Song listening data processing method and device, equipment, medium and product

Abstract

The invention relates to the technical field of computers, and discloses a song listening data processing method and device, equipment, a medium and a product, and the method comprises the steps: obtaining song listening behavior data of a user in a first preset time period; grouping the first preset time period according to a preset grouping rule, and determining a plurality of time period groups; for any time period group, determining a plurality of candidate songs corresponding to the time period group according to the song listening behavior data in the time period group; determining a target emotion type corresponding to the time period group according to the rhythm parameters of the plurality of candidate songs in the time period group; and generating a corresponding song listening emotion page according to the target emotion type corresponding to each time period group. According to the method, emotion judgment is more objective and emotion features can be quantified by utilizing the rhythm parameters, the song listening emotion recognition of the user can be simply and accurately realized, the song listening emotion change or song listening emotion distribution condition of the user can be displayed based on the song listening emotion page, and more diversified song listening behavior information can be displayed.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to methods, apparatus, devices, media, and products for processing music listening data. Background Technology

[0002] When users engage with music services, such as playing music through a music player (a music application) or browser installed on their device, corresponding behavioral data is generated. Analyzing this behavioral data can determine user preferences, generate a user listening behavior profile, and display it on a webpage, such as in the user's annual listening report.

[0003] In visualizations used to represent user listening behavior, the primary method is to statistically analyze the number of times each song has been played, thus presenting the user's listening behavior, such as displaying the most played songs of the year. This method of presentation is relatively singular and fails to showcase more diverse information. Summary of the Invention

[0004] In view of this, this application provides a method, apparatus, device, medium and product for processing music listening data to solve the problem of relatively single display dimensions in the user's music listening behavior page.

[0005] Firstly, this application provides a method for processing music listening data, the method comprising: Acquire user listening behavior data within a first preset time period; The first preset time period is grouped according to preset grouping rules to determine multiple time period groups; For any of the time period groups, multiple candidate songs corresponding to the time period group are determined based on the listening behavior data within the time period group. Based on the rhythm parameters of multiple candidate songs within the time period group, the target emotional type corresponding to the time period group is determined; Based on the target emotional type corresponding to each of the aforementioned time periods, a corresponding emotional page for listening to music is generated.

[0006] Optionally, determining multiple candidate songs corresponding to the time period group based on listening behavior data within the time period group includes: determining first playback parameters for each song corresponding to the time period group based on listening behavior data within the time period group; and selecting songs whose first playback parameters meet preset filtering conditions as candidate songs.

[0007] Optionally, determining the target emotion type corresponding to the time period group based on the rhythm parameters of multiple candidate songs within the time period group includes: determining the parameter interval to which the rhythm parameters of each candidate song within the time period group belong; the parameter interval corresponding to the emotion type; determining the number of candidate songs corresponding to each parameter interval; and taking the emotion type corresponding to the parameter interval with the largest number of candidate songs as the target emotion type corresponding to the time period group.

[0008] Optionally, generating a corresponding listening emotion page based on the target emotion type corresponding to each of the time period groups includes: for at least some target emotion types, determining the third playback parameter corresponding to the target emotion type within each of the time period groups; determining the emotion change curve corresponding to the target emotion type based on the third playback parameter corresponding to the target emotion type in each time period group; and generating a corresponding listening emotion page based on the emotion change curve corresponding to the at least some target emotion types.

[0009] Optionally, determining the emotional change curve corresponding to the target emotional type based on the third playback parameters corresponding to the target emotional type in each time period group includes: determining the single extreme value waveform corresponding to each time period group based on the third playback parameters corresponding to the target emotional type in each time period group; the extreme value of the single extreme value waveform is positively correlated with the third playback parameters; and splicing the single extreme value waveforms of the target emotional type in each time period group to form the emotional change curve corresponding to the target emotional type.

[0010] Optionally, if the target emotion type is positive, the emotion change curve corresponding to the target emotion type is located in a first region of the target page; if the target emotion type is negative, the emotion change curve corresponding to the target emotion type is located in a second region of the target page that is symmetrical to the first region.

[0011] Optionally, the method further includes: acquiring user listening behavior data within a second preset time period; the second preset time period includes multiple sub-time periods; determining a first style tag to be displayed based on the listening behavior data within each of the sub-time periods; and generating a corresponding listening style page based on each of the first style tags.

[0012] Optionally, determining the first style tag to be displayed based on the listening behavior data within each of the sub-time periods includes: for any sub-time period, determining at least one candidate style tag based on the listening behavior data within the sub-time period; and performing deduplication processing on the candidate style tags corresponding to each sub-time period to obtain the deduplicated first style tag.

[0013] Optionally, determining at least one candidate style tag based on the listening behavior data within the sub-time period includes: determining the fourth playback parameter of each song within the sub-time period based on the listening behavior data within the sub-time period; statistically analyzing the fourth playback parameters of each song belonging to the same style tag to determine the fourth playback parameter corresponding to each style tag; and selecting style tags whose fourth playback parameters meet preset conditions as candidate style tags.

[0014] Optionally, generating a corresponding music listening style page based on each of the first style tags includes: for any first style tag, determining the fifth playback parameter corresponding to the first style tag in each of the sub-time periods; determining the style change curve corresponding to the first style tag based on the fifth playback parameter corresponding to the first style tag in each of the sub-time periods; and generating a corresponding music listening style page based on the style change curve corresponding to each of the first style tags.

[0015] Optionally, determining the style change curve corresponding to the first style tag based on the fifth playback parameter corresponding to the first style tag in each of the sub-time periods includes: for any sub-time period, determining the proportion of playback parameters corresponding to each first style tag based on the fifth playback parameter corresponding to each first style tag in the sub-time period; determining the amplitude corresponding to the proportion of playback parameters of the first style tag based on a preset correspondence between the proportion and the amplitude; and determining the style change curve corresponding to the first style tag based on the amplitude corresponding to the first style tag in each of the sub-time periods; the style change curve is used to represent the change in the amplitude corresponding to the first style tag according to the time sequence of each of the sub-time periods.

[0016] Optionally, the method further includes: determining a style change category based on the first style tag corresponding to each of the sub-time periods; selecting a portion of the first style tags as second style tags based on the style change category; and generating style change text containing the second style tags. The step of generating corresponding music listening style pages based on each of the first style tags includes: generating corresponding music listening style pages based on the style change text and each of the first style tags.

[0017] Optionally, determining the style change category based on the first style tag corresponding to each of the sub-time periods includes: for each time period interval within the second preset time period, determining a unique tag set corresponding to each of the time period intervals and a common tag set for multiple time period intervals; the time period interval includes at least one of the sub-time periods; and determining the style change category of the user's listening style within the second preset time period based on the unique tag set and the common tag set.

[0018] Optionally, the second preset time period includes a first time period interval, a second time period interval, and a third time period interval arranged in chronological order; The step of determining the style change category of the user's listening style within the second preset time period based on the unique tag set and the shared tag set includes: if the shared tag set of the first time period interval, the second time period interval, and the third time period interval contains no less than a first preset number of first style tags, then the style change category is set as a first category; if both the unique tag set of the first time period interval and the unique tag set of the third time period interval contain no less than a second preset number of first style tags, then the style change category is set as a second category; if the shared tag set of the first time period interval and the third time period interval contains no less than a third preset number of first style tags, then the style change category is set as a third category; if the unique tag set of the second time period interval contains no less than a fourth preset number of first style tags, then the style change category is set as a fourth category; if the number of first style tags exceeds a fifth preset number, then the style change category is set as a fifth category.

[0019] Secondly, this application provides a device for processing music listening data, the device comprising: The acquisition module is used to acquire user listening behavior data within a first preset time period; The grouping module is used to group the first preset time period according to preset grouping rules to determine multiple time period groups; The filtering module is used to determine multiple candidate songs corresponding to any given time period group based on listening behavior data within the time period group. The processing module is used to determine the target emotional type corresponding to the time period group based on the rhythm parameters of multiple candidate songs within the time period group; The generation module is used to generate corresponding listening emotion pages based on the target emotion type corresponding to each of the time period groups.

[0020] Thirdly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the music data processing method of the first aspect or any corresponding embodiment described above.

[0021] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the music data processing method described in the first aspect or any corresponding embodiment.

[0022] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute the music data processing method described in the first aspect or any corresponding embodiment.

