CN110309345A - Online song search method and search engine based on vehicle-mounted radio - Google Patents
Online song search method and search engine based on vehicle-mounted radio Download PDFInfo
- Publication number
- CN110309345A CN110309345A CN201810124840.7A CN201810124840A CN110309345A CN 110309345 A CN110309345 A CN 110309345A CN 201810124840 A CN201810124840 A CN 201810124840A CN 110309345 A CN110309345 A CN 110309345A
- Authority
- CN
- China
- Prior art keywords
- song
- query intention
- intention
- vehicle
- user
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Classifications
-
- 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
Abstract
This application involves a kind of online song search method and search engine based on vehicle-mounted radio, method therein include: to receive speech polling instruction；According to the query intention of the content recognition user of speech polling instruction；Key word of the inquiry relevant to song information is obtained according to the query intention, the song information includes song title, singer name, types of songs, song style, recommends classification and number of songs；Online song is searched for according to the key word of the inquiry of acquisition；The online song searched is exported to play out by vehicle-mounted radio.In this way, the application can search out the online song for meeting user's intention according to the query intention of user, optimize user experience.
Description
Technical field
This application involves search technique fields, and in particular to a kind of online song search method based on vehicle-mounted radio with
Search engine.
Background technique
Song search engine is a kind of Internet service, and convenient access entry can be provided for user.User can lead to
It is crossed to retrieve the music that oneself wants downloading/audition.In general, user wants the song of retrieval according to oneself, one is constructed
To multiple search keys, the retrieval request comprising search key, the inspection for inputting search engine according to user are then submitted
Rope keyword is retrieved, and the song for finding matching user search keyword is presented to the user.
Vehicle-mounted radio is mounted in a kind of voice entertainment configuration on automobile, is that vehicle-mounted video and music entertainment system is most common
One of configuration, the song search engine based on vehicle-mounted radio can play out the song of retrieval by vehicle-mounted radio.
However, the query intention of user, Bu Nenggen can not be understood completely in the song search engine based on vehicle-mounted radio of the prior art
It is intended to screen the song searched according to user, when the song of the same name that current queries arrive is too many, user needs to spend very much
Time could select required song, and be easy to search for out the network song of lower tone, non-legal copy, in addition, cannot be according to user
It is intended to provide the temperature ranking and recommendation of associated song, the real demand of user is unable to satisfy so as to cause the song searched,
Poor user experience.
Summary of the invention
The purpose of the application is, provides a kind of online song search method and search engine based on vehicle-mounted radio,
It can solve above-mentioned technical problem, and the online song for meeting user's intention can be searched out according to the query intention of user, excellent
Change user experience.
In order to solve the above technical problems, the application provides a kind of online song search method based on vehicle-mounted radio, packet
It includes:
Receive speech polling instruction；
According to the query intention of the content recognition user of speech polling instruction；
Key word of the inquiry relevant to song information is obtained according to the query intention, the song information includes song title
Title, types of songs, song style, recommends classification and number of songs at singer name；
Online song is searched for according to the key word of the inquiry of acquisition；
The online song searched is exported to play out by vehicle-mounted radio.
Wherein, the query intention of the content recognition user according to speech polling instruction, comprising:
The speech polling is instructed according to the content of speech polling instruction and carries out semantic parsing；
Query intention corresponding with the semanteme parsing result is identified according to semantic parsing result；
Judge whether the query intention identified is complete；
If the query intention identified is complete, query intention of the query intention that will identify that as user.
It is wherein, described that query intention corresponding with the semanteme parsing result is identified according to semantic parsing result, comprising:
Obtain the identidication key in the semantic parsing result；
Obtain the corresponding default intention content of each identidication key；
The default intention content that will acquire according to each identidication key in the context relation of the semantic parsing result into
Row is in conjunction with to identify query intention corresponding with the semanteme parsing result.
