Music pushing method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a music singing method and device, electronic equipment and storage medium, comprising: in response to identifying that a user sings a target song, obtaining target song tree data, the target song comprising N playing paragraphs; determining a first playing strategy based on the target song tree data, the i-th playing strategy corresponding to the i-th playing paragraph of the target song, i being a positive integer; collecting the i-th singing data of the user based on the i-th playing strategy, and determining the i+1-th playing strategy based on the i-th singing data and the target song tree data, i being a positive integer less than N. Through the closed-loop mechanism of "song structure analysis, paragraph-level strategy generation, real-time singing feedback, and dynamic evolution of the next paragraph strategy", the present scheme realizes the paradigm upgrade of karaoke system from a mechanical scoring tool to a context-aware, personalized and intelligent singing coach, significantly improving user experience, singing quality and intelligence level.

Description

Technical Field

[0001] This disclosure relates to the fields of artificial intelligence and music technology, and in particular to a music playback method, device, electronic device and storage medium. Background Technology

[0002] With the rapid development of digital audio processing and human-computer interaction technologies, karaoke has expanded from traditional offline entertainment scenarios to mobile and smart terminal applications. Currently, mainstream karaoke software and offline smart KTV equipment generally adopt a standardized singing assistance system: the system uses the original version of the song or a top-selected cover version as a fixed reference template to generate an accompaniment track with dynamic lyrics subtitles; it collects the user's vocal signal in real time through the microphone and compares the user's voice with the standard template based on basic acoustic characteristics such as pitch and rhythm, thereby synchronously displaying pitch trajectory, beat prompts, and segmented scores on the screen. After the performance, users can perform post-processing on the recorded audio, such as pitch correction, reverb selection, and pitch adjustment, and obtain a comprehensive evaluation including singing score and percentage of users beaten.

[0003] While the aforementioned technologies have significantly improved the karaoke experience for the general public, there are still obvious shortcomings in terms of AI-driven intelligent and personalized singing deduction. Summary of the Invention

[0004] This disclosure aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, one purpose of this disclosure is to propose a method for music deduction.

[0006] The second objective of this disclosure is to propose a music push-singing device.

[0007] The third objective of this disclosure is to propose an electronic device.

[0008] The fourth objective of this disclosure is to provide a non-transitory computer-readable storage medium.

[0009] The fifth objective of this disclosure is to provide a computer program product.

[0010] To achieve the above objectives, a first aspect of this disclosure provides a music playback method, comprising: in response to recognizing a user singing a target song, acquiring target song tree data, wherein the target song includes N playback segments; determining a first playback strategy based on the target song tree data, wherein the i-th playback strategy corresponds to the i-th playback segment of the target song, and i is a positive integer; collecting the i-th singing data of the user based on the i-th playback strategy, and determining an (i+1)-th playback strategy based on the i-th singing data and the target song tree data, wherein i is a positive integer less than N.

[0011] According to one embodiment of this disclosure, obtaining target song tree data includes: in response to the existence of at least one user song tree data for the user, using the user's user song tree data as the target song tree data; in response to the absence of user song tree data for the user, using popular song tree data as the target song tree data.

[0012] According to one embodiment of this disclosure, in response to the existence of user song tree data, determining a first playback strategy based on the song tree data includes: obtaining the recommendation priority of the user song tree data; and selecting the candidate first playback strategy of the user song tree data with the highest recommendation priority as the first playback strategy.

[0013] According to one embodiment of this disclosure, determining the (i+1)th playback strategy based on the i-th singing data and the target song tree data includes: determining at least one candidate (i+1)th playback strategy based on the user song tree data; and determining the (i+1)th playback strategy from the candidate (i+1)th playback strategies based on the i-th singing data.

[0014] According to one embodiment of this disclosure, determining the (i+1)th playback strategy from the candidate (i+1)th playback strategies based on the i-th singing data includes: calculating the binarized data of the i-th singing data; matching the binarized data with all the user song tree data to determine the target song tree data; and using the candidate (i+1)th playback strategy of the target song tree data as the (i+1)th playback strategy.

