Animal music production method, recommendation method, medium, device and computing device

Abstract

The embodiments of the present disclosure provide a method for producing animal music. The method comprises: using an animal music prediction model to predict each piece of first human music to obtain second human music, where the second human music is first human music suitable for producing animal music; producing the first animal music based on the second human music. The animal music prediction model can screen out second human music suitable for producing animal music from multiple pieces of first human music, that is, animal music can be prepared using existing human music, without creating specific melodies for animals, that is, the creator does not need to have good musical literacy and knowledge of animal auditory perception to produce animal music, thereby reducing the production cost of animal music. In addition, the embodiments of the present disclosure provide a method, medium, device and computing device for recommending animal music.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of animal music production, and more specifically, embodiments of the present disclosure relate to animal music production methods, recommendation methods, media, devices, and computing devices. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the present disclosure. No description herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] Animal music is a type of music that is specially tailored for animals. Animal music can arouse the emotions of animals. For example, animal music can soothe animals and make them feel happy.

[0004] Animal music includes specific melodies that evoke emotions in animals. Due to differences in ecology and sensory perception among different animals, different types of animals will have different feelings about the same melody, so specific melodies need to be formulated through the auditory perception of animals.

[0005] The creation of specific melodies in animal music requires the creator to have sufficient musical literacy, and the customization of specific melodies requires knowledge of animals' auditory perception. In other words, the creation of animal music may require the participation of zoologists and musicians, resulting in a higher production cost for animal music. Summary of the invention

[0006] The present disclosure provides a method for producing animal music, a method for recommending animal music, a medium, a device and a computing device to solve the problem of high production cost of animal music.

[0007] In a first aspect of the disclosed embodiments, a method for producing animal music is provided, comprising: using an animal music prediction model to predict each piece of first human music to obtain second human music, wherein the second human music is the first human music suitable for producing animal music; and producing first animal music based on the second human music.

[0008] In another embodiment of the present disclosure, the step of producing the first animal music based on the second human music includes: acquiring sound information, the sound information including sounds that cause emotional changes in animals; and producing the first animal music based on the sound information and the second human music.

[0009] In another embodiment of the present disclosure, the step of producing the first animal music based on the sound information and the second human music includes: processing the sound information to obtain auxiliary sound material; extracting music clips suitable for producing animal music from the second human music, and processing the music clips to obtain main sound material; mixing the main sound material with the auxiliary sound material to generate the first animal music.

[0010] In another embodiment of the present disclosure, the processing of the music clip includes at least one of the following: modifying the sound intensity in the music clip; modifying the sound frequency of the music clip; modifying the rhythm of the music clip; modifying the sound of the instrument in the music clip; and modifying the timbre in the music clip.

[0011] In another embodiment of the present disclosure, after the step of processing the music clip to obtain the main sound material, it also includes: storing the auxiliary sound material and the main sound material in a material database.

[0012] In another embodiment of the present disclosure, before the step of using the animal music prediction model to predict each first human music, it also includes: obtaining each second animal music and each third human music, the third human music is provided with a label, and the label is used to indicate that the third human music is suitable or unsuitable for making animal music; training a preset model according to each second animal music and each third human music to obtain the animal music prediction model.

[0013] In another embodiment of the present disclosure, after the step of producing the first animal music according to the second human music, it also includes: determining the first animal to which the second human music is suitable; and associating the identifier corresponding to the first animal with the first animal music and storing it in an animal music database.

[0014] In another embodiment of the present disclosure, after the step of associating the identifier corresponding to the first animal with the first animal music and storing it in an animal music database, it also includes: obtaining animal information and determining the second animal to which the animal information belongs; in the animal music database, obtaining the third animal music matched by the identifier of the second animal; and outputting the third animal music.

[0015] In a second aspect of the disclosed embodiments, a method for recommending animal music is provided, comprising: obtaining animal information; determining, in each piece of first animal music, a plurality of third animal music pieces that match the animal information, wherein the first animal music is produced based on second human music, and the second human music is human music suitable for producing animal music, and outputting each of the third animal music pieces.

[0016] In one embodiment of the present disclosure, the step of determining multiple pieces of third animal music that match the animal information in each piece of first animal music includes: determining multiple pieces of fourth animal music that match the animal information in each piece of first animal music; and determining multiple pieces of third animal music in each piece of fourth animal music based on the heat value of each piece of fourth animal music, the heat value of the third animal music being greater than a preset threshold.

[0017] In another embodiment of the present disclosure, the step of determining multiple third animal music matching the animal information in each piece of first animal music includes: determining the second animal to which the animal information belongs, and determining the emotion required by the second animal based on the animal information; and determining the third animal music matching the second animal and the emotion in each piece of the first animal music.

[0018] In a third aspect of the disclosed embodiment, a device for producing animal music is provided, comprising: a prediction model for predicting each piece of first human music using an animal music prediction model to obtain second human music, wherein the second human music is the first human music suitable for producing animal music; and a production module for producing first animal music based on the second human music.

[0019] In one embodiment of the present disclosure, an animal music production device includes: an acquisition module for acquiring sound information, wherein the sound information includes sounds that cause animals to have emotional changes; and the production module is also used to produce a first animal music corresponding to the animal based on the sound information and the second human music.

[0020] In another embodiment of the present disclosure, the device for producing animal music includes: a processing module, which is used to process the sound information to obtain auxiliary sound materials; an extraction module, which is used to extract music clips suitable for producing animal music from the second human music, and process the music clips to obtain main sound materials; the processing module is also used to mix the main sound materials with the auxiliary sound materials to generate first animal music corresponding to the animal music.

[0021] In another embodiment of the present disclosure, the device for producing animal music includes: the processing module is also used to perform at least one of the following processing on the music clip: modifying the sound intensity in the music clip; modifying the sound frequency of the music clip; modifying the rhythm of the music clip; modifying the sound of the instrument in the music clip; modifying the timbre in the music clip.