Wherein, the query intention of the content recognition user according to speech polling instruction, further includes:
If the query intention corresponding with the semanteme parsing result identified is imperfect, according to the semantic parsing knot
Fruit and current voice scene Recognition go out query intention of the complete query intention as user；Or,
If the query intention corresponding with the semanteme parsing result identified is imperfect, voice guide is carried out to user
Until identifying query intention of the complete query intention as user.
Wherein, the online song searched that exports by vehicle-mounted radio to be played out, comprising:
The online song searched the playlist current in the vehicle-mounted radio is determined according to the query intention of user
In output position；
The online song searched is added to the current playlist of the vehicle-mounted radio according to the output position
In corresponding position.
Wherein, described to determine that the online song that searches is in the vehicle-mounted radio current according to the query intention of user
Output position in playlist, comprising:
Broadcasting keyword relevant to broadcast mode is obtained according to the query intention of user, the broadcast mode includes direct
Play, wait currently playing playback of songs after play and wait automatically whole playback of songs knots in current play list
It is played automatically after beam；
The online song searched the playlist current in the vehicle-mounted radio is determined according to the broadcasting keyword
In output position.
The application also provides a kind of online song search engine based on vehicle-mounted radio, comprising:
Command reception module, for receiving speech polling instruction；
Intention assessment module, the query intention of the content recognition user for being instructed according to the speech polling；
Keyword obtains module, for obtaining key word of the inquiry relevant to song information, institute according to the query intention
Song information is stated to include song title, singer name, types of songs, song style, recommend classification and number of songs；
Search module, for searching for online song according to the key word of the inquiry of acquisition；
Output module, for exporting the online song searched to play out by vehicle-mounted radio.
Wherein, the intention assessment module, comprising:
Semantic resolution unit, the content for being instructed according to the speech polling, which instructs the speech polling, carries out semanteme
Parsing；
First intention recognition unit, for being identified and described semantic parsing result is corresponding looks into according to semantic parsing result
It askes and is intended to；
Whether judging unit, the query intention for judging to identify are complete；
Intent determination unit, if the query intention for identifying is complete, the query intention that will identify that is as user
Query intention.
Wherein, the intention assessment module, further includes:
Second intention recognition unit, if the query intention corresponding with the semanteme parsing result for identifying is endless
It is whole, then complete query intention is gone out as the inquiry of user according to the semantic parsing result and current voice scene Recognition and anticipated
Figure；Or,
Third intention assessment unit, if the query intention corresponding with the semanteme parsing result for identifying is endless
It is whole, then voice guide is carried out to user until identifying query intention of the complete query intention as user.
Wherein, the output module, comprising:
Output position determination unit, for determining the online song searched described vehicle-mounted according to the query intention of user
Output position in the current playlist of radio；
Output unit is worked as the online song searched to be added to the vehicle-mounted radio according to the output position
Corresponding position in preceding playlist.
The online song search method and search engine based on vehicle-mounted radio of the application refers to receiving speech polling
It enables, according to the query intention of the content recognition user of speech polling instruction, and it is related to song information according to query intention acquisition
Key word of the inquiry, song information includes song title, singer name, types of songs, song style, recommends classification and number of songs
Amount searches for online song further according to the key word of the inquiry of acquisition, export the online song that searches with by vehicle-mounted radio into
Row plays.In this way, the application can search out the online song for meeting user's intention according to the query intention of user,
Optimize user experience.
Above description is only the general introduction of technical scheme, in order to better understand the technological means of the application,
And it can be implemented in accordance with the contents of the specification, and in order to allow the above and other objects, features and advantages of the application can
It is clearer and more comprehensible, it is special below to lift preferred embodiment, and cooperate attached drawing, detailed description are as follows.
Detailed description of the invention
Fig. 1 is a kind of stream of online song search method based on vehicle-mounted radio shown according to an exemplary embodiment
Journey schematic diagram.