[0023] The music listening data processing method provided in this application groups the user's preferred first preset time period into multiple time period groups. Based on the rhythm parameters of candidate songs within each time period group, it performs emotion recognition to determine the corresponding target emotion type. This allows for the generation of music listening emotion pages related to the target emotion type for each time period group. These pages can display changes or distributions of the user's listening emotions, providing more diverse listening behavior information. Furthermore, using rhythm parameters such as the number of beats per minute for emotion recognition effectively reduces the inaccuracy of emotion assessment caused by using genre tags or lyrics. Utilizing rhythm parameters makes emotion judgment more objective and quantifiable, enabling simple and accurate identification of the user's listening emotions. Moreover, each user's music listening emotion page is generated based on their listening behavior data, allowing for the creation of pages that match their individual listening emotion characteristics, thus facilitating personalized expression of the music listening page. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram illustrating an application scenario according to an embodiment of this application; Figure 2 This is a schematic flowchart of a first method for processing music listening data according to an embodiment of this application; Figure 3 This is a schematic diagram of a second method for processing music listening data according to an embodiment of this application; Figure 4 This is a schematic diagram of a music listening emotion page according to an embodiment of this application; Figure 5A This is a schematic diagram illustrating the effect of a music listening emotion page according to an embodiment of this application; Figure 5B This is an illustration of another effect of the music listening emotion page according to an embodiment of this application; Figure 5C This is another schematic diagram illustrating the effect of the music listening emotion page according to an embodiment of this application; Figure 6 This is a schematic diagram of the third process of processing music listening data according to an embodiment of this application; Figure 7 This is a schematic diagram illustrating the effect of a music playback style page according to an embodiment of this application; Figure 8 This is a structural block diagram of a music playback data processing device according to an embodiment of this application; Figure 9 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0028] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0029] Most songs can be tagged with genres such as soundtrack, anime, and rock. To showcase more diverse user information in scenarios like annual reports, user genre statistics can be compiled to determine their preferred or followed genres. Alternatively, some solutions may map emotions to song genres or lyrics, assigning different emotional words to different genres to display content relevant to the user's feelings.

[0030] However, relying on genre tags or lyrics, which are often manually defined or categorized, lacks objectivity in judging emotions and leads to uncertainty in recognizing users' feelings or moods. Furthermore, determining corresponding emotional terms based on lyrics generally requires model-based implementation, which involves significant processing power and is inefficient.

[0031] As one optional application scenario in the embodiments of this application, such as Figure 1 As shown, application 101 is installed in terminal device 110, and user 130 can interact with application 101 through terminal device 110 and / or access device of terminal device 110. For example, application 101 can be any application, such as a music application or a browser that supports online music playback. Figure 1 In the application scenario shown, if application 101 is active, the terminal device 110 can display the interface 102 of application 101. The interface 102 may include various pages that application 101 can provide, such as interactive pages, settings pages, query pages, etc.

[0032] In some embodiments, terminal device 110 is communicatively connected to server 120 to provide services to application 101. Terminal device 110 may be a mobile terminal, fixed terminal, or portable terminal, including but not limited to mobile phones, desktop computers, laptop computers, multimedia tablets, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 110 may also support any type of interface, and server 120 may be various types of computing systems or servers capable of providing computing power, including but not limited to mainframes, edge computing nodes, and computing devices in cloud environments.

[0033] It should be noted that, Figure 1 This is merely an example of an application scenario and does not limit the scope of protection of this application. The embodiments of this application will be described below with reference to the accompanying drawings. It should be understood that the page shown in the drawings is merely an example, and various page designs are possible in practice. The various graphic elements on the page can have different arrangements and different visual representations, one or more elements can be omitted or replaced, and one or more other elements may also be present; no limitations are made in the embodiments of this application. Furthermore, the embodiments are mainly described below with reference to terminal device 110. It should be understood that the actions described relative to terminal device 110 can be performed by application 101 on terminal device 110, or can be performed by application 101 in conjunction with its server (e.g., server 120).

[0034] According to an embodiment of this application, a method for processing music listening data is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] This embodiment provides a method for processing music listening data, which can be used on the aforementioned terminal device or server, depending on actual needs. Figure 2 This is a flowchart of a method for processing music listening data according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps.

[0036] Step S201: Obtain user listening behavior data within the first preset time period.

[0037] In this embodiment, when there is a need to display a page related to a user's music listening behavior, a corresponding page can be generated based on the user's music listening behavior data. This page can be pre-generated and displayed directly on the user's terminal device when the user requests it, or it can be generated and displayed on the user's terminal device when the user initiates the display action. For example, this page could be a section from the user's annual music listening report.

[0038] In this embodiment, a relevant page is generated based on the user's music listening behavior data. Specifically, this page is related to a pre-set time period, namely the first preset time period; at this time, the user's music listening behavior data within the first preset time period can be obtained. For example, if an annual report needs to be generated for the user, the first preset time period is the time period corresponding to the corresponding year; if a monthly report needs to be generated for the user, the first preset time period is the time period corresponding to the corresponding month.

[0039] This music listening behavior data records information related to the user's music listening behavior, such as the name of the song the user listened to, the time, etc.; in addition, the music listening behavior data may also include some attribute parameters of each song, which can be used to generate the target page later.

[0040] Step S202: Group the first preset time period according to the preset grouping rules to determine multiple time period groups.

[0041] In this embodiment, the first preset time period can be divided into multiple time periods, thus resulting in multiple time period groups. Specifically, rules for grouping the first preset time period can be preset, i.e., grouping rules, thereby dividing the first preset time period into multiple time period groups. It can be understood that each time period group is a subset of the first preset time period.

[0042] Step S203: For any time period group, determine multiple candidate songs corresponding to the time period group based on the listening behavior data within the time period group.

[0043] For any given time period, we can determine the listening behavior data within that time period, such as the number of songs a user listens to within that time period.

[0044] Since users may listen to a large number of songs within a time period, a portion of these songs can be selected as candidate songs to be processed, thus reducing the processing load. Of course, in cases where the number of songs listened to is small, all songs within the corresponding time period can be used as candidate songs.

[0045] Step S204: Determine the target emotional type corresponding to the time period group based on the rhythm parameters of multiple candidate songs within the time period group.

[0046] In this embodiment, the listening behavior data may include attribute parameters of each candidate song, which may include rhythm parameters related to the song's tempo. For example, the rhythm parameter may be BPM (Beat Per Minute), which defines the tempo of the song.

[0047] For a given time period, the tempo parameters of each candidate song within that time period can be determined, thus identifying the primary tempo parameters for that time period. Furthermore, different tempo parameters can, to some extent, represent the user's listening emotions, specifically their mood or mood. For example, songs with a faster tempo (e.g., higher BPM) generally evoke a more upbeat and dynamic emotion, while songs with a slower tempo (e.g., lower BPM) generally evoke a more peaceful or relaxed emotion. Therefore, based on the tempo parameters of the candidate songs within a time period, the corresponding emotional type for each time period can be determined. For instance, multiple emotional types can be pre-defined, and the corresponding emotional type, i.e., the target emotional type, can be determined based on the actual tempo parameters. The corresponding target emotional type can be determined for each time period.

[0048] Step S205: Generate corresponding listening emotion pages based on the target emotion type corresponding to each time period group.

[0049] In this embodiment, after determining the target emotion type corresponding to each time period group, a page related to the emotion for the user within the first preset time period can be generated, namely the music listening emotion page.

[0050] For example, the type tags corresponding to each target emotion type can be determined, and the generated music listening emotion page contains the type tags corresponding to each time period group, so that the music listening emotion page can represent the emotion type corresponding to different time period groups, thereby showing the changes or distribution of users' music listening emotions.

[0051] This music listening emotion page can be displayed to users. For example, in response to a user-initiated page display action, the music listening emotion page can be displayed in a graphical user interface. This page display action could be a user-initiated click to view an annual music listening report, thus displaying the annual music listening report containing the music listening emotion page to the user.

[0052] The music listening data processing method provided in this embodiment groups the first preset time period that the user is interested in into multiple time period groups. Based on the rhythm parameters of candidate songs within each time period group, emotion recognition is performed to determine the corresponding target emotion type. This allows for the generation of music listening emotion pages related to the target emotion type of each time period group. These music listening emotion pages can display changes or distributions of the user's listening emotions, providing more diverse listening behavior information. Furthermore, using rhythm parameters such as the number of beats per minute to identify the emotion of a song effectively reduces the problem of inaccurate emotion judgment caused by using genre tags or lyrics. Utilizing rhythm parameters makes emotion judgment more objective and quantifiable, enabling simple and accurate identification of the user's listening emotions. Moreover, each user's music listening emotion page is generated based on their listening behavior data, allowing for the generation of pages that match their individual listening emotion characteristics, thus facilitating personalized expression of the music listening page.

[0053] This embodiment provides a method for processing music listening data, which can be used on the aforementioned terminal device or server, depending on actual needs. Figure 3 This is a flowchart of a method for processing music listening data according to an embodiment of this application, such as... Figure 3 As shown, the process includes the following steps.

[0054] Step S301: Obtain user listening behavior data within the first preset time period. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0055] Step S302: Group the first preset time period according to the preset grouping rules to determine multiple time period groups.