[0022] In another embodiment of the present disclosure, the device for producing animal music includes: a storage module, used to store the auxiliary sound material and the main sound material in a material database.

[0023] In another embodiment of the present disclosure, an animal music production device includes: an acquisition module, used to acquire each piece of second animal music and each piece of third human music, wherein the third human music is provided with a label, and the label is used to indicate whether the third human music is suitable or unsuitable for producing animal music; a training module, used to train a preset model according to each piece of second animal music and each piece of third human music to obtain an animal music prediction model.

[0024] In another embodiment of the present disclosure, the device for producing animal music includes: a determination module, which is also used to determine the first animal to which the second human music is suitable; and a storage module, which is used to associate the identifier corresponding to the first animal with the first animal music and store it in an animal music database.

[0025] In another embodiment of the present disclosure, an animal music production device includes: an acquisition module, used to acquire animal information and determine the second animal to which the animal information belongs; the acquisition module is also used to acquire third animal music matching the identification of the second animal in the animal music database; and a first output module, used to output the third animal music.

[0026] In a fourth aspect of the disclosed embodiments, a device for recommending animal music is provided, comprising: a second acquisition module for acquiring animal information; a second determination module for determining, in each piece of first animal music, a plurality of third animal music pieces that match the animal information, wherein the first animal music is produced based on second human music, and the second human music is human music suitable for producing animal music; and a second output module for outputting each piece of the third animal music.

[0027] In another embodiment of the present disclosure, it includes: the second determination module is also used to determine multiple fourth animal music matching the animal information in each of the first animal music; the second determination module is also used to determine multiple third animal music in each of the fourth animal music according to the popularity value of each of the fourth animal music, and the popularity value of the third animal music is greater than a preset threshold.

[0028] In another embodiment of the present disclosure, it includes: the second determination module is also used to determine the second animal to which the animal information belongs, and determine the emotion required by the second animal based on the animal information; the second determination module is also used to determine the second animal and the third animal music that matches the emotion in each piece of the first animal music.

[0029] In a fifth aspect of the embodiments of the present disclosure, a medium is provided, comprising: computer execution instructions, which, when executed by a processor, are used to implement the above-mentioned method for producing animal music or the method for recommending animal music.

[0030] In the sixth aspect of the present disclosure, a computing device is provided, comprising: a memory and a processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory, so that the processor executes the animal music production method or animal music recommendation method as described above.

[0031] According to the animal music prediction model of the embodiment of the present disclosure, second human music suitable for making animal music can be screened out from multiple first human music. That is, animal music can be prepared by using existing human music, without creating specific melodies for animals. In other words, animal music can be made without the creator having good musical literacy and knowledge of animal auditory perception, thereby reducing the production cost of animal music. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which:

[0033] Figure 1 The following schematically shows a schematic diagram of the production process of animal music according to an embodiment of the present disclosure;

[0034] Figure 2 The flowchart of an embodiment of a method for producing animal music according to the present disclosure is schematically shown;

[0035] Figure 3 The flowchart of another embodiment of the method for making animal music according to the present disclosure is schematically shown;

[0036] Figure 4 The flowchart of another embodiment of the method for producing animal music according to the present disclosure is schematically shown;

[0037] Figure 5 The flowchart of an embodiment of a method for recommending animal music according to the present disclosure is schematically shown;

[0038] Figure 6 The flowchart of another embodiment of the method for recommending animal music according to the present disclosure is schematically shown;

[0039] Figure 7 The flowchart of another embodiment of the method for recommending animal music according to the present disclosure is schematically shown;

[0040] Figure 8 A schematic diagram schematically shows a program product provided according to an embodiment of the present disclosure;

[0041] Fig. 9 The structure diagram of the device for producing animal music provided in accordance with the embodiment of the present disclosure is schematically shown;

[0042] Fig.10 The structure diagram of the device for recommending animal music provided according to the embodiment of the present disclosure is schematically shown;

[0043] Fig.11 The schematic diagram shows the structure of a computing device provided according to an embodiment of the present disclosure.

[0044] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0045] The principles and spirit of the present disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present disclosure, and are not intended to limit the scope of the present disclosure in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0046] Those skilled in the art will appreciate that the embodiments of the present disclosure may be implemented as a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0047] According to an embodiment of the present disclosure, a method for producing animal music, a method for recommending animal music, a medium, an apparatus and a computing device are proposed.

[0048] In this article, it is important to understand that the terms and their meanings are as follows:

[0049] Animal music prediction model: It can predict human music suitable for a certain animal to listen to from multiple human music.

[0050] First human music: generally refers to music suitable for human listening.

[0051] Second human music: music suitable for humans and suitable for listening to certain animals.

[0052] First Animal Music: Animal music produced from Second Human Music.

[0053] Sound information: including sounds that cause animals to experience emotional changes.

[0054] Auxiliary sound material: refers to the sound after sound information is processed.

[0055] Main sound material: chords and melodies obtained through second human music processing.

[0056] Material database: refers to the database that stores auxiliary sound materials and main sound materials.

[0057] Second animal music: refers to the produced animal music used for training.

[0058] Third human music: refers to human music that has been labeled as suitable for making animal music or not suitable for making animal music.

[0059] Animal Music Database: A database storing the produced animal music.

[0060] First Animal: refers to the animal to which the Second Human Music applies;

[0061] Second animal: refers to the animal for which animal music is to be recommended.

[0062] Third animal music: recommends animal music for animals corresponding to the animal information to listen to.

[0063] Fourth animal music: animal music with heat value.

[0064] In addition, any number of elements in the drawings is for illustration and not limitation, and any naming is only for distinction and does not have any limiting meaning.