Fig. 2 is a kind of knot of online song search engine based on vehicle-mounted radio shown according to an exemplary embodiment
Structure schematic diagram.
Specific embodiment
Further to illustrate that the application is the technical means and efficacy reaching predetermined application purpose and being taken, below in conjunction with
Attached drawing and preferred embodiment propose the online song search method according to the application based on vehicle-mounted radio with search engine
Specific embodiment, method, step, structure, feature and its effect, detailed description are as follows.
Aforementioned and other technology contents, feature and effect in relation to the application refer to the preferable reality of schema in following cooperation
Applying in the detailed description of example can clearly appear from.By the explanation of specific embodiment, when can be that reach predetermined mesh to the application
The technical means and efficacy taken be able to more deeply and it is specific understand, however institute's accompanying drawings are only to provide with reference to and say
It is bright to be used, not it is used to limit the application.
Fig. 1 is a kind of flow diagram of the method for searching for point of interest shown according to an exemplary embodiment.It please refers to
Fig. 1, the online song search method based on vehicle-mounted radio of the present embodiment, including but not limited to following steps:
Step 110, speech polling instruction is received.
Wherein, after vehicle-mounted radio opens intelligent radio station function, as user listens song, replacement at beginning of looking on the bright side of things in use
Currently playing song continues the song of style for listening oneself to like, and the intention of itself can be expressed by way of voice,
Namely the query intention for oneself wanting the song listened is obtained, so that input inquiry instructs, for example, saying, " I wants to listen Chengdu and this
The more pleasing to the ear songs of singer ", " after this song, playing the singer more pleasing to the ear song for a moment ", " I wants to listen more similar
The classical English song of style, but should not be too old " etc..
Step 120, according to the query intention of the content recognition user of speech polling instruction.
In one embodiment, the query intention for the content recognition user that the step 120 is instructed according to speech polling, tool
Body may include following procedure:
Speech polling is instructed according to the content of speech polling instruction and carries out semantic parsing；
Query intention corresponding with semantic parsing result is identified according to semantic parsing result；
Judge whether the query intention identified is complete；
If the query intention identified is complete, query intention of the query intention that will identify that as user.
Wherein, when receiving the voice signal of speech polling instruction, the voice characteristics information of voice signal is extracted in framing,
The recognition result of voice signal namely the content of speech polling instruction are generated according to voice characteristics information and acoustic model, then,
Semantic parsing is carried out according to the content of speech polling instruction, effective knowledge is extracted from the sentence of recognition result, according to sentence
Syntactic structure and sentence in word the information such as the meaning of a word, the meaning of speech polling instruction is derived, to obtain semantic parsing result.
For example, can be inferred that be inquired is song from " I wants to listen Chengdu and the more pleasing to the ear songs of this singer ", song is
Pleasing to the ear song, number of songs are multiple, are sung by specific singer, and Chengdu is a first song, also, the specific singer is Chengdu
The singer of this song, and, other songs of the singer of Chengdu this song and Chengdu this song will inquire, to analyze language
The meaning of sound inquiry instruction.
The identification of query intention corresponding with semantic parsing result is carried out after obtaining semantic parsing result.In an embodiment party
It is described that query intention corresponding with semantic parsing result is identified according to semantic parsing result in formula, it can specifically include following
Process:
Obtain the identidication key in semantic parsing result；
Obtain the corresponding default intention content of each identidication key；
It is tied according to each identidication key in the default intention content that the context relation of semantic parsing result will acquire
It closes to identify query intention corresponding with semantic parsing result.