[0056] Specifically, step S302, "grouping the first preset time period according to the preset grouping rules to determine multiple time period groups", includes step S3021.

[0057] Step S3021: Based on the periodic characteristics of each sub-time period within the first preset time period, group each sub-time period into multiple time period groups; each time period group includes multiple sub-time periods with the same periodic characteristics.

[0058] In this embodiment, the first preset time period can be divided into multiple sub-time periods according to a certain duration. For example, if the duration of a sub-time period is one day, and the first preset time period is a certain month, then approximately 30 sub-time periods can be divided; if the first preset time period is a certain year, then approximately 365 sub-time periods can be divided. Furthermore, each sub-time period has a characteristic related to a period, i.e., a periodic characteristic. This periodic characteristic can represent the characteristic of the corresponding sub-time period changing with the period. Sub-time periods with the same periodic characteristic are grouped together to form corresponding time period groups; it can be understood that the number of time period groups matches the number of types of periodic characteristics. For example, the periodic characteristic can be a characteristic with a seven-day cycle, that is, dividing Monday to Sunday into seven time period groups.

[0059] In this embodiment, the sub-time periods are grouped by periodic features, so that the time periods corresponding to each sub-time period group are not completely adjacent. In other words, the sub-time period groups are not obtained by simply dividing the first preset time period. This is different from related technologies that analyze listening behavior in dimensions such as year and month.

[0060] Step S303: For any given time period group, determine multiple candidate songs corresponding to that time period group based on the listening behavior data within that group. See details below. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0061] In some optional implementations, step S303, "determining multiple candidate songs corresponding to a time period group based on listening behavior data within the time period group," includes: determining the first playback parameters of each song corresponding to the time period group based on listening behavior data within the time period group; and selecting songs whose first playback parameters meet preset filtering conditions as candidate songs.

[0062] In this embodiment, for any given time period, the playback parameters corresponding to the songs listened to by the user within that time period can be determined based on listening behavior data; these are known as the first playback parameters. The playback parameters are parameters related to song playback behavior, such as the number of plays or playback duration. Furthermore, pre-set conditions for filtering song playback parameters are established; if a song's first playback parameters meet the pre-set filtering conditions, then that song can be considered a candidate song.

[0063] For example, the first playback parameter can be the number of plays, and the first preset time period can be a certain year. Each time period group corresponds to different times such as Monday and Tuesday. Then, for the time period group corresponding to Monday, the number of plays of each song in the user's listening cycle within a year can be determined. Then, the songs with a number of plays greater than a preset threshold or the top N songs in terms of play count (i.e., Top N songs) are selected as candidate songs. For example, N=5, 10, 100, etc., which can be determined based on actual needs.

[0064] Step S304: Based on the rhythm parameters of multiple candidate songs within the time period group, determine the target emotional type corresponding to the time period group. For details, please refer to [link to details]. Figure 2 Step S204 of the illustrated embodiment will not be described again here.

[0065] In some optional implementations, step S304, "determining the target emotional type corresponding to the time period group based on the rhythm parameters of multiple candidate songs within the time period group," may include steps a1 to a3.

[0066] Step a1: Determine the parameter range to which the rhythm parameters of each candidate song in the time period group belong; the parameter range corresponds to the emotion type.

[0067] Step a2: Determine the number of candidate songs corresponding to each parameter range.

[0068] Step a3: The sentiment type corresponding to the parameter interval with the largest number of candidate songs is taken as the target sentiment type for the time period group.

[0069] In this embodiment, the rhythm parameter is divided into multiple parameter intervals based on its value range, with each interval corresponding to a different emotion type. For a given time period, each candidate song can be partitioned according to the parameter interval to which its rhythm parameter belongs, thus determining the number of candidate songs in each group, i.e., the number of candidate songs corresponding to each parameter interval.

[0070] By comparing the number of candidate songs corresponding to each parameter interval, the maximum number of candidate songs can be determined, and the sentiment type corresponding to this maximum number of candidate songs is taken as the selected target sentiment type. If multiple parameter intervals have the same maximum number of candidate songs, one of them can be randomly selected as the parameter interval with the maximum number of candidate songs. The same method can be used to determine the corresponding target sentiment type for other time periods, which will not be elaborated here.

[0071] For example, the rhythm parameter BPM can be divided into five fine parameter ranges, each matching a different emotional type. Specifically, range 1 is 70, representing a calm / relaxed / healing emotional type; range 2 is 70-100, representing a relaxed / stable / slow-burning emotional type; range 3 is 100-120, representing a bright / energetic / slightly exciting emotional type; range 4 is 120-140, representing a distinctly dynamic / fast-paced emotional type; and range 5 is >140, representing a high-energy / explosive rhythmic emotional type. This range division accurately reflects the emotional style under different rhythms, making BPM a quantifiable standard for emotional mapping.

[0072] In this embodiment, candidate songs are first selected by combining the first playback parameters and rhythm parameters of the song. This can avoid interference from outliers in a single song. Furthermore, the frequency of the song's BPM falling into the range is counted, so that the most suitable target emotion type can be selected. Emotion analysis can be achieved based on the BPM distribution of the Top N songs, which can enhance the narrative and dynamism of the performance.

[0073] Step S305: Generate corresponding music listening emotion pages based on the target emotion type for each time period group. For details, please refer to [link / reference]. Figure 2 Step S205 of the illustrated embodiment will not be described again here.

[0074] In some optional implementations, step S305, "generating corresponding listening emotion pages based on the target emotion type corresponding to each time period group," includes steps b1 to b2.

[0075] Step b1: For any time period group, determine the target emotional content corresponding to the target emotional type based on the mapping relationship between emotional type and emotional content.

[0076] Step b2: Generate corresponding emotional pages for listening to music based on the target emotional content of each time period group.

[0077] In this embodiment, appropriate emotional content is pre-configured for each emotion type. This emotional content describes the corresponding emotion type, meaning there is a mapping relationship between emotion types and emotional content. Taking the aforementioned BPM intervals as an example, for emotion types with larger BPMs, the specific emotional content can be: exhilaration, high energy, high burst, etc.

[0078] After determining the target emotional type corresponding to each time period group, the target emotional content corresponding to that type can be further determined based on this mapping relationship. Once the target emotional content for each time period group is determined, a corresponding music listening emotional page can be generated. For example, this music listening emotional page includes the target emotional content for each time period group.

[0079] Figure 4 This shows a schematic diagram of a music listening emotion page. For example... Figure 4 As shown, the first preset time period is one year, and each time period group corresponds to a day within a week, resulting in a total of seven time period groups. Furthermore, by representing emotional content using emotional tags, the emotional tag corresponding to each time period group can be determined. For example, the emotional tag for Monday is relaxation, and the emotional tag for Tuesday is calmness, etc.

[0080] Furthermore, the listening emotion page can also display the playback parameters (such as number of plays, playback duration, etc.) corresponding to the emotional type in each time period group. Figure 4 The gray progress bar represents the corresponding playback parameter; the longer the progress bar, the larger the playback parameter.

[0081] In addition, the "Listening to Music Emotions" page can include emotion-related text. For example, it could display the longest day of listening to music and its associated mood tag, as well as the shortest day of listening to music and its associated mood tag. Figure 4 As shown, the copy could include: You love listening to music on Wednesdays, and you especially like listening to upbeat songs; Tuesdays are probably your busiest time, so you listen to music less and feel more at peace.

[0082] Optionally, there is a mapping relationship between emotion types and multiple emotion contents. Step b1 above, "determine the target emotion content corresponding to the target emotion type based on the mapping relationship between emotion types and emotion contents," may specifically include step b11.

[0083] Step b11: When multiple time periods correspond to the same target emotion type, the target emotion content corresponding to the target emotion type is determined for each of the multiple time periods based on the mapping relationship between the emotion type and multiple emotion contents; wherein the target emotion contents corresponding to the multiple time periods are different from each other.

[0084] In this embodiment, for a certain emotion type, the corresponding emotion content is not unique; that is, it can have a mapping relationship with multiple emotion contents. Furthermore, the number of emotion contents corresponding to an emotion type is no less than the number of time period groups to ensure deduplication of emotion content.

[0085] Specifically, for multiple time period groups divided from the first preset time period, some of these time period groups may correspond to the same target emotion type. For example, if the BPM of multiple time period groups falls into the same BPM range, different target emotion content can be determined for different time period groups to avoid duplication of multiple emotion content.

[0086] For example, a resource library can be set up, containing various pre-defined emotional content for different emotion types. This emotional content can include emotional text in text format. Using time periods corresponding to Monday through Sunday, the following process can be executed sequentially from Monday to Sunday: For a given time period, if its corresponding BPM interval is the same as other time periods with determined emotional content, a new emotional text is extracted from the resource library for that interval. If the new text is still duplicated, it is extracted again, until no duplicates are found for 7 days (each emotion type in the resource library can be configured with at least 7 emotional texts to ensure no duplication).