[0065] The principle and spirit of the present disclosure are explained in detail below with reference to several representative embodiments of the present disclosure. SUMMARY OF THE INVENTION

[0067] The inventors have found that animal music is usually created by musicians for a certain animal according to specific rules. Due to the differences in ecology and sensory perception between species, animals of different species may also have completely different feelings about the same musical melody. Therefore, specific rules need to be formulated in combination with the auditory perception and vocalization skills of specific animals so that animal music can play a role in arousing the emotions of animals. It can be seen that animal music requires creators not only to have sufficient musical literacy, but also to have a full grasp of animal knowledge, and even requires zoologists to directly participate in it. The production cost of animal music is high.

[0068] Because of this, the amount of animal music is very limited, and it is impossible to meet the scene requirements of recommending music for specific animals.

[0069] Since music designed specifically for animals is difficult to produce, there is a relatively small amount of animal music. In actual application scenarios, such as some sample facilities, animal shelters and other places, some specific genres of human music are often used as substitutes to calm the emotions of animals. For example, some studies have shown that classical music has a certain soothing effect on pets such as cats and dogs. In actual scenarios, ordinary people can filter music from human music. However, human perception of sound is different from animal perception of sound, and the filtered human music may not be suitable for animals. For example, the filtered human music has high notes, but animals of different species have different perception ranges of high notes. These auditory differences may cause animals to feel human music differently from what the filter imagines. For example, the high notes of filtered human music may be too high for some animals, and may even hurt their ears, while some animals may not be able to hear the high notes.

[0070] The inventor of this patent therefore came up with the idea of ​​selecting human music suitable for making animal music from human music through a trained animal music prediction model, thereby making it possible to produce a large amount of animal music. Even if the creator has no musical literacy and no animal knowledge, animal music can be created, reducing the production cost of animal music.

[0071] Furthermore, when making animal music, sounds that can cause animals to have emotional changes are added so that the produced animal music can serve the purpose of arousing the emotions of animals.

[0072] In addition, as the efficiency of animal music production is improved and animal music can be produced from human music, enough animal music can be produced, that is, music suitable for animals to listen to can be found from a large amount of animal music, thus realizing the recommendation of animal music.

[0073] After introducing the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are described in detail below.

[0074] Application Scenario Overview

[0075] First reference Figure 1 , Figure 1 This is a schematic diagram of the production process of animal music according to the embodiment of the present disclosure. The specific process is as follows:

[0076] 1. The terminal device 100 uses the existing animal music and human music with labels to train the preset model 110 to obtain the animal music prediction model 120, wherein the labels indicate whether the human music is suitable or not suitable for making animal music;

[0077] 2. The terminal device 100 predicts human music suitable for making animal music from unlabeled human music through the animal music prediction model 120;

[0078] 3. The terminal device 100 processes human music suitable for making animal music to obtain animal music.

[0079] Exemplary Methods

[0080] Combine the following Figure 1 For application scenarios, refer to Figure 2-Figure 4 To describe the method for making animal music according to an exemplary embodiment of the present disclosure. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of the present disclosure, and the embodiments of the present disclosure are not limited in this regard. On the contrary, the embodiments of the present disclosure can be applied to any applicable scenario.

[0081] Exemplarily, the execution device of the embodiments of the present disclosure may be a terminal with data processing capability.

[0082] refer to Figure 2 , Figure 2 The flowchart of an embodiment of a method for producing animal music provided in accordance with an embodiment of the present disclosure is exemplarily shown. The method for producing animal music includes:

[0083] Step S201, using the animal music prediction model to predict each first human music to obtain second human music, where the second human music is the first human music suitable for making animal music.

[0084] In this embodiment, the execution subject is an animal music production device, and the animal music production device can be any terminal with data processing capabilities. For the convenience of description, the production device is used below to refer to the animal music production device.

[0085] The production device is provided with an animal music prediction model, which is used to predict whether human music is suitable for producing animal music. In this embodiment, animals include but are not limited to pets and domesticated animals. Pets may be cats, dogs, etc., and domesticated animals include chickens, ducks, sheep, geese, pigs, etc. The animal music prediction model can predict from human music that music is suitable for producing a specific animal, or predict from human music that music is suitable for producing multiple animals.

[0086] In one example, the model may be trained using the produced animal music to obtain the animal music prediction model.

[0087] In another example, since the amount of animal music that has been produced is relatively small, after obtaining the produced animal music (second animal music), various third human music is obtained. The third human music is provided with a label, and the label is used to indicate whether the third human music is suitable or not suitable for producing animal music, that is, the label can be "unsuitable" or "suitable". The model trained with the third human music with such labels can predict the music suitable for producing specific animals from human music. For example, if the label is used to indicate whether the third human music is suitable or not for producing animal music for dogs, the trained model is used to predict the second human music suitable for producing dog music from each piece of first human music.

[0088] In addition, if the trained animal music prediction model can predict suitable music for making multiple animals from human music, the label of the third human music used for training is used to indicate that the third human music is suitable for making animal music for a certain animal, or the label is used to indicate that the third human music is not suitable for making animal music. The model trained by these third human music can predict the second human music suitable for making a certain animal music from each first human music.

[0089] In addition, the label can also be a score, which represents the degree to which the third human music corresponding to the label is "suitable for making music for a certain animal". The higher the degree of suitability, the higher the score, and the scoring standard depends on the fit between the melody and chords of the human music and the animal. The label of the third human music can be manually annotated. The animal music prediction model can be obtained by training the preset model based on each second animal music and each third human music. The animal music prediction model can be a CNN (Convolutional Neural Networks) model. The CNN model can be an AlexNeT model, a VGG (visual geometry group, super-resolution test sequence)-16 model, or a GoogLeNet model. The AlexNeT model, the VGG-16 model, and the GoogLeNet model are convolutional neural network models proposed by different teams.