[0015] According to one embodiment of this disclosure, calculating the binarized data of the i-th singing data includes: determining multiple singing features based on the i-th singing data; determining sub-binarized data corresponding to each of the multiple singing features; and determining the binarized data of the i-th singing data based on the sub-binarized data.

[0016] According to one embodiment of this disclosure, the step of matching the binarized data with all the user song tree data to determine the target song tree data includes: obtaining the binarized data of each candidate (i+1)th playback strategy of all the user song tree data; calculating the similarity value between the binarized data of the i-th performance data and the binarized data of the candidate i-th playback strategy; and taking the song tree data corresponding to the candidate i-th playback strategy with the largest similarity value as the target song tree data.

[0017] According to one embodiment of this disclosure, the method further includes: determining the pre-embedded points of the target song; and generating a pre-embedded point singing recommendation strategy based on the pre-embedded points and the user's singing data.

[0018] According to one embodiment of this disclosure, the method further includes: generating a target song tree based on playback strategies 1 to N in response to the user ending the performance of the target song.

[0019] To achieve the above objectives, a second aspect of this disclosure provides a music playback device, comprising: an acquisition module, configured to acquire target song tree data in response to recognizing a user singing a target song, the target song comprising N playback segments; a first generation module, configured to determine a first playback strategy based on the target song tree data, the i-th playback strategy corresponding to the i-th playback segment of the target song, i being a positive integer; and a second generation module, configured to collect the i-th singing data of the user based on the i-th playback strategy, and determine an (i+1)-th playback strategy based on the i-th singing data and the target song tree data, i being a positive integer less than N.

[0020] To achieve the above objectives, a third aspect of this disclosure provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to implement the music push-singing method as described in the first aspect of this disclosure.

[0021] To achieve the above objectives, a fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the music push-singing method as described in the first aspect of this disclosure.

[0022] To achieve the above objectives, a fifth aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the music push-singing method as described in the first aspect of this disclosure.

[0023] Beneficial effects: Attached Figure Description

[0024] Figure 1 This is a schematic diagram of a music counting method according to one embodiment of the present disclosure; Figure 2 This is a schematic diagram of another music counting method according to one embodiment of the present disclosure; Figure 3 This is a schematic diagram of another music counting method according to one embodiment of the present disclosure; Figure 4 This is a schematic diagram of another music counting method according to one embodiment of the present disclosure; Figure 5 This is a schematic diagram of a music push-singing device according to one embodiment of the present disclosure; Figure 6 This is a schematic diagram of an electronic device according to one embodiment of the present disclosure. Detailed Implementation

[0025] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0026] The acquisition, storage, use, and processing of data in this disclosed technical solution all comply with the relevant provisions of relevant laws and regulations.

[0027] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0028] Existing karaoke software and offline smart KTV equipment provide users with highly mechanical karaoke services that lack personalized adaptation capabilities.

[0029] Existing systems generally rely on a single, static original recording or a high-scoring cover as the sole evaluation criterion, failing to consider the significant differences among individual users in terms of vocal range, timbre, singing habits, and emotional expression. For example, even if a user with a low voice performs a high-pitched pop song consistently and emotionally, the system may still award a low score because the vocal range deviates from the original high-note template. Furthermore, current segmented scoring mechanisms are mostly based on mechanical matching using preset time-pitch grids, failing to dynamically adjust the evaluation criteria according to the user's actual singing ability. This results in a disconnect between the scoring results and the actual singing level, leading to a homogenized user experience.

[0030] Meanwhile, existing karaoke software and offline smart KTV equipment lack the ability to perceive and enhance the context of lyrics at the paragraph level.

[0031] Existing technologies struggle to perform fine-grained, semantic real-time analysis of a user's singing process. Systems typically only provide feedback on pitch deviations within the current note or a short time window, failing to combine the already sung content with the context of the lyrics to be sung. For example, in the chorus, the system cannot identify the downward trend in pitch caused by insufficient breath support, nor can it provide advance warnings such as "pay attention to strengthening support for the next high note." When specific words (such as dialect words or foreign words) are mispronounced, there is a lack of precise location and correction suggestions based on speech recognition and pronunciation models. Furthermore, it cannot dynamically recommend appropriate performance intensity or embellishment treatment methods based on the song's emotional progression (such as from calm to rousing).