[0087] Optionally, time period groups correspond to grouping types; and different time period groups of different grouping types have different mapping relationships, wherein the emotional content corresponding to the same emotional type is different in different mapping relationships.

[0088] Furthermore, step b1 above, "determining the target emotional content corresponding to the target emotional type based on the mapping relationship between emotional type and emotional content," may include steps b12 to b13.

[0089] Step b12: Determine the target mapping relationship between emotion type and emotion content based on the target grouping type corresponding to the time period group.

[0090] Step b13: Determine the target emotional content corresponding to the target emotional type based on the target mapping relationship.

[0091] In this embodiment, it is necessary to first determine the grouping type corresponding to the time period group, i.e. the target grouping type, and then determine the target mapping relationship corresponding to the target grouping type, so that time period groups of different grouping types can correspond to different emotional content.

[0092] For example, if there are seven time slot groups, each corresponding to Monday through Sunday, then two grouping types can be set: weekdays and weekends. That is, Monday through Friday corresponds to the weekday grouping type, and Saturday through Sunday corresponds to the weekend grouping type.

[0093] Furthermore, separate material libraries are set up for weekdays and weekends. In the weekday material library, at least five emotional contents are set for each type of emotion, and in the weekend material library, at least two emotional contents are set for each type of emotion, thus ensuring that the emotional contents are not repeated.

[0094] In this embodiment, by deduplicating emotional content, it is possible to ensure that the emotional presentation across multiple time periods reflects the actual pace of life while enhancing the diversity of the copy and providing rich narrative. Furthermore, by differentiating the emotional atmosphere between weekdays and weekends and using two independent material libraries, the copy can better align with the rhythm of daily life.

[0095] Optionally, the emotional content may include not only emotional text but also emotional emoticons, such as emotional emojis. Furthermore, step b2, "generating corresponding emotional pages for listening to music based on the target emotional content for each time period group," may include steps b21 to b22.

[0096] Step b21: For any time period group, determine the number of target emotional expressions corresponding to the target emotional type based on the second playback parameters of the candidate songs corresponding to the target emotional type within the time period group.

[0097] Step b22: Generate the listening emotion page; the listening emotion page includes the target emotion expressions corresponding to each time period group.

[0098] In this embodiment, for any time period group, the determined target emotional content can include not only text-based copywriting but also corresponding emotional expressions. For example, for a slower-paced time period group, its BPM is lower, so the corresponding emotional expression could be a melancholic expression, etc. It is understood that for the same emotional type, a mapping relationship between it and multiple emotional expressions can also be set to ensure that the emotional expressions are not repetitive.

[0099] Furthermore, in this embodiment, the number of emotional expressions represents the playback parameter size of related songs within a time period group. Specifically, the playback parameters of candidate songs corresponding to the target emotional type within the time period group can be determined, i.e., the second playback parameters. These second playback parameters can be the number of plays, total playback duration, etc. The first and second playback parameters can be the same or different, depending on the actual needs.

[0100] Among them, there is a positive relationship between the second playback parameter and the number of target emotional expressions, that is, the larger the second playback parameter is, the larger the number of target emotional expressions is determined.

[0101] Figure 5A This image shows a schematic of one possible effect of the emotional page for listening to music. For example... Figure 5A As shown, for Monday through Sunday, in addition to displaying emotional texts such as "calm" and "numb," there is also a corresponding number of emotional emoticons. The more emoticons there are, the more songs the listener has listened to and the higher the emotional intensity.

[0102] This allows setting a maximum number of emotional expressions to determine the number of emotional expressions for each time period group within that limit. For example, under this maximum limit, the second playback parameters for each time period group can be sorted, and a larger number of emotional expressions can be assigned to the time period groups that rank higher (the larger the second playback parameter, the higher the ranking, i.e., sorted in descending order). Alternatively, a functional relationship can be set between the second playback parameter and the number of emotional expressions, and the number of emotional expressions for each time period group can be determined based on this relationship, ultimately achieving the display of emotional expressions.

[0103] In this embodiment, the listening emotion page can not only present the listening emotions of different time periods to indicate the strength of emotions, but also display the differences in the amount of music listened to, realizing a multi-dimensional overlay display of listening behavior.

[0104] In some optional implementations, the above step S305, "generating corresponding listening emotion pages according to the target emotion type corresponding to each time period group," may include steps c1 to c3.

[0105] Step c1: For at least some of the target emotion types, determine the third playback parameter corresponding to the target emotion type in each time period group.

[0106] Step c2: Determine the emotional change curve corresponding to the target emotional type based on the third playback parameters corresponding to each time period group.

[0107] Step c3: Generate corresponding listening emotion pages based on the emotion change curves corresponding to at least some of the target emotion types.

[0108] In this embodiment, for each time period group, a target emotion type can be determined, for example, a unique target emotion type can be determined based on step a3; or, multiple target emotion types can be determined, for example, multiple emotion types with the highest number of candidate songs can be used as target emotion types.

[0109] After determining the target sentiment types for each time period, some or all of these target sentiment types can be selected to display their changes. All target sentiment types can be selected; alternatively, when there are many target sentiment types, a certain number can be selected; for example, three or four target sentiment types can be randomly selected to generate their respective sentiment change curves. Furthermore, for a specific target sentiment type, playback parameters related to the songs within that target sentiment type can be determined based on listening behavior data within each time period—that is, third playback parameters. These third playback parameters could be, for example, playback duration or number of plays.

[0110] Although the target emotional type may be different for each time period group, there will still be songs corresponding to various emotional types within each time period group. Therefore, after determining the target emotional type for each time period group, it is still possible to determine the third playback parameter corresponding to a specific target emotional type within each time period group.

[0111] For example, if the target emotion type is determined to be "excited" based on a certain time period group A, then for the target emotion type "excited", in other time period groups other than time period group A (such as time period group B, time period group C, etc.), the third playback parameters related to "excited" can still be determined, such as the number of times or the duration of "excited" songs listened to by the user in other time period groups.

[0112] For a specific emotional type, after determining the third playback parameter within each time period group, a curve representing the change of the third playback parameter can be generated based on each third playback parameter. This curve can also represent the change of the specific emotional type in different time periods, and this curve is called the emotional change curve.

[0113] Once the emotional change curves corresponding to each target emotional type are determined, a corresponding music listening emotion page can be generated. This music listening emotion page contains the emotional change curves corresponding to each target emotional type, thus displaying how various emotional types change over time.

[0114] Optionally, step c2, "determine the emotional change curve corresponding to the target emotional type based on the third playback parameters corresponding to each time period group of the target emotional type", may include steps c21 to c22.

[0115] Step c21: Based on the third playback parameter corresponding to the target emotion type in each time period group, determine the single extreme value waveform corresponding to each time period group; the extreme value of the single extreme value waveform is positively correlated with the third playback parameter.

[0116] Step c22: stitch together the single extreme value waveforms of the target emotion type in each time period group to form the emotion change curve corresponding to the target emotion type.

[0117] In this embodiment, in order to better represent the changes in emotions, the emotion change curve is divided into multiple parts according to the number of time period groups. Each part is represented by a single extreme value waveform, that is, each time period group corresponds to a single extreme value waveform. By utilizing the fluctuation characteristic of the single extreme value waveform itself, the changes in the user's emotions while listening to music are further reflected.

[0118] As the name suggests, a single extreme value waveform is a waveform with only one extreme value (maximum or minimum value). For example, a single extreme value waveform can be a single-peak waveform, that is, it has only one peak; for example, a single extreme value waveform can be a sine wave, a triangular wave, etc., which can be determined based on actual needs.

[0119] For any target emotional type, when determining the single extreme value waveform corresponding to a certain time period group, the extreme value of the single extreme value waveform can be determined based on the third playback parameter, and there is a positive correlation between the two; that is, the larger the third playback parameter, the larger the corresponding extreme value. If we distinguish between maxima and minima, more precisely, the absolute value of the extreme value waveform can be determined based on the third playback parameter, and the larger the third playback parameter, the larger the absolute value of the extreme value. After determining the single extreme value waveforms for each time period group, these single extreme value waveforms are spliced ​​together to obtain an emotional change curve that can represent the changes in the target emotional type, ultimately generating a music listening emotion page.

[0120] Figure 5B This shows another illustration of the emotional aspect of listening to music. (For example...) Figure 5B As shown, the first preset time period is three years, from 2023 to 2025. Each time period group contains one year, resulting in three time period groups. For each time period group, the single-extreme waveform of each target emotional type can be determined. Figure 5B Using a Gaussian waveform as an example, the final result can generate and display the emotion change curves corresponding to each target emotion type.

