WO2017092493A1 - 场景音乐搜索方法及场景音乐搜索装置 - Google Patents

场景音乐搜索方法及场景音乐搜索装置 Download PDF

Info

Publication number
WO2017092493A1
WO2017092493A1 PCT/CN2016/100405 CN2016100405W WO2017092493A1 WO 2017092493 A1 WO2017092493 A1 WO 2017092493A1 CN 2016100405 W CN2016100405 W CN 2016100405W WO 2017092493 A1 WO2017092493 A1 WO 2017092493A1
Authority
WO
WIPO (PCT)
Prior art keywords
music
scene
search
tag
label
Prior art date
Application number
PCT/CN2016/100405
Other languages
English (en)
French (fr)
Inventor
张茜
Original Assignee
腾讯科技（深圳）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 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Publication of WO2017092493A1 publication Critical patent/WO2017092493A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings

Definitions

  • the present invention relates to the field of the Internet, and in particular, to a scene music search method and a scene music search device.
  • existing music software or music playing platforms can classify music according to the playing scene, such as songs that are listened to before going to bed, songs that are heard on the way home, or songs that are heard while walking.
  • the scene music mentioned above is operated manually, that is, the scene is partially associated with some music, and thus the type of the scene is limited. If the user wants to listen to music during cooking in the kitchen, there may be no scenes in the music software or music playing platform, which may make it difficult for the user to find the corresponding scene music. At the same time, the music content corresponding to the existing scene music is manually added, wherein the music content is updated slowly and the content is relatively fixed.
  • the existing music playing platform cannot provide rich and more accurate scene music.
  • the embodiment of the invention provides a scene music search method and a scene music search device with relatively comprehensive and fast updated music content; to solve the existing scene music search method and the scene music search device, the music content is less and the music content is updated. Slow technical issues.
  • the embodiment of the invention provides a scene music searching method, which includes:
  • the music library includes the music, the music tag, and a correspondence between the music and the music tag;
  • the scene music search term and the corresponding music are displayed.
  • the embodiment of the invention further provides a scene music searching device, which comprises:
  • a statement splitting module configured to acquire a scene music search statement; and split the scene music search sentence to obtain at least one scene music search term;
  • a music tag acquisition module configured to acquire, according to the scene music search term, a music tag corresponding to the scene music search term
  • a music search module configured to search for a corresponding music in a music library using the music tag; wherein the music library includes the music, the music tag, and a correspondence between the music and the music tag;
  • a music display module configured to display the scene music search word and the corresponding music.
  • An embodiment of the present invention further provides a storage medium, where the storage medium is configured to store program code for performing the following steps, including:
  • the music library includes the music, the music tag, and a correspondence between the music and the music tag;
  • the scene music search term and the corresponding music are displayed.
  • the scene music search method and the scene music search device of the embodiment of the present invention analyze the scene music search sentence input by the user to obtain a corresponding music label, and further Get the corresponding music; show it to the user within the music
  • the content is more comprehensive; and the latest music content can be obtained in real time; the existing scene music search method and the technical problem that the scene music search device has less music content and the music content update is slower is solved.
  • FIG. 1 is a flow chart of a first preferred embodiment of a scene music search method of the present invention
  • FIG. 2 is a flow chart of a second preferred embodiment of the scene music searching method of the present invention.
  • FIG. 3 is a second flowchart of a second preferred embodiment of the scene music searching method of the present invention.
  • FIG. 4 is a third flowchart of a second preferred embodiment of the scene music searching method of the present invention.
  • FIG. 5 is a schematic structural diagram of a first preferred embodiment of a scene music search apparatus according to the present invention.
  • FIG. 6 is a schematic structural diagram of a second preferred embodiment of a scene music search device according to the present invention.
  • FIG. 7 is a schematic structural diagram of a sentence splitting module of a second preferred embodiment of the scene music search device of the present invention.
  • FIG. 8 is a schematic structural diagram of a music tag acquiring module according to a second preferred embodiment of the scene music searching device of the present invention.
  • FIG. 9 is a schematic structural diagram of a music display module according to a second preferred embodiment of the scene music search device of the present invention.
  • FIG. 10A to FIG. 10B are schematic diagrams showing the use of a scene music search method and a scene music search apparatus according to a specific embodiment of the present invention.
  • FIG. 11 is a schematic structural diagram of a working environment of an electronic device in which a scene music search device of the present invention is located.
  • the scene music search device of the embodiments of the present invention may be implemented using various electronic devices including, but not limited to, a personal computer, a server computer, a handheld or laptop device, a mobile device (such as a mobile phone, a personal digital assistant ( PDA), media player, etc., multi-processor systems, consumer electronics, small computers, mainframe computers, distributed computing environments including any of the systems or devices described above, and the like.
  • the electronic device is preferably a music search platform or a music search server, so as to effectively improve the music search success rate and the music content update speed of the music search platform or the music search server.
  • FIG. 1 is a flowchart of a first preferred embodiment of a scene music searching method according to the present invention.
  • the scene music search method of the preferred embodiment may be implemented by using the above-mentioned electronic device, and the scene music search method includes:
  • Step S101 acquiring a scene music search sentence; and splitting the scene music search sentence to obtain at least one scene music search term;
  • Step S102 Acquire a music label corresponding to the scene music search term according to the scene music search word
  • Step S103 using a music tag, searching for a corresponding music in the music library
  • Step S104 displaying the scene music search word and the corresponding music.
  • step S101 the scene music searching device acquires a scene music search sentence, where the scene music search sentence can be a sentence input by a user or a voice input sentence, such as a user inputting "I am in the sea”
  • the scene music search sentence of the "blowing” is the scene music search words obtained after the splitting are "I", “at”, “seaside”, “hair blowing”. Then, the process proceeds to step S102.
  • step S102 the scene music searching device acquires a music tag corresponding to the scene music search word according to the scene music search word acquired in step S101.
  • the scene music search word is used as a keyword to retrieve the same or similar music labels in the music library. In this way, regardless of whether the music tag of the music library has the scene music search word, a music tag strongly related to the scene music search word can be obtained to ensure the validity of the search. Then it proceeds to step S103.
  • the scene music search means searches for the corresponding music in the music library using the music tag acquired in step S102.
  • the music library here includes music, music labels, and music and music label correspondence.
  • the music tag in the music library can generate tags for users of social media, authoritative tags reviewed by music publishers or professionals, or supplemental tags generated by machine learning methods, and the like.
  • the music library here is a real-time updated online music database, which can directly call the online music database of the local music website or the online music database of other websites. Then it proceeds to step S104.
  • step S104 the scene music searching device displays the scene music search word acquired in step S101 and the corresponding music acquired in step S103 for the user to perform a playback operation.
  • the scene music search method of the preferred embodiment analyzes the scene music search sentence input by the user, acquires the corresponding music label, and then acquires the corresponding music; and improves the search success by using the scene music search word as a keyword for searching.
  • the music is returned through the real-time updated music library, which improves the update speed of the search music content and the comprehensiveness of the search music content, so the music content displayed to the user is more comprehensive.
  • FIG. 2 is a flowchart of a second preferred embodiment of the scene music searching method of the present invention.
  • the scene music search method of the preferred embodiment may be implemented by using the above-mentioned electronic device, and the scene music search method includes:
  • Step S201 splitting the scene music search statement into a plurality of basic words
  • Step S202 using verbs and nouns in the basic words as scene music search words
  • Step S203 it is determined whether the scene music search word has a corresponding music label; if there is a corresponding music label, go to step S204; if there is no corresponding music label, go to step S205;
  • Step S204 acquiring a music label
  • Step S205 Acquire a similar search term of the scene music search term, and obtain a corresponding music tag according to the similar search term;
  • Step S206 using a music tag, searching for a corresponding music in the music library
  • Step S207 obtaining a weight value of the music tag in all the music that is searched.
  • Step S208 sorting and displaying all the searched music according to the weight value of the music label.
  • step S201 the scene music searching device acquires a scene music search statement, where the scene music search sentence may be a sentence input by a user or a voice input sentence, for example, if the user inputs a scene music search sentence of “I am blowing at the beach”,
  • the basic words obtained after splitting are "I", “At”, “Seaside”, “Blowing”. Then it proceeds to step S202.
  • step S202 since the scene music search word is generally a meaningful name or verb, other person-named pronouns, prepositions or conjunctions are meaningless as scene music search words, so the scene music search device here uses the verbs in the basic words and Nouns are used as scene music search terms.
  • the "seaside" and "hair blowing" in the basic words acquired in step S201 can be set as scene music search words. Then it proceeds to step S203.
  • step S203 the scene music searching device acquires a music tag corresponding to the scene music search term according to the scene music search word acquired in step S202.
  • step S204 if the scene music search word acquired in step S202 has a corresponding music label, for example, the scene music search word "seaside" obtained in step S202 itself can be used as a music label.
  • the music search device directly acquires the music tag. Then it proceeds to step S205.
  • step S205 if the scene music search word acquired in step S202 does not have a corresponding music label, for example, the scene music search word "hair dryer" acquired in step S202 is not itself a music label, the scene music search device acquires the scene music search. Similar search terms for words.
  • the similar search words can also use different databases to parse and obtain the scene music search words, such as the explanation of the scene music search words obtained on the website of the word interpretation, such as "hair dryer” on the Baidu website has "air blowing is a mood, such as : We go out to blow the air and take a walk, so we can also set the similar search words for "hair dryer” as “walking” or "walking”. Then it proceeds to step S206.
  • the scene music search means searches for the corresponding music in the music library using the music tags acquired in step S204 and step S205.
  • the music library here includes music, music labels, music and music label correspondences, and weight values for all music labels corresponding to the music.
  • the music tag in the music library can generate tags for users of social media, authoritative tags reviewed by music publishers or professionals, or supplemental tags generated by machine learning methods, and the like.
  • the music library here is a real-time updated online music database, which can directly call the online music database of the local music website or the online music database of other websites.
  • step S204 if a plurality of music tags are acquired in step S204 and step S205, all music that satisfies at least one music tag is searched in the music library. Then it proceeds to step S207.
  • step S207 since the music is presented to the user, the music most likely to be required by the user should be preferentially displayed. Therefore, in this step, the scene music search means acquires the weight value of all the music searched in step S206 by the music tag corresponding to the scene music search word. That is, the size of each music associated with the scene music search term and the relevance of the scene music search word is obtained.
  • the weight values of all the music searched by the scene music search phrase in step S206 are acquired. That is, the weight value of the scene music search phrase in a certain music is the superposition of the weight values of the music search words in the music in each of the scene music search phrases.
  • the scene music search phrase includes the scene music search word A and the scene music search word B, and the scene music search word A has weight values of 20, 30, and 50 in the music a, the music b, and the music c, respectively; the scene music search word B is in the The weights in music a, music b, and music c are 40, 10, and 0, respectively.
  • the scene music search phrase has weights of 60, 40, and 50 in music a, music b, and music c. Then it proceeds to step S208.
  • step S208 while the scene music searching device displays the scene music search word, the scene music searching device sorts and displays all the music searched according to the weight value of the music label acquired in step S207 for the user to play. operating.
  • the music can be corrected by using the current heat of the music. For example, a plurality of music whose weight value is different from the set value relative to the music search word of a certain scene is sorted according to the current heat of the music. Since the music is sorted according to the relevance and popularity of the scene music search words, the user can easily obtain the music that he wants to listen to.
  • FIG. 3 is a second flowchart of a second preferred embodiment of the scene music searching method of the present invention.
  • the scene music searching method of the preferred embodiment further includes after step S208:
  • Step S301 the scene music searching device receives the search word modification instruction, and modifies the scene music search word according to the search word modification instruction.