[0090] Third, using human music as training samples can provide the model with sufficient training data, and the training samples include produced animal music, which can enable the animal music prediction model to combine the characteristics of animal music and the characteristics of labeled human music, and accurately determine the human music suitable for making animal music from unlabeled human music.

[0091] The production device uses the animal music prediction model to predict each first human music, thereby obtaining the second human music, the second human music is the first human music suitable for producing animal music, the first human music is unlabeled human music, and the first human music can be obtained from the music database. Specifically, the unlabeled first human music is input into the animal music prediction model, and the animal music prediction model outputs the human music with a label, and the content of the label is that the human music suitable for producing animal music is determined as the second human music.

[0092] Step S202, producing the first animal music according to the second human music.

[0093] After obtaining the second human music, the production device processes the second human music to produce the first animal music. The processing may be to adjust the second human music according to set rules, for example, to adjust the frequency range in the second human music to the frequency perception range of a certain animal.

[0094] Furthermore, after producing the first animal music, the production device determines the first animal to which the second human music is applicable, thereby associating the identifier of the first animal with the first animal music and storing it in the animal music database. Specifically, the animal music prediction model can predict that the second human music is suitable for producing animal music of a certain animal, and thus, the production device can determine the first animal to which the second human music is applicable based on the animal music prediction model. The identifier of the first animal can be the name of the animal or the species of the animal.

[0095] By obtaining music suitable for making animal music from human music, a large amount of animal music can be made, that is, the animal music database stores a large amount of animal music. Animal music can be recommended through the animal music database to meet the actual application scenarios of animal music.

[0096] In one example, the production device obtains animal information, which may be a picture of an animal or an audio of an animal sound. Based on the animal information, the production device can determine the second animal to which the animal information belongs. The production device searches in an animal music database to obtain third animal music that matches the identifier of the second animal. For example, the second animal is a cat. Then, animal music identified as a cat is obtained in the animal music database as the third animal music.

[0097] In the technical solution provided in this embodiment, the animal music prediction model can screen out second human music suitable for making animal music from multiple first human music. That is, animal music can be prepared using existing human music without creating specific melodies for animals. In other words, animal music can be made without the creator having good musical literacy and knowledge of animal auditory perception, thereby reducing the production cost of animal music.

[0098] In one embodiment, the label of the third human music used to train the model can be used to indicate that the third human music is suitable for producing animal music that produces a certain emotion, or the label is used to indicate that the third human is not suitable for producing animal music. Then, the trained model can predict the animal music that is suitable for producing a certain emotion from each piece of first human music. After the production device produces the first animal music, it stores the first animal music in the animal music database. The first animal music stored in the animal music database has a label, and the label content includes at least an animal identification and an emotion. For example, the label content of the first animal music in the animal music database is "can make dogs excited". When recommending animal music, the production device obtains animal information including emotions and animal species. For example, if the animal information is "needs dogs to produce stable emotions", the animal species is dog and the emotion is stable, and the production device can search the animal music that can make dogs produce stable emotions in the animal music database as the third animal music.

[0099] Reference Figure 3 , Figure 3 This is a flow chart of another embodiment of the method for producing animal music disclosed in the present invention, based on Figure 2 In the illustrated embodiment, step S202 includes:

[0100] Step S301, obtaining sound information, where the sound information includes sounds that cause animals to have emotional changes.

[0101] In this embodiment, sound information is obtained from the preferred environment of the animal, and the sound information includes sounds that cause the animal to have emotional changes. The preferred environment refers to the environment where the animal's activity area is located, that is, the sound is extracted from the environment that the animal likes. The preferred environment can cause the animal to have specific emotions, and thus the sound extracted from the environment can be regarded as the sound that causes the animal to have emotional changes. For example, the animal is an artificially raised duck, the duck's preferred environment is a river, and the sound of the river's water flow can make the duck feel stable in the river, then the sound of the river's water flow is extracted as the sound information. For another example, the animal is a pet dog, the pet dog's preferred environment is home, and the sound of a rattle can make the pet dog feel excited at home, then the sound of the rattle is extracted as the sound information.

[0102] Step S302, producing the first animal music according to the sound information and the second human music.

[0103] The production device can produce the first animal music based on the sound information and the second human music. Specifically, the sound in the sound information can be added to the human music to produce the first animal music.

[0104] In the technical solution provided in this embodiment, the production device obtains the sound that causes the animal to have emotional changes, and then produces animal music that can cause the animal to have certain emotions based on the sound and the second human music.

[0105] Reference Figure 4 , Figure 4 is a flow chart of another embodiment of the method for producing animal music disclosed in the present invention, based on Figure 3 In the illustrated embodiment, step S302 includes:

[0106] Step S401, processing the sound information to obtain auxiliary sound material.

[0107] In this embodiment, the production device first processes the sound information. For example, if the sound in the sound information is relatively small, the volume of the sound can be appropriately increased. For another example, if the sound in the sound information is noisy, the noise can be removed. The production device processes the sound information to obtain auxiliary sound materials. Auxiliary sound materials are not a necessary factor in animal music, and can be added or not. Alternatively, auxiliary music materials refer to music elements that account for a relatively small proportion in animal music.

[0108] Step S402: extracting music clips suitable for making animal music from the second human music, and processing the music clips to obtain main sound materials.