[0121] in, Figure 5B The diagram shows four emotion change curves, which can be used to identify four target emotion types. Figure 5B For example, if the four target emotion types are: excitement, happiness, depression, and sadness, then the four emotion change curves represent the changes in these four emotions, respectively. (Reference) Figure 5B Different line types can be set for different emotion change curves to distinguish different target emotion types. For example, taking the waveform corresponding to 2025 as an example, the emotion types corresponding to the four waveforms from top to bottom are: excitement, happiness, depression, and sadness.

[0122] Or, such as Figure 5C As shown, different colors can also be used to represent different target emotion types, and emotion change curves can be plotted with the corresponding colors. See also Figure 5C As shown, the colors corresponding to the four emotion types—excitement, happiness, depression, and sadness—are red, light red, light blue, and blue, respectively, making it easier for users to intuitively distinguish between the different emotion types.

[0123] Optionally, if the target sentiment type is positive, the corresponding sentiment change curve is located in the first region of the target page. If the target sentiment type is negative, the corresponding sentiment change curve is located in the second region of the target page, symmetrical to the first region.

[0124] If there are many target emotion types and they are displayed in a uniform way, it is difficult to distinguish the different emotion change curves. In this embodiment, the characteristic that emotion types can be divided into positive and negative emotions is utilized, and different display methods are used for different emotion types. This allows for better differentiation of the emotion change curves of each target emotion type on the music listening emotion page.

[0125] Specifically, the emotion display curve on the music listening emotion page can be divided into two symmetrical areas, namely the first area and the second area; the first area is used to display the emotion change curve of positive emotions, and the second area is used to display the emotion change curve of negative emotions.

[0126] by Figure 5B and Figure 5C As shown, the upper half of the display area is the first area, which displays the emotional change curves corresponding to positive emotions such as excitement and happiness; while the lower half of the display area is the second area, which displays the emotional change curves corresponding to negative emotions such as sadness and grief. Furthermore, the two areas are symmetrical, meaning they display the emotional change curves for different emotions in a symmetrical manner. Figure 5B and Figure 5C As shown, the emotional change curve of positive emotions has a corresponding peak, while the emotional change curve of negative emotions has a corresponding trough.

[0127] By dividing the display area into a first area and a second area, and displaying emotional change curves for different types of emotions, a larger number of emotional change curves can be displayed intuitively, making it easier to express the fluctuations in the user's emotional state while listening to music.

[0128] The music listening data processing method provided in this embodiment can display changes or distributions of user listening emotions on the music listening emotion page, providing more diverse information about listening behavior. Furthermore, by identifying emotions in songs based on rhythm parameters such as the number of beats per minute, it effectively reduces the inaccuracy of emotion judgment caused by using genre tags or lyrics. Utilizing rhythm parameters makes emotion judgment more objective and quantifiable, enabling simple and accurate identification of user listening emotions with more stable and attributable results. Grouping based on the periodic characteristics of time periods, unlike traditional focus on years, months, or quarters, can present the periodic changes in user listening behavior and provide fine-grained representation of micro-emotional changes throughout the seven days of the week. This rhythmic variation in listening makes the page display more ritualistic and relatable. Deduplicating emotional content of the same emotion type effectively avoids repetitive text or emoticons, allowing for a more diverse display of user emotions.

[0129] This embodiment provides a method for processing music listening data, which can be used on the aforementioned terminal device or server, depending on actual needs. In addition to generating music listening emotion pages, this method can also generate music listening style pages. Figure 6 This is a flowchart of a method for processing music listening data according to an embodiment of this application, such as... Figure 6 As shown, the process of generating a music listening style page includes the following steps.

[0130] Step S601: Obtain user listening behavior data within a second preset time period; the second preset time period includes multiple sub-time periods.

[0131] In this embodiment, similar to obtaining user listening behavior data within a first preset time period in step S201 above, listening behavior data within a second preset time period can also be determined. The first and second preset time periods can be the same or different.

[0132] For example, when generating an annual listening report, the first preset time period can be the corresponding year, and the second preset time period can be the same year or multiple years including the same year, so that the changes in listening styles in different years can be displayed in the subsequently generated listening style page.

[0133] Furthermore, the second preset time period can be divided into multiple sub-time periods. For example, if the first preset time period is one year, then each sub-time period can be one month or one quarter (including three consecutive months); if the first preset time period is several years (e.g., five years), then each sub-time period is the corresponding year.

[0134] Step S602: Determine the first style tag to be displayed based on the listening behavior data in each sub-time period.

[0135] In this embodiment, for any sub-time period, by analyzing the user's listening behavior data within that sub-time period, the style tags that the user is interested in can be determined. For example, the style tags corresponding to songs that the user frequently listens to, i.e., the first style tag. For each song, a suitable style tag can be pre-assigned to represent the song's genre, such as rock or jazz. The appropriate first style tag is determined by statistically analyzing the style tags of relevant songs within the sub-time period.

[0136] Step S603: Generate the corresponding music listening style page based on each primary style tag.

[0137] In this embodiment, after determining each first style tag, for any first style tag, information related to the first style tag in each sub-time period can be determined. Based on the information related to each first style tag, a page that can represent the user's listening style, i.e., a listening style page, can be generated.

[0138] In some optional implementations, step S602, "determining the first style tag to be displayed based on the listening behavior data in each sub-time period," may include steps d1 to d2.

[0139] Step d1: For any sub-time period, determine at least one candidate style tag based on the listening behavior data within the sub-time period.

[0140] In this embodiment, a certain number of style tags are selected from each sub-time period as candidate style tags to be processed. Specifically, for a certain sub-time period, the listening behavior data corresponding to that sub-time period can be obtained, and then the style tags of each song in that sub-time period can be statistically analyzed based on the listening behavior data to select candidate style tags that can be displayed.

[0141] Optionally, step d1, "determine at least one candidate style tag based on listening behavior data within a sub-time period", may include steps d11 to d13.

[0142] Step d11: Determine the fourth playback parameters for each song within the sub-time period based on the listening behavior data within the sub-time period.

[0143] Step d12 involves statistically analyzing the fourth playback parameters of each song belonging to the same style tag to determine the fourth playback parameters corresponding to each style tag.

[0144] Step d13: Select style tags that meet the preset conditions for the fourth playback parameter as candidate style tags.

[0145] In this embodiment, for any sub-time period, the playback parameters of each song (i.e., the songs listened to by the user in the sub-time period) can be obtained based on the corresponding listening behavior data, namely the fourth playback parameter; for example, the fourth playback parameter can be the number of plays, the playback duration, etc., which can be the same as or different from the first playback parameter and the second playback parameter.

[0146] Furthermore, each song has a corresponding style tag, such as rock or anime. Grouping songs based on these style tags allows for the identification of songs belonging to the same style tag. The fourth playback parameter for each song is then statistically analyzed to determine the fourth playback parameter corresponding to each style tag. For example, if the fourth playback parameter is playback duration, then the fourth playback parameter for a particular style tag is: the total playback duration of songs belonging to that style tag listened to by the user within a sub-time period. Alternatively, the songs listened to by the user within the sub-time period can be filtered first, selecting a subset of candidate songs, and then the fourth playback parameters of these candidate songs can be statistically analyzed. This embodiment does not limit this approach.

[0147] For a given style tag, if its fourth playback parameter meets preset conditions, then that style tag can be used as a candidate style tag. For example, for each sub-time period, K style tags can be selected, where K ≥ 2, meaning the K style tags with the largest fourth playback parameters can be used as candidate style tags. For example, K = 3, 5, etc.

[0148] Step d2 involves deduplicating the candidate style tags for each sub-time period to obtain the deduplicated first style tag.

[0149] A user might listen to the same style of music in different time periods, resulting in potentially identical candidate style tags across these periods. Therefore, deduplication is performed on these candidate style tags to remove duplicates from different time periods, ultimately yielding unique style tags, known as the first style tag. In essence, the first style tag is the deduplicated candidate style tag.

[0150] For example, if the first preset time period is the past two years, and the candidate style tags for the first year include "rock" and "electronic," while the candidate style tags for the second year include "rock" and "anime / manga," then there is a duplicate style tag "rock" between the two years. Therefore, it is necessary to remove duplicates. After deduplication, the various primary style tags can be determined, specifically including: rock, electronic, and anime / manga. By removing duplicate style tags, the style changes corresponding to each style tag can be displayed without repetition.

[0151] Optionally, step S603, "generating corresponding music listening style pages based on each first style tag", may include steps e1 to e3.

[0152] Step e1: For any first style tag, determine the fifth playback parameter corresponding to the first style tag in each sub-time period.

[0153] Step e2: Determine the style change curve corresponding to the first style tag based on the fifth playback parameter corresponding to the first style tag in each sub-time period.

[0154] Step e3: Generate the corresponding music listening style page based on the style change curves corresponding to each first style tag.