  • the search term modification instruction may be sent to the scene music search device through the client.
  • the scene music search words "Seaside” and “Blowing” are acquired in step S202, and finally the step S208 performs music display according to the scene music search words "Seaside” and "Blowing".
  • the scene music search device receives the search word modification instruction, and modifies the scene music search word according to the search word modification instruction, such as the scene music search word. "Blow" is deleted.
  • Step S302 the scene music searching device acquires the weight value of all the music searched in the music label corresponding to the modified scene music search word in step S206.
  • step S303 the scene music searching device re-sorts all the searched music according to the weight value of the music label acquired in step S302 for the user to perform the playing operation.
  • FIG. 4 is a third flowchart of a second preferred embodiment of the scene music searching method of the present invention.
  • the scene music searching method of the preferred embodiment further includes after step S208:
  • Step S401 Receive a music play instruction of the client, and perform a play operation on the displayed music according to the music play instruction.
  • Step S402 if the user is dissatisfied with the music displayed by the scene music searching device, the music playing instruction may not be sent for music playing, so the scene music searching device may be based on the ratio of the number of times the music of the displayed music is played to the number of times the music is displayed. Correct the weight value of the music tag in the display music.
  • the weight value of the music label in the displayed music is increased; if the ratio of the number of times the music is played to the number of times the music is displayed is small, then Decrease the weight value of the music tag in the display music.
  • the number of music playing operations whose playing time is less than the set value may be deleted from the number of music playing times.
  • the weight value of the music label corresponding to the music in the music library is corrected in real time, so that the accuracy of the music label in the music library is higher, and the success rate of the music search is further improved.
  • the scene music searching method of the preferred embodiment deletes the invalid scene music search words on the basis of the first preferred embodiment, and improves the search hit rate of the scene music search words by setting the similar search words, and simultaneously
  • the time for music search is shortened by setting the weight value of the music tag. Improve the success rate of music search.
  • FIG. 5 is a schematic structural diagram of a first preferred embodiment of the scene music search device of the present invention.
  • the scene music search device 50 of the preferred embodiment is implemented using the first preferred embodiment of the scene music search method described above.
  • the scene music search device 50 includes a sentence splitting module 51, a music tag acquisition module 52, a music search module 53, and a music display module 54.
  • the statement splitting module 51 is configured to acquire a scene music search sentence; and split the scene music search sentence to obtain at least one scene music search term.
  • the music tag acquisition module 52 is configured to acquire a music tag corresponding to the scene music search term according to the scene music search term.
  • the music search module 53 is for searching for the corresponding music in the music library using the music tag.
  • the music display module 54 is configured to display the scene music search words and the corresponding music.
  • the sentence splitting module 51 first acquires a scene music search sentence, where the scene music search sentence can be a sentence input by a user or a voice input sentence, for example, the user inputs “I am at The scene music search statement of the "Blowing by the Sea", the scene music search words obtained after the split is "I", “At”, “Seaside”, “Blowing”.
  • the music tag acquisition module 52 acquires the music tag corresponding to the scene music search term according to the scene music search word acquired by the sentence splitting module 51. Instead of directly using the scene music search word as a music label, the scene music search word is used as a keyword to retrieve the same or similar music labels in the music library. In this way, regardless of whether the music tag of the music library has the scene music search word, a music tag strongly related to the scene music search word can be obtained to ensure the validity of the search.
  • the music search module 53 uses the music tag acquired by the music tag acquisition module 52 to search for the corresponding music in the music library.
  • the music library here includes music, music labels, and music and music label correspondence.
  • the music tag in the music library can generate tags for users of social media, authoritative tags reviewed by music publishers or professionals, or supplemental tags generated by machine learning methods, and the like.
  • the music library here is a real-time updated online music database, which can directly call the online music database of the local music website or the online music database of other websites.
  • the final music display module 54 displays the scene music search word acquired by the sentence splitting module 51 and the corresponding music acquired by the music search module 53 for the user to perform a play operation.
  • the scene music searching device of the preferred embodiment parses the scene music search sentence input by the user, acquires the corresponding music label, and then acquires the corresponding music; and improves the search success by using the scene music search word as a keyword for searching.
  • the music is returned through the real-time updated music library, which improves the update speed of the search music content and the comprehensiveness of the search music content, so the music content displayed to the user is more comprehensive.
  • FIG. 6 is a schematic structural diagram of a second preferred embodiment of a scene music search apparatus according to the present invention.
  • the scene music search device 60 of the preferred embodiment is implemented using the second preferred embodiment of the scene music search method described above.
  • the scene music search device 60 includes a sentence splitting module 61, a music tag acquisition module 62, a music search module 63, a music display module 64, a play module 65, and a weight value correction module 66.
  • the statement splitting module 61 is configured to acquire a scene music search statement; and split the scene music search sentence to obtain at least one scene music search term.
  • the music tag acquisition module 62 is configured to acquire a music tag corresponding to the scene music search term according to the scene music search term.
  • the music search module 3 is for searching for the corresponding music in the music library using the music tag.
  • the music display module 64 is configured to display the scene music search words and the corresponding music.
  • the playing module 65 is configured to receive a music playing instruction, and perform a playing operation on the displayed music according to the music playing instruction.
  • the weight value correction module 66 is configured to correct the weight value of the music label in the displayed music according to the ratio of the number of times the music is played and the number of times the music is displayed.
  • FIG. 7 is a schematic structural diagram of a sentence splitting module according to a second preferred embodiment of the scene music searching device of the present invention.
  • the sentence splitting module 61 includes a splitting unit 611 and a search term setting unit 612.
  • the splitting unit 611 is configured to split the scene music search sentence into a plurality of basic words;
  • the search word setting unit 612 is configured to use the verbs and nouns in the basic words as the scene music search words.
  • FIG. 8 is a schematic structural diagram of a music tag acquiring module according to a second preferred embodiment of the scene music searching device of the present invention.
  • the music tag acquisition module 62 includes a determination unit 621, a first music tag acquisition unit 622, and a second music tag acquisition unit 623.
  • the determining unit 621 is configured to determine whether the scene music search word has a corresponding music label;
  • the first music label obtaining unit 622 is configured to acquire the music label if the scene music search word has a corresponding music label;
  • the second music label acquiring unit 623 For acquiring a similar music word of the scene music search word, if the scene music search word does not have a corresponding music label, and acquiring a corresponding music label according to the similar search word.
  • FIG. 9 is a schematic structural diagram of a music display module according to a second preferred embodiment of the scene music search device of the present invention.
  • the music presentation module 64 includes a first weight value acquisition unit 641, a first ranking display unit 642, a search term modification unit 643, a second weight value acquisition unit 644, and a second ranking display unit 645.
  • the first weight value obtaining unit 641 is configured to acquire a weight value of the music label corresponding to the scene music search term and all the music that is searched.
  • the first sorting display unit 642 is configured to sort all the searched music by the weight value of the music label in the music.
  • the search word modification unit 643 is configured to receive a search word modification instruction, and modify the scene music search word according to the search word modification instruction.
  • the second weight value obtaining unit 644 is configured to acquire a weight value of the music tag in all the music that is searched.
  • the second sorting display unit 645 is configured to reorder all the searched music by the weight value of the music label.
  • the splitting unit 611 of the first sentence splitting module 61 first acquires a scene music search sentence, where the scene music search sentence can be a sentence or a voice input sentence manually input by the user, such as The user inputs the scene music search statement "I am blowing at the beach", and the basic words obtained after the split are "I", “At”, “Seaside”, “Blowing".
  • the search word setting unit 612 of the subsequent sentence splitting module 61 will be in the basic words.
  • Verbs and nouns are used as scene music search terms. For example, "Seaside” and “Blowing" in the basic words obtained can be set as scene music search words.
  • the music tag acquisition module 62 searches for the scene music search word according to the sentence splitting module 61. Get the music label corresponding to the scene music search term.
  • the determining unit 621 of the music tag acquiring module 62 first determines whether the scene music search word has a corresponding music tag.
  • the first music label acquisition unit 622 of the music label acquisition module 62 directly acquires the music label.
  • the second music label acquisition unit 623 of the music label acquisition module 62 acquires the scene music search word. Similar search words, here to ensure that the similar search words obtained can be used as music labels, so the similarity between the scene music search words and each music label can be calculated according to the similarity of word vectors, and the music label with the highest similarity is selected as the scene.
  • the music tag corresponding to the music search term is selected as the scene.
  • the similar search words can also use different databases to parse and obtain the scene music search words, such as the explanation of the scene music search words obtained on the website of the word interpretation, such as "hair dryer” on the Baidu website has "air blowing is a mood, such as : We go out to blow the air and take a walk, so we can also set the similar search words for "hair dryer” as “walking” or "walking”.
  • the music search module 63 uses the music tag acquired by the music tag acquisition module 62 to search for the corresponding music in the music library.
  • the music library here includes music, music labels, music and music label correspondences, and weight values for all music labels corresponding to the music.
  • the music tag in the music library can generate tags for users of social media, authoritative tags reviewed by music publishers or professionals, or supplemental tags generated by machine learning methods, and the like.
  • the music library here is a real-time updated online music database, which can directly call the online music database of the local music website or the online music database of other websites.
  • the music search module 63 searches the music library for all music that satisfies at least one music tag.
  • the first weight value obtaining unit 641 of the music display module 64 acquires the music label corresponding to the scene music search word. Sign, the weight value of all the music found in the music search module. That is, the size of each music associated with the scene music search term and the relevance of the scene music search word is obtained.
  • the first weight value acquisition unit 641 combines the plurality of scene music search words into one scene music search phrase.
  • the weight values of the scene music search phrases in all the music searched by the music search module 63 are then acquired by superposition. That is, the weight value of the scene music search phrase in a certain music is the superposition of the weight values of the music search words in the music in each of the scene music search phrases.
  • the scene music search phrase includes the scene music search word A and the scene music search word B, and the scene music search word A has weight values of 20, 30, and 50 in the music a, the music b, and the music c, respectively; the scene music search word B is in the The weights in music a, music b, and music c are 40, 10, and 0, respectively.
  • the scene music search phrase has weights of 60, 40, and 50 in music a, music b, and music c.
  • the first sorting display unit 642 of the last music display module 64 displays the all the music of the search according to the weight value of the music label acquired by the first weight value obtaining unit 641 while displaying the scene music search word, For the user to play.
  • the music can be corrected by using the current heat of the music. For example, a plurality of music whose weight value is different from the set value relative to the music search word of a certain scene is sorted according to the current heat of the music. Since the music is sorted according to the relevance and popularity of the scene music search words, the user can easily obtain the music that he wants to listen to. Since the music is sorted by the relevance of the scene music search words, the user can easily obtain the music he wants to listen to.
  • the scene music search device 60 of the preferred embodiment can also perform real-time correction on the presentation scene music search words. Specifically:
  • the search word modification unit 643 of the music display module 64 receives the search word modification instruction, and modifies the scene music search word according to the search word modification instruction.
  • the search term modification command may be sent to the scene music search device 60 by the client.
  • the sentence splitting module 61 obtains the scene music search words "Seaside” and “Blowing”