[0109] The animal music prediction model can be used to predict that a certain section of the second human music is suitable for making animal music. Therefore, the production device extracts a music segment suitable for making animal music from the second human music. The production device then processes the music segment to obtain the main sound material. Specifically, the first human music is divided into multiple music segments, and the multiple music segments of the first human music are sequentially input into the animal music prediction model. The animal music prediction model first converts the music segment into sound signal features, and the sound signal features include but are not limited to Mel-spectrogram. The convolutional neural network of the animal music prediction model extracts features from the sound signal features again, and the extracted features can be sound signal features that characterize the melody or chord in the music segment. The animal music prediction model determines the probability P that the music segment is suitable as animal music based on the extracted features. By comparing P with a set threshold, the animal music prediction model outputs a music segment with a label, and the label content includes whether it is suitable or not suitable for making animal music. For example, if P is greater than or equal to the set threshold, the label content of the music segment is: suitable for making animal music; if P is less than the set threshold, the label content of the music segment is: not suitable for making animal music.

[0110] The main sound material refers to the main or necessary material for making animal music.

[0111] In one example, processing a music clip includes: modifying the sound intensity in the music clip, modifying the sound frequency of the music clip, modifying the rhythm of the music clip, modifying the instrument sound of the music clip, and / or modifying the timbre in the music clip. Since animals and humans may have different ranges of perception of the sound intensity and frequency of sound, the production device needs to modify the sound intensity and sound frequency in the music clip to conform to the animal's perception of the sound intensity and sound frequency. The rhythm of human music is often closer to the human mentality frequency, but this rhythm may not be suitable for animals, so it is necessary to modify the rhythm of the music clip to conform to the animal's perception rhythm. Human music includes instrument sounds, some of which may cause animals to have negative emotions, such as drum beats, so it is necessary to remove the instrument sounds that cause animals to have negative emotions in the music clip. In addition, human voices may include some sharp and hoarse timbres, which can cause animals to have excited emotions. If the purpose of making animal music is to calm the animals, the timbre needs to be modified, that is, the timbre needs to be modified to a soft timbre.

[0112] After the production device obtains the main sound material, the auxiliary sound material and the main sound material can be stored in the material database. The material database is open to users, and users can directly obtain the main music material and auxiliary music material required for making animal music from the material database, and then make animal music. That is, the material database facilitates users to make animal music, and there is no need to use a specific device to obtain the main and auxiliary music materials, which reduces the difficulty of making animal music.

[0113] Step S403, mixing the main sound material with the auxiliary sound material to generate the first animal music.

[0114] After obtaining the main sound material and the auxiliary sound material, the main sound material and the auxiliary sound material are mixed according to the set rules to generate the first animal music.

[0115] In this embodiment, the production device processes the sound information to obtain auxiliary sound material, extracts music clips suitable for making animal music from the second human music, processes the music clips to obtain main sound material, and then mixes the auxiliary sound material and the main sound material to generate animal music suitable for animals to listen to.

[0116] refer to Figure 5 , Figure 5 The flowchart of an embodiment of a method for recommending animal music provided by an embodiment of the present disclosure is exemplarily shown. The method for recommending animal music includes:

[0117] Step S501, obtaining animal information.

[0118] In this embodiment, the execution subject is an animal music recommendation device. For the convenience of description, the recommendation device is used below to refer to the animal music recommendation device. The recommendation device can be any terminal device with data processing capability and push function.

[0119] The recommendation device obtains animal information. The animal information may be pictures or audio containing animals. The animal information may be uploaded by the user's terminal device or collected by the recommendation device in real time. For example, the recommendation device receives a play instruction for animal music, and collects animal information in the space.

[0120] Step S502, determining multiple third animal music pieces whose animal information matches in each of the first animal music pieces, wherein the first animal music pieces are produced based on the second human music, and the second human music is human music suitable for producing animal music.

[0121] The recommendation device can determine multiple third animal music pieces that match the animal information from multiple first animal music pieces. The first animal music is produced based on the second human music, and the second human music is human music suitable for producing animal music. The production process of the first animal music is specifically referred to the above description, and will not be repeated here. Each first animal music piece is stored in an animal music database, and the recommendation device can obtain multiple first animal music pieces from the animal music database.

[0122] The recommendation device determines the animal based on the animal information, thereby finding the animal music corresponding to the animal in each first animal music as the third animal music. The animal music corresponding to the animal to which the animal information belongs is the third animal music matched by the animal information.

[0123] Step S503, output each third animal music.

[0124] After determining each piece of third animal music, the recommendation device can output the third animal music. For example, each piece of third animal music can be pushed as a song list to the terminal device that sends the animal information.

[0125] In the technical solution provided in this embodiment, the recommendation device obtains animal information and obtains third animal music that matches the animal information from multiple first animal music. Since the animal music is produced by human music suitable for producing animal music, enough animal music can be produced, that is, music suitable for animals to listen to can be found from a large amount of animal music, thereby realizing a large number of recommendations of animal music.

[0126] Reference Figure 6 , Figure 6 is a flow chart of another embodiment of the method for recommending animal music disclosed in the present invention, based on Figure 5In the illustrated embodiment, step S502 includes:

[0127] Step S601, determining a plurality of fourth animal music pieces whose animal information matches in each of the first animal music pieces.

[0128] In this embodiment, the recommendation device first determines multiple fourth animal music pieces that match the animal information in each first animal music piece. For example, if the animal to which the animal information belongs is a dog, then animal music suitable for dogs to listen to is found from all the first animal music pieces as the fourth animal music.

[0129] Step S602, according to the popularity value of each piece of fourth animal music, multiple pieces of third animal music are determined in each piece of fourth animal music, and the popularity value of the third animal music is greater than a preset threshold.