[0155] In this embodiment, the music style page is specifically used to represent the changes in various styles for the user within a second preset time period. Specifically, the determined first style tag (e.g., the style tag obtained after deduplication) is the style tag that needs to be displayed on the music style page; therefore, for each sub-time period, the playback parameters corresponding to the first style tag can be determined, namely the fifth playback parameters, such as the number of plays, playback duration, etc., which can be the same as or different from the aforementioned fourth playback parameters.

[0156] After determining the fifth playback parameter corresponding to the first style tag in each sub-time period, the playback parameter changes of the first style tag can be determined based on the fifth playback parameter in different sub-time periods. Based on this, the corresponding style changes are reflected, forming the style change curve corresponding to the first style tag.

[0157] The style change curve represents the change of a style tag's playback parameter (fifth playback parameter) over time. For example, the horizontal axis of the style change curve represents time, and the vertical axis represents the fifth playback parameter or other parameters that have a mapping relationship with the fifth playback parameter. In this embodiment, each sub-time period is a continuous time period segmented from the second preset time period, and the sub-time periods have a temporal order.

[0158] Once the style change curves corresponding to each primary style tag are determined, a corresponding music style page can be generated. This music style page can include the style change curves corresponding to each primary style tag to represent the changes in various styles within a second preset time period.

[0159] Optionally, step e2, "determine the style change curve corresponding to the first style tag based on the fifth playback parameter corresponding to the first style tag in each sub-time period", may include steps e21 to e23.

[0160] Step e21: For any sub-time period, determine the proportion of playback parameters corresponding to each first style tag based on the fifth playback parameters corresponding to each first style tag within the sub-time period.

[0161] Step e22: Determine the amplitude corresponding to the playback parameter percentage of the first style tag based on the preset correspondence between percentage and amplitude.

[0162] Step e23: Determine the style change curve corresponding to the first style tag based on the amplitude of the first style tag in each sub-time period; the style change curve is used to represent the change of the amplitude of the first style tag in the order of time of each sub-time period.

[0163] In this embodiment, for a certain first style tag, when determining its corresponding style change curve, the fifth playback parameter corresponding to each time period can be determined, and the corresponding playback parameter proportion can be determined. Specifically, the playback parameter proportion corresponding to a certain sub-time period can be the ratio of the fifth playback parameter of the first style tag to the sum of the fifth playback parameters of all style tags (e.g., all first style tags) within that sub-time period.

[0164] For example, for the i-th first style tag, its fifth playback parameter in the j-th sub-time period is: For example, if the fifth playback parameter is the playback duration, then the sum of the fifth playback parameters for all first style tags within the j-th sub-time period is: Let N be the total number of first style tags. Then, the percentage of playback parameters corresponding to the i-th first style tag in the j-th sub-time period. for: For different sub-time periods, i.e., for different j, the corresponding proportion of playback parameters can be determined. Finally, the proportion of each playback parameter corresponding to the i-th first style tag is determined. , … M represents the number of sub-time periods, for example, M=5.

[0165] Furthermore, the correspondence between percentage and amplitude is pre-defined, such as the correspondence between percentage range and amplitude. After determining the percentage of each playback parameter, its corresponding amplitude can be determined. This amplitude is the value corresponding to the corresponding sub-time period in the style change curve corresponding to the first style tag. In other words, the vertical axis of the style change curve is the amplitude. By mapping percentage to amplitude, similar playback parameter percentages can be mapped to different amplitudes, thus making the style change curve more prominently display the style change.

[0166] For example, there is a preset correspondence between the percentage range and the amplitude. When the percentage range is 20%~40%, the corresponding amplitude is 2. When the percentage range is 40%~60%, the corresponding amplitude is 4. Then, when the percentage of the playback parameter is 39%, the amplitude is 2, and when the percentage of the playback parameter is 41%, the amplitude is 4, which can more prominently represent the style change.

[0167] Figure 7 The image shows a schematic of one possible effect of the music listening style page, such as... Figure 7 As shown, the second preset time period is a five-year period from 2021 to 2025, with each year being a sub-time period. The first style tags, determined after deduplication, include: rock, pop, anime, slow rock, jazz, folk, instrumental, hip-hop, soundtrack, rhythm and blues, and electronic. Figure 7 The style tags shown can be arranged from top to bottom in chronological order of their appearance.

[0168] Furthermore, for each primary style tag, its corresponding style variation curve can be determined. Figure 7 The style change curves of each primary style tag are represented by an envelope symmetrical along the time axis, and different colors are assigned to them for display, forming a spectrum of style evolution to reflect the changes of different style tags.

[0169] In addition, different correspondences can be set for different sub-time periods, that is, the correspondence between the proportion and the magnitude will change with the sub-time period. This also allows the style change curve to have a certain dynamic change effect, which can represent the evolution of the user's listening style.

[0170] In some optional implementations, the music style page may also include corresponding text. Specifically, the method further includes steps f1 to f2.

[0171] Step f1: Determine the style change category based on the first style tag corresponding to each sub-time period.

[0172] Step f2: Select some of the first style tags as second style tags according to the style change category, and generate style change text containing the second style tags.

[0173] Furthermore, step S603, "generating corresponding music listening style pages based on each first style tag," can specifically include: generating corresponding music listening style pages based on the style change text and each first style tag.

[0174] In this embodiment, after determining each first style tag, the user's listening style changes can be determined based on the occurrence of each first style tag in each sub-time period, thereby determining the corresponding style change type.

[0175] For example, multiple style change types can be preset, and the style change type corresponding to the second preset time period can be determined based on the distribution of each first style tag in each sub-time period. For example, style change types can include the following types: Type 1, Type 2, Type 3, etc.

[0176] Type 1: Stable and consistent, meaning that the style tags that are focused on are basically the same across multiple sub-time periods, with a steady preference across the year.

[0177] Type 2: Recurring preference type, focusing on certain style tags at the beginning and end of the time period, while focusing on other style tags in the middle of the time period.

[0178] Type 3: New music preference type, which means that as time goes on, the user listens to more and more songs with more and more style tags. For example, there are many style tags that were not listened to at the beginning but were added later.

[0179] It is understandable that other types may be provided, but this embodiment does not limit this.

[0180] Once the style change type is determined, it's possible to identify which of the displayed first style tags are suitable for prominence and use them as second style tags. Furthermore, based on this style change type, text containing each of the second style tags is generated—this is the style change text.

[0181] For example, with Figure 7 For example, the style tags of the songs a user listens to change gradually each year, which can be classified as type three above. Furthermore, the first style tag that the user was initially interested in is used as the second style tag, including rock, pop, anime, etc., and the first style tag that the user was interested in later is also used as the second style tag, including folk, hip-hop, electronic, etc. The final style change text is: 5 years ago, you liked rock, pop, and anime; in 2024, you started exploring folk, hip-hop, and electronic; the diverse musical styles have formed your unique musical taste.

[0182] In some optional implementations, step f1, "determining the style change category based on the first style tag corresponding to each sub-time period," may specifically include steps f11 to f12.

[0183] Step f11: For each time interval within the second preset time period, determine the unique tag set corresponding to each time interval and the common tag set of multiple time intervals; the time interval includes at least one sub-time period.

[0184] Step f12: Determine the style change category of the user's listening style within the second preset time period based on the unique tag set and the shared tag set.

[0185] In this embodiment, each sub-time period within the second preset time period is partitioned to generate corresponding time period intervals, and each time period interval includes at least one sub-time period. Specifically, a time period interval includes one sub-time period or multiple consecutive sub-time periods. Furthermore, for each time period interval, its corresponding first style tag can be determined, thereby forming a corresponding tag set. This embodiment mainly focuses on two types of sets: a unique tag set and a shared tag set.

[0186] The unique tag set for a specific time period includes first-style tags that are unique to that time period, meaning they are not present in other time periods. The shared tag set for multiple time periods includes first-style tags that exist in all of the time periods.

[0187] If each first style tag is obtained by deduplicating candidate style tags, the tag set for each time period can also be determined based on the repetition of each candidate style tag.

[0188] For example, if one time interval corresponds to candidate style tags A, B, and C, and another time interval corresponds to candidate style tags A, C, and D, then the unique tag set of the first time interval can be determined as {B}, the unique tag set of the second time interval as {D}, and the common tag set of the two is {A,C}. If a third time interval corresponds to candidate style tags A, B, and E, then the unique tag set of the first time interval is empty (null), and the common tag set of the three is {A}.

[0189] Based on some or all of these unique tag sets and shared tag sets, the changes in the user's listening style during the second preset time period can be determined, thereby identifying the corresponding style change category.

[0190] Optionally, the second preset time period includes a first time period interval, a second time period interval, and a third time period interval arranged in chronological order. For example, each sub-time period corresponds to a specific year. If the second preset time period includes three years, then each sub-time period can serve as its corresponding time period interval. Alternatively, ... Figure 7 For example, the second preset time period is divided into 5 years, which can be further divided into three broader time periods. For instance, 2021 can be used as the first time period, 2022-2024 as the second time period, and 2025 as the third time period; or, 2021-2022 can be used as the first time period, 2023 as the second time period, and 2024-2025 as the third time period.