Wherein, after obtaining semantic parsing result, although it is known that the meaning of speech polling instruction, but still cannot correspond to
To exact query intention, such as, it is known that " Chengdu " is song title, but cannot understand that the song to be inquired of user " Chengdu " is
Which type of song is that original song or various network singers compile the song after singing, for another example, it is known that " more ", but cannot
Understand the quantity to be inquired of user, for another example, it is known that " pleasing to the ear ", but cannot understand the song recommendations classification to be inquired of user.Therefore,
By presetting the type of identidication key and being intended to the corresponding relationship of content, the query intention for identifying user can be helped, specifically
For, identidication key " Chengdu ", " singer of Chengdu this song ", " more ", " pleasing to the ear " are obtained, in corresponding default intention
Holding is respectively " original song ' Chengdu ' ", " singer of original song ' Chengdu ' ", " ten first ", " ranking most before ", according to each identification
Keyword is combined in the default intention content that the context relation of semantic parsing result will acquire, to identify user's
Query intention is original song " Chengdu ", rather than various network singers and most preceding ten song of his ranking.
That is, in one embodiment, the corresponding default intention content of song title is original song, quantity is indicated
The corresponding default content that is intended to of word is the number of songs set, the corresponding default intention of the Sentiment orientations word such as " pleasing to the ear ", " good "
Content be ranking most before.It, can be by presetting the type of identidication key and being intended to the corresponding relationship of content according to this mode
To realize the identification to query intention.
After identifying query intention corresponding with semantic parsing result, judge whether the query intention identified is complete,
Specifically, the query intention that " I wants to listen Chengdu and the more pleasing to the ear songs of this singer " identifies be " original song ' at
All ', rather than various network singers and most preceding ten song of his ranking ", the song title to be inquired of expressed intact, song
Bent type, artist name, number of songs and recommend classification, it is intended that it is complete, and according to " after this song, playing the singer for a moment
The query intention that more pleasing to the ear songs " identify is " after this song, directly to listen the first song of the ranking of the singer of this song most preceding ten
It is bent ", based on semantic parsing result, " this song " refers to certain song, but it is which is first that query intention, which does not give expression to " this song " clearly,
Song, it is intended that imperfect.It should be understood that if the query intention identified according to " English song for looking for more classics " is " to listen ten first warps
The English song of allusion quotation " although not expressing the information such as song title, but still can find institute according to the classification of online song song library
The song needed, it is therefore contemplated that it is intended to completely, that is to say, that complete query intention only needs that determining inquiry rule can be corresponded to
Then, however it is not limited to be intended to whether expressed intact all information.
Wherein, if the query intention identified is complete, query intention of the query intention that will identify that as user.?
In one embodiment, if the query intention corresponding with semantic parsing result identified is imperfect, according to semantic parsing result
And current voice scene Recognition goes out query intention of the complete query intention as user.
Specifically, the query intention identified according to " after this song, playing the singer more pleasing to the ear song for a moment "
For " after this song, most preceding ten song of ranking for the singer for directly listening this to sing ", which head is expressed intact " this song " be not
Song, it is intended that it is imperfect, at this point, being needed in conjunction with current voice field according to semantic parsing result it is found that this song refers to certain song
Scape is such as currently at the scene for listening to song, then can determine that expressed by " this song " be the song being currently played, from
And identify complete query intention.In this way, when that can not identify complete intention, current voice can be referred to
Scene Direct Recognition goes out complete query intention.
In another embodiment, if the query intention corresponding with semantic parsing result identified is imperfect, to
Family carries out voice guide until identifying query intention of the complete query intention as user.For example, according to " song just now is listened
The query intention that the more pleasing to the ear song of hand " identifies is " most preceding ten song of ranking for playing singer just now ", not completely
Expression " singer just now " refers to that history plays which of the singer of song, it is intended that it is imperfect, at this point it is possible to export voice
Guidance information " singer that singer just now refers to a song ", according to received voice messaging " yes " again
Determining is the singer of a upper song expressed by " singer just now ", to identify complete query intention.
Step 130, key word of the inquiry relevant to song information is obtained according to query intention, song information includes song title
Title, types of songs, song style, recommends classification and number of songs at singer name.
