is mapped to 0.1, 26-35 years old is mapped to 0.2, etc.; gender can be represented by [0,1] for male and female respectively. The converted user basic feature vector is concatenated with the preference vector to obtain a comprehensive preference vector. Assume that the preference vector is L=[p1,p2,p3,...,p n ], the user's basic feature vector is F=[f1,f2,f3,...,f m ], then the comprehensive preference vector C=[p1,p2,p3,...,p n ,f1,f2,f3,...,f m ].

[0064] Normalize the comprehensive preference vector to obtain a normalized preference vector: determine the normalization method (such as maximum and minimum normalization, Z-score normalization, etc.), process the comprehensive preference vector according to the selected normalization method, and obtain the normalized preference vector. For example, using the maximum and minimum normalization method, for each element in the comprehensive preference vector , the normalized element value is:

[0065] Where min(C) and max(C) are the minimum and maximum values ​​in the comprehensive preference vector, respectively.

[0066] After normalization, all element values ​​in the comprehensive preference vector are within a specific range, which is convenient for subsequent calculations and comparisons.

[0067] The normalized preference vector is analyzed and determined as the user's target preference vector according to the specific algorithm design. The specific algorithm design includes building a user preference model and continuously optimizing the model to improve accuracy and performance. For example, a user preference model based on a neural network can be established, and the model can be better fitted to the user's behavior data and audio parameters by training and adjusting the network parameters. When optimizing the model, cross-validation, regularization and other techniques can be used to prevent overfitting and improve the generalization ability of the model; at the same time, new user data can be continuously collected to update and improve the model to adapt to changes in user preferences.

[0068] It can be concluded from the above that this embodiment forms a more comprehensive comprehensive preference vector by integrating the basic characteristics and preference vectors of users, and normalizes it, thereby ensuring the fairness and comparability of preferences in different dimensions. This process not only improves the accuracy of user preference analysis, but also enables the final target preference vector to more accurately reflect the real needs of users.

[0069] In one embodiment of the present disclosure, determining a list of audio files to be recommended based on a user's target preference vector includes: Calculating the similarity between the user's target preference vector and the audio parameters of each audio file in the audio file database; The first k audio files whose similarity is greater than a first threshold are selected from the audio file database to generate a list of audio files to be recommended.

[0070] In this embodiment, the user's target preference vector is determined based on the preference vector and the user's basic characteristics, and includes the user's preference for different audio parameters and other information related to the user. For example, if the weight of a certain audio parameter in the target preference vector is high, it means that the user has a strong preference for this parameter. When calculating the similarity, the audio file with a high matching degree with the parameter can obtain a higher similarity score.

[0071] The similarity between the user's target preference vector and the audio parameters of each audio file in the audio file database is calculated using algorithms such as cosine similarity, Euclidean distance or Pearson correlation coefficient. For example, the similarity is calculated using the first formula, which includes:

[0072] in, represents the i-th element of the target preference vector; Represents the i-th element of the audio parameter vector of the audio file; Indicates similarity. Its value is between [-1,1]. The closer the value is, the more similar the two vectors are, and the closer the value is, the less similar the two vectors are.

[0073] The first threshold can be determined according to the storage capacity of the audio file database, the amount of data calculated by the resource, and the time of the resource calculation. The first threshold is obtained according to the second formula, and the second formula includes:

[0074] Where Q is the first threshold, is the first coefficient; is the storage capacity of the audio file database; The maximum storage capacity of the audio file database; is the second coefficient; The amount of data calculated for the resource; The average amount of data required for each calculation; is the third coefficient; is the time influencing factor.

[0075] Time calculated with resources Related. It can be divided into three intervals: fast calculation time, medium calculation time and slow calculation time. The fast calculation time threshold is set to , the medium computation time threshold is ,if Less than or equal to , then the time impact factor is 1; if , then the time impact factor is 2; if , then the time impact factor is 3.

[0076] According to the similarity calculation result, audio files with similarity greater than a first threshold are selected from the audio file database. Then, the first k audio files are selected to generate a list of audio files to be recommended. The value of k can be adjusted according to actual conditions, for example, it can be determined according to factors such as the display space of the user interface and the diversity requirements of the recommendation. Selecting the first k audio files can ensure that the length of the recommendation list is moderate, which will not make the user feel overloaded with information and can provide enough choices.

[0077] In one embodiment of the present disclosure, calculating the similarity between the user's target preference vector and the audio parameters of each audio file in the audio file database includes: respectively calculating a first similarity between the user's target preference vector and each audio parameter corresponding to each audio file in the audio file database; The first similarities corresponding to the audio parameters in each audio file are weighted to obtain the similarities between the user's target preference vector and the audio parameters of each audio file in the audio file database.