[0032] To address the aforementioned problems, this disclosure proposes a music deduction method. Figure 1 This is a schematic diagram of a music counting method according to one embodiment of the present disclosure, such as... Figure 1 As shown, this music recommendation method includes the following steps: S101, in response to recognizing that the user is singing the target song, obtain the target song tree data, the target song includes N playback segments.

[0033] The music push-singing method of this application embodiment can be applied to scenarios where users sing songs. The execution subject of the music push-singing in this application embodiment can be the music push-singing device of this application embodiment, which can be installed on an electronic device.

[0034] In this embodiment of the disclosure, there are various methods for identifying a user singing a target song, and no limitation is made here. For example, the song that the user is about to sing or is currently singing can be confirmed through any of the following methods: Users actively select songs, for example, by clicking on song A in the playlist; Automatically match songs using audio fingerprinting or humming recognition; Real-time recognition of intro / vocals input from the microphone.

[0035] Once the identification is successful, the subsequent process of loading structured song data is triggered.

[0036] It should be noted that song tree data is a hierarchical and structured semantic model of songs, which organizes the multidimensional information of your songs in a "tree" shape.

[0037] Each node in the tree corresponds to a playback segment or section, such as verse, chorus, bridge, intro, interlude, outro, etc.

[0038] N playback segments represent the target song being finely divided into N logical units. For example, these could be continuous vocal performances, with each segment possessing attributes such as time boundaries, semantic tags, and musical features. It should be noted that N logical units could be N lines of lyrics from the target song, or they could be a complete vocal segment (e.g., several consecutive lines can also be considered a playback segment).

[0039] It should be noted that the target song tree data in this embodiment can be constructed based on the user's historical singing data, or it can be pre-configured data, or it can be constructed based on popular singing data. No limitations are made here.

[0040] S102, determine the first playback strategy based on the target song tree data. The i-th playback strategy corresponds to the i-th playback segment of the target song, where i is a positive integer.

[0041] It should be noted that the i-th playback strategy is not a single parameter, but a set of strategies, which may include multiple sub-strategies. For example, it may include reference pitch curve (dynamically generating pitch templates that adapt to the user's vocal range), rhythm tolerance (adjusting the rhythm scoring threshold according to the characteristics of the paragraph), emotional interpretation suggestions (pushing real-time prompts based on emotional tags), etc.

[0042] The target song tree data includes multiple playback strategies, and each playback strategy corresponds to at least one playback segment.

[0043] S103: Collect the i-th singing data of the user based on the i-th playback strategy, and determine the (i+1)-th playback strategy based on the i-th singing data and the target song tree data, where i is a positive integer less than N.

[0044] It should be noted that the i-th singing data can include various types of data, without any limitations here. For example, it can include the following data: Real-time vocal audio stream: The raw audio signal of the user singing during the i-th playback segment, captured by a microphone.

[0045] Pitch trajectory, reflecting the pitch changes of the user's actual singing, i-th singing data.

[0046] Rhythm alignment information: The time offset between the user's sung notes and the standard beat, used to assess rhythmic stability.

[0047] Energy / loudness characteristics: a time-series curve representing the intensity of a user's voice, helping to determine the degree of breath support and emotional engagement.

[0048] Emotional expression characteristics: The emotional fit of the current paragraph inferred through acoustic models (such as prosody, vibrato frequency, dynamic range).

[0049] Abnormal performance event markers: including detection results of abnormal behaviors such as voice cracking, loss of voice, long pauses, and rushing / dragging out the beat.

[0050] In this embodiment of the disclosure, the system has loaded the song tree data of the target song and generated the i-th playback strategy for the i-th segment. During the user's performance of the i-th segment, the accompaniment and real-time feedback are driven synchronously according to the i-th playback strategy, and the above-mentioned multi-dimensional i-th performance data are collected and analyzed in real time.

