[go: up one dir, main page]

WO2018184249A1 - Music generation method and terminal - Google Patents

Music generation method and terminal Download PDF

Info

Publication number
WO2018184249A1
WO2018184249A1 PCT/CN2017/079829 CN2017079829W WO2018184249A1 WO 2018184249 A1 WO2018184249 A1 WO 2018184249A1 CN 2017079829 W CN2017079829 W CN 2017079829W WO 2018184249 A1 WO2018184249 A1 WO 2018184249A1
Authority
WO
WIPO (PCT)
Prior art keywords
music
picture
information
parameter information
generating
Prior art date
Application number
PCT/CN2017/079829
Other languages
French (fr)
Chinese (zh)
Inventor
陈崇震
Original Assignee
格兰比圣(深圳)科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 格兰比圣(深圳)科技有限公司 filed Critical 格兰比圣(深圳)科技有限公司
Priority to PCT/CN2017/079829 priority Critical patent/WO2018184249A1/en
Publication of WO2018184249A1 publication Critical patent/WO2018184249A1/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16Sound input; Sound output

Definitions

  • the present invention relates to the field of mobile terminals, and in particular, to a music generating method and a terminal.
  • the music associated with the picture can also be played at the same time as the picture is displayed on the terminal.
  • the conventional method is that the terminal first searches for a matching music on the network or a pre-established music library according to, for example, a location and a time of the captured picture, and then plays the same picture through the player while browsing the picture. Match the music.
  • the technical problem to be solved by the present invention lies in the existing way of providing music matching the picture, the matching effect of the searched music and the picture is poor, and the searched music cannot reflect the defect of the content in the picture well. .
  • the technical solution adopted by the present invention to solve the technical problem thereof is: Providing a music generating method, comprising the following steps:
  • the step of generating music according to the acquired element information and parameter information of the element includes:
  • the sound of the element is generated using a sound simulation method.
  • the step of generating music according to the acquired element information and the parameter information of the element comprises: [0011] determining a note type corresponding to the element information; [0012] acquiring a note in a corresponding note category according to parameter information of the element;
  • the music of the element is generated according to the acquired note.
  • the step of generating music according to the acquired element information and parameter information of the element further comprises:
  • the music of each element of the picture is superimposed and/or arranged in order to generate music that matches the picture.
  • the music generating method of the present invention further includes:
  • the music generating method of the present invention further includes:
  • a music generating terminal including:
  • an image recognition module configured to identify a picture, obtain element information in the picture, and parameter information of the element
  • the music generating module is configured to generate music according to the acquired element information and parameter information of the element.
  • the music generating terminal of the present invention further includes:
  • an association module configured to associate the generated music with the picture.
  • the music generating terminal of the present invention further includes:
  • a playing module configured to play the generated music after receiving the play instruction.
  • the generated music can directly reflect the elements in the picture, and the matching effect is good, and the visual to auditory conversion is realized.
  • FIG. 1 is a schematic flow chart of a first embodiment of a music generating method provided by the present invention.
  • step S12 in the first embodiment of the music generating method provided by the present invention
  • FIG. 3 is a schematic flowchart of step S22 in the second embodiment of the present invention.
  • FIG. 4 is a flowchart of a third embodiment of the music generating method provided by the present invention. Schematic diagram
  • FIG. 5 is a schematic flow chart of a fourth embodiment of a music generating method provided by the present invention.
  • FIG. 6 is a schematic structural diagram of a first embodiment of a music generating terminal provided by the present invention.
  • FIG. 7 is a structural diagram of a music generation module in another embodiment of a music generation terminal provided by the present invention.
  • FIG. 1 is a music generating method according to the present invention.
  • the operating method of the embodiment includes the following steps:
  • Step S11 Identify a picture, obtain element information in the picture, and parameter information of the element.
  • Step S12 Generate music according to the acquired element information and the parameter information of the element.
  • the picture can be acquired in various ways, such as by network downloading, camera shooting, and the like.
  • the element information in the picture and the parameter information of the element may be automatically identified and acquired, or the element information of the corresponding picture and the parameter information of the element may be identified and obtained after receiving the control instruction.
  • the user can input control commands by interacting with the terminal.
  • the element is the content recorded in the photo that can be simulated, such as a picture of a frog on a pond in a rainy day, which can be both an elementary rain and a frog.
  • the parameter information of an element includes information reflecting the characteristics of the element, such as the number of elements, radians, length, and the like.
  • the elements in the picture and their parameters can be identified by various image recognition technologies, preferably, The image edge detection algorithm (PattemRecognition) is used to identify various elements contained in the image, as well as various parameter information of each element.
  • the image edge detection algorithm PattemRecognition
  • step S12 includes the following sub-steps:
  • Sub-step S121 generating music of the element by using a sound simulation method according to the acquired element information and the parameter information of the element;
  • Sub-step S122 superimposing and/or arranging the music of each element of the picture to generate music that matches the picture.
  • music can be generated by various sound simulation calculation methods.
  • the subject that needs to perform the sound simulation is determined according to the element information, and the feature that the theme is finally simulated into the sound is determined according to the parameter information.
  • the element is rain
  • the parameter information of the element includes a large number of raindrops and a large length
  • the sound of the downpour is simulated by a sound simulation calculation method.
  • the element is a frog
  • the parameter information of the element is a plurality of numbers
  • the sound of the frog is simulated by a sound simulation calculation method.
  • the music of the element acts as music that matches the picture. If the image contains multiple elements, the music of each element can be superimposed and/or arranged in order. For example, the sound of a downpour is superimposed on the frog's screams, and then the sound of a torrential rain and then the frog's cry. Again, the sound of the downpour and the sound of the frog's screams, and then the sound of the trees swaying in the wind.