  • the music display module 64 performs music display according to the scene music search words "Seaside” and "Blowing”.
  • the user thinks that the scene music he wants does not need to "blow”, and at this time, the scene music search word "hair dryer” can be deleted by sending a search word modification instruction to the search word modification unit 643.
  • the search term modification unit 643 receives the search term modification instruction, and modifies the scene music search term according to the search term modification command, such as deleting the scene music search term "hair dryer".
  • the second weight value obtaining unit 644 of the music display module 64 acquires the weight value of all the music searched by the music search module 63 for the music label corresponding to the modified scene music search word.
  • the second sorting display unit 645 of the last music display module 64 reorders all the searched music according to the weight value of the music label acquired by the second weight value obtaining unit 644 for the user to perform the playing operation.
  • the scene music searching device 60 of the preferred embodiment can also correct the weight value of the music tag in the music library in real time. Specifically:
  • the playing module 65 receives the music playing instruction of the client, and performs a playing operation on the displayed music according to the music playing instruction.
  • the music playing instruction may not be sent for music playing, so the weight value correcting module 66 may be based on the ratio of the number of times the music of the displayed music is played to the number of times the music is displayed, The music tag is corrected for the weight value in the displayed music.
  • the weight value correction module 66 increases the weight value of the music label in the displayed music; for example, the number of times the music is played and the number of times the music is displayed When the ratio is small, the weight value correction module 66 reduces the weight value of the music tag in the displayed music.
  • the number of music playback operations whose playback time is less than the set value is deleted from the number of music playbacks.
  • the weight value of the music label corresponding to the music in the music library is corrected in real time, so that the accuracy of the music label in the music library is higher, and the success rate of the music search is further improved.
  • the scene music searching device of the preferred embodiment deletes the invalid scene music search word on the basis of the first preferred embodiment, and improves the search hit rate of the scene music search word by setting the similar search word,
  • the setting of the weight value of the music label shortens the time of the music search and improves the success rate of the music search.
  • FIG. 10A and FIG. 10B are schematic diagrams showing the use of the scene music searching method and the scene music searching apparatus according to the present invention.
  • the scene music search device is set on the scene music search server. This embodiment includes the following steps:
  • the user enters the scene music search sentence "I am blowing at the beach” in the scene music search server.
  • the scene music search device obtains a valid scene music search word "seaside” and "hair dryer”, and according to the above scene music search words “seaside” and “hair dryer”, obtain music labels “seaside” and "walking", that is, Music suitable for listening to the beach or in the context of a walk.
  • the scene music search device obtains the corresponding music in the music library according to the music label "seaside” and “walking", and the weight value of the music label "seaside” and “walking” in all the music searched, that is, the music label The weight value of "Beach” in all music and the superposition of the weight value of the music tag "walking" in all music.
  • the scene music search device sorts and displays all the searched music according to the weight values of the music label "Seaside” and “walking" in the music, as shown in FIG. 10A. At this time, the user can click on any piece of music to play.
  • the scene music search device only counts the weight value of the music label "Seaside" in all the music.
  • the scene music search device reorders all the searched music according to the weight value of the music label "Beach" in the music, as shown in FIG. 10B. At this time, the user can click on any piece of music to play.
  • the scene music searching method and the scene music searching device of the embodiment of the present invention parse the scene music search sentence input by the user, obtain the corresponding music label, and then obtain the corresponding music; the music content displayed to the user is comprehensive and the music content can be The invention is timely updated; the existing scene music search method and the technical problem that the scene music search device has less music content and the music content update is slower are solved.
  • the embodiment of the invention further provides a storage medium.
  • the storage medium is configured to store program code for performing the following steps, comprising: acquiring a scene music search sentence; and splitting the scene music search sentence to obtain at least one scene music search word; searching according to the scene music a word, obtaining a music tag corresponding to the scene music search word; using the music tag, searching for a corresponding music in the music library; wherein the music library includes a music, a music tag, and a correspondence between the music and the music tag; and a search word for the scene music and The corresponding music is displayed.
  • the storage medium is configured to store program code for performing the steps of: splitting the scene music search statement into a plurality of basic words; and using the verbs and nouns in the basic words as scene music search words.
  • the storage medium is configured to store program code for performing the following steps, comprising: determining whether the scene music search term has a corresponding music tag; and acquiring the music tag if the scene music search term has a corresponding music tag; If the scene music search word does not have a corresponding music label, the similar search words of the scene music search word are obtained, and the corresponding music label is obtained according to the similar search word.
  • the storage medium is configured to store program code for performing the following steps, comprising: obtaining a weight value of the music tag in all the music that is searched, wherein the music library further includes a weight value of all music tags corresponding to the music. ; and sorting all the music that was searched by the weight value of the music tag.
  • the storage medium is configured to store program code for performing the following steps, including: receiving a search term modification instruction, and modifying the scene music search term according to the search term modification instruction; acquiring the modified scene music search term corresponding Music tag, the weight value in all the music that is searched; and the re-sorting of all the music that is searched by the weight value of the music tag in the music.
  • the storage medium is configured to store program code for performing the following steps, comprising: receiving a music play instruction, and performing a play operation on the displayed music according to the music play instruction; and displaying the music according to the number of times the music is displayed The ratio of the number of times the music is displayed, and the weight value of the music label in the displayed music is corrected.
  • ком ⁇ онент can be, but is not limited to being, a process running on a processor, a processor, an object, an executable application, a thread of execution, a program, and/or a computer.
  • a component can be, but is not limited to being, a process running on a processor, a processor, an object, an executable application, a thread of execution, a program, and/or a computer.
  • an application running on a controller and the controller can be a component.
  • One or more components can reside within a process and/or thread of execution, and a component can be located on a computer and/or distributed between two or more computers.
  • the claimed subject matter can be implemented as a method, apparatus, or article of manufacture that uses standard programming and/or engineering techniques to produce software, firmware, hardware, or any combination thereof, to control a computer to implement the disclosed subject matter.
  • article of manufacture as used herein is intended to encompass a computer program accessible from any computer-readable device, carrier, or media.
  • Example electronic device 1112 includes, but is not limited to, a personal computer, a server computer, a handheld or laptop device, a mobile device (such as a mobile phone, a personal digital assistant (PDA), a media player, etc.), a multi-processor system, a consumer Electronic devices, small computers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like.
  • Computer readable instructions may be distributed via computer readable media (discussed below).
  • Computer readable instructions may be implemented as program modules, such as functions, objects, application programming interfaces (APIs), data structures, etc. that perform particular tasks or implement particular abstract data types.
  • program modules such as functions, objects, application programming interfaces (APIs), data structures, etc. that perform particular tasks or implement particular abstract data types.
  • APIs application programming interfaces
  • data structures such as lists, etc. that perform particular tasks or implement particular abstract data types.
  • the functionality of the computer readable instructions can be combined or distributed at will in various environments.
  • FIG. 11 illustrates an example of an electronic device 1112 that includes one or more embodiments of a scene music search device of an embodiment of the present invention.
  • electronic device 1112 includes at least one processing unit 1116 and memory 1118.
  • memory 1118 can be volatile (such as RAM), non-volatile (such as ROM, flash memory, etc.) or some combination of the two. This configuration is illustrated in Figure 11 by dashed line 1114.
  • electronic device 1112 may include additional features and/or functionality.
  • device 1112 may also include additional storage (eg, removable and/or non-removable) including, but not limited to, magnetic storage, optical storage, and the like.
  • additional storage is illustrated by storage device 1120 in FIG.
  • computer readable instructions for implementing one or more embodiments provided herein may be in storage device 1120.
  • Storage device 1120 can also store other computer readable instructions for implementing an operating system, applications, and the like.
  • Computer readable instructions may be loaded into memory 1118 for execution by, for example, processing unit 1116.
  • Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions or other data.
  • Memory 1118 and storage device 1120 are examples of computer storage media.
  • Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage device, cassette, tape, disk storage or other magnetic storage device, or can be used to store desired information and can be electronic Any other medium accessed by device 1112. Any such computer storage media may be part of the electronic device 1112.
  • the electronic device 1112 may also include a communication connection 1126 that allows the electronic device 1112 to communicate with other devices.
  • Communication connection 1126 may include, but is not limited to, a modem, a network interface card (NIC), an integrated network interface, a radio frequency transmitter/receiver, an infrared port, a USB connection, or other interface for connecting electronic device 1112 to other electronic devices.
  • Communication connection 1126 can include a wired connection or a wireless connection.
  • Communication connection 1126 can transmit and/or receive communication media.
  • Computer readable medium can include a communication medium.
  • Communication media typically embodies computer readable instructions or other data in "modulated data signals" such as carrier waves or other transport mechanisms, and includes any information delivery media.
  • modulated data signal can include a signal that one or more of the signal characteristics are set or changed in such a manner as to encode the information into the signal.
  • the electronic device 1112 can include an input device 1124 such as a keyboard, mouse, pen, voice input device, touch input device, infrared camera, video input device, and/or any other input device.
  • Output device 1122 may also be included in device 1112, such as one or more displays, speakers, printers, and/or any other output device.
  • Input device 1124 and output device 1122 can be coupled to electronic device 1112 via a wired connection, a wireless connection, or any combination thereof.
  • an input device or output device from another electronic device can be used as the input device 1124 or output device 1122 of the electronic device 1112.
  • the components of electronic device 1112 can be connected by various interconnects, such as a bus.
  • interconnects may include Peripheral Component Interconnect (PCI) (such as Fast PCI), Universal Serial Bus (USB), Firewire (IEEE 1394), optical bus architecture, and the like.
  • PCI Peripheral Component Interconnect
  • USB Universal Serial Bus
  • Firewire IEEE 1394
  • optical bus architecture and the like.
  • the components of electronic device 1112 can be interconnected by a network.
  • memory 1118 can be comprised of multiple physical memory units that are interconnected by a network located in different physical locations.
  • a storage device for storing computer readable instructions can span Network distribution.
  • electronic device 1130 accessible via network 1128 can store computer readable instructions for implementing one or more embodiments of the present disclosure.
  • the electronic device 1112 can access the electronic device 1130 and download a portion or all of the computer readable instructions for execution.
  • electronic device 1112 can download a plurality of computer readable instructions as needed, or some of the instructions can be executed at electronic device 1112 and some of the instructions can be executed at electronic device 1130.
  • the one or more operations may constitute computer readable instructions stored on one or more computer readable media that, when executed by an electronic device, cause the computing device to perform the operations.
  • the order in which some or all of the operations are described should not be construed as implying that the operations must be sequential. Those skilled in the art will appreciate alternative rankings that have the benefit of this specification. Moreover, it should be understood that not all operations must be present in every embodiment provided herein.
  • the word "preferred” as used herein is intended to serve as an example, instance, or illustration. Any aspect or design described as “preferred” by the text is not necessarily to be construed as being more advantageous than other aspects or designs. Instead, the use of the word “preferred” is intended to present a concept in a specific manner.
  • the term “or” as used in this application is intended to mean an “or” or “an” That is, unless otherwise specified or clear from the context, "X employs A or B” means naturally including any one of the permutations. That is, if X uses A; X uses B; or X uses both A and B, then "X uses A or B" is satisfied in any of the foregoing examples.
  • Each functional unit in the embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
  • the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.