[0051] When the i-th paragraph ends (or is nearing the end), the user's current state is assessed by comparing the i-th singing data with the expected performance of the i-th paragraph in the song tree. This allows for the prediction of potential challenges for the i+1-th paragraph (such as "the next section is a higher chorus, requiring stronger breath support"). The i+1-th playback strategy is then dynamically generated or adapted to achieve feedforward and feedback-based intelligent control.

[0052] In this embodiment, firstly, in response to the recognition that a user is singing a target song, target song tree data is acquired. The target song includes N playback segments. Then, based on the target song tree data, a first playback strategy is determined. The i-th playback strategy corresponds to the i-th playback segment of the target song, where i is a positive integer. Finally, the user's i-th singing data based on the i-th playback strategy is collected, and based on the i-th singing data and the target song tree data, the (i+1)-th playback strategy is determined, where i is a positive integer less than N. Through a closed-loop mechanism of "structured song parsing, segment-level strategy generation, real-time singing feedback, and dynamic evolution of the next segment strategy," this solution achieves a paradigm upgrade of the karaoke system from a mechanical scoring tool to a context-aware, personalized, and intelligent singing coach, significantly improving user experience, singing quality, and intelligence level.

[0053] It should be noted that the target song tree data in this embodiment may include two types: in response to the existence of at least one user song tree data, the user's user song tree data is used as the target song tree data; in response to the absence of user song tree data, popular song tree data is used as the target song tree data.

[0054] In the above embodiments, in response to the existence of user song tree data, the first playback strategy is determined based on the song tree data, and can also be determined by... Figure 2 To further explain, the method includes: S201, Obtain the recommendation priority of the user's song tree data.

[0055] In this embodiment of the disclosure, for the same target song, due to the different singing scenarios or singing states of the users, the user song tree data generated each time is different. However, each version is a complete "song tree" containing N paragraphs and their corresponding performance metadata.

[0056] The comprehensive score or ranking weight of the user's song tree data, calculated for each song tree version, is used to measure its current suitability and recommendation value to the user.

[0057] S202, the candidate first playback strategy of the user song tree data with the highest recommendation priority is used as the first playback strategy.

[0058] It should be noted that the recommendation priority can be fixed or non-fixed, and can be derived by weighted fusion of multiple contextual factors. For example, it can be determined based on the user's historical vocal range distribution, commonly used pitch shifts, singing style preferences, and skill level, or by weighting factors such as the current device (mobile phone / professional microphone), ambient noise, and time of day.

[0059] In the above embodiments, in response to the existence of user song tree data, the (i+1)th playback strategy is determined based on the i-th singing data and the target song tree data. It can also be achieved through... Figure 3 To further explain, the method includes: S301, determine at least one candidate i+1th playback strategy based on the user song tree data.

[0060] In this embodiment of the disclosure, the candidate i-th playback strategy in the user song tree data has a one-to-one correspondence with the i-th playback segment of the target song. Therefore, the corresponding candidate playback strategy can be determined according to the segment number currently sung by the user.

[0061] S302, determine the (i+1)th playback strategy from the candidate (i+1)th playback strategies based on the i-th singing data.

[0062] In this embodiment of the disclosure, the binarized data of the i-th singing data can be calculated first, and then the binarized data can be matched with all user song tree data to determine the target song tree data. Finally, the candidate i+1 playback strategy of the target song tree data is used as the i+1 playback strategy.

[0063] It should be noted that when a user sings lyrics m1-mn, the association features between leaf nodes (lyrics to be sung) and parent nodes (sung parts) in the tree structure are analyzed. Taking the third verse m3 and the fourth verse m4 as examples, the singing feature data m1-m3 before m4 is converted into binary data using the MRTS algorithm. The historical optimal singing links M1-M3 are obtained through the user's song tree N1 in the three-dimensional vector space and compared with the features of the user's actual singing links m1-m2a-m3b using the MRTS algorithm. At the same time, the optimal leaf node M4 for m4 is generated in the song tree N1.