Wherein, after getting complete query intention, can with rule searching corresponding with query intention network,
Corresponding song is searched in line song library.Since the target to be inquired is song, song information is not limited to include song title, singer
Name, song style, recommends classification and number of songs at types of songs, therefore, it is related need to obtain song information according to query intention
Key word of the inquiry.Specifically, according to query intention " original song ' Chengdu ', rather than various network singers and his ranking
The confirmable key word of the inquiry of most preceding ten song " is, song title is " Chengdu ", singer name be " original song ' at
Singer ' ", types of songs is " original ", classification is recommended to be " ranking most before " and number of songs is " ten is first ", thus obtain with
The corresponding rule searching of query intention.
Step 140, online song is searched for according to the key word of the inquiry of acquisition.
Wherein, after obtaining key word of the inquiry, online song is searched for according to key word of the inquiry, specifically, finding first
Song title is the song in " Chengdu ", may have at this time several as a result, including that original song and other networks singer compile and sing
Song etc., then, according to types of songs be " original ", filter out a wherein song, obtain the singer of the song filtered out,
Ten most preceding first songs of singer's ranking are searched for according to the singer of acquisition, finally, obtaining search result namely original song " Chengdu "
With ten songs of recommendation.In this way, the online song searched according to the query intention of user is without user, to carry out song again same
Name screening understands the desired song recommendations type of user, ranking, also, is presented to the user for the song of high tone quality, is promoted
User experience.
Step 150, the online song searched is exported to play out by vehicle-mounted radio.
In one embodiment, the online song that step 150 output searches by vehicle-mounted radio to be broadcast
It puts, can specifically include following procedure:
Determine the online song searched in the current playlist of vehicle-mounted radio according to the query intention of user
Output position；
The correspondence being added to the online song searched according to output position in the current playlist of vehicle-mounted radio
Position.
Wherein, the step: determine that the online song searched is current in vehicle-mounted radio according to the query intention of user
Playlist in output position, following procedure can be specifically included:
Broadcasting keyword relevant to broadcast mode is obtained according to the query intention of user, broadcast mode includes directly broadcasting
Put, wait currently playing playback of songs after play and wait automatically whole playback of songs in current play list to terminate
It is automatic afterwards to play；
Output of the online song searched in the current playlist of vehicle-mounted radio is determined according to keyword is played
Position.
Wherein, when in the semanteme of the Context resolution instructed according to speech polling including the meaning relevant to broadcast mode,
The user query that then identify are intended to include also mode that user wishes to play the online song searched, for example, according to finger
The query intention for enabling " after this song, playing the singer more pleasing to the ear song for a moment " to identify is " after this song, directly to listen
Most preceding ten song of ranking of the singer of this song ", can learn the corresponding broadcast mode of query intention are as follows: wait currently playing
Automatically the song searched is played after playback of songs, corresponding broadcasting keyword may be set to that " song insertion is currently playing
Song after ", so that it is determined that output position of the online song searched in the current playlist of vehicle-mounted radio.
According to other instructions, other broadcast modes can also be identified, such as directly play or wait the whole in current play list
It is played automatically after playback of songs, corresponding broadcasting keyword may be set to " song substitutes currently playing song " and " song
After song insertion the current list ", to equally can determine the online song searched the played column current in vehicle-mounted radio
Output position in table.Finally, it is current that the online song searched is added to vehicle-mounted radio according to determining output position
Playlist in, realize play.
The online song search method based on vehicle-mounted radio of the application is receiving speech polling instruction, according to voice
The query intention of the content recognition user of inquiry instruction, and inquiry key relevant to song information is obtained according to query intention
Word, song information include song title, singer name, types of songs, song style, recommend classification and number of songs, further according to
The key word of the inquiry of acquisition searches for online song, exports the online song searched to play out by vehicle-mounted radio.It is logical
This mode is crossed, the application can search out the online song for meeting user's intention according to the query intention of user, optimize use
Family experience.