  • the music generated by performing sound simulation by using the element information in the picture and the parameter information of the element can directly reflect the content in the picture, and the degree of matching with the picture is high. , the realization of the transition from visual to auditory.
  • the music generating method includes the following steps:
  • Step S20 Identify a picture, obtain element information in the picture, and parameter information of the element.
  • Step S21 Generate music according to the acquired element information and the parameter information of the element.
  • step S21 includes the following sub-steps:
  • Sub-step S211 determining a note category corresponding to the element information
  • Sub-step S212 Acquire notes in corresponding note categories according to parameter information of the element
  • Sub-step S213 generating music of the element according to the acquired note; [0057] Sub-step S214: superimposing and/or arranging the music of each element of the picture to generate music that matches the picture.
  • the notes for simulating the generation of various elements are classified in advance, one element corresponds to one note type, and one note category includes a plurality of notes for expressing the element features.
  • the corresponding note type is obtained according to the acquired element information
  • the sub-step S212 all the notes for embodying the feature of the element are found from the note type according to the feature information of the element.
  • the music of the element is generated using all of the acquired notes in sub-step S213. If there is only one element in the picture, the music of the element is used as the music matching the picture. If the picture contains multiple elements, in sub-step S214, the music of each element is superimposed and/or pressed. The order of the lines produces music that matches the picture.
  • the light and heavy fluctuations of the music generated by using the element information in the picture and the note corresponding to the parameter information of the element can directly reflect the content in the picture and match the picture. High degree, achieving a transition from visual to auditory.
  • the music generating method includes the following steps:
  • Step S40 Identify a picture, obtain element information in the picture, and parameter information of the element.
  • Step S41 generating music according to the acquired element information and parameter information of the element
  • Step S42 Associating the generated music with the picture.
  • step S42 the music generated in step S41 is associated with the corresponding picture, and the music and the association relationship are saved.
  • There are several ways to associate music with a picture for example, setting up a relationship table, and recording the generated music and pictures in the table.
  • the user can be allowed to know or use the corresponding picture when playing the music, or when browsing the picture. Get or play the corresponding music.
  • the music generating method includes the following steps: [0068] Step S50: identifying a picture, acquiring element information in the picture and parameter information of the element
  • Step S51 generating music according to the acquired element information and parameter information of the element
  • Step S52 associate the generated music with the picture
  • Step S53 When the play command is received, the generated music is played.
  • the difference between this embodiment and the third embodiment is that when the terminal receives the play command, the generated music will be played. Specifically, when the user browses the picture with the matching music, the terminal receives the play instruction, and automatically plays the music that matches the picture.
  • a play command can also be input through interaction with other means of the terminal device to play music that matches the picture. For example, after browsing the picture, the user double-clicks the picture, and the terminal receives the play command, and then plays the music that matches the picture.
  • the terminal when the user browses to the picture where the matching music exists, the terminal can automatically play the matched music, thereby improving the user experience.
  • a music generating terminal 600 includes:
  • an image recognition module 610 configured to identify a picture, obtain element information in the picture, and parameter information of the element
  • a music generating module 620 configured to generate music according to the acquired element information and parameter information of the element
  • an association module 630 configured to associate the generated music with a picture
  • the playing module 640 is configured to play the generated music after receiving the play instruction.
  • the music generating module 620 includes:
  • a first element music sub-module 621 configured to generate music of the element by using a sound simulation method according to the acquired element information and parameter information of the element;
  • the music synthesis sub-module 622 is configured to superimpose and/or sequentially arrange the music of each element of the picture to generate music that matches the picture.
  • the music generating module may further include: [0084] a category determining submodule 710, configured to determine a note category corresponding to the element information;
  • a note acquisition sub-module 720 configured to obtain a note in a corresponding note category according to the parameter information of the element
  • a second element music sub-module 730 configured to generate music of the element according to the acquired note
  • the music synthesis sub-module 740 is configured to superimpose and/or arrange the music of each element of the picture to generate music that matches the picture.
  • the music generated by performing sound simulation by using the element information in the picture and the parameter information of the element can directly reflect the content in the picture, and the degree of matching with the picture is high. , the realization of the transition from visual to auditory.
  • Modules or units or subunits in the apparatus of the embodiments of the present invention may be combined, divided, and deleted according to actual needs.
  • a person skilled in the art can understand that all or part of the steps of the foregoing embodiments can be completed by a program to instruct terminal device related hardware, and the program can be stored in a computer readable storage medium, and the storage medium can be Including: flash drive, read-only memory (ROM), random access memory (Random Access Memory, RAM), disk or CD, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Processing Or Creating Images (AREA)

Abstract

A music generation method and a terminal. The method comprises the following steps: recognizing an image to acquire element information in the image and parameter information of elements; and generating music according to the acquired element information and the parameter information of the elements. The terminal comprises: an image recognition module, for recognizing an image to acquire element information in the image and parameter information of elements; and a music generation module, for generating music according to the acquired element information and the parameter information of the elements. The music generated by using the technical solution can directly reflect the elements in the image, with a good matching effect, and achieving a visual to auditory conversion.