Abstract

一种场景音乐搜索方法及场景音乐搜索装置，该场景音乐搜索方法包括获取场景音乐搜索语句；并对场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词（S101）；根据场景音乐搜索词，获取与场景音乐搜索词对应的音乐标签（S102）；使用音乐标签，在音乐库中搜索对应的音乐（S103）；以及对场景音乐搜索词以及对应的音乐进行展示（S104）。一种场景音乐搜索装置，该场景音乐搜索方法及场景音乐搜索装置通过对用户输入的场景音乐搜索语句进行解析，获取相应的音乐标签，进而获取对应的音乐；展示给用户的音乐内容较为全面且音乐内容可得到及时更新。

Description

场景音乐搜索方法及场景音乐搜索装置
本申请要求于2015年12月03日提交中国专利局、申请号为201510884497.2、发明名称为“场景音乐搜索方法及场景音乐搜索装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及互联网领域，特别是涉及一种场景音乐搜索方法及场景音乐搜索装置。
背景技术
随着互联网技术的飞速发展，人们可以从互联网获取各种各样的内容，如视频以及音乐等。为了给用户提供满意的音乐内容，现有的音乐软件或音乐播放平台可按播放场景对音乐进行分类，如睡觉前听的歌曲、回家路上听的歌曲或散步时听的歌曲等。
但是上述的场景音乐均是通过人工进行运营的，即人工将场景和部分音乐进行关联，因此场景的种类是有限的。如用户想听在厨房做饭时的音乐，可能音乐软件或音乐播放平台上没有厨房的场景，导致用户无法方便的找到对应的场景音乐。同时现有的场景音乐对应的音乐内容由于是人工添加的，其中的音乐内容更新较慢且内容较为固定。
因此现有的音乐播放平台无法提供较为丰富以及较为准确场景音乐。
发明内容
本发明实施例提供一种音乐内容较为全面且更新较快的场景音乐搜索方法及场景音乐搜索装置；以解决现有的场景音乐搜索方法及场景音乐搜索装置的音乐内容较少且音乐内容更新较慢的技术问题。
本发明实施例提供一种场景音乐搜索方法，其包括：
获取场景音乐搜索语句；并对所述场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词；
根据所述场景音乐搜索词，获取与所述场景音乐搜索词对应的音乐标签；
使用所述音乐标签，在音乐库中搜索对应的音乐；其中所述音乐库包括所述音乐、所述音乐标签以及所述音乐和所述音乐标签的对应关系；以及
对所述场景音乐搜索词以及对应的所述音乐进行展示。
本发明实施例还提供一种场景音乐搜索装置，其包括：
语句拆分模块，用于获取场景音乐搜索语句；并对所述场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词；
音乐标签获取模块，用于根据所述场景音乐搜索词，获取与所述场景音乐搜索词对应的音乐标签；
音乐搜索模块，用于使用所述音乐标签，在音乐库中搜索对应的音乐；其中所述音乐库包括所述音乐、所述音乐标签以及所述音乐和所述音乐标签的对应关系；以及
音乐展示模块，用于对所述场景音乐搜索词以及对应的所述音乐进行展示。
本发明实施例还提供一种存储介质，所述存储介质被设置为存储用于执行以下步骤的程序代码，包括：
获取场景音乐搜索语句，并对所述场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词；
根据所述场景音乐搜索词，获取与所述场景音乐搜索词对应的音乐标签；
使用所述音乐标签，在音乐库中搜索对应的音乐，其中，所述音乐库包括所述音乐、所述音乐标签以及所述音乐和所述音乐标签的对应关系；以及
对所述场景音乐搜索词以及对应的所述音乐进行展示。
相较于现有技术的场景音乐搜索方法及场景音乐搜索装置，本发明实施例的场景音乐搜索方法及场景音乐搜索装置通过对用户输入的场景音乐搜索语句进行解析，获取相应的音乐标签，进而获取对应的音乐；展示给用户的音乐内 容较为全面；且可实时获取最新的音乐内容；解决了现有的场景音乐搜索方法及场景音乐搜索装置的音乐内容较少且音乐内容更新较慢的技术问题。
附图说明
图1为本发明的场景音乐搜索方法的第一优选实施例的流程图；
图2为本发明的场景音乐搜索方法的第二优选实施例的流程图之一；
图3为本发明的场景音乐搜索方法的第二优选实施例的流程图之二；
图4为本发明的场景音乐搜索方法的第二优选实施例的流程图之三；
图5为本发明的场景音乐搜索装置的第一优选实施例的结构示意图；
图6为本发明的场景音乐搜索装置的第二优选实施例的结构示意图；
图7为本发明的场景音乐搜索装置的第二优选实施例的语句拆分模块的结构示意图；
图8为本发明的场景音乐搜索装置的第二优选实施例的音乐标签获取模块的结构示意图；
图9为本发明的场景音乐搜索装置的第二优选实施例的音乐展示模块的结构示意图；
图10A至图10B为本发明的场景音乐搜索方法及场景音乐搜索装置的具体实施例的使用示意图；
图11为本发明的场景音乐搜索装置所在的电子设备的工作环境结构示意图。
具体实施方式
请参照图式，其中相同的组件符号代表相同的组件，本发明的原理是以实施在一适当的运算环境中来举例说明。以下的说明是基于所例示的本发明具体实施例，其不应被视为限制本发明未在此详述的其它具体实施例。
在以下的说明中，本发明的具体实施例将参考由一部或多部计算机所执行 之作业的步骤及符号来说明，除非另有述明。因此，其将可了解到这些步骤及操作，其中有数次提到为由计算机执行，包括了由代表了以一结构化型式中的数据之电子信号的计算机处理单元所操纵。此操纵转换该数据或将其维持在该计算机之内存系统中的位置处，其可重新配置或另外以本领域技术人员所熟知的方式来改变该计算机之运作。该数据所维持的数据结构为该内存之实体位置，其具有由该数据格式所定义的特定特性。但是，本发明原理以上述文字来说明，其并不代表为一种限制，本领域技术人员将可了解到以下所述的多种步骤及操作亦可实施在硬件当中。
本发明实施例的场景音乐搜索装置可使用各种电子设备进行实施，该电子设备包括但不限于个人计算机、服务器计算机、手持式或膝上型设备、移动设备(比如移动电话、个人数字助理(PDA)、媒体播放器等等)、多处理器系统、消费型电子设备、小型计算机、大型计算机、包括上述任意系统或设备的分布式计算环境，等等。但该电子设备优选为音乐搜索平台或音乐搜索服务器，以便有效的提高音乐搜索平台或音乐搜索服务器的音乐搜索成功率以及音乐内容更新速度。
请参照图1，图1为本发明的场景音乐搜索方法的第一优选实施例的流程图。本优选实施例的场景音乐搜索方法可使用上述的电子设备进行实施，该场景音乐搜索方法包括：
步骤S101，获取场景音乐搜索语句；并对场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词；
步骤S102，根据场景音乐搜索词，获取与场景音乐搜索词对应的音乐标签；
步骤S103，使用音乐标签，在音乐库中搜索对应的音乐；
步骤S104，对场景音乐搜索词以及对应的音乐进行展示。
下面详细说明本优选实施例的场景音乐搜索方法的各步骤的具体流程。
在步骤S101中，场景音乐搜索装置获取场景音乐搜索语句，这里的场景音乐搜索语句可为用户手动输入的语句或语音输入的语句，如用户输入“我在海 边吹风”的场景音乐搜索语句，则拆分后获取的场景音乐搜索词为“我”、“在”、“海边”、“吹风”。随后转到步骤S102。
在步骤S102中，场景音乐搜索装置根据步骤S101获取的场景音乐搜索词，获取与场景音乐搜索词对应的音乐标签。这里并非直接使用场景音乐搜索词作为音乐标签，而是将场景音乐搜索词作为关键词，在音乐库中检索相同或相近的音乐标签。这样不管音乐库的音乐标签中是否具有该场景音乐搜索词，均可获取一与该场景音乐搜索词强相关的音乐标签，以保证搜索的有效性。随后转到步骤S103。
在步骤S103中，场景音乐搜索装置使用步骤S102获取的音乐标签，在音乐库中搜索对应的音乐。这里的音乐库包括音乐、音乐标签以及音乐和音乐标签对应关系。其中音乐库中的音乐标签可为社交媒体的用户生成标签、音乐发行商或专业人士审核的权威标签、或通过机器学习方法生成的补充标签等。这里的音乐库为实时更新的在线音乐数据库，可直接调用本地音乐网站的在线音乐数据库或其他网站的在线音乐数据库。随后转到步骤S104。
在步骤S104中，场景音乐搜索装置对步骤S101获取的场景音乐搜索词以及步骤S103获取的对应的音乐进行展示，以供用户进行播放操作。
这样即完成了本优选实施例的场景音乐搜索方法的场景音乐搜索过程。
本优选实施例的场景音乐搜索方法通过对用户输入的场景音乐搜索语句进行解析，获取相应的音乐标签，进而获取对应的音乐；由于使用场景音乐搜索词作为关键词进行搜索，提高了搜索的成功率；同时通过实时更新的音乐库返回音乐，提升了搜索音乐内容的更新速度以及搜索音乐内容的全面性，因此展示给用户的音乐内容较为全面。
请参照图2，图2为本发明的场景音乐搜索方法的第二优选实施例的流程图。本优选实施例的场景音乐搜索方法可使用上述的电子设备进行实施，该场景音乐搜索方法包括：
步骤S201，将场景音乐搜索语句拆分为多个基本词语；
步骤S202，将基本词语中的动词以及名词作为场景音乐搜索词；
步骤S203，判断场景音乐搜索词是否具有对应的音乐标签；如具有对应的音乐标签，则转到步骤S204；如没有对应的音乐标签，则转到步骤S205；
步骤S204，获取音乐标签；
步骤S205，获取场景音乐搜索词的相似搜索词，并根据相似搜索词获取相应的音乐标签；
步骤S206，使用音乐标签，在音乐库中搜索对应的音乐；
步骤S207，获取音乐标签在搜索到的所有音乐中的权重值；
步骤S208，按音乐标签的权重值，对搜索到的所有音乐进行排序展示。
下面详细说明本优选实施例的场景音乐搜索方法的各步骤的具体流程。
在步骤S201中，场景音乐搜索装置获取场景音乐搜索语句，这里的场景音乐搜索语句可为用户手动输入的语句或语音输入的语句，如用户输入“我在海边吹风”的场景音乐搜索语句，则拆分后获取的基本词语为“我”、“在”、“海边”、“吹风”。随后转到步骤S202。
在步骤S202中，由于场景音乐搜索词一般为具有意义的名称或动词，其他人称代词、介词或连词作为场景音乐搜索词是不具备意义的，因此这里场景音乐搜索装置将基本词语中的动词以及名词作为场景音乐搜索词。如步骤S201中获取的基本词语中的“海边”以及“吹风”可设定为场景音乐搜索词。随后转到步骤S203。
在步骤S203中，场景音乐搜索装置根据步骤S202获取的场景音乐搜索词，获取与场景音乐搜索词对应的音乐标签。在本步骤中先判断场景音乐搜索词是否具有对应的音乐标签，如具有相应的音乐标签，则转到步骤S204；如不具有相应的音乐标签，则转到步骤S205。
在步骤S204中，若步骤S202获取的场景音乐搜索词具有相应的音乐标签，例如步骤S202中获取的场景音乐搜索词“海边”本身即可作为音乐标签，则场 景音乐搜索装置直接获取该音乐标签。随后转到步骤S205。
在步骤S205中，若步骤S202获取的场景音乐搜索词不具有相应的音乐标签，例如步骤S202中获取的场景音乐搜索词“吹风”本身不可作为音乐标签，则场景音乐搜索装置获取该场景音乐搜索词的相似搜索词。
这里要保证获取的相似搜索词本身可以作为音乐标签，因此可根据词向量相似性计算场景音乐搜索词与每个音乐标签的相似度，选择相似度最高的音乐标签作为该场景音乐搜索词对应的音乐标签。
同时相似搜索词还可使用不同数据库对场景音乐搜索词进行解析获取，如在词语解释的网站获取场景音乐搜索词的解释说明等，如“吹风”在百度网站具有“吹风是一种心情，比如：我们出去吹吹风，散散步”的解释，因此也可将“吹风”的相似搜索词设为“散步”或“漫步”等。随后转到步骤S206。
在步骤S206中，场景音乐搜索装置使用步骤S204和步骤S205获取的音乐标签，在音乐库中搜索对应的音乐。这里的音乐库包括音乐、音乐标签、音乐和音乐标签对应关系以及音乐对应的所有音乐标签的权重值。其中音乐库中的音乐标签可为社交媒体的用户生成标签、音乐发行商或专业人士审核的权威标签、或通过机器学习方法生成的补充标签等。这里的音乐库为实时更新的在线音乐数据库，可直接调用本地音乐网站的在线音乐数据库或其他网站的在线音乐数据库。
需要说明的是，为了避免遗漏相关音乐，如果在步骤S204和步骤S205获取多个音乐标签，则在音乐库中搜索满足至少一个音乐标签的所有音乐。随后转到步骤S207。
在步骤S207中，由于向用户展示音乐时，应当优先展示用户最有可能需求的音乐。因此在本步骤中，场景音乐搜索装置获取场景音乐搜索词对应的音乐标签在步骤S206中搜索到的所有音乐中的权重值。即获取与场景音乐搜索词相关的每个音乐，与该场景音乐搜索词的相关性的大小。
如有多个场景音乐搜索词，则将多个场景音乐搜索词合并为一场景音乐搜 索词组。然后通过叠加的方式，获取场景音乐搜索词组在步骤S206中搜索到的所有音乐中的权重值。即场景音乐搜索词组在某个音乐中的权重值，为场景音乐搜索词组中的每个场景音乐搜索词在该音乐中的权重值的叠加。如场景音乐搜索词组包括场景音乐搜索词A和场景音乐搜索词B，场景音乐搜索词A在音乐a、音乐b以及音乐c中的权重值分别为20、30以及50；场景音乐搜索词B在音乐a、音乐b以及音乐c中的权重分别为40、10以及0。这样该场景音乐搜索词组在音乐a、音乐b以及音乐c的权重为60、40以及50。随后转到步骤S208。