Fig. 2 is a kind of knot of online song search engine based on vehicle-mounted radio shown according to an exemplary embodiment
Structure schematic diagram.Referring to FIG. 2, the online song search engine based on vehicle-mounted radio of the present embodiment, including command reception mould
Block 210, intention assessment module 220, keyword obtain module 230, search module 240 and output module 250.
Wherein, command reception module 210, for receiving speech polling instruction.Intention assessment module 220, for according to language
The query intention of the content recognition user of sound inquiry instruction.Keyword obtains module 230, for being obtained and being sung according to query intention
The relevant key word of the inquiry of bent information, song information include song title, singer name, types of songs, song style, recommend class
Other and number of songs.Search module 240, for searching for online song according to the key word of the inquiry of acquisition.Output module 250 is used
In the online song that output searches to be played out by vehicle-mounted radio.
In one embodiment, it is intended that identification module 220 includes semantic resolution unit, first intention recognition unit, judgement
Unit and intent determination unit.Wherein, semantic resolution unit, the content for being instructed according to speech polling instruct speech polling
Carry out semantic parsing.First intention recognition unit, it is corresponding with semantic parsing result for being identified according to semantic parsing result
Query intention.Whether judging unit, the query intention for judging to identify are complete.Intent determination unit, if for identifying
Query intention it is complete, then query intention of the query intention that will identify that as user.
In one embodiment, it is intended that identification module 220 further include: second intention recognition unit or third intention assessment list
Member.Wherein, second intention recognition unit, if the query intention corresponding with semantic parsing result for identifying is imperfect,
Go out query intention of the complete query intention as user according to semantic parsing result and current voice scene Recognition.Third meaning
Figure recognition unit carries out voice to user if the query intention corresponding with semantic parsing result for identifying is imperfect
Guidance is until identify query intention of the complete query intention as user.
In one embodiment, output module 250 includes output position determination unit and output unit.Wherein, output bit
Determination unit is set, for determining the online song searched the played column current in vehicle-mounted radio according to the query intention of user
Output position in table.Output unit is worked as the online song searched to be added to vehicle-mounted radio according to output position
Corresponding position in preceding playlist.
The course of work of each functional module please join in the online song search engine based on vehicle-mounted radio of the present embodiment
Embodiment illustrated in fig. 1, details are not described herein.
The online song search engine based on vehicle-mounted radio of the application is receiving speech polling instruction, according to voice
The query intention of the content recognition user of inquiry instruction, and inquiry key relevant to song information is obtained according to query intention
Word, song information include song title, singer name, types of songs, song style, recommend classification and number of songs, further according to
The key word of the inquiry of acquisition searches for online song, exports the online song searched to play out by vehicle-mounted radio.It is logical
This mode is crossed, the application can search out the online song for meeting user's intention according to the query intention of user, optimize use
Family experience.
The application also provides a kind of cloud server, and the cloud server includes processor, and the processor is for holding
Line program data, the step of to realize the online song search method based on vehicle-mounted radio as shown in Figure 1.
The above is only the preferred embodiment of the application, not makes any form of restriction to the application, though
Right the application has been disclosed in a preferred embodiment above, however is not limited to the application, any technology people for being familiar with this profession
Member, is not departing within the scope of technical scheme, when the technology contents using the disclosure above make a little change or modification
For the equivalent embodiment of equivalent variations, but all technical spirits pair without departing from technical scheme content, according to the application
Any simple modification, equivalent change and modification made by above embodiments, in the range of still falling within technical scheme.
Claims (10)
1. a kind of online song search method based on vehicle-mounted radio characterized by comprising
Receive speech polling instruction；
According to the query intention of the content recognition user of speech polling instruction；
Obtain relevant to song information key word of the inquiry according to the query intention, the song information include song title,
Singer name, song style, recommends classification and number of songs at types of songs；
Online song is searched for according to the key word of the inquiry of acquisition；
The online song searched is exported to play out by vehicle-mounted radio.