Description

说明书 发明名称:一种音乐生成方法和终端  Instruction title: A music generation method and terminal
技术领域  Technical field
[0001] 本发明涉及移动终端领域, 尤其涉及一种音乐生成方法和终端。  [0001] The present invention relates to the field of mobile terminals, and in particular, to a music generating method and a terminal.
背景技术  Background technique
[0002] 为了增加浏览图片吋的趣味性, 在终端显示图片的同吋, 还可以播放与该图片 关联的音乐。 目前, 传统的做法是, 终端首先根据已拍摄图片的例如地点和吋 间, 在网络上或者预先建立的音乐库中査找与之匹配的音乐, 然后, 通过播放 器在浏览该图片的同吋播放与之匹配的音乐。  [0002] In order to increase the interest of browsing pictures, the music associated with the picture can also be played at the same time as the picture is displayed on the terminal. At present, the conventional method is that the terminal first searches for a matching music on the network or a pre-established music library according to, for example, a location and a time of the captured picture, and then plays the same picture through the player while browsing the picture. Match the music.
[0003] 现有的提供与图片相匹配的音乐的方式, 由于是在现有的音乐库中搜索与图片 匹配的音乐, 因此经常会出现搜索到的音乐不能很好的反应图片中记载的各种 元素的情况, 匹配效果差, 搜索到的音乐不能很好地反映图片中的内容。  [0003] The existing method of providing music matching the picture, because the existing music library is searched for music matching the picture, it is often found that the searched music does not respond well to each of the pictures recorded in the picture. In the case of elements, the matching effect is poor, and the searched music does not reflect the content in the picture well.
技术问题  technical problem
[0004] 本发明要解决的技术问题在于现有的提供与图片相匹配的音乐的方式, 搜索到 的音乐和图片的匹配效果差, 搜索到的音乐不能很好地反映图片中的内容的缺 陷。  [0004] The technical problem to be solved by the present invention lies in the existing way of providing music matching the picture, the matching effect of the searched music and the picture is poor, and the searched music cannot reflect the defect of the content in the picture well. .
问题的解决方案  Problem solution
技术解决方案  Technical solution
[0005] 本发明解决其技术问题所采用的技术方案是: 提供一种音乐生成方法, 包括以 下步骤:  [0005] The technical solution adopted by the present invention to solve the technical problem thereof is: Providing a music generating method, comprising the following steps:
[0006] 对图片进行识别, 获取所述图片中的元素信息以及元素的参数信息;  [0006] identifying a picture, acquiring element information in the picture and parameter information of the element;
[0007] 根据获取的元素信息以及元素的参数信息生成音乐。  [0007] Music is generated based on the acquired element information and parameter information of the element.
[0008] 优选地, 根据获取的元素信息以及元素的参数信息生成音乐的步骤包括: [0008] Preferably, the step of generating music according to the acquired element information and parameter information of the element includes:
[0009] 根据获取的元素信息以及元素的参数信息, 使用声音模拟方法生成该元素的音 乐。 [0009] Based on the acquired element information and the parameter information of the element, the sound of the element is generated using a sound simulation method.
[0010] 优选地, 根据获取的元素信息以及元素的参数信息生成音乐的步骤包括: [0011] 确定与所述元素信息相对应的音符类别; [0012] 根据所述元素的参数信息在相对应的音符类别中获取音符; [0010] Preferably, the step of generating music according to the acquired element information and the parameter information of the element comprises: [0011] determining a note type corresponding to the element information; [0012] acquiring a note in a corresponding note category according to parameter information of the element;
[0013] 根据获取的音符生成该元素的音乐。 [0013] The music of the element is generated according to the acquired note.
[0014] 进一步优选地, 根据获取的元素信息以及元素的参数信息生成音乐的步骤还包 括:  [0014] Further preferably, the step of generating music according to the acquired element information and parameter information of the element further comprises:
[0015] 将所述图片的各元素的音乐进行叠加和 /或按顺序排列生成与所述图片相匹配 的音乐。  [0015] The music of each element of the picture is superimposed and/or arranged in order to generate music that matches the picture.
[0016] 优选地, 本发明的音乐生成方法还包括:  [0016] Preferably, the music generating method of the present invention further includes:
[0017] 将生成的音乐与所述图片建立关联。  [0017] associating the generated music with the picture.
[0018] 优选地, 本发明的音乐生成方法还包括:  [0018] Preferably, the music generating method of the present invention further includes:
[0019] 当接收到播放指令吋, 播放生成的音乐。  [0019] When a play command is received, the generated music is played.
[0020] 进一步优选地, 当浏览所述图片吋, 接收到播放指令。  [0020] Further preferably, when the picture is browsed, a play instruction is received.
[0021] 提供一种音乐生成终端, 包括:  [0021] A music generating terminal is provided, including:
[0022] 图像识别模块, 用于对图片进行识别, 获取所述图片中的元素信息以及元素的 参数信息;  [0022] an image recognition module, configured to identify a picture, obtain element information in the picture, and parameter information of the element;
[0023] 音乐生成模块, 用于根据获取的元素信息以及元素的参数信息生成音乐。  [0023] The music generating module is configured to generate music according to the acquired element information and parameter information of the element.