在步骤S208中，场景音乐搜索装置在展示场景音乐搜索词的同时，场景音乐搜索装置根据步骤S207获取的音乐标签在音乐中的权重值，对搜索的所有音乐进行排序展示，以供用户进行播放操作。同时这里还可使用音乐的当前热度对音乐的排序进行修正，如将相对某个场景音乐搜索词的权重值差异小于设定值的多个音乐，按该音乐的当前热度进行排序。由于这里按与场景音乐搜索词的相关性以及热度对音乐排序，因此用户可以较容易的获取到想听的音乐。
这样即完成了本优选实施例的场景音乐搜索方法的场景音乐搜索过程。
优选的，请参照图3，图3为本发明的场景音乐搜索方法的第二优选实施例的流程图之二。本优选实施例的场景音乐搜索方法在步骤S208之后还包括：
步骤S301，场景音乐搜索装置接收搜索词修改指令，并根据搜索词修改指令对场景音乐搜索词进行修改。
由于不同的用户可能对某个场景音乐的理解不同，因此如果用户认为场景音乐搜索词获取的不准确，则可以通过客户端向场景音乐搜索装置发送搜索词修改指令。如步骤S202中获取到场景音乐搜索词“海边”以及“吹风”，并且最后步骤S208均按照场景音乐搜索词“海边”以及“吹风”进行音乐展示。而用户认为他想要的场景音乐不需要“吹风”，这时可以通过发送搜索词修改指令将场景音乐搜索词“吹风”删除。这样场景音乐搜索装置接收搜索词修改指令，并根据搜索词修改指令对场景音乐搜索词进行修改，如将场景音乐搜索词 “吹风”删除。
步骤S302，场景音乐搜索装置获取修改后的场景音乐搜索词对应的音乐标签，在步骤S206中搜索到的所有音乐中的权重值。
步骤S303，场景音乐搜索装置根据步骤S302获取的音乐标签在音乐中的权重值，对搜索的所有音乐进行重新排序展示，以供用户进行播放操作。
这样增强了本优选实施例的场景音乐搜素方法的音乐搜索的灵活性，进一步提高了音乐搜索的成功率。
优选的，请参照图4，图4为本发明的场景音乐搜索方法的第二优选实施例的流程图之三。本优选实施例的场景音乐搜索方法在步骤S208之后还包括：
步骤S401，接收客户端的音乐播放指令，并根据音乐播放指令，对展示的音乐进行播放操作。
步骤S402，如用户对场景音乐搜索装置展示的音乐不满意，则可能不会发送音乐播放指令进行音乐播放，因此场景音乐搜索装置可根据展示音乐的音乐播放的次数与音乐展示的次数的比值，对音乐标签在展示音乐中的权重值进行修正。
如展示音乐的音乐播放的次数与音乐展示的次数的比值较大，则加大音乐标签在展示音乐中的权重值；如展示音乐的音乐播放的次数与音乐展示的次数的比值较小，则减小音乐标签在展示音乐中的权重值。当然这里为了避免将用户的试听操作误认为音乐播放操作，可将播放时间小于设定值的音乐播放操作的次数从音乐播放次数中删除。
通过统计用户的播放操作，对音乐库中的音乐对应的音乐标签的权重值进行实时修正，使得音乐库中的音乐标签的准确度更高，进一步提高了音乐搜索的成功率。
本优选实施例的场景音乐搜索方法在第一优选实施例的基础上，对无效的场景音乐搜索词进行了删除，以及通过相似搜索词的设定提高了场景音乐搜索词的搜索命中率，同时通过音乐标签的权重值的设定缩短了音乐搜索的时间， 提高了音乐搜索的成功率。
本发明实施例还提供一种场景音乐搜索装置，请参照图5，图5为本发明的场景音乐搜索装置的第一优选实施例的结构示意图。本优选实施例的场景音乐搜索装置50使用上述的场景音乐搜索方法的第一优选实施例进行实施。
该场景音乐搜索装置50包括语句拆分模块51、音乐标签获取模块52、音乐搜索模块53以及音乐展示模块54。语句拆分模块51用于获取场景音乐搜索语句；并对场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词。音乐标签获取模块52用于根据场景音乐搜索词，获取与场景音乐搜索词对应的音乐标签。音乐搜索模块53用于使用音乐标签，在音乐库中搜索对应的音乐。音乐展示模块54用于对场景音乐搜索词以及对应的音乐进行展示。
本优选实施例的场景音乐搜索装置50使用时，首先语句拆分模块51获取场景音乐搜索语句，这里的场景音乐搜索语句可为用户手动输入的语句或语音输入的语句，如用户输入“我在海边吹风”的场景音乐搜索语句，则拆分后获取的场景音乐搜索词为“我”、“在”、“海边”、“吹风”。
随后音乐标签获取模块52根据语句拆分模块51获取的场景音乐搜索词，获取与场景音乐搜索词对应的音乐标签。这里并非直接使用场景音乐搜索词作为音乐标签，而是将场景音乐搜索词作为关键词，在音乐库中检索相同或相近的音乐标签。这样不管音乐库的音乐标签中是否具有该场景音乐搜索词，均可获取一与该场景音乐搜索词强相关的音乐标签，以保证搜索的有效性。
然后音乐搜索模块53使用音乐标签获取模块52获取的音乐标签，在音乐库中搜索对应的音乐。这里的音乐库包括音乐、音乐标签以及音乐和音乐标签对应关系。其中音乐库中的音乐标签可为社交媒体的用户生成标签、音乐发行商或专业人士审核的权威标签、或通过机器学习方法生成的补充标签等。这里的音乐库为实时更新的在线音乐数据库，可直接调用本地音乐网站的在线音乐数据库或其他网站的在线音乐数据库。
最后音乐展示模块54对语句拆分模块51获取的场景音乐搜索词以及音乐搜索模块53获取的对应的音乐进行展示，以供用户进行播放操作。
这样即完成了本优选实施例的场景音乐搜索装置50的场景音乐搜索过程。
本优选实施例的场景音乐搜索装置通过对用户输入的场景音乐搜索语句进行解析，获取相应的音乐标签，进而获取对应的音乐；由于使用场景音乐搜索词作为关键词进行搜索，提高了搜索的成功率；同时通过实时更新的音乐库返回音乐，提升了搜索音乐内容的更新速度以及搜索音乐内容的全面性，因此展示给用户的音乐内容较为全面。
请参照图6，图6为本发明的场景音乐搜索装置的第二优选实施例的结构示意图。本优选实施例的场景音乐搜索装置60使用上述的场景音乐搜索方法的第二优选实施例进行实施。
该场景音乐搜索装置60包括语句拆分模块61、音乐标签获取模块62、音乐搜索模块63、音乐展示模块64、播放模块65以及权重值修正模块66。语句拆分模块61用于获取场景音乐搜索语句；并对场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词。音乐标签获取模块62用于根据场景音乐搜索词，获取与场景音乐搜索词对应的音乐标签。音乐搜索模块3用于使用音乐标签，在音乐库中搜索对应的音乐。音乐展示模块64用于对场景音乐搜索词以及对应的音乐进行展示。播放模块65用于接收音乐播放指令，并根据音乐播放指令，对展示的音乐进行播放操作。权重值修正模块66用于根据展示音乐的音乐播放的次数与音乐展示的次数的比值，对音乐标签在展示音乐中的权重值进行修正。
请参照图7，图7为本发明的场景音乐搜索装置的第二优选实施例的语句拆分模块的结构示意图。该语句拆分模块61包括拆分单元611以及搜索词设定单元612。拆分单元611用于将场景音乐搜索语句拆分为多个基本词语；搜索词设定单元612用于将基本词语中的动词以及名词作为场景音乐搜索词。
请参照图8，图8为本发明的场景音乐搜索装置的第二优选实施例的音乐标签获取模块的结构示意图。该音乐标签获取模块62包括判断单元621、第一音乐标签获取单元622以及第二音乐标签获取单元623。判断单元621用于判断场景音乐搜索词是否具有对应的音乐标签；第一音乐标签获取单元622用于如场景音乐搜索词具有对应的音乐标签，则获取该音乐标签；第二音乐标签获取单元623用于如场景音乐搜索词不具有对应的音乐标签，则获取场景音乐搜索词的相似搜索词，并根据相似搜索词获取相应的音乐标签。
请参照图9，图9为本发明的场景音乐搜索装置的第二优选实施例的音乐展示模块的结构示意图。该音乐展示模块64包括第一权重值获取单元641、第一排序展示单元642、搜索词修改单元643、第二权重值获取单元644以及第二排序展示单元645。第一权重值获取单元641用于获取场景音乐搜索词对应的音乐标签，在搜索到的所有音乐中的权重值。第一排序展示单元642用于按音乐标签在音乐中的权重值，对搜索到的所有音乐进行排序展示。搜索词修改单元643用于接收搜索词修改指令，并根据搜索词修改指令对场景音乐搜索词进行修改。第二权重值获取单元644用于获取音乐标签在搜索到的所有音乐中的权重值。第二排序展示单元645用于按音乐标签的权重值，对搜索到的所有音乐进行重新排序展示。
本优选实施例的场景音乐搜索装置60使用时，首先语句拆分模块61的拆分单元611获取场景音乐搜索语句，这里的场景音乐搜索语句可为用户手动输入的语句或语音输入的语句，如用户输入“我在海边吹风”的场景音乐搜索语句，则拆分后获取的基本词语为“我”、“在”、“海边”、“吹风”。
由于场景音乐搜索词一般为具有意义的名称或动词，其他人称代词、介词或连词作为场景音乐搜索词是不具备意义的，因此随后语句拆分模块61的搜索词设定单元612将基本词语中的动词以及名词作为场景音乐搜索词。如获取的基本词语中的“海边”以及“吹风”可设定为场景音乐搜索词。
然后音乐标签获取模块62根据语句拆分模块61获取的场景音乐搜索词， 获取与场景音乐搜索词对应的音乐标签。音乐标签获取模块62的判断单元621先判断场景音乐搜索词是否具有对应的音乐标签。
若获取的场景音乐搜索词具有相应的音乐标签，例如获取的场景音乐搜索词“海边”本身即可作为音乐标签，则音乐标签获取模块62的第一音乐标签获取单元622直接获取该音乐标签。
若获取的场景音乐搜索词不具有相应的音乐标签，例如获取的场景音乐搜索词“吹风”本身不可作为音乐标签，则音乐标签获取模块62的第二音乐标签获取单元623获取该场景音乐搜索词的相似搜索词，这里要保证获取的相似搜索词本身可以作为音乐标签，因此可根据词向量相似性计算场景音乐搜索词与每个音乐标签的相似度，选择相似度最高的音乐标签作为该场景音乐搜索词对应的音乐标签。
同时相似搜索词还可使用不同数据库对场景音乐搜索词进行解析获取，如在词语解释的网站获取场景音乐搜索词的解释说明等，如“吹风”在百度网站具有“吹风是一种心情，比如：我们出去吹吹风，散散步”的解释，因此也可将“吹风”的相似搜索词设为“散步”或“漫步”等。
随后音乐搜索模块63使用音乐标签获取模块62获取的音乐标签，在音乐库中搜索对应的音乐。这里的音乐库包括音乐、音乐标签、音乐和音乐标签对应关系以及音乐对应的所有音乐标签的权重值。其中音乐库中的音乐标签可为社交媒体的用户生成标签、音乐发行商或专业人士审核的权威标签、或通过机器学习方法生成的补充标签等。这里的音乐库为实时更新的在线音乐数据库，可直接调用本地音乐网站的在线音乐数据库或其他网站的在线音乐数据库。
需要说明的是，为了避免遗漏相关音乐，如果音乐标签获取模块62获取多个音乐标签，则音乐搜索模块63在音乐库中搜索满足至少一个音乐标签的所有音乐。
由于向用户展示音乐时，应当优先展示用户最有可能需求的音乐。因此音乐展示模块64的第一权重值获取单元641获取场景音乐搜索词对应的音乐标 签，在音乐搜索模块搜索到的所有音乐中的权重值。即获取与场景音乐搜索词相关的每个音乐，与该场景音乐搜索词的相关性的大小。
如有多个场景音乐搜索词，则第一权重值获取单元641将多个场景音乐搜索词合并为一场景音乐搜索词组。然后通过叠加的方式，获取场景音乐搜索词组在音乐搜索模块63搜索到的所有音乐中的权重值。即场景音乐搜索词组在某个音乐中的权重值，为场景音乐搜索词组中的每个场景音乐搜索词在该音乐中的权重值的叠加。如场景音乐搜索词组包括场景音乐搜索词A和场景音乐搜索词B，场景音乐搜索词A在音乐a、音乐b以及音乐c中的权重值分别为20、30以及50；场景音乐搜索词B在音乐a、音乐b以及音乐c中的权重分别为40、10以及0。这样该场景音乐搜索词组在音乐a、音乐b以及音乐c的权重为60、40以及50。
最后音乐展示模块64的第一排序展示单元642在展示场景音乐搜索词的同时，根据第一权重值获取单元641获取的音乐标签在音乐中的权重值，对搜索的所有音乐进行排序展示，以供用户进行播放操作。同时这里还可使用音乐的当前热度对音乐的排序进行修正，如将相对某个场景音乐搜索词的权重值差异小于设定值的多个音乐，按该音乐的当前热度进行排序。由于这里按与场景音乐搜索词的相关性以及热度对音乐排序，因此用户可以较容易的获取到想听的音乐。由于这里按与场景音乐搜索词的相关性对音乐排序，因此用户可以较容易的获取到想听的音乐。
这样即完成了本优选实施例的场景音乐搜索装置60的场景音乐搜索过程。
优选的，本优选实施例的场景音乐搜索装置60还可对展示场景音乐搜索词进行实时修正。具体为：
首先音乐展示模块64的搜索词修改单元643接收搜索词修改指令，并根据搜索词修改指令对场景音乐搜索词进行修改。
由于不同的用户可能对某个场景音乐的理解不同，因此如果用户认为场景 音乐搜索词获取的不准确，则可以通过客户端向场景音乐搜索装置60发送搜索词修改指令。如语句拆分模块61获取到场景音乐搜索词“海边”以及“吹风”，并且最后音乐展示模块64均按照场景音乐搜索词“海边”以及“吹风”进行音乐展示。而用户认为他想要的场景音乐不需要“吹风”，这时可以通过向搜索词修改单元643发送搜索词修改指令将场景音乐搜索词“吹风”删除。这样搜索词修改单元643接收搜索词修改指令，并根据搜索词修改指令对场景音乐搜索词进行修改，如将场景音乐搜索词“吹风”删除。