2. the online song search method according to claim 1 based on vehicle-mounted radio, which is characterized in that the basis
The query intention of the content recognition user of the speech polling instruction, comprising:
The speech polling is instructed according to the content of speech polling instruction and carries out semantic parsing；
Query intention corresponding with the semanteme parsing result is identified according to semantic parsing result；
Judge whether the query intention identified is complete；
If the query intention identified is complete, query intention of the query intention that will identify that as user.
3. the online song search method according to claim 2 based on vehicle-mounted radio, which is characterized in that the basis
Semantic parsing result identifies query intention corresponding with the semanteme parsing result, comprising:
Obtain the identidication key in the semantic parsing result；
Obtain the corresponding default intention content of each identidication key；
It is tied according to each identidication key in the default intention content that the context relation of the semantic parsing result will acquire
It closes to identify query intention corresponding with the semanteme parsing result.
4. the online song search method according to claim 2 or 3 based on vehicle-mounted radio, which is characterized in that described
According to the query intention of the content recognition user of speech polling instruction, further includes:
If the query intention corresponding with the semantic parsing result identified is imperfect, according to the semantic parsing result and
Current voice scene Recognition goes out query intention of the complete query intention as user；Or,
If the query intention corresponding with the semantic parsing result identified is imperfect, voice guide is carried out to user until
Identify query intention of the complete query intention as user.
5. the online song search method according to claim 1 based on vehicle-mounted radio, which is characterized in that the output
The online song searched by vehicle-mounted radio to be played out, comprising:
Determine the online song searched in the current playlist of the vehicle-mounted radio according to the query intention of user
Output position；
The online song searched is added in the current playlist of the vehicle-mounted radio according to the output position
Corresponding position.
6. the online song search method according to claim 5 based on vehicle-mounted radio, which is characterized in that the basis
The query intention of user determines output position of the online song searched in the current playlist of the vehicle-mounted radio,
Include:
Broadcasting keyword relevant to broadcast mode is obtained according to the query intention of user, the broadcast mode includes directly broadcasting
Put, wait currently playing playback of songs after play and wait automatically whole playback of songs in current play list to terminate
It is automatic afterwards to play；
Determine the online song searched in the current playlist of the vehicle-mounted radio according to the broadcasting keyword
Output position.
7. a kind of online song search engine based on vehicle-mounted radio characterized by comprising
Command reception module, for receiving speech polling instruction；
Intention assessment module, the query intention of the content recognition user for being instructed according to the speech polling；
Keyword obtains module, for obtaining key word of the inquiry relevant to song information, the song according to the query intention
Bent information includes song title, singer name, types of songs, song style, recommends classification and number of songs；
Search module, for searching for online song according to the key word of the inquiry of acquisition；
Output module, for exporting the online song searched to play out by vehicle-mounted radio.
8. the online song search engine according to claim 7 based on vehicle-mounted radio, which is characterized in that the intention
Identification module, comprising:
Semantic resolution unit, the content for being instructed according to the speech polling, which instructs the speech polling, carries out semantic solution
Analysis；
First intention recognition unit, for identifying that inquiry corresponding with the semanteme parsing result is anticipated according to semantic parsing result
Figure；
Whether judging unit, the query intention for judging to identify are complete；
Intent determination unit, if the query intention for identifying is complete, the query intention that will identify that is looked into as user's
It askes and is intended to.
9. the online song search engine according to claim 8 based on vehicle-mounted radio, which is characterized in that the intention
Identification module, further includes:
Second intention recognition unit, if the query intention corresponding with the semanteme parsing result for identifying is imperfect,
Go out query intention of the complete query intention as user according to the semantic parsing result and current voice scene Recognition；
Or,
Third intention assessment unit, if the query intention corresponding with the semanteme parsing result for identifying is imperfect,
Voice guide is carried out to user until identifying query intention of the complete query intention as user.