[0024] 优选地, 本发明的音乐生成终端还包括:  [0024] Preferably, the music generating terminal of the present invention further includes:
[0025] 关联模块, 用于将生成的音乐与所述图片建立关联。  [0025] an association module, configured to associate the generated music with the picture.
[0026] 优选地, 本发明的音乐生成终端还包括:  [0026] Preferably, the music generating terminal of the present invention further includes:
[0027] 播放模块, 用于在接收到播放指令吋, 播放生成的音乐。  [0027] a playing module, configured to play the generated music after receiving the play instruction.
发明的有益效果  Advantageous effects of the invention
有益效果  Beneficial effect
[0028] 实施本发明的技术方案, 生成的音乐能够直接反映图片中的元素, 匹配效果好 , 实现了视觉到听觉的转换。  [0028] Implementing the technical solution of the present invention, the generated music can directly reflect the elements in the picture, and the matching effect is good, and the visual to auditory conversion is realized.
对附图的简要说明  Brief description of the drawing
附图说明  DRAWINGS
[0029] 为了更清楚地说明本发明实施例或现有技术中的技术方案, 下面将对实施例或 现有技术描述中所需要使用的附图作简单地介绍, 显而易见地, 下面描述中的 附图仅仅是本发明的一些实施例, 对于本领域普通技术人员来讲, 在不付出创 造性劳动的前提下, 还可以根据这些附图获得其他的附图。 [0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings to be used in the embodiments or the prior art description will be briefly described below, and obviously, in the following description The drawings are only some of the embodiments of the present invention, and those of ordinary skill in the art will not On the premise of creative labor, other drawings can also be obtained from these drawings.
[0030] 图 1是本发明提供的一种音乐生成方法的第一实施例的流程示意图。  1 is a schematic flow chart of a first embodiment of a music generating method provided by the present invention.
[0031] 图 2是本发明提供的- -种音乐生成方法的第一实施例中步骤 S12的流程示意图; 2 is a schematic flowchart of step S12 in the first embodiment of the music generating method provided by the present invention;
[0032] 图 3是本发明提供的- -种音乐生成方法的第二实施例中步骤 S22流程示意图; [0033] 图 4是本发明提供的- -种音乐生成方法的第三实施例的流程示意图; 3 is a schematic flowchart of step S22 in the second embodiment of the present invention. [0033] FIG. 4 is a flowchart of a third embodiment of the music generating method provided by the present invention. Schematic diagram
[0034] 图 5是本发明提供的- -种音乐生成方法的第四实施例的流程示意图; 5 is a schematic flow chart of a fourth embodiment of a music generating method provided by the present invention;
[0035] 图 6是本发明提供的- -种音乐生成终端第一实施例的结构示意图; 6 is a schematic structural diagram of a first embodiment of a music generating terminal provided by the present invention;
[0036] 图 7是本发明提供的- 中音乐生成终端的其他实施例中音乐生成模块的结构示 7 is a structural diagram of a music generation module in another embodiment of a music generation terminal provided by the present invention.
本发明的实施方式 Embodiments of the invention
[0037] 下面将结合本发明实施例中的附图, 对本发明实施例中的技术方案进行清楚、 完整地描述, 显然, 所描述的实施例仅仅是本发明一部分实施例, 而不是全部 的实施例。 基于本发明中的实施例, 本领域普通技术人员在没有做出创造性劳 动前提下所获得的所有其他实施例, 都属于本发明保护的范围。  The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. example. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.
[0038] 请参阅图 1, 图 1为本发明提供的一种音乐生成方法, 该实施例的操作方法包括 如下步骤:  Referring to FIG. 1, FIG. 1 is a music generating method according to the present invention. The operating method of the embodiment includes the following steps:
[0039] 步骤 S11 : 对图片进行识别, 获取所述图片中的元素信息以及元素的参数信息  [0039] Step S11: Identify a picture, obtain element information in the picture, and parameter information of the element.
[0040] 步骤 S12: 根据获取的元素信息以及元素的参数信息生成音乐。 [0040] Step S12: Generate music according to the acquired element information and the parameter information of the element.
[0041] 在步骤 S11中, 图片可以通过各种方式获取, 例如通过网络下载、 摄像头拍摄 等。 在获取图片之后, 可以自动对图片中的元素信息以及元素的参数信息进行 识别和获取, 也可以在接收到控制指令吋, 对相应图片的元素信息和元素的参 数信息进行识别和获取。 用户可以通过与终端的交互来输入控制指令。  [0041] In step S11, the picture can be acquired in various ways, such as by network downloading, camera shooting, and the like. After obtaining the picture, the element information in the picture and the parameter information of the element may be automatically identified and acquired, or the element information of the corresponding picture and the parameter information of the element may be identified and obtained after receiving the control instruction. The user can input control commands by interacting with the terminal.
[0042] 元素为照片中记载的可以被拟声的内容, 例如一张下雨天池塘边青蛙的照片, 可以被拟声的雨、 青蛙都为元素。 元素的参数信息包括反映元素特征的信息, 例如元素的数量、 弧度、 长度等。  [0042] The element is the content recorded in the photo that can be simulated, such as a picture of a frog on a pond in a rainy day, which can be both an elementary rain and a frog. The parameter information of an element includes information reflecting the characteristics of the element, such as the number of elements, radians, length, and the like.