随后音乐展示模块64的第二权重值获取单元644获取修改后的场景音乐搜索词对应的音乐标签，在音乐搜索模块63搜索到的所有音乐中的权重值。
最后音乐展示模块64的第二排序展示单元645根据第二权重值获取单元644获取的音乐标签在音乐中的权重值，对搜索的所有音乐进行重新排序展示，以供用户进行播放操作。
这样增强了本优选实施例的场景音乐搜索装置60的音乐搜索的灵活性，进一步提高了音乐搜索的成功率。
优选的，本优选实施例的场景音乐搜索装置60还可对音乐库中的音乐标签的权重值进行实时修正。具体为：
播放模块65接收客户端的音乐播放指令，并根据音乐播放指令，对展示的音乐进行播放操作。
如用户对场景音乐搜索装置60展示的音乐不满意，则可能不会发送音乐播放指令进行音乐播放，因此权重值修正模块66可根据展示音乐的音乐播放的次数与音乐展示的次数的比值，对音乐标签在展示音乐中的权重值进行修正。
如展示音乐的音乐播放的次数与音乐展示的次数的比值较大，则权重值修正模块66加大音乐标签在展示音乐中的权重值；如展示音乐的音乐播放的次数与音乐展示的次数的比值较小，则权重值修正模块66减小音乐标签在展示音乐中的权重值。当然这里为了避免将用户的试听操作误认为音乐播放操作，可将 播放时间小于设定值的音乐播放操作的次数从音乐播放次数中删除。
通过统计用户的播放操作，对音乐库中的音乐对应的音乐标签的权重值进行实时修正，使得音乐库中的音乐标签的准确度更高，进一步提高了音乐搜索的成功率。
本优选实施例的场景音乐搜索装置在第一优选实施例的基础上，对无效的场景音乐搜索词进行了删除，以及通过相似搜索词的设定提高了场景音乐搜索词的搜索命中率，同时通过音乐标签的权重值的设定缩短了音乐搜索的时间，提高了音乐搜索的成功率。
下面通过一具体实施例说明本发明的场景音乐搜索方法及场景音乐搜索装置的具体工作原理。请参照图10A和图10B，图10A至图10B为本发明的场景音乐搜索方法及场景音乐搜索装置的具体实施例的使用示意图。该场景音乐搜索装置设置在场景音乐搜索服务器上。该具体实施例包括以下步骤：
一、用户在场景音乐搜索服务器输入场景音乐搜索语句“我在海边吹风”。
二、场景音乐搜索装置获取到有效的场景音乐搜索词“海边”以及“吹风”，并根据上述场景音乐搜索词“海边”以及“吹风”，获取音乐标签“海边”以及“散步”，即在海边或在散步的情境下适合听的音乐。
三、场景音乐搜索装置根据音乐标签“海边”以及“散步”，在音乐库中获取对应的音乐，以及音乐标签“海边”以及“散步”在搜索到的所有音乐中的权重值，即音乐标签“海边”在所有音乐中的权重值以及音乐标签“散步”在所有音乐中的权重值的叠加。
四、场景音乐搜索装置按音乐标签“海边”以及“散步”在音乐中的权重值，对搜索到的所有音乐进行排序展示，如图10A所示。这时用户可以点击任何一首音乐进行播放。
五、如用户认为获取的场景音乐搜索词不准确，如用户不希望有场景音乐搜索词“吹风”则用户可向场景音乐搜索服务器发送搜索词修改指令，即点击 吹风的标签，使之处于未选定状态。这样场景音乐搜索装置只统计音乐标签“海边”在所有音乐中的权重值。
六、场景音乐搜索装置按音乐标签“海边”在音乐中的权重值，对搜索到的所有音乐进行重新排序展示，如图10B所示。这时用户可以点击任何一首音乐进行播放。
这样即完成了具体实施例的场景音乐搜索装置的场景音乐搜索以及场景音乐播放的过程。
本发明实施例的场景音乐搜索方法及场景音乐搜索装置通过对用户输入的场景音乐搜索语句进行解析，获取相应的音乐标签，进而获取对应的音乐；展示给用户的音乐内容较为全面且音乐内容可得到及时更新；解决了现有的场景音乐搜索方法及场景音乐搜索装置的音乐内容较少且音乐内容更新较慢的技术问题。
本发明实施例还提供了一种存储介质。
可选地，存储介质被设置为存储用于执行以下步骤的程序代码，包括：获取场景音乐搜索语句；并对场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词；根据场景音乐搜索词，获取与场景音乐搜索词对应的音乐标签；使用音乐标签，在音乐库中搜索对应的音乐；其中音乐库包括音乐、音乐标签以及音乐和音乐标签的对应关系；以及对场景音乐搜索词以及对应的音乐进行展示。
可选地，存储介质被设置为存储用于执行以下步骤的程序代码，包括：将场景音乐搜索语句拆分为多个基本词语；以及将基本词语中的动词以及名词作为场景音乐搜索词。
可选地，存储介质被设置为存储用于执行以下步骤的程序代码，包括：判断场景音乐搜索词是否具有对应的音乐标签；如场景音乐搜索词具有对应的音乐标签，则获取音乐标签；以及如场景音乐搜索词不具有对应的音乐标签，则获取场景音乐搜索词的相似搜索词，并根据相似搜索词获取相应的音乐标签。
可选地，存储介质被设置为存储用于执行以下步骤的程序代码，包括：获取音乐标签在搜索到的所有音乐中的权重值，其中，音乐库还包括音乐对应的所有音乐标签的权重值；以及按音乐标签的权重值，对搜索到的所有音乐进行排序展示。
可选地，存储介质被设置为存储用于执行以下步骤的程序代码，包括：接收搜索词修改指令，并根据搜索词修改指令对场景音乐搜索词进行修改；获取修改后的场景音乐搜索词对应的音乐标签，在搜索到的所有音乐中的权重值；以及按音乐标签在音乐中的权重值，对搜索到的所有音乐进行重新排序展示。
可选地，存储介质被设置为存储用于执行以下步骤的程序代码，包括：接收音乐播放指令，并根据音乐播放指令，对展示的音乐进行播放操作；以及根据展示音乐的音乐播放的次数与音乐展示的次数的比值，对音乐标签在展示音乐中的权重值进行修正。
如本申请所使用的术语“组件”、“模块”、“系统”、“接口”、“进程”等等一般地旨在指计算机相关实体：硬件、硬件和软件的组合、软件或执行中的软件。例如，组件可以是但不限于是运行在处理器上的进程、处理器、对象、可执行应用、执行的线程、程序和/或计算机。通过图示，运行在控制器上的应用和该控制器二者都可以是组件。一个或多个组件可以有在于执行的进程和/或线程内，并且组件可以位于一个计算机上和/或分布在两个或更多计算机之间。
而且，要求保护的主题可以被实现为使用标准编程和/或工程技术产生软件、固件、硬件或其任意组合以控制计算机实现所公开的主题的方法、装置或制造品。本文所使用的术语“制造品”旨在包含可从任意计算机可读设备、载体或介质访问的计算机程序。当然，本领域技术人员将认识到可以对该配置进行许多修改，而不脱离要求保护的主题的范围或精神。
图11和随后的讨论提供了对实现本发明实施例所述的场景音乐搜索装置所在的电子设备的工作环境的简短、概括的描述。图11的工作环境仅仅是适当 的工作环境的一个实例并且不旨在建议关于工作环境的用途或功能的范围的任何限制。实例电子设备1112包括但不限于个人计算机、服务器计算机、手持式或膝上型设备、移动设备(比如移动电话、个人数字助理(PDA)、媒体播放器等等)、多处理器系统、消费型电子设备、小型计算机、大型计算机、包括上述任意系统或设备的分布式计算环境，等等。
尽管没有要求，但是在“计算机可读指令”被一个或多个电子设备执行的通用背景下描述实施例。计算机可读指令可以经由计算机可读介质来分布(下文讨论)。计算机可读指令可以实现为程序模块，比如执行特定任务或实现特定抽象数据类型的功能、对象、应用编程接口(API)、数据结构等等。典型地，该计算机可读指令的功能可以在各种环境中随意组合或分布。
图11图示了包括本发明实施例的场景音乐搜索装置的一个或多个实施例的电子设备1112的实例。在一种配置中，电子设备1112包括至少一个处理单元1116和存储器1118。根据电子设备的确切配置和类型，存储器1118可以是易失性的(比如RAM)、非易失性的(比如ROM、闪存等)或二者的某种组合。该配置在图11中由虚线1114图示。
在其他实施例中，电子设备1112可以包括附加特征和/或功能。例如，设备1112还可以包括附加的存储装置(例如可移除和/或不可移除的)，其包括但不限于磁存储装置、光存储装置等等。这种附加存储装置在图11中由存储装置1120图示。在一个实施例中，用于实现本文所提供的一个或多个实施例的计算机可读指令可以在存储装置1120中。存储装置1120还可以存储用于实现操作系统、应用程序等的其他计算机可读指令。计算机可读指令可以载入存储器1118中由例如处理单元1116执行。
本文所使用的术语“计算机可读介质”包括计算机存储介质。计算机存储介质包括以用于存储诸如计算机可读指令或其他数据之类的信息的任何方法或技术实现的易失性和非易失性、可移除和不可移除介质。存储器1118和存储装置1120是计算机存储介质的实例。计算机存储介质包括但不限于RAM、ROM、 EEPROM、闪存或其他存储器技术、CD-ROM、数字通用盘(DVD)或其他光存储装置、盒式磁带、磁带、磁盘存储装置或其他磁存储设备、或可以用于存储期望信息并可以被电子设备1112访问的任何其他介质。任意这样的计算机存储介质可以是电子设备1112的一部分。
电子设备1112还可以包括允许电子设备1112与其他设备通信的通信连接1126。通信连接1126可以包括但不限于调制解调器、网络接口卡(NIC)、集成网络接口、射频发射器/接收器、红外端口、USB连接或用于将电子设备1112连接到其他电子设备的其他接口。通信连接1126可以包括有线连接或无线连接。通信连接1126可以发射和/或接收通信媒体。
术语“计算机可读介质”可以包括通信介质。通信介质典型地包含计算机可读指令或诸如载波或其他传输机构之类的“己调制数据信号”中的其他数据，并且包括任何信息递送介质。术语“己调制数据信号”可以包括这样的信号：该信号特性中的一个或多个按照将信息编码到信号中的方式来设置或改变。
电子设备1112可以包括输入设备1124，比如键盘、鼠标、笔、语音输入设备、触摸输入设备、红外相机、视频输入设备和/或任何其他输入设备。设备1112中也可以包括输出设备1122，比如一个或多个显示器、扬声器、打印机和/或任意其他输出设备。输入设备1124和输出设备1122可以经由有线连接、无线连接或其任意组合连接到电子设备1112。在一个实施例中，来自另一个电子设备的输入设备或输出设备可以被用作电子设备1112的输入设备1124或输出设备1122。
电子设备1112的组件可以通过各种互连(比如总线)连接。这样的互连可以包括外围组件互连(PCI)(比如快速PCI)、通用串行总线(USB)、火线(IEEE 1394)、光学总线结构等等。在另一个实施例中，电子设备1112的组件可以通过网络互连。例如，存储器1118可以由位于不同物理位置中的、通过网络互连的多个物理存储器单元构成。
本领域技术人员将认识到，用于存储计算机可读指令的存储设备可以跨越 网络分布。例如，可经由网络1128访问的电子设备1130可以存储用于实现本发明所提供的一个或多个实施例的计算机可读指令。电子设备1112可以访问电子设备1130并且下载计算机可读指令的一部分或所有以供执行。可替代地，电子设备1112可以按需要下载多条计算机可读指令，或者一些指令可以在电子设备1112处执行并且一些指令可以在电子设备1130处执行。
本文提供了实施例的各种操作。在一个实施例中，所述的一个或多个操作可以构成一个或多个计算机可读介质上存储的计算机可读指令，其在被电子设备执行时将使得计算设备执行所述操作。描述一些或所有操作的顺序不应当被解释为暗示这些操作必需是顺序相关的。本领域技术人员将理解具有本说明书的益处的可替代的排序。而且，应当理解，不是所有操作必需在本文所提供的每个实施例中存在。
而且，本文所使用的词语“优选的”意指用作实例、示例或例证。奉文描述为“优选的”任意方面或设计不必被解释为比其他方面或设计更有利。相反，词语“优选的”的使用旨在以具体方式提出概念。如本申请中所使用的术语“或”旨在意指包含的“或”而非排除的“或”。即，除非另外指定或从上下文中清楚，“X使用A或B”意指自然包括排列的任意一个。即，如果X使用A；X使用B；或X使用A和B二者，则“X使用A或B”在前述任一示例中得到满足。
而且，尽管已经相对于一个或多个实现方式示出并描述了本公开，但是本领域技术人员基于对本说明书和附图的阅读和理解将会想到等价变型和修改。本公开包括所有这样的修改和变型，并且仅由所附权利要求的范围限制。特别地关于由上述组件(例如元件、资源等)执行的各种功能，用于描述这样的组件的术语旨在对应于执行所述组件的指定功能(例如其在功能上是等价的)的任意组件(除非另外指示)，即使在结构上与执行本文所示的本公开的示范性实现方式中的功能的公开结构不等同。此外，尽管本公开的特定特征已经相对于若干实现方式中的仅一个被公开，但是这种特征可以与如可以对给定或特定应用而言是期望和有利的其他实现方式的一个或多个其他特征组合。而且，就术 语“包括”、“具有”、“含有”或其变形被用在具体实施方式或权利要求中而言，这样的术语旨在以与术语“包含”相似的方式包括。
本发明实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。上述提到的存储介质可以是只读存储器，磁盘或光盘等。上述的各装置或系统，可以执行相应方法实施例中的方法。
综上所述，虽然本发明已以优选实施例揭露如上，但上述优选实施例并非用以限制本发明，本领域的普通技术人员，在不脱离本发明的精神和范围内，均可作各种更动与润饰，因此本发明的保护范围以权利要求界定的范围为准。