[0130] Each piece of fourth animal music has a corresponding heat value. The heat value can be converted from the playback volume of the fourth animal music. The greater the playback volume, the greater the heat value. In addition, the heat value can also be determined based on the user's evaluation of the fourth animal music. The first ratio of the number of positive evaluations of the fourth animal music to the total number of evaluations can be determined as the heat value. A positive evaluation is, for example, "My dog ​​listened to this song and was particularly quiet, great!", that is, the content of the positive evaluation includes comments on the emotions generated by the fourth animal music specified by the user. In addition, it is also necessary to reduce the heat value based on the negative evaluation to obtain the final heat value of the fourth animal music. For example, the heat value of the fourth animal music can be reduced based on the second ratio of the number of negative evaluations to the total number of evaluations. The larger the second ratio, the greater the reduction.

[0131] A preset threshold may be set in the recommendation device, and the preset threshold may be a preset popularity value. The recommendation device determines multiple third animal music in each fourth animal music based on the popularity value of each fourth animal music, that is, the fourth animal music with a popularity value greater than the preset threshold is the third animal music.

[0132] When outputting each piece of third animal music, the music may be sorted in descending order according to the popularity value of each piece of third animal music to form a playlist, and then the playlist may be pushed to the terminal device of the user who uploaded the animal information.

[0133] In this embodiment, the recommendation device determines multiple fourth animal music pieces whose animal information matches in each first animal music piece, and then determines multiple third animal music pieces in each fourth animal music piece based on the popularity value of the fourth animal music, thereby recommending animal music with higher popularity to the user.

[0134] Reference Figure 7 , Figure 7 is a flow chart of another embodiment of the method for recommending animal music disclosed in the present invention, based on Figure 5In the illustrated embodiment, step S502 includes:

[0135] Step S701, determining the second animal to which the animal information belongs, and determining the emotion required by the second animal according to the animal information.

[0136] In this embodiment, the animal information can be uploaded by the user, and the animal information includes animal music recommended by the user that can make the animal produce a specified emotion. The recommendation device can determine the animal and the emotion required by the animal based on the animal information. The animal to which the animal information belongs is the animal for which the animal music is to be recommended, and the animal to which the animal information belongs is defined as the second animal.

[0137] In one example, the animal information includes the sound of the animal. The recommendation device can identify the animal and the current state of the animal based on the sound of the animal, and the recommendation device determines the desired emotion of the animal based on the current state of the animal. For example, if the animal information includes the sound of a cat, the second animal is a cat, and the sound frequency of the cat's sound is high, the recommendation device identifies that the current state of the cat is panic, and the emotion required by the cat is stability.

[0138] In another example, the animal information includes an animal picture. The recommendation device identifies the animal in the animal picture and can determine the current state of the animal based on the body movements of the animal in the animal picture. For example, if the animal picture shows a dog biting a sofa, the recommendation device identifies that the current state of the dog is excited, and the recommendation device can determine that the emotion required by the dog is calm.

[0139] Step S702, determining the second animal and the third animal music with matching emotions in each piece of first animal music.

[0140] The recommendation device first determines multiple fourth animal music belonging to the second animal in each first animal music. Each animal music is provided with an emotion tag, and the recommendation device finds the animal music with the tag of the emotion required by the second animal in each fourth animal music as the third animal music. For example, if the emotion required by the second animal is calm, the fourth animal music with the calm tag is determined as the third animal music.

[0141] It should be noted that the recommendation device can determine the third animal music in each first animal music according to the heat value, the second animal and the emotion required by the second animal. The specific implementation method is as follows Figure 6 The illustrated embodiment and the description of this embodiment will not be repeated here.

[0142] In this embodiment, the recommendation device determines the second animal and the emotion required by the second animal based on the animal information, and thus determines the second animal and the animal music with the emotion required by the second animal in each piece of animal music for recommendation.

[0143] Exemplary Media

[0144] After introducing the method of the exemplary embodiment of the present disclosure, next, refer to Figure 8 A storage medium according to an exemplary embodiment of the present disclosure is described.

[0145] refer to Figure 8 As shown, the storage medium 80 stores a program product for implementing the above method according to an embodiment of the present disclosure, which may adopt a portable compact disk read-only memory (CD-ROM) and include computer execution instructions, which are used to enable a computing device to execute the method for making animal music or the method for recommending animal music provided by the present disclosure. However, the program product of the present disclosure is not limited thereto.

[0146] The program product may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0147] The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-executable instructions. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than a readable storage medium.

[0148] Computer-executable instructions for performing the disclosed operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" or similar programming languages. The computer-executable instructions may be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN).

[0149] Exemplary Devices

[0150] After introducing the medium of the exemplary embodiment of the present disclosure, next, reference is made to Fig. 9 The animal music production device of the exemplary embodiment of the present disclosure is described, which is used to implement the animal music production method in any of the above embodiments. The implementation principle and technical effect are similar and will not be repeated here.

[0151] refer to Fig. 9 , Fig. 9 The structure diagram of the device for making animal music according to the embodiment of the present disclosure is schematically shown. Fig. 9 As shown, the device for making animal music includes:

[0152] A prediction module 901 is used to predict each first human music by using an animal music prediction model to obtain second human music, where the second human music is the first human music suitable for making animal music;

[0153] The production module 902 is used to produce the first animal music according to the second human music.

[0154] In one embodiment of the present disclosure, the device for producing animal music includes:

[0155] A first acquisition module 903 is used to acquire sound information, where the sound information includes sounds that cause the animal to have emotional changes;

[0156] The production module 902 is further used to produce first animal music corresponding to the animal according to the sound information and the second human music.

[0157] In another embodiment of the present disclosure, the device for producing animal music includes:

[0158] A processing module 904 is used to process the sound information to obtain auxiliary sound materials;

[0159] An extraction module 905 is used to extract music clips suitable for making animal music from the second human music, and process the music clips to obtain main sound materials;

[0160] The processing module 904 is further used to mix the main sound material with the auxiliary sound material to generate the first animal music corresponding to the animal music.