[0043] 可以通过各种图像识别技术对图片中的元素及其参数进行识别, 优选地, 可以 使用图像边缘检测算法 (PattemRecognition) 来识别出图片中包含的各种元素, 以及各元素的各种参数信息。 [0043] The elements in the picture and their parameters can be identified by various image recognition technologies, preferably, The image edge detection algorithm (PattemRecognition) is used to identify various elements contained in the image, as well as various parameter information of each element.
[0044] 在本实施例中, 如图 2所示, 步骤 S12包括以下子步骤: [0044] In this embodiment, as shown in FIG. 2, step S12 includes the following sub-steps:
[0045] 子步骤 S121 : 根据获取的元素信息以及元素的参数信息, 使用声音模拟方法生 成该元素的音乐;  [0045] Sub-step S121: generating music of the element by using a sound simulation method according to the acquired element information and the parameter information of the element;
[0046] 子步骤 S122: 将图片的各元素的音乐进行叠加和 /或按顺序排列生成与图片相 匹配的音乐。  [0046] Sub-step S122: superimposing and/or arranging the music of each element of the picture to generate music that matches the picture.
[0047] 在子步骤 S121中, 可以通过各种声音模拟计算方法来生成音乐。 具体的, 根据 元素信息确定需要进行声音模拟的主题, 根据其参数信息确定该主题最终被模 拟成声的特征。 例如, 元素为雨, 元素的参数信息包括雨滴数量多, 长度大, 通过声音模拟计算方法模拟出倾盆大雨的声音。 元素为青蛙, 元素的参数信息 为数量为多只, 通过声音模拟计算方法模拟出此起彼伏的青蛙叫声。  [0047] In sub-step S121, music can be generated by various sound simulation calculation methods. Specifically, the subject that needs to perform the sound simulation is determined according to the element information, and the feature that the theme is finally simulated into the sound is determined according to the parameter information. For example, the element is rain, and the parameter information of the element includes a large number of raindrops and a large length, and the sound of the downpour is simulated by a sound simulation calculation method. The element is a frog, and the parameter information of the element is a plurality of numbers, and the sound of the frog is simulated by a sound simulation calculation method.
[0048] 在子步骤 S122中, 若图片中仅有一个元素, 则该元素的音乐作为与图片相匹配 的音乐。 若图片中包含多个元素, 则可以将各元素的音乐进行叠加和 /或按顺序 排列。 例如, 将倾盆大雨的声音与此起彼伏的青蛙叫声叠加, 再如先是倾盆大 雨的声音然后是此起彼伏的青蛙叫声。 再如先是倾盆大雨的声音与此起彼伏的 青蛙叫声叠加的声音, 然后是树木在风中摇曳的声音。  [0048] In sub-step S122, if there is only one element in the picture, the music of the element acts as music that matches the picture. If the image contains multiple elements, the music of each element can be superimposed and/or arranged in order. For example, the sound of a downpour is superimposed on the frog's screams, and then the sound of a torrential rain and then the frog's cry. Again, the sound of the downpour and the sound of the frog's screams, and then the sound of the trees swaying in the wind.
[0049] 在本发明的音乐生成方法的第一实施例中, 通过使用图片中的元素信息以及元 素的参数信息进行声音模拟而生成的音乐, 能够直接反映图片中的内容, 与图 片匹配度高, 实现了从视觉到听觉的转换。  [0049] In the first embodiment of the music generating method of the present invention, the music generated by performing sound simulation by using the element information in the picture and the parameter information of the element can directly reflect the content in the picture, and the degree of matching with the picture is high. , the realization of the transition from visual to auditory.
[0050] 在本发明的音乐生成方法的第二实施例中, 音乐生成方法包括以下步骤: [0050] In a second embodiment of the music generating method of the present invention, the music generating method includes the following steps:
[0051] 步骤 S20: 对图片进行识别, 获取所述图片中的元素信息以及元素的参数信息 [0051] Step S20: Identify a picture, obtain element information in the picture, and parameter information of the element.
[0052] 步骤 S21 : 根据获取的元素信息以及元素的参数信息生成音乐。 [0052] Step S21: Generate music according to the acquired element information and the parameter information of the element.
[0053] 本实施例与第一实施例的区别在于, 如图 3所示, 步骤 S21包括以下子步骤: [0053] The difference between this embodiment and the first embodiment is that, as shown in FIG. 3, step S21 includes the following sub-steps:
[0054] 子步骤 S211 : 确定与元素信息相对应的音符类别; [0054] Sub-step S211: determining a note category corresponding to the element information;
[0055] 子步骤 S212: 根据元素的参数信息在相对应的音符类别中获取音符;  [0055] Sub-step S212: Acquire notes in corresponding note categories according to parameter information of the element;
[0056] 子步骤 S213: 根据获取的音符生成该元素的音乐; [0057] 子步骤 S214: 将图片的各元素的音乐进行叠加和 /或按顺序排列生成与图片相 匹配的音乐。 [0056] Sub-step S213: generating music of the element according to the acquired note; [0057] Sub-step S214: superimposing and/or arranging the music of each element of the picture to generate music that matches the picture.
[0058] 在本实施例中, 预先将用于模拟生成各种元素的音符进行了分类, 一个元素对 应一种音符类型, 一种音符类别中包含用于表现该元素特征的多个音符。  [0058] In the present embodiment, the notes for simulating the generation of various elements are classified in advance, one element corresponds to one note type, and one note category includes a plurality of notes for expressing the element features.