Claims (18)

  1. 一种场景音乐搜索方法，包括：
    获取场景音乐搜索语句，并对所述场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词；
    根据所述场景音乐搜索词，获取与所述场景音乐搜索词对应的音乐标签；
    使用所述音乐标签，在音乐库中搜索对应的音乐，其中，所述音乐库包括所述音乐、所述音乐标签以及所述音乐和所述音乐标签的对应关系；以及
    对所述场景音乐搜索词以及对应的所述音乐进行展示。
  2. 根据权利要求1所述的场景音乐搜索方法，其中，所述对所述场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词的步骤包括：
    将所述场景音乐搜索语句拆分为多个基本词语；以及
    将所述基本词语中的动词以及名词作为所述场景音乐搜索词。
  3. 根据权利要求1所述的场景音乐搜索方法，其中，所述根据所述场景音乐搜索词，获取与所述场景音乐搜索词对应的音乐标签的步骤包括：
    判断所述场景音乐搜索词是否具有对应的音乐标签；
    如所述场景音乐搜索词具有对应的音乐标签，则获取所述音乐标签；以及如所述场景音乐搜索词不具有对应的音乐标签，则获取所述场景音乐搜索词的相似搜索词，并根据所述相似搜索词获取相应的音乐标签。
  4. 根据权利要求1所述的场景音乐搜索方法，其中，所述音乐库还包括所述音乐对应的所有音乐标签的权重值；
    所述对所述场景音乐搜索词以及对应的所述音乐进行展示的步骤包括：
    获取所述音乐标签在搜索到的所有音乐中的权重值；以及
    按所述音乐标签的权重值，对搜索到的所有音乐进行排序展示。
  5. 根据权利要求4所述的场景音乐搜索方法，其中，所述对所述场景音乐搜索词以及对应的所述音乐进行展示的步骤之后还包括：
    接收搜索词修改指令，并根据所述搜索词修改指令对所述场景音乐搜索词进行修改；
    获取修改后的所述场景音乐搜索词对应的音乐标签，在搜索到的所有音乐中的权重值；以及
    按所述音乐标签在所述音乐中的权重值，对搜索到的所有音乐进行重新排序展示。
  6. 根据权利要求4所述的场景音乐搜索方法，其中，所述场景音乐搜索方法还包括：
    接收音乐播放指令，并根据所述音乐播放指令，对展示的所述音乐进行播放操作；以及
    根据展示音乐的所述音乐播放的次数与所述音乐展示的次数的比值，对所述音乐标签在所述展示音乐中的权重值进行修正。
  7. 一种场景音乐搜索装置，包括：
    语句拆分模块，用于获取场景音乐搜索语句，并对所述场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词；
    音乐标签获取模块，用于根据所述场景音乐搜索词，获取与所述场景音乐搜索词对应的音乐标签；
    音乐搜索模块，用于使用所述音乐标签，在音乐库中搜索对应的音乐，其中，所述音乐库包括所述音乐、所述音乐标签以及所述音乐和所述音乐标签的对应关系；以及
    音乐展示模块，用于对所述场景音乐搜索词以及对应的所述音乐进行展示。
  8. 根据权利要求7所述的场景音乐搜索装置，其中，所述语句拆分模块包括：
    拆分单元，用于将所述场景音乐搜索语句拆分为多个基本词语；以及
    搜索词设定单元，用于将所述基本词语中的动词以及名词作为所述场景音乐搜索词。
  9. 根据权利要求7所述的场景音乐搜索装置，其中，所述音乐标签获取模块包括：
    判断单元，用于判断所述场景音乐搜索词是否具有对应的音乐标签；
    第一音乐标签获取单元，用于如所述场景音乐搜索词具有对应的音乐标签，则获取所述音乐标签；以及
    第二音乐标签获取单元，用于如所述场景音乐搜索词不具有对应的音乐标签，则获取所述场景音乐搜索词的相似搜索词，并根据所述相似搜索词获取相应的音乐标签。
  10. 根据权利要求7所述的场景音乐搜索装置，其中，所述音乐库还包括音乐对应的音乐标签的权重值；
    所述音乐展示模块包括：
    第一权重值获取单元，用于获取所述音乐标签，在搜索到的所有音乐中的权重值；以及
    第一排序展示单元，用于按所述音乐标签的权重值，对搜索到的所有音乐进行排序展示。
  11. 根据权利要求10所述的场景音乐搜索装置，其中，所述音乐展示模块还包括：
    搜索词修改单元，用于接收搜索词修改指令，并根据所述搜索词修改指令对所述场景音乐搜索词进行修改；
    第二权重值获取单元，用于获取修改后的所述场景音乐搜索词对应的音乐标签，在搜索到的所有音乐中的权重值；以及
    第二排序展示单元，用于按所述音乐标签在所述音乐中的权重值，对搜索到的所有音乐进行重新排序展示。
  12. 根据权利要求10所述的场景音乐搜索装置，其中，所述场景音乐搜索装置还包括：
    播放模块，用于接收音乐播放指令，并根据所述音乐播放指令，对展示的 音乐进行播放操作；以及
    权重值修正模块，用于根据展示音乐的所述音乐播放的次数与所述音乐展示的次数的比值，对所述音乐标签在所述展示音乐中的权重值进行修正。
  13. 一种存储介质，所述存储介质被设置为存储用于执行以下步骤的程序代码，包括：
    获取场景音乐搜索语句，并对所述场景音乐搜索语句进行拆分，以获得至少一个场景音乐搜索词；
    根据所述场景音乐搜索词，获取与所述场景音乐搜索词对应的音乐标签；
    使用所述音乐标签，在音乐库中搜索对应的音乐，其中，所述音乐库包括所述音乐、所述音乐标签以及所述音乐和所述音乐标签的对应关系；以及
    对所述场景音乐搜索词以及对应的所述音乐进行展示。
  14. 根据权利要求13所述的存储介质，所述存储介质被设置为存储用于执行以下步骤的程序代码，包括：
    将所述场景音乐搜索语句拆分为多个基本词语；以及
    将所述基本词语中的动词以及名词作为所述场景音乐搜索词。
  15. 根据权利要求13所述的存储介质，所述存储介质被设置为存储用于执行以下步骤的程序代码，包括：
    判断所述场景音乐搜索词是否具有对应的音乐标签；
    如所述场景音乐搜索词具有对应的音乐标签，则获取所述音乐标签；以及如所述场景音乐搜索词不具有对应的音乐标签，则获取所述场景音乐搜索词的相似搜索词，并根据所述相似搜索词获取相应的音乐标签。
  16. 根据权利要求13所述的存储介质，所述存储介质被设置为存储用于执行以下步骤的程序代码，包括：
    获取所述音乐标签在搜索到的所有音乐中的权重值，其中，所述音乐库还包括所述音乐对应的所有音乐标签的权重值；以及
    按所述音乐标签的权重值，对搜索到的所有音乐进行排序展示。
  17. 根据权利要求16所述的存储介质，所述存储介质被设置为存储用于执行以下步骤的程序代码，包括：
    接收搜索词修改指令，并根据所述搜索词修改指令对所述场景音乐搜索词进行修改；
    获取修改后的所述场景音乐搜索词对应的音乐标签，在搜索到的所有音乐中的权重值；以及
    按所述音乐标签在所述音乐中的权重值，对搜索到的所有音乐进行重新排序展示。
  18. 根据权利要求16所述的存储介质，所述存储介质被设置为存储用于执行以下步骤的程序代码，包括：
    接收音乐播放指令，并根据所述音乐播放指令，对展示的所述音乐进行播放操作；以及
    根据展示音乐的所述音乐播放的次数与所述音乐展示的次数的比值，对所述音乐标签在所述展示音乐中的权重值进行修正。
PCT/CN2016/100405 2015-12-03 2016-09-27 场景音乐搜索方法及场景音乐搜索装置 WO2017092493A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510884497.2A CN105550217B (zh) 2015-12-03 2015-12-03 场景音乐搜索方法及场景音乐搜索装置
CN201510884497.2 2015-12-03