[0078] In this embodiment, the user's target preference vector includes the user's preference for different audio parameters. Each audio file in the audio file database also has corresponding audio parameters, which describe the characteristics of the audio file in various aspects. For each audio parameter, the first similarity between the user's target preference vector and the audio parameter corresponding to the audio file is calculated respectively.

[0079] For each audio parameter, the first similarity between the user's target preference vector and the audio parameter corresponding to the audio file is calculated respectively. A variety of similarity calculation methods can be used, such as cosine similarity, Euclidean distance, Pearson correlation coefficient, etc.

[0080] The first similarities corresponding to each audio parameter in each audio file are weighted to obtain the overall similarity between the user's target preference vector and the audio file. The weight values ​​of the first similarities corresponding to different audio parameters in the overall similarity are determined according to the user's emphasis on different audio parameters; the weight values ​​of the first similarities corresponding to different audio parameters in the overall similarity can also be determined according to the importance of the audio parameters themselves. For example, if the user pays special attention to a certain audio parameter, such as high-frequency response, the weight of the first similarity corresponding to the parameter in the overall similarity can be relatively high. The dynamic range has a greater impact on audio quality, so a higher weight can be given when calculating the overall similarity. The first similarities corresponding to each audio parameter in each audio file are weighted to obtain the similarity between the user's target preference vector and the audio parameters of each audio file in the audio file database.

[0081] Assume that the audio file has n audio parameters, and the corresponding first similarities are s1, s2, ..., s n , the weights are w1, w2, ..., w n . Then the similarity between the user's target preference vector and the audio parameters of the audio file can be calculated as:

[0082] For example, an audio file has three parameters: high frequency response, low frequency response, and dynamic range, and the corresponding first similarities are 0.8, 0.7, and 0.9, and the weights are 0.3, 0.2, and 0.5, respectively. The overall similarity is 0.83.

[0083] It can be concluded from the above that this embodiment calculates the first similarity between the user target preference vector and each audio parameter of each audio file in the audio file database, and further weights and summarizes these first similarities to accurately measure the overall matching degree between the user preference and the audio file. This method not only improves the personalization of the recommendation, but also ensures the accuracy of the recommendation, provides users with audio content that is more in line with their preferences, and significantly enhances the user experience.

[0084] Corresponding to the digital media processing method of the above embodiment, Figure 2 This is a structural block diagram of a digital media processing device provided by an embodiment of the present disclosure. For ease of description, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The digital media processing device 20 includes: a parameter acquisition module 21, a vector acquisition module 22, a list determination module 23 and a playback module 24.

[0085] The parameter acquisition module 21 is used to extract audio parameters corresponding to each audio file, where the audio files are files acquired from different channels; A vector acquisition module 22, configured to obtain a user's preference vector for different audio parameters based on the playback characteristics of the audio file corresponding to the audio parameter, and determine a user's target preference vector based on the preference vector and the user's basic characteristics; A list determination module 23, used to determine a list of audio files to be recommended based on the user's target preference vector; The playing module 24 is used to play the audio file list according to the preset time list; the preset time list is obtained according to the audio file.

[0086] In one embodiment of the present disclosure, the vector acquisition module 22 is specifically used to: Count the number of times and duration of playback of the audio file containing each audio parameter; The user's preference vector for different audio parameters is constructed based on the number of times the audio file is played and the duration of the playback.

[0087] In one embodiment of the present disclosure, the vector acquisition module 22 is specifically used to: Assign a weight value to each audio parameter based on the number of times the audio file is played and the duration of the play; Taking the audio parameter as the dimension and the weight value corresponding to each audio parameter as the vector element, a user preference vector for different audio parameters is constructed.

[0088] In one embodiment of the present disclosure, the vector acquisition module 22 is specifically used to: Calculate the average number of playbacks and average playback duration of the audio files containing each audio parameter; Assign an initial playback count weight value to each audio parameter according to the average playback count corresponding to each audio parameter; Assigning an initial playback duration weight value to each audio parameter according to the average playback duration corresponding to each audio parameter; The initial playback times weight value and the initial playback duration weight value of each parameter are processed to obtain a weight value corresponding to each audio parameter.

[0089] In one embodiment of the present disclosure, the vector acquisition module 22 is specifically used for: The basic features of the user are concatenated into the preference vector to obtain a comprehensive preference vector; Normalizing the comprehensive preference vector to obtain a normalized preference vector; A target preference vector of the user is determined based on the normalized preference vector.

[0090] In one embodiment of the present disclosure, the list determination module 23 is specifically used to: Calculating the similarity between the user's target preference vector and the audio parameters of each audio file in the audio file database; The first k audio files whose similarity is greater than a first threshold are selected from the audio file database to generate a list of audio files to be recommended.