[0161] In another embodiment of the present disclosure, the processing module is further configured to perform at least one of the following processing on the music clip:

[0162] modify the intensity of sounds in a piece of music;

[0163] Modify the sound frequency of a piece of music;

[0164] modify the tempo of a piece of music;

[0165] modify the sound of instruments in a musical clip;

[0166] Modify the timbre of a musical clip.

[0167] In another embodiment of the present disclosure, the device for producing animal music includes:

[0168] The storage module 906 is used to store the auxiliary sound material and the main sound material in the material database.

[0169] In another embodiment of the present disclosure, the device for producing animal music includes:

[0170] The first acquisition module 903 is used to acquire each second animal music and each third human music, wherein the third human music is provided with a label, and the label is used to indicate whether the third human music is suitable or not suitable for making animal music;

[0171] The training module 907 is used to train the preset model according to each second animal music and each third human music to obtain an animal music prediction model.

[0172] In another embodiment of the present disclosure, the device for producing animal music includes:

[0173] The first determination module 908 is further used to determine the first animal to which the second human music is applicable;

[0174] The storage module 906 is used to associate the identifier corresponding to the first animal with the first animal music and store it in the animal music database.

[0175] In another embodiment of the present disclosure, the device for producing animal music includes:

[0176] A first acquisition module 903 is used to acquire animal information and determine the second animal to which the animal information belongs;

[0177] The first acquisition module 903 is further used to acquire the third animal music matched with the identifier of the second animal in the animal music database;

[0178] The first output module 909 is used to output the third animal music.

[0179] After introducing the medium of the exemplary embodiment of the present disclosure, next, reference is made to Fig.10 The device for recommending animal music according to the exemplary embodiment of the present disclosure is described, which is used to implement the method for recommending animal music in any of the above embodiments. The implementation principle and technical effect are similar and will not be repeated here.

[0180] like Fig.10 As shown, recommended devices for animal music include:

[0181] The second acquisition module 1001 is used to acquire animal information;

[0182] The second determination module 1002 is used to determine a plurality of third animal music pieces matching the animal information in each of the first animal music pieces, wherein the first animal music pieces are produced based on the second human music pieces, and the second human music pieces are human music pieces suitable for producing animal music;

[0183] The second output module 1003 is used to output each piece of third animal music.

[0184] In one embodiment of the present disclosure, the device for recommending animal music includes:

[0185] The second determination module 1002 is further used to determine a plurality of fourth animal music pieces whose animal information matches in each of the first animal music pieces;

[0186] The second determination module 1002 is further used to determine multiple third animal music in each fourth animal music according to the popularity value of each fourth animal music, and the popularity value of the third animal music is greater than a preset threshold.

[0187] In another embodiment of the present disclosure, the device for recommending animal music includes:

[0188] The second determination module 1002 is further used to determine the second animal to which the animal information belongs, and determine the emotion required by the second animal according to the animal information;

[0189] The second determination module 1002 is further used to determine the second animal and the third animal music with matching emotions in each piece of first animal music.

[0190] Exemplary Computing Devices

[0191] After introducing the method, medium and apparatus of the exemplary embodiments of the present disclosure, next, reference is made to Fig.11 A computing device according to an exemplary embodiment of the present disclosure is described.

[0192] Fig.11 The computing device 110 shown is only an example and should not bring any limitation to the functionality and scope of use of the embodiments of the present disclosure.

[0193] like Fig.11As shown, the computing device 110 is in the form of a general computing device. The components of the computing device 110 may include, but are not limited to: at least one processing unit 1101, at least one storage unit 1102, and a bus 1103 connecting different system components (including the processing unit 1101 and the storage unit 1102). Among them, at least one storage unit 1102 stores computer-executable instructions; at least one processing unit 1101 includes a processor, and the processor executes the computer-executable instructions to implement the method described above.

[0194] The bus 1103 includes a data bus, a control bus, and an address bus.

[0195] The storage unit 1102 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 11021 and / or a cache memory 11022 , and may further include a readable medium in the form of a non-volatile memory, such as a read-only memory (ROM) 11023 .

[0196] The storage unit 1102 may also include a program / utility 11025 having a set (at least one) of program modules 11028, such program modules 11028 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0197] The computing device 110 may also communicate with one or more external devices 1108 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 1105. In addition, the computing device 110 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 1106. Fig.11 As shown, the network adapter 1106 communicates with other modules of the computing device 110 via the bus 1103. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the computing device 110, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0198] It should be noted that although several units / modules or sub-units / modules of the animal music production device and the animal music recommendation device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0199] In addition, although the operations of the disclosed method are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0200] Although the spirit and principles of the present disclosure have been described with reference to several specific embodiments, it should be understood that the present disclosure is not limited to the specific embodiments disclosed, and the division of various aspects does not mean that the features in these aspects cannot be combined to benefit. This division is only for convenience of expression.

Claims

1. A method for producing animal music, characterized in that: include: Using an animal music prediction model to predict each first human music to obtain second human music, wherein the second human music is the first human music suitable for making animal music; producing first animal music based on said second human music; The step of producing the first animal music according to the second human music comprises: Acquiring sound information, wherein the sound information includes sounds that cause the animal to have emotional changes; Processing the sound information to obtain auxiliary sound material; Extracting music clips suitable for making animal music from the second human music, and processing the music clips to obtain main sound materials; The main sound material is mixed with the auxiliary sound material to generate the first animal music.

2. The method for producing animal music according to claim 1, characterized in that: The processing of the music clip comprises at least one of the following: modifying the intensity of sounds in the music clip; Modifying the sound frequency of the music clip; modifying the tempo of the music clip; modifying the sound of musical instruments in the music clip; Modify the timbre of the music segment.

3. The method for producing animal music according to claim 1, characterized in that: After the step of processing the music clip to obtain the main sound material, the method further includes: The auxiliary sound material and the main sound material are stored in a material database.