[0191] Furthermore, step f12, "determining the style change category of the user's listening style within the second preset time period based on the unique tag set and the shared tag set," may specifically include the following steps.

[0192] Step f121: If the common tag set of the first time interval, the second time interval, and the third time interval contains no less than a first preset number of first style tags, then the style change category is set as the first category.

[0193] Step f122: If both the unique tag set of the first time interval and the unique tag set of the third time interval contain no less than the second preset number of first style tags, then the style change category is set as the second category.

[0194] Step f123: If the common tag set of the first time interval and the third time interval contains no less than a third preset number of first style tags, then set the style change category to the third category.

[0195] Step f124: If the unique tag set of the second time period contains no less than a fourth preset number of first style tags, then set the style change category to the fourth category.

[0196] Step f125: If the number of first style tags exceeds the fifth preset number, then set the style change category to the fifth category.

[0197] In this embodiment, if the common tag set of the first time interval, the second time interval, and the third time interval contains no less than a first preset number of first style tags, it indicates that the user's frequently listened-to song style has appeared in multiple consecutive time intervals, such as the style the user listens to every year. Therefore, the style change category can be set as the first category, and the frequently listened-to song style can be highlighted. For example, from the common tag set of the three time intervals, style tags that the user listens to every year can be selected, sorted according to playback parameters such as the number of songs listened to or the duration, and the second style tags required in the copy can be selected. The number of second style tags can be at most 4 and at least 1.

[0198] If both the unique tag set for the first time period and the unique tag set for the third time period contain at least a second preset number of first style tags, it indicates that the user listened to different song styles in different sub-time periods (e.g., different years) within the second preset time period. Therefore, the style change category can be set as the second category, and the music styles frequently listened to by the user in different periods can be highlighted. For example, the top style tag in the first time period and the top style tag or more style tags in the third time period can be identified, and these style tags can be used as the second style tags.

[0199] If the shared tag set of the first and third time intervals contains at least a third preset number of first style tags, it indicates that within the second preset time interval, the user listened to songs of roughly the same style at the beginning and end of different sub-time intervals (e.g., different years), but may have listened to songs of different styles in the middle of the second time interval. In other words, the user's listening style fluctuates. Therefore, the style change category can be set as the third category, and the relevant styles should be highlighted. For example, one or more first style tags ranked high in the shared tag set can be identified and used as the second style tags needed in the copy.

[0200] If the unique tag set for the second time period contains no fewer than the fourth preset number of first style tags, it indicates that there are musical styles that were listened to in the middle but not at the beginning or end of the three time periods. Therefore, the style change category can be set as the fourth category, and the unique musical styles of the second time period can be highlighted. For example, one or more first style tags can be identified from the unique tag set for the second time period, and all of them can be used as the second style tags needed in the copy.

[0201] If the number of first style tags exceeds the fifth preset number, it means that the number of style tags after deduplication is large, and correspondingly, the number of style tags in the common tag set is small. Therefore, in this case, the style change category can be set as the fifth category, and the unique style tags of each time period can be highlighted. For example, the top-ranked first style tag in the unique tag set of each time period can be used as the second style tag.

[0202] It is understood that the first, second, third, fourth, and fifth categories mentioned above are five pre-set different style variation categories. The first, second, third, fourth, and fifth preset quantities can be the same or different; this embodiment does not limit this.

[0203] For the five scenarios shown in steps f121 to f125 above, appropriate priorities can be set for each scenario to determine which scenario is currently met. For example, if the priorities of steps f121 to f125 gradually decrease, they can be executed sequentially from f121 to f125 until a scenario is met and the style change category can be determined. Conversely, if the priorities of steps f121 to f125 gradually increase, they should be executed sequentially from f125 to f121. Of course, other priorities can be set based on actual needs; this embodiment does not limit this. If none of the priorities are met, a fallback message is triggered, displaying a basic summary of the music style preference.

[0204] In addition, if the number of sub-time periods within the second preset time period is too small to divide into three time period intervals, for example, if the second preset time period only contains two sub-time periods and can only generate two time period intervals, then other simplified logic can be used to determine the style change category and thus determine the appropriate second style tag.

[0205] For example, if the number of first style tags in the shared tag set of two time intervals is greater than a preset number (e.g., the sixth preset number), then a certain number (e.g., two) of the first style tags are selected from the shared tag set as the second style tags to be displayed. If the number of first style tags in the shared tag set of two time intervals is less than a preset number (e.g., the sixth preset number), then the first style tag with the largest playback parameter corresponding to each time interval is selected as the second style tag, for example, the style tag with the highest playback volume is selected as the second style tag required in the copy.

[0206] The music listening data processing method provided in this embodiment analyzes a user's listening style over a certain period of time, identifies the relevant first style tags, and generates a music listening style page. This page displays the differences in a user's listening style across different sub-time periods, thus representing changes in listening style. Generating style change curves for each first style tag visually demonstrates changes in the user's musical taste, providing a multi-dimensional view of the user's listening behavior. Furthermore, selecting some first style tags as second style tags and adding relevant style change text to the music listening style page facilitates user interpretation. Based on the unique and shared tag sets corresponding to each time period, the method can accurately determine changes in the user's listening style, allowing for targeted selection of the required second style tags in the text based on the actual style change categories.

[0207] This embodiment also provides a device for processing music playback data, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0208] This embodiment provides a device for processing music listening data, such as... Figure 8 As shown, the device includes: The acquisition module 801 is used to acquire user listening behavior data within a first preset time period; Grouping module 802 is used to group the first preset time period according to preset grouping rules to determine multiple time period groups; The filtering module 803 is used to determine multiple candidate songs corresponding to any time period group based on the listening behavior data within the time period group. The processing module 804 is used to determine the target emotional type corresponding to the time period group based on the rhythm parameters of multiple candidate songs within the time period group. The generation module 805 is used to generate corresponding listening emotion pages based on the target emotion type corresponding to each time period group.

[0209] In some optional implementations, the step of grouping the first preset time period according to a preset grouping rule to determine multiple time period groups includes: grouping each sub-time period according to the periodic characteristics of each sub-time period within the first preset time period to determine multiple time period groups; the time period group includes multiple sub-time periods with the same periodic characteristics.

[0210] In some optional implementations, determining multiple candidate songs corresponding to the time period group based on listening behavior data within the time period group includes: determining first playback parameters for each song corresponding to the time period group based on listening behavior data within the time period group; and selecting songs whose first playback parameters meet preset filtering conditions as candidate songs.

[0211] In some optional implementations, determining the target emotional type corresponding to the time period group based on the rhythm parameters of multiple candidate songs within the time period group includes: determining the parameter interval to which the rhythm parameters of each candidate song within the time period group belong; the parameter interval corresponding to the emotional type; determining the number of candidate songs corresponding to each parameter interval; and taking the emotional type corresponding to the parameter interval with the largest number of candidate songs as the target emotional type corresponding to the time period group.

[0212] In some optional implementations, generating corresponding music listening emotion pages based on the target emotion type corresponding to each of the time period groups includes: for any time period group, determining the target emotion content corresponding to the target emotion type based on the mapping relationship between emotion type and emotion content; and generating corresponding music listening emotion pages based on the target emotion content of each of the time period groups.

[0213] In some alternative implementations, there is a mapping relationship between emotion types and multiple emotion contents; The step of determining the target emotional content corresponding to the target emotional type based on the mapping relationship between emotional type and emotional content includes: when multiple time periods correspond to the same target emotional type, determining the target emotional content corresponding to the target emotional type for each of the multiple time periods based on the mapping relationship between emotional type and multiple emotional contents; wherein the target emotional contents corresponding to the multiple time periods are different from each other.

[0214] In some alternative implementations, the emotional content includes emotional expressions; The step of generating a corresponding listening emotion page based on the target emotion content of each time period group includes: for any time period group, determining the number of target emotion expressions corresponding to the target emotion type based on the second playback parameters of the candidate songs corresponding to the target emotion type within the time period group; generating a listening emotion page; the listening emotion page includes the number of target emotion expressions corresponding to each time period group.

[0215] In some optional implementations, the time period group corresponds to a grouping type; different time period groups with different grouping types have different mapping relationships; The step of determining the target emotional content corresponding to the target emotional type based on the mapping relationship between emotional type and emotional content includes: determining the target mapping relationship between emotional type and emotional content based on the target grouping type corresponding to the time period group; and determining the target emotional content corresponding to the target emotional type based on the target mapping relationship.