[0091] In one embodiment of the present disclosure, the list determination module 23 is specifically used to: respectively calculating a first similarity between the user's target preference vector and each audio parameter corresponding to each audio file in the audio file database; The first similarities corresponding to the audio parameters in each audio file are weighted to obtain the similarities between the user's target preference vector and the audio parameters of each audio file in the audio file database.

[0092] See also Figure 3 , Figure 3 This is a schematic block diagram of an audio playback device provided by an embodiment of the present disclosure. Figure 3 The audio playback device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 24 are shown.

[0093] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0094] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0095] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0096] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the digital media processing method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the audio playback device described in the embodiments of the present disclosure, which will not be repeated here.

[0097] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0098] The computer-readable storage medium may be an internal storage unit of the audio playback device of any of the aforementioned embodiments, such as a hard disk or memory of the audio playback device. The computer-readable storage medium may also be an external storage device of the audio playback device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the audio playback device. Further, the computer-readable storage medium may also include both an internal storage unit of the audio playback device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the audio playback device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0099] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0100] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the audio playback device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0101] In the several embodiments provided in the present application, it should be understood that the disclosed audio playback device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components 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 an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0103] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0104] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A digital media processing method, characterized in that: include: Extracting audio parameters corresponding to each audio file, wherein the audio files are files obtained from different channels; Obtaining a user's preference vector for different audio parameters based on the playback characteristics of the audio file corresponding to the audio parameter, and determining a user's target preference vector based on the preference vector and the user's basic characteristics; Determining a list of audio files to be recommended based on the user's target preference vector; Play the audio file list according to the preset time list; The preset time list is obtained according to the audio file.

2. The digital media processing method according to claim 1, wherein: The obtaining of the user's preference vectors for different audio parameters based on the playback characteristics of the audio file corresponding to the audio parameter includes: Count the number of times and duration of playback of the audio file containing each audio parameter; A user preference vector for different audio parameters is constructed according to the number of times the audio file is played and the duration of the play.

3. The digital media processing method according to claim 2, wherein: The step of constructing a user preference vector for different audio parameters according to the number of times the audio file is played and the duration of the audio file played includes: Assigning a weight value to each audio parameter according to the number of times the audio file is played and the duration of the play; A user preference vector for different audio parameters is constructed with the audio parameters as dimensions and the weight value corresponding to each audio parameter as a vector element.

4. The digital media processing method according to claim 3, characterized in that: The step of assigning a weight value to each audio parameter according to the number of times the audio file is played and the duration of the audio file played includes: Calculate the average number of playbacks and average playback duration of the audio files containing each audio parameter; Assign an initial playback count weight value to each audio parameter according to the average playback count corresponding to each audio parameter; Assigning an initial playback duration weight value to each audio parameter according to the average playback duration corresponding to each audio parameter; The initial playback times weight value and the initial playback duration weight value of each parameter are processed to obtain a weight value corresponding to each audio parameter.

5. The digital media processing method according to claim 1, wherein: The determining the target preference vector of the user based on the preference vector and the basic characteristics of the user includes: splicing the basic features of the user into the preference vector to obtain a comprehensive preference vector; Normalizing the comprehensive preference vector to obtain a normalized preference vector; A target preference vector of the user is determined based on the normalized preference vector.

6. The digital media processing method according to claim 1, wherein: The step of determining a list of audio files to be recommended based on the user's target preference vector comprises: Calculating the similarity between the user's target preference vector and the audio parameters of each audio file in the audio file database; The first k audio files whose similarity is greater than a first threshold are selected from the audio file database to generate a list of audio files to be recommended.

7. The digital media processing method according to claim 6, wherein: The calculating the similarity between the user's target preference vector and the audio parameters of each audio file in the audio file database comprises: respectively calculating a first similarity between the user's target preference vector and each audio parameter corresponding to each audio file in the audio file database; The first similarities corresponding to the audio parameters in each audio file are weighted to obtain the similarities between the user's target preference vector and the audio parameters of each audio file in the audio file database.

8. A digital media processing device, characterized in that: include: A parameter acquisition module, used to extract audio parameters corresponding to each audio file, wherein the audio files are files acquired from different channels; A vector acquisition module, used to obtain the user's preference vectors for different audio parameters based on the playback characteristics of the audio file corresponding to the audio parameter, and determine the user's target preference vector based on the preference vector and the user's basic characteristics; A list determination module, used to determine a list of audio files to be recommended based on the user's target preference vector; A playing module, used to play the audio file list according to a preset time list; The preset time list is obtained according to the audio file.

9. An audio playback device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images