Publications (1)

Publication Number Publication Date
WO2017092493A1 true WO2017092493A1 (zh) 2017-06-08

Family

ID=55829406

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/100405 WO2017092493A1 (zh) 2015-12-03 2016-09-27 场景音乐搜索方法及场景音乐搜索装置

Country Status (2)

Country Link
CN (1) CN105550217B (zh)
WO (1) WO2017092493A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105550217B (zh) * 2015-12-03 2021-05-07 腾讯科技（深圳）有限公司 场景音乐搜索方法及场景音乐搜索装置
CN108153898A (zh) * 2018-01-10 2018-06-12 上海展扬通信技术有限公司 音频播放方法、终端和计算机可读存储介质
CN109587554B (zh) 2018-10-29 2021-08-03 百度在线网络技术（北京）有限公司 视频数据的处理方法、装置及可读存储介质
CN109299314B (zh) * 2018-11-13 2019-12-27 百度在线网络技术（北京）有限公司 音乐检索与推荐的方法、装置、存储介质和终端设备
CN110209870B (zh) * 2019-05-10 2021-11-09 杭州网易云音乐科技有限公司 音乐日志生成方法、装置、介质和计算设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101105815A (zh) * 2007-09-06 2008-01-16 腾讯科技（深圳）有限公司 互联网音乐文件排序方法、系统和搜索方法及搜索引擎
US20080256106A1 (en) * 2007-04-10 2008-10-16 Brian Whitman Determining the Similarity of Music Using Cultural and Acoustic Information
US20140074269A1 (en) * 2012-09-11 2014-03-13 Google Inc. Method for Recommending Musical Entities to a User
CN104933028A (zh) * 2015-06-23 2015-09-23 百度在线网络技术（北京）有限公司 信息推送方法和装置
CN104951485A (zh) * 2014-09-02 2015-09-30 腾讯科技（深圳）有限公司 音乐文件的数据处理方法和装置
CN104991943A (zh) * 2015-07-10 2015-10-21 百度在线网络技术（北京）有限公司 音乐搜索方法及装置
CN105550217A (zh) * 2015-12-03 2016-05-04 腾讯科技（深圳）有限公司 场景音乐搜索方法及场景音乐搜索装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101996195B (zh) * 2009-08-28 2012-07-11 中国移动通信集团公司 音频文件中语音信息的搜索方法、装置及设备
CN102508920B (zh) * 2011-11-18 2013-03-13 广州索答信息科技有限公司 一种基于Boosting分类算法的信息检索方法
CN103425687A (zh) * 2012-05-21 2013-12-04 阿里巴巴集团控股有限公司 一种基于关键词的检索方法和系统
CN103150356B (zh) * 2013-02-22 2019-05-28 百度在线网络技术（北京）有限公司 一种应用的泛需求检索方法及系统
CN103279513B (zh) * 2013-05-22 2017-03-01 百度在线网络技术（北京）有限公司 产生内容标签的方法、提供多媒体内容信息的方法及装置
CN103886099B (zh) * 2014-04-09 2017-02-15 中国人民大学 一种模糊概念的语义检索系统及方法
CN104281705B (zh) * 2014-10-23 2017-12-22 百度在线网络技术（北京）有限公司 搜索方法及搜索装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080256106A1 (en) * 2007-04-10 2008-10-16 Brian Whitman Determining the Similarity of Music Using Cultural and Acoustic Information
CN101105815A (zh) * 2007-09-06 2008-01-16 腾讯科技（深圳）有限公司 互联网音乐文件排序方法、系统和搜索方法及搜索引擎
US20140074269A1 (en) * 2012-09-11 2014-03-13 Google Inc. Method for Recommending Musical Entities to a User
CN104951485A (zh) * 2014-09-02 2015-09-30 腾讯科技（深圳）有限公司 音乐文件的数据处理方法和装置
CN104933028A (zh) * 2015-06-23 2015-09-23 百度在线网络技术（北京）有限公司 信息推送方法和装置
CN104991943A (zh) * 2015-07-10 2015-10-21 百度在线网络技术（北京）有限公司 音乐搜索方法及装置
CN105550217A (zh) * 2015-12-03 2016-05-04 腾讯科技（深圳）有限公司 场景音乐搜索方法及场景音乐搜索装置

Also Published As

Publication number Publication date
CN105550217B (zh) 2021-05-07
CN105550217A (zh) 2016-05-04

Similar Documents

Publication Publication Date Title
CN107256267B (zh) 查询方法和装置
US11164568B2 (en) Speech recognition method and apparatus, and storage medium
US20220214775A1 (en) Method for extracting salient dialog usage from live data
US10691685B2 (en) Converting natural language input to structured queries
CN107683471B (zh) 索引具有深度链接的网页
WO2017092493A1 (zh) 场景音乐搜索方法及场景音乐搜索装置
US20200210468A1 (en) Document recommendation method and device based on semantic tag
US11580181B1 (en) Query modification based on non-textual resource context
US10698654B2 (en) Ranking and boosting relevant distributable digital assistant operations
US11354510B2 (en) System and method for semantic analysis of song lyrics in a media content environment
US10810374B2 (en) Matching a query to a set of sentences using a multidimensional relevancy determination
US11016968B1 (en) Mutation architecture for contextual data aggregator
US20170109435A1 (en) Apparatus and method for searching for information
CN109241319B (zh) 一种图片检索方法、装置、服务器和存储介质
KR20160127810A (ko) 온스크린 아이템 선택 및 명확화를 위한 모델 기반 방식
US10360260B2 (en) System and method for semantic analysis of song lyrics in a media content environment
US11080330B2 (en) Generation of digital content navigation data
CN110147494B (zh) 信息搜索方法、装置，存储介质及电子设备
TW201606750A (zh) 使用外國字文法的語音辨識
CN105637509A (zh) 在图像内搜索和注释
CN111324700A (zh) 资源召回方法、装置、电子设备及计算机可读存储介质
CN112262382A (zh) 上下文深层书签的注释和检索
US9910918B2 (en) Presenting tags of a tag cloud in a more understandable and visually appealing manner
US9811592B1 (en) Query modification based on textual resource context
US9251141B1 (en) Entity identification model training

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: 16869804

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 09.11.2018)

122 Ep: pct application non-entry in european phase

Ref document number: 16869804

Country of ref document: EP

Kind code of ref document: A1