[0064] It should be noted that to calculate the binarized data of the i-th singing data, we can first determine multiple singing features based on the i-th singing data, then determine the sub-binarized data corresponding to each of the multiple singing features, and finally determine the binarized data of the i-th singing data based on the sub-binarized data.

[0065] It should be noted that to calculate the binarized data of the i-th singing data, multiple singing features can be extracted first based on the i-th singing data. Then, for each singing feature, corresponding sub-binarized data is generated according to its semantic meaning and evaluation criteria. Finally, all sub-binarized data are integrated through preset fusion rules (such as logical AND, weighted OR, bit concatenation, etc.) to determine the overall binarized representation of the i-th singing data.

[0066] In this embodiment of the disclosure, several key dimensions of quantization features are extracted from the original singing data (audio stream, pitch trajectory, rhythm alignment result, etc.) of the i-th segment. The quantization features may include various types, such as pitch features, rhythm features, and pronunciation features.

[0067] For each feature, set a threshold or rule with clear business or acoustic significance, and map it to 0 or 1.

[0068] The sub-binarized data are merged to generate an overall binary representation. It should be noted that different fusion strategies can be adopted, such as concatenating the sub-binary data into a binary string in a fixed order, giving higher weight to high-weight features (such as pitch), or mapping the binary vectors to unique integer IDs.

[0069] In the above embodiments, the target song tree data is determined by matching the binarized data with all user song tree data. Alternatively, it can be determined by... Figure 4 To further explain, the method includes: S401, obtain the binarized data of the (i+1)th playback strategy for each user's song tree data.

[0070] S402, calculate the similarity value between the binarized data of the i-th singing data and the binarized data of the candidate i-th playback strategy, and take the song tree data corresponding to the candidate i-th playback strategy with the largest similarity value as the target song tree data.

[0071] It should be noted that after the i-th segment is finished, the system needs to determine the optimal playback strategy for the (i+1)-th segment. Since there are multiple possible versions of the song performance (i.e., multiple "user song tree data"), each version corresponds to a candidate (i+1)-th playback strategy. The system uses binary feature comparison to select the one that best matches the user's current singing style. This allows for a comparison of whether the "user's singing behavior pattern" is consistent with the "behavioral pattern expected by each strategy."

[0072] In the above embodiments, a pre-embedded point singing recommendation strategy can also be generated based on the pre-embedded points and the user's singing data by identifying the pre-embedded points of the target song.

[0073] It should be noted that "pre-embedded cue points" refer to key singing nodes that are pre-marked in the structured data (such as song trees) of the target song, and have clear musical semantics, technical difficulties, or expressive intentions.

[0074] Pre-embedded points include: marked "high note breathing", "easy to break voice", "requires strong breath", emotional turning point, verse to chorus transition sentence, emotional climax point of the bridge, or marked "emotional rise" "requires stronger resonance", key words, foreign words, dialect words, tongue twisters, etc.

[0075] After loading the target song tree data, the system parses and extracts all pre-embedded points, and activates the nearest pre-embedded points based on the current playback progress or the segment the user is about to enter.

[0076] In one possible implementation, this method supports filtering by priority (e.g., focusing only on "high difficulty" or "weak user history" types).

[0077] For each activated pre-embedded point, a personalized and executable recommendation strategy is dynamically generated. For example, if a user's history shows insufficient breath support in 80% of high-pitched passages, a strategy can be generated: 3 seconds in advance, a voice message can be given saying, "Prepare for the high note, take a deep breath!" At the same time, the drum beats in the accompaniment can be reduced to highlight the melody, and the "high-pitched protection" pitch correction mode can be enabled.

[0078] In this embodiment of the disclosure, in response to the user finishing singing the target song, a target song tree is generated based on the first to Nth playback strategies.

[0079] In one possible implementation, after a user finishes singing, the optimal link M1-MN has already been constructed in the user's song count. At the same time, based on the actual singing link matched by the user, such as m1-m2b-m3a-, the analysis is performed to determine the matching degree of the user's performance based on their best derived interpretation and emotional enhancement, and a customized score is given. The tree link M1-MN based on the song N1 sung this time and the user's actual performance data m1-m2b-m3a are persisted to the cloud three-dimensional vector space and used as one of the many historical benchmark analysis data for the user's next performance.