4. The method for producing animal music according to claim 1, characterized in that: Before the step of using the animal music prediction model to predict each first human music, the method further includes: Acquire each piece of second animal music and each piece of third human music, wherein the third human music is provided with a label, and the label is used to indicate whether the third human music is suitable or not suitable for making animal music; The preset model is trained according to each piece of the second animal music and each piece of the third human music to obtain the animal music prediction model.

5. The method for producing animal music according to claim 1, characterized in that: After the step of producing the first animal music according to the second human music, the method further includes: determining a first animal to which the second human music is applicable; The identifier corresponding to the first animal is associated with the first animal music and stored in an animal music database.

6. The method for producing animal music according to claim 5, characterized in that: After the step of associating the identifier corresponding to the first animal with the first animal music and storing it in the animal music database, the method further includes: Acquire animal information, and determine the second animal to which the animal information belongs; In the animal music database, obtaining third animal music matched with the identifier of the second animal; The third animal music is output.

7. A method for recommending animal music, characterized in that: include: Get animal information; Determining multiple third animal music pieces that match the animal information in each first animal music piece, wherein the first animal music is obtained by mixing a main sound material with an auxiliary sound material, wherein the auxiliary sound material is obtained by processing sound information, and the main sound material is obtained by extracting a music clip suitable for making animal music from a second human music and processing the music clip; the sound information includes sounds that cause animals to have emotional changes, and the second human music is human music suitable for making animal music; Output each piece of the third animal music.

8. The method for recommending animal music according to claim 7, characterized in that: The step of determining a plurality of third animal music pieces matching the animal information in each of the first animal music pieces comprises: Determining a plurality of fourth animal music pieces matching the animal information in each of the first animal music pieces; According to the popularity value of each piece of the fourth animal music, a plurality of pieces of the third animal music are determined in each piece of the fourth animal music, and the popularity value of the third animal music is greater than a preset threshold.

9. The method for recommending animal music according to claim 7, characterized in that: The step of determining a plurality of third animal music pieces matching the animal information in each of the first animal music pieces comprises: determining a second animal to which the animal information belongs, and determining a desired emotion of the second animal according to the animal information; In each piece of the first animal music, determine the second animal and the third animal music that matches the emotion.

10. A device for producing animal music, characterized in that: include: A prediction model, used to predict each first human music by using the animal music prediction model to obtain second human music, wherein the second human music is the first human music suitable for making animal music; A production module, used for producing first animal music according to the second human music; A first acquisition module is used to acquire sound information, wherein the sound information includes sounds that cause the animal to have emotional changes; A processing module, used for processing the sound information to obtain auxiliary sound material; An extraction module, used for extracting music clips suitable for making animal music from the second human music, and processing the music clips to obtain main sound materials; The processing module is further used to mix the main sound material with the auxiliary sound material to generate first animal music corresponding to the animal music.

11. The device for producing animal music according to claim 10, characterized in that: The processing module is further configured to perform at least one of the following processing on the music clip: modifying the intensity of sounds in the music clip; Modifying the sound frequency of the music clip; modifying the tempo of the music clip; modifying the sound of musical instruments in the music clip; Modify the timbre of the music segment.

12. The device for producing animal music according to claim 11, characterized in that: include: The storage module is used to store the auxiliary sound material and the main sound material in a material database.

13. The device for producing animal music according to claim 10, characterized in that: include: A first acquisition module is used to acquire each second animal music and each third human music, wherein the third human music is provided with a label, and the label is used to indicate whether the third human music is suitable or not suitable for making animal music; The training module is used to train the preset model according to each of the second animal music and each of the third human music to obtain an animal music prediction model.

14. The device for producing animal music according to claim 10, characterized in that: include: The first determination module is further used to determine the first animal to which the second human music is suitable; The storage module is used to associate the identifier corresponding to the first animal with the first animal music and store it in an animal music database.

15. The device for producing animal music according to claim 14, characterized in that: include: A first acquisition module, used to acquire animal information and determine the second animal to which the animal information belongs; The first acquisition module is further used to acquire, in the animal music database, third animal music matched with the identifier of the second animal; The first output module is used to output the third animal music.

16. A device for recommending animal music, characterized in that: include: The second acquisition module is used to acquire animal information; A second determination module is used to determine multiple third animal music pieces that match the animal information in each first animal music piece, wherein the first animal music is obtained by mixing a main sound material with an auxiliary sound material, the auxiliary sound material is obtained by processing sound information, the main sound material is obtained by extracting a music clip suitable for making animal music from a second human music, and processing the music clip; the sound information includes sounds that cause animals to have emotional changes, and the second human music is human music suitable for making animal music; The second output module is used to output each piece of the third animal music.

17. The device for recommending animal music according to claim 16, characterized in that: include: The second determination module is further used to determine a plurality of fourth animal music pieces matching the animal information in each of the first animal music pieces; The second determination module is further used to determine multiple pieces of the third animal music in each piece of the fourth animal music according to the popularity value of each piece of the fourth animal music, and the popularity value of the third animal music is greater than a preset threshold.

18. The device for recommending animal music according to claim 16, characterized in that: include: The second determination module is further used to determine the second animal to which the animal information belongs, and determine the emotion required by the second animal according to the animal information; The second determination module is further used to determine the second animal and the third animal music that matches the emotion in each piece of the first animal music.

19. A medium, characterized in that include: Computer-executable instructions, which, when executed by a processor, are used to implement the method for producing animal music as described in any one of claims 1 to 6 or the method for recommending animal music as described in claims 7 to 9.

20. A computing device, characterized in that include: Memory and processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for producing animal music as described in any one of claims 1 to 6 or the method for recommending animal music as described in claims 7 to 9.

Images