[0059] 在子步骤 S211中根据获取的元素信息获取其对应的音符类型, 在子步骤 S212中 根据该元素的特征信息从该音符类型中査找出所有用于体现该元素的特征的音 符, 在子步骤 S213中使用获取的所有音符来生成该元素的音乐。 若图片中仅有 一个元素, 贝 1」使用该元素的音乐作为与图片相匹配的音乐, 若图片中包含多个 元素, 在子步骤 S214中, 将各元素的音乐进行叠加和 /或按一定的顺序排列生成 与图片相匹配的音乐。  [0059] In the sub-step S211, the corresponding note type is obtained according to the acquired element information, and in the sub-step S212, all the notes for embodying the feature of the element are found from the note type according to the feature information of the element. The music of the element is generated using all of the acquired notes in sub-step S213. If there is only one element in the picture, the music of the element is used as the music matching the picture. If the picture contains multiple elements, in sub-step S214, the music of each element is superimposed and/or pressed. The order of the lines produces music that matches the picture.
[0060] 在本发明的音乐生成方法的第二实施例中, 通过使用图片中的元素信息以及元 素的参数信息对应的音符而生成的音乐的轻重缓急起伏能够直接反映图片中的 内容, 与图片匹配度高, 实现了从视觉到听觉的转换。  [0060] In the second embodiment of the music generating method of the present invention, the light and heavy fluctuations of the music generated by using the element information in the picture and the note corresponding to the parameter information of the element can directly reflect the content in the picture and match the picture. High degree, achieving a transition from visual to auditory.
[0061] 在本发明的音乐生成方法的第三实施例中, 如图 4所示, 音乐生成方法包括以 下步骤:  [0061] In the third embodiment of the music generating method of the present invention, as shown in FIG. 4, the music generating method includes the following steps:
[0062] 步骤 S40: 对图片进行识别, 获取所述图片中的元素信息以及元素的参数信息  [0062] Step S40: Identify a picture, obtain element information in the picture, and parameter information of the element.
[0063] 步骤 S41 : 根据获取的元素信息以及元素的参数信息生成音乐; [0063] Step S41: generating music according to the acquired element information and parameter information of the element;
[0064] 步骤 S42: 将生成的音乐与图片建立关联。 [0064] Step S42: Associating the generated music with the picture.
[0065] 在本实施例与第一或者第二实施例的区别在于, 步骤 S42中, 将步骤 S41中生成 的音乐与对应图片建立关联, 并将音乐以及关联关系进行保存。 可以通过多种 方式将音乐与图片建立关联, 例如, 设置关联关系表, 在表中将生成的音乐和 图片对应记录。  The difference between this embodiment and the first or second embodiment is that, in step S42, the music generated in step S41 is associated with the corresponding picture, and the music and the association relationship are saved. There are several ways to associate music with a picture, for example, setting up a relationship table, and recording the generated music and pictures in the table.
[0066] 在本发明的音乐生成方法的第三实施例中, 通过将音乐与图片建立关联, 能够 允许用户在播放音乐的吋候了解到或者使用对应的图片, 也可以在浏览图片的 吋候获取或者播放对应的音乐。  [0066] In the third embodiment of the music generating method of the present invention, by associating the music with the picture, the user can be allowed to know or use the corresponding picture when playing the music, or when browsing the picture. Get or play the corresponding music.
[0067] 在本发明的音乐生成方法的第四实施例中, 如图 5所示, 音乐生成方法包括以 下步骤: [0068] 步骤 S50: 对图片进行识别, 获取所述图片中的元素信息以及元素的参数信息 [0067] In the fourth embodiment of the music generating method of the present invention, as shown in FIG. 5, the music generating method includes the following steps: [0068] Step S50: identifying a picture, acquiring element information in the picture and parameter information of the element
[0069] 步骤 S51 : 根据获取的元素信息以及元素的参数信息生成音乐; [0069] Step S51: generating music according to the acquired element information and parameter information of the element;
[0070] 步骤 S52: 将生成的音乐与图片建立关联;  [0070] Step S52: associate the generated music with the picture;
[0071] 步骤 S53: 当接收到播放指令吋, 播放生成的音乐。  [0071] Step S53: When the play command is received, the generated music is played.
[0072] 本实施例与第三实施例的区别在于, 当终端接收到播放指令吋, 将播放生成的 音乐。 具体的, 当用户在浏览存在相匹配的音乐的图片吋, 终端接收到播放指 令, 自动播放与该图片相匹配的音乐。 在其他实施例中, 还可以通过与终端设 备的其他方式的交互来输入播放指令, 以播放与图片相匹配的音乐。 例如, 用 户在浏览图片吋, 双击图片吋, 终端接收到播放指令, 则播放与图片相匹配的 音乐。  [0072] The difference between this embodiment and the third embodiment is that when the terminal receives the play command, the generated music will be played. Specifically, when the user browses the picture with the matching music, the terminal receives the play instruction, and automatically plays the music that matches the picture. In other embodiments, a play command can also be input through interaction with other means of the terminal device to play music that matches the picture. For example, after browsing the picture, the user double-clicks the picture, and the terminal receives the play command, and then plays the music that matches the picture.
[0073] 在本实施例中, 当用户浏览到存在匹配音乐的图片吋, 终端能够自动播放该匹 配的音乐, 提高了用户体验。  [0073] In this embodiment, when the user browses to the picture where the matching music exists, the terminal can automatically play the matched music, thereby improving the user experience.