[0080] Corresponding to the music push-singing methods provided in the above embodiments, one embodiment of this disclosure also provides a music push-singing device. Since the music push-singing device provided in this disclosure corresponds to the music push-singing methods provided in the above embodiments, the implementation methods of the above music push-singing methods are also applicable to the music push-singing device provided in this disclosure, and will not be described in detail in the following embodiments.

[0081] Figure 5 This is a schematic diagram of a music push-to-sing device according to one embodiment of the present disclosure. As shown in FIG5, the music push-to-sing device 500 includes: The acquisition module 510 is used to acquire the target song tree data in response to the recognition that the user is singing the target song. The target song includes N playback segments.

[0082] The first generation module 520 is used to determine the first playback strategy based on the target song tree data. The i-th playback strategy corresponds to the i-th playback segment of the target song, where i is a positive integer.

[0083] The second generation module 530 is used to collect the i-th singing data of the user based on the i-th playback strategy, and determine the (i+1)-th playback strategy based on the i-th singing data and the target song tree data, where i is a positive integer less than N, and the i-th singing data includes...

[0084] According to one embodiment of this disclosure, obtaining target song tree data includes: in response to the existence of at least one user song tree data for the user, using the user's user song tree data as the target song tree data; in response to the absence of user song tree data for the user, using popular song tree data as the target song tree data.

[0085] According to one embodiment of this disclosure, in response to the existence of user song tree data, determining a first playback strategy based on the song tree data includes: obtaining the recommendation priority of the user song tree data; and selecting the candidate first playback strategy of the user song tree data with the highest recommendation priority as the first playback strategy.

[0086] According to one embodiment of this disclosure, determining the (i+1)th playback strategy based on the i-th singing data and the target song tree data includes: determining at least one candidate (i+1)th playback strategy based on the user song tree data; and determining the (i+1)th playback strategy from the candidate (i+1)th playback strategies based on the i-th singing data.

[0087] According to one embodiment of this disclosure, determining the (i+1)th playback strategy from the candidate (i+1)th playback strategies based on the i-th singing data includes: calculating the binarized data of the i-th singing data; matching the binarized data with all the user song tree data to determine the target song tree data; and using the candidate (i+1)th playback strategy of the target song tree data as the (i+1)th playback strategy.

[0088] According to one embodiment of this disclosure, calculating the binarized data of the i-th singing data includes: determining multiple singing features based on the i-th singing data; determining sub-binarized data corresponding to each of the multiple singing features; and determining the binarized data of the i-th singing data based on the sub-binarized data.

[0089] According to one embodiment of this disclosure, the step of matching the binarized data with all the user song tree data to determine the target song tree data includes: obtaining the binarized data of each candidate (i+1)th playback strategy of all the user song tree data; calculating the similarity value between the binarized data of the i-th performance data and the binarized data of the candidate i-th playback strategy; and taking the song tree data corresponding to the candidate i-th playback strategy with the largest similarity value as the target song tree data.

[0090] According to one embodiment of this disclosure, the method further includes: determining the pre-embedded points of the target song; and generating a pre-embedded point singing recommendation strategy based on the pre-embedded points and the user's singing data.

[0091] According to one embodiment of this disclosure, the method further includes: generating a target song tree based on playback strategies 1 to N in response to the user ending the performance of the target song.

[0092] Through a closed-loop mechanism of "structured song analysis, segment-level strategy generation, real-time performance feedback, and dynamic evolution of the next segment strategy," this solution achieves a paradigm shift for karaoke systems, transforming them from mechanical scoring tools to context-aware, personalized, and intelligent singing coaches, significantly improving user experience, performance quality, and intelligence.