[0216] In some optional implementations, generating corresponding listening emotion pages based on the target emotion type corresponding to each of the time period groups includes: for at least some target emotion types, determining the third playback parameters corresponding to the target emotion type within each of the time period groups; determining the emotion change curve corresponding to the target emotion type based on the third playback parameters corresponding to the target emotion type in each time period group; and generating corresponding listening emotion pages based on the emotion change curves corresponding to the at least some target emotion types.

[0217] In some optional implementations, determining the emotional change curve corresponding to the target emotional type based on the third playback parameters corresponding to the target emotional type in each time period group includes: determining the single extreme value waveform corresponding to each time period group based on the third playback parameters corresponding to the target emotional type in each time period group; the extreme value of the single extreme value waveform is positively correlated with the third playback parameters; and splicing the single extreme value waveforms of the target emotional type in each time period group to form the emotional change curve corresponding to the target emotional type.

[0218] In some optional implementations, when the target emotion type is positive, the emotion change curve corresponding to the target emotion type is located in a first region of the target page; when the target emotion type is negative, the emotion change curve corresponding to the target emotion type is located in a second region of the target page that is symmetrical to the first region.

[0219] In some optional implementations, the acquisition module 801 is further configured to: acquire user listening behavior data within a second preset time period; the second preset time period includes multiple sub-time periods; The processing module 804 is further configured to determine the first style tag to be displayed based on the listening behavior data in each of the sub-time periods. The generation module 805 is further configured to generate corresponding music listening style pages based on each of the first style tags.

[0220] In some optional implementations, determining the first style tag to be displayed based on the listening behavior data within each of the sub-time periods includes: for any sub-time period, determining at least one candidate style tag based on the listening behavior data within the sub-time period; and performing deduplication processing on the candidate style tags corresponding to each sub-time period to obtain the deduplicated first style tag.

[0221] In some optional implementations, determining at least one candidate style tag based on listening behavior data within the sub-time period includes: determining the fourth playback parameter of each song within the sub-time period based on listening behavior data within the sub-time period; statistically analyzing the fourth playback parameters of each song belonging to the same style tag to determine the fourth playback parameter corresponding to each style tag; and selecting style tags whose fourth playback parameters meet preset conditions as candidate style tags.

[0222] In some optional implementations, generating a corresponding music listening style page based on each of the first style tags includes: for any first style tag, determining the fifth playback parameter corresponding to the first style tag in each of the sub-time periods; determining the style change curve corresponding to the first style tag based on the fifth playback parameter corresponding to the first style tag in each of the sub-time periods; and generating a corresponding music listening style page based on the style change curve corresponding to each of the first style tags.

[0223] In some optional implementations, determining the style change curve corresponding to the first style tag based on the fifth playback parameter corresponding to the first style tag in each of the sub-time periods includes: for any sub-time period, determining the proportion of playback parameters corresponding to each first style tag based on the fifth playback parameter corresponding to each first style tag in the sub-time period; determining the amplitude corresponding to the proportion of playback parameters of the first style tag based on a preset correspondence between the proportion and the amplitude; and determining the style change curve corresponding to the first style tag based on the amplitude corresponding to the first style tag in each of the sub-time periods; the style change curve is used to represent the change in the amplitude corresponding to the first style tag according to the chronological order of each of the sub-time periods.

[0224] In some optional implementations, the processing module 804 is further configured to: determine the style change category based on the first style tag corresponding to each of the sub-time periods; select a portion of the first style tags as second style tags based on the style change category, and generate style change text containing the second style tag; The step of generating corresponding music listening style pages based on each of the first style tags includes: generating corresponding music listening style pages based on the style change text and each of the first style tags.

[0225] In some optional implementations, determining the style change category based on the first style tag corresponding to each of the sub-time periods includes: for each time period interval within the second preset time period, determining a unique tag set corresponding to each of the time period intervals and a common tag set for multiple time period intervals; the time period interval includes at least one of the sub-time periods; and determining the style change category of the user's listening style within the second preset time period based on the unique tag set and the common tag set.

[0226] In some optional implementations, the second preset time period includes a first time period interval, a second time period interval, and a third time period interval arranged in chronological order; The step of determining the style change category of the user's listening style within the second preset time period based on the unique tag set and the shared tag set includes: if the shared tag set of the first time period interval, the second time period interval, and the third time period interval contains no less than a first preset number of first style tags, then the style change category is set as a first category; if both the unique tag set of the first time period interval and the unique tag set of the third time period interval contain no less than a second preset number of first style tags, then the style change category is set as a second category; if the shared tag set of the first time period interval and the third time period interval contains no less than a third preset number of first style tags, then the style change category is set as a third category; if the unique tag set of the second time period interval contains no less than a fourth preset number of first style tags, then the style change category is set as a fourth category; if the number of first style tags exceeds a fifth preset number, then the style change category is set as a fifth category.

[0227] The music playback data processing apparatus provided in this disclosure can execute the music playback data processing method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0228] Figure 9 This is a schematic diagram of an electronic device provided in an embodiment of this application. See below for details. Figure 9 This diagram illustrates a suitable structural schematic for implementing the electronic device described in the embodiments of this application. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 901, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 902 or a program loaded from memory 908 into random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the electronic device. The processor 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0229] Typically, the following devices can be connected to I / O interface 905: input devices 906 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 907 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 908 including, for example, magnetic tapes, hard disks, etc.; and communication devices 909. Communication device 909 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 9Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0230] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 909, or installed from a memory 908, or installed from a ROM 902. When the computer program is executed by the processor 901, it performs the functions defined in the music data processing method of embodiments of this application.

[0231] Figure 9 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0232] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the method for processing music listening data shown in the above embodiments is implemented.

[0233] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0234] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for processing music listening data, characterized in that, The method includes: Acquire user listening behavior data within a first preset time period; The first preset time period is grouped according to preset grouping rules to determine multiple time period groups; For any of the time period groups, multiple candidate songs corresponding to the time period group are determined based on the listening behavior data within the time period group. Based on the rhythm parameters of multiple candidate songs within the time period group, the target emotional type corresponding to the time period group is determined; Based on the target emotional type corresponding to each of the aforementioned time periods, a corresponding emotional page for listening to music is generated.

2. The method according to claim 1, characterized in that, The step of grouping the first preset time period according to a preset grouping rule to determine multiple time period groups includes: Based on the periodic characteristics of each sub-time period within the first preset time period, the sub-time periods are grouped to determine multiple time period groups; each time period group includes multiple sub-time periods with the same periodic characteristics.

3. The method according to claim 1, characterized in that, The step of generating corresponding music listening emotion pages based on the target emotion type corresponding to each of the time period groups includes: For any of the time period groups, the target emotional content corresponding to the target emotional type is determined based on the mapping relationship between emotional type and emotional content; Based on the target emotional content of each time period group, a corresponding emotional page for listening to music is generated.

4. The method according to claim 3, characterized in that, There is a mapping relationship between emotion types and multiple emotion contents; The step of determining the target emotional content corresponding to the target emotional type based on the mapping relationship between emotional type and emotional content includes: When multiple time periods correspond to the same target emotion type, the target emotion content corresponding to the target emotion type is determined for each of the multiple time periods based on the mapping relationship between the emotion type and multiple emotion contents; wherein the target emotion contents corresponding to the multiple time periods are different from each other.

5. The method according to claim 3, characterized in that, The emotional content includes emotional expressions; The step of generating corresponding emotional listening pages based on the target emotional content of each time period group includes: For any of the time period groups, the number of target emotional expressions corresponding to the target emotional type is determined based on the second playback parameters of the candidate songs corresponding to the target emotional type within the time period group; Generate a music listening emotion page; the music listening emotion page includes a number of target emotion expressions corresponding to each of the time periods.

6. The method according to any one of claims 3 to 5, characterized in that, The time period group corresponds to a grouping type; different grouping types of time period groups have different mapping relationships; The step of determining the target emotional content corresponding to the target emotional type based on the mapping relationship between emotional type and emotional content includes: Based on the target grouping type corresponding to the time period group, determine the target mapping relationship between emotion type and emotion content; Based on the target mapping relationship, determine the target emotional content corresponding to the target emotional type.

7. A device for processing music playback data, characterized in that, The device includes: The acquisition module is used to acquire user listening behavior data within a first preset time period; The grouping module is used to group the first preset time period according to preset grouping rules to determine multiple time period groups; The filtering module is used to determine multiple candidate songs corresponding to any given time period group based on listening behavior data within the time period group. The processing module is used to determine the target emotional type corresponding to the time period group based on the rhythm parameters of multiple candidate songs within the time period group; The generation module is used to generate corresponding listening emotion pages based on the target emotion type corresponding to each of the time period groups.

8. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the computer instructions to perform the method for processing music listening data as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method for processing music listening data as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions, which are used to cause a computer to perform the method for processing music listening data according to any one of claims 1 to 6.

Images