[0074] 在本发明的音乐生成方法的其他实施例中, 还可以在检测到用户使用图片作为 手机某个联系人的来电显示图象吋, 自动将该图片的匹配音乐设置为该用户的 来电铃声。 [0074] In other embodiments of the music generating method of the present invention, it is also possible to automatically set the matching music of the picture as the incoming call of the user after detecting that the user uses the picture as the caller ID image of a contact of the mobile phone. ring.
[0075] 如图 6所示为本发明提供的一种音乐生成终端 600, 包括:  [0075] As shown in FIG. 6, a music generating terminal 600 according to the present invention includes:
[0076] 图像识别模块 610, 用于对图片进行识别, 获取图片中的元素信息以及元素的 参数信息; [0076] an image recognition module 610, configured to identify a picture, obtain element information in the picture, and parameter information of the element;
[0077] 音乐生成模块 620, 用于根据获取的元素信息以及元素的参数信息生成音乐; [0077] a music generating module 620, configured to generate music according to the acquired element information and parameter information of the element;
[0078] 关联模块 630, 用于将生成的音乐与图片建立关联; [0078] an association module 630, configured to associate the generated music with a picture;
[0079] 播放模块 640, 用于在接收到播放指令吋, 播放生成的音乐。  [0079] The playing module 640 is configured to play the generated music after receiving the play instruction.
[0080] 在本实施例中, 音乐生成模块 620包括:  [0080] In this embodiment, the music generating module 620 includes:
[0081] 第一元素音乐子模块 621, 用于根据获取的元素信息以及元素的参数信息, 使 用声音模拟方法生成该元素的音乐;  [0081] a first element music sub-module 621, configured to generate music of the element by using a sound simulation method according to the acquired element information and parameter information of the element;
[0082] 音乐合成子模块 622, 用于将图片的各元素的音乐进行叠加和 /或按顺序排列生 成与图片相匹配的音乐。 [0082] The music synthesis sub-module 622 is configured to superimpose and/or sequentially arrange the music of each element of the picture to generate music that matches the picture.
[0083] 在其他实施例中, 如图 7所示, 音乐生成模块还可以包括: [0084] 类别确定子模块 710, 用于确定与所述元素信息相对应的音符类别; [0083] In other embodiments, as shown in FIG. 7, the music generating module may further include: [0084] a category determining submodule 710, configured to determine a note category corresponding to the element information;
[0085] 音符获取子模块 720, 用于根据所述元素的参数信息在相对应的音符类别中获 取音符; [0085] a note acquisition sub-module 720, configured to obtain a note in a corresponding note category according to the parameter information of the element;
[0086] 第二元素音乐子模块 730, 用于根据获取的音符生成该元素的音乐;  [0086] a second element music sub-module 730, configured to generate music of the element according to the acquired note;
[0087] 音乐合成子模块 740, 用于将图片的各元素的音乐进行叠加和 /或按顺序排列生 成与图片相匹配的音乐。  [0087] The music synthesis sub-module 740 is configured to superimpose and/or arrange the music of each element of the picture to generate music that matches the picture.
[0088] 在本发明的音乐生成终端的第一实施例中, 通过使用图片中的元素信息以及元 素的参数信息进行声音模拟而生成的音乐, 能够直接反映图片中的内容, 与图 片匹配度高, 实现了从视觉到听觉的转换。  [0088] In the first embodiment of the music generating terminal of the present invention, the music generated by performing sound simulation by using the element information in the picture and the parameter information of the element can directly reflect the content in the picture, and the degree of matching with the picture is high. , the realization of the transition from visual to auditory.
[0089] 本发明实施例的方法中的步骤可以根据实际需要进行顺序调整、 合并和刪减。  [0089] The steps in the method of the embodiment of the present invention may be sequentially adjusted, merged, and deleted according to actual needs.
本发明实施例的装置中的模块或单元或子单元可以根据实际需要进行合并、 划 分和刪减。 本领域普通技术人员可以理解上述实施例的各种方法中的全部或部 分步骤是可以通过程序来指令终端设备相关的硬件来完成, 该程序可以存储于 一计算机可读存储介质中, 存储介质可以包括: 闪存盘、 只读存储器 (Read-Only Memory , ROM)、 随机存取器 (Random Access Memory, RAM)、 磁盘或光盘等  Modules or units or subunits in the apparatus of the embodiments of the present invention may be combined, divided, and deleted according to actual needs. A person skilled in the art can understand that all or part of the steps of the foregoing embodiments can be completed by a program to instruct terminal device related hardware, and the program can be stored in a computer readable storage medium, and the storage medium can be Including: flash drive, read-only memory (ROM), random access memory (Random Access Memory, RAM), disk or CD, etc.
[0090] 以上所揭露的仅为本发明的较佳实施例而已, 当然不能以此来限定本发明的权 利范围, 本领域普通技术人员可以理解实现上述实施例的全部或部分流程, 并 依本发明权利要求所作的等同变化, 仍属于发明所涵盖的范围。 The above is only the preferred embodiment of the present invention, and the scope of the present invention is not limited thereto. Those skilled in the art can understand all or part of the process of implementing the above embodiments, and Equivalent variations of the claims of the invention are still within the scope of the invention.