[0093] To implement the above embodiments, this disclosure also proposes an electronic device 600. Figure 6 This is a schematic diagram of an electronic device according to one embodiment of the present disclosure, such as... Figure 6 As shown, the electronic device 600 includes: a processor 601 and a memory 602 communicatively connected to the processor. The memory 602 stores instructions executable by at least one processor. The instructions are executed by at least one processor 601 to implement the functions described in this disclosure. Figures 1-4 The music playback method of the embodiment.

[0094] To implement the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to implement the present disclosure. Figures 1-4 The music playback method of the embodiment.

[0095] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program, which, when executed by a processor, implements the features of this disclosure. Figures 1-4 The music playback method of the embodiment.

[0096] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0097] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0098] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0099] Furthermore, 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. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0100] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0101] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that contains, stores, communicates, propagates, or transmits programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0102] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0103] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0104] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0105] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for music deduction and singing, characterized in that, include: In response to the recognition that a user is singing a target song, the target song tree data is obtained, wherein the target song includes N playback segments; Based on the target song tree data, the first playback strategy is determined, where the i-th playback strategy corresponds to the i-th playback segment of the target song, and i is a positive integer. Collect the user's i-th singing data based on the i-th playback strategy, and determine the (i+1)-th playback strategy based on the i-th singing data and the target song tree data, where i is a positive integer less than N.

2. The method according to claim 1, characterized in that, The acquisition of the target song tree data includes: In response to the existence of at least one user song tree data for the user, the user song tree data of the user is used as the target song tree data; In response to the absence of user song tree data for the user, popular song tree data is used as the target song tree data.

3. The method according to claim 2, characterized in that, In response to the existence of user song tree data, the step of determining the first playback strategy based on the song tree data includes: Obtain the recommendation priority of the user's song tree data; The candidate first playback strategy of the user song tree data with the highest recommendation priority is used as the first playback strategy.

4. The method according to claim 3, characterized in that, The determination of the (i+1)th playback strategy based on the i-th singing data and the target song tree data includes: Based on the user song tree data, at least one candidate i+1th playback strategy is determined; The (i+1)th playback strategy is determined from the candidate (i+1)th playback strategies based on the i-th singing data.

5. The method according to claim 4, characterized in that, The step of determining the (i+1)th playback strategy from the candidate (i+1)th playback strategies based on the i-th singing data includes: Calculate the binarized data of the i-th singing data; The target song tree data is determined by matching the binarized data with all the user song tree data. The candidate i+1th playback strategy of the target song tree data is taken as the i+1th playback strategy.

6. The method according to claim 4, characterized in that, The calculation of the binarized data of the i-th singing data includes: Multiple singing features are determined based on the i-th singing data; Determine the sub-binarized data corresponding to each of the multiple singing features; The binarized data of the i-th singing data is determined based on the sub-binarized data.

7. The method according to claim 5 or 6, characterized in that, The step of matching the binarized data with all the user song tree data to determine the target song tree data includes: Obtain the binarized data of the (i+1)th playback strategy for each of the user song tree data; Calculate the similarity value between the binarized data of the i-th singing data and the binarized data of the candidate i-th playback strategy, and take the song tree data corresponding to the candidate i-th playback strategy with the largest similarity value as the target song tree data.

8. The method according to any one of claims 1-6, characterized in that, The method further includes: Determine the pre-embedded points for the target song; A pre-embedded point singing recommendation strategy is generated based on the pre-embedded points and the user's singing data.

9. The method according to any one of claims 1-6, characterized in that, The method further includes: In response to the user finishing singing the target song, a target song tree is generated based on playback strategies 1 to N.

10. A music push-singing device, characterized in that, include: The acquisition module is used to acquire target song tree data in response to the recognition that a user is singing a target song, wherein the target song includes N playback segments; The first generation module is used to determine the first playback strategy based on the target song tree data, where the i-th playback strategy corresponds to the i-th playback segment of the target song, and i is a positive integer. The second generation module is used to collect the user's i-th singing data based on the i-th playback strategy, and determine the (i+1)-th playback strategy based on the i-th singing data and the target song tree data, where i is a positive integer less than N.

11. An electronic device, characterized in that, Including memory and processor; The processor reads executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-9.

Images