Claims

权利要求书 Claim
[权利要求 1] 一种音乐生成方法, 其特征在于, 包括以下步骤:  [Claim 1] A music generating method, comprising the steps of:
对图片进行识别, 获取所述图片中的元素信息以及元素的参数信息; 根据获取的元素信息以及元素的参数信息生成音乐。  Identifying a picture, obtaining element information in the picture and parameter information of the element; generating music according to the acquired element information and parameter information of the element.
[权利要求 2] 根据权利要求 1所述的音乐生成方法, 其特征在于, 根据获取的元素 信息以及元素的参数信息生成音乐的步骤包括: 根据获取的元素信息以及元素的参数信息, 使用声音模拟方法生成该 元素的音乐。  [Claim 2] The music generating method according to claim 1, wherein the step of generating music based on the acquired element information and parameter information of the element comprises: using sound simulation based on the acquired element information and parameter information of the element The method generates music for this element.
[权利要求 3] 根据权利要求 1所述的音乐生成方法, 其特征在于, 根据获取的元素 信息以及元素的参数信息生成音乐的步骤包括: 确定与所述元素信息相对应的音符类别;  [Claim 3] The music generating method according to claim 1, wherein the step of generating music based on the acquired element information and the parameter information of the element comprises: determining a note type corresponding to the element information;
根据所述元素的参数信息在相对应的音符类别中获取音符; 根据获取的音符生成该元素的音乐。  Acquiring a note in the corresponding note class according to the parameter information of the element; generating music of the element according to the acquired note.
[权利要求 4] 根据权利要求 2或 3所述的音乐生成方法, 其特征在于, 根据获取的元 素信息以及元素的参数信息生成音乐的步骤还包括: [Claim 4] The music generating method according to claim 2 or 3, wherein the step of generating music based on the acquired element information and the parameter information of the element further comprises:
将所述图片的各元素的音乐进行叠加和 /或按顺序排列生成与所述图 片相匹配的音乐。  The music of each element of the picture is superimposed and/or arranged in order to generate music that matches the picture.
[权利要求 5] 根据权利要求 1所述的音乐生成方法, 其特征在于, 还包括:  [Claim 5] The music generating method according to claim 1, further comprising:
将生成的音乐与所述图片建立关联。  The generated music is associated with the picture.
[权利要求 6] 根据权利要求 1所述的音乐生成方法, 其特征在于, 还包括: [Claim 6] The music generating method according to claim 1, further comprising:
当接收到播放指令吋, 播放生成的音乐。  When the play command is received, the generated music is played.
[权利要求 7] 根据权利要求 6所述的音乐生成方法, 其特征在于, 当浏览所述图片 吋, 接收到播放指令。 [Claim 7] The music generating method according to claim 6, wherein when the picture is browsed, a play instruction is received.
[权利要求 8] —种音乐生成终端, 其特征在于, 包括: [Claim 8] A music generating terminal, comprising:
图像识别模块, 用于对图片进行识别, 获取所述图片中的元素信息以 及元素的参数信息;  An image recognition module, configured to identify a picture, obtain element information in the picture, and parameter information of the element;
音乐生成模块, 用于根据获取的元素信息以及元素的参数信息生成音 乐。 a music generating module, configured to generate music according to the acquired element information and parameter information of the element.
[权利要求 9] 根据权利要求 8所述的音乐生成终端, 其特征在于, 还包括: 关联模块, 用于将生成的音乐与所述图片建立关联。 [Claim 9] The music generating terminal according to claim 8, further comprising: an association module, configured to associate the generated music with the picture.
[权利要求 10] 根据权利要求 8所述的音乐生成终端, 其特征在于, 还包括:  [Claim 10] The music generating terminal according to claim 8, further comprising:
播放模块, 用于在接收到播放指令吋, 播放生成的音乐。  The play module is configured to play the generated music after receiving the play command.
PCT/CN2017/079829 2017-04-08 2017-04-08 Music generation method and terminal WO2018184249A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/079829 WO2018184249A1 (en) 2017-04-08 2017-04-08 Music generation method and terminal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/079829 WO2018184249A1 (en) 2017-04-08 2017-04-08 Music generation method and terminal

Publications (1)

Publication Number Publication Date
WO2018184249A1 true WO2018184249A1 (en) 2018-10-11

Family

ID=63712776

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/079829 WO2018184249A1 (en) 2017-04-08 2017-04-08 Music generation method and terminal

Country Status (1)

Country Link
WO (1) WO2018184249A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100325581A1 (en) * 2006-11-10 2010-12-23 Microsoft Corporation Data object linking and browsing tool
CN103475789A (en) * 2013-08-26 2013-12-25 宇龙计算机通信科技(深圳)有限公司 Mobile terminal and control method thereof
CN104065869A (en) * 2013-03-18 2014-09-24 三星电子株式会社 Method for displaying image in combination with playing audio in electronic device
CN105045840A (en) * 2015-06-30 2015-11-11 广东欧珀移动通信有限公司 Picture display method and mobile terminal
CN105912722A (en) * 2016-05-04 2016-08-31 广州酷狗计算机科技有限公司 Song sending method and apparatus

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100325581A1 (en) * 2006-11-10 2010-12-23 Microsoft Corporation Data object linking and browsing tool
CN104065869A (en) * 2013-03-18 2014-09-24 三星电子株式会社 Method for displaying image in combination with playing audio in electronic device
CN103475789A (en) * 2013-08-26 2013-12-25 宇龙计算机通信科技(深圳)有限公司 Mobile terminal and control method thereof
CN105045840A (en) * 2015-06-30 2015-11-11 广东欧珀移动通信有限公司 Picture display method and mobile terminal
CN105912722A (en) * 2016-05-04 2016-08-31 广州酷狗计算机科技有限公司 Song sending method and apparatus

Similar Documents

Publication Publication Date Title
US12278859B2 (en) Creating a cinematic storytelling experience using network-addressable devices
US8347213B2 (en) Automatically generating audiovisual works
CN105159639B (en) Audio cover display methods and device
US12176008B2 (en) Method and apparatus for matching music with video, computer device, and storage medium
JP2019212308A (en) Video service providing method and service server using the same
CN107170432B (en) Music generation method and device
US11511200B2 (en) Game playing method and system based on a multimedia file
CN110675886A (en) Audio signal processing method, audio signal processing device, electronic equipment and storage medium
US20230368461A1 (en) Method and apparatus for processing action of virtual object, and storage medium
WO2024188242A1 (en) Question answering method and apparatus, device, and storage medium
CN109474843A (en) The method of speech control terminal, client, server
US11568871B1 (en) Interactive media system using audio inputs
US20170171471A1 (en) Method and device for generating multimedia picture and an electronic device
CN113792178B (en) Song generation method, device, electronic device and storage medium
CN112380871A (en) Semantic recognition method, apparatus, and medium
WO2018184249A1 (en) Music generation method and terminal
CN115243087B (en) Audio and video shooting processing method and device, terminal equipment and storage medium
CN115119041B (en) Control method, device and equipment for cross-screen playing and computer storage medium
WO2022209648A1 (en) Information processing device, information processing method, and non-transitory computer-readable medium
CN115148184B (en) Voice synthesis and broadcasting method, teaching method, live broadcasting method and device
WO2018187890A1 (en) Method and device for generating music according to image
CN119207346A (en) Karaoke method, computer device, readable storage medium and computer program product
CN113192533A (en) Audio processing method and device, electronic equipment and storage medium
TWI590077B (en) Multimedia file playing method and electronic device
CN113840152A (en) Live broadcast key point processing method and device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17904822

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17904822

Country of ref document: EP

Kind code of ref document: A1