10. the online song search engine according to claim 7 based on vehicle-mounted radio, which is characterized in that described defeated
Module out, comprising:
Output position determination unit, for determining the online song searched in the vehicle-mounted radio according to the query intention of user
Output position in the current playlist of machine；
Output unit, it is current for the online song searched to be added to the vehicle-mounted radio according to the output position
Corresponding position in playlist.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810124840.7A CN110309345A (en) | 2018-02-07 | 2018-02-07 | Online song search method and search engine based on vehicle-mounted radio |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810124840.7A CN110309345A (en) | 2018-02-07 | 2018-02-07 | Online song search method and search engine based on vehicle-mounted radio |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110309345A true CN110309345A (en) | 2019-10-08 |
Family
ID=68073613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810124840.7A Pending CN110309345A (en) | 2018-02-07 | 2018-02-07 | Online song search method and search engine based on vehicle-mounted radio |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110309345A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111128168A (en) * | 2019-12-30 | 2020-05-08 | 斑马网络技术有限公司 | Voice control method, device and storage medium |
| CN111198965A (en) * | 2019-12-31 | 2020-05-26 | 腾讯科技（深圳）有限公司 | Song retrieval method, device, server and storage medium |
| CN112148848A (en) * | 2020-08-28 | 2020-12-29 | 出门问问(苏州)信息科技有限公司 | Question and answer processing method and device |
| CN112751635A (en) * | 2020-12-16 | 2021-05-04 | 北京百度网讯科技有限公司 | Method, device and equipment for playing vehicle radio station and storage medium |
| CN111198965B (en) * | 2019-12-31 | 2024-04-19 | 腾讯科技（深圳）有限公司 | Song retrieval method, song retrieval device, server and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542459A (en) * | 2010-12-29 | 2012-07-04 | 上海博泰悦臻电子设备制造有限公司 | Vehicle-mounted terminal and vehicle-mounted information service system |
| CN102724309A (en) * | 2012-06-14 | 2012-10-10 | 广东好帮手电子科技股份有限公司 | Vehicular voice network music system and control method thereof |
| CN103078915A (en) * | 2012-12-28 | 2013-05-01 | 深圳职业技术学院 | Vehicle-mounted voice song request system based on cloud computing vehicle networking and method thereof |
| CN104679855A (en) * | 2015-02-13 | 2015-06-03 | 广东欧珀移动通信有限公司 | Playlist creation method and terminal device |
| CN204539202U (en) * | 2014-04-17 | 2015-08-05 | 深圳市掌翼星通科技有限公司 | The online song system of a kind of vehicle-carried sound-controlled playing speech on demand |
| EP3144825A1 (en) * | 2015-09-16 | 2017-03-22 | Valossa Labs Oy | Enhanced digital media indexing and retrieval |
| CN107247769A (en) * | 2017-06-05 | 2017-10-13 | 北京智能管家科技有限公司 | Method for ordering song by voice, device, terminal and storage medium |
| WO2018020275A1 (en) * | 2016-07-29 | 2018-02-01 | Unifai Holdings Limited | Computer vision systems |
-
2018
- 2018-02-07 CN CN201810124840.7A patent/CN110309345A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542459A (en) * | 2010-12-29 | 2012-07-04 | 上海博泰悦臻电子设备制造有限公司 | Vehicle-mounted terminal and vehicle-mounted information service system |
| CN102724309A (en) * | 2012-06-14 | 2012-10-10 | 广东好帮手电子科技股份有限公司 | Vehicular voice network music system and control method thereof |
| CN103078915A (en) * | 2012-12-28 | 2013-05-01 | 深圳职业技术学院 | Vehicle-mounted voice song request system based on cloud computing vehicle networking and method thereof |
| CN204539202U (en) * | 2014-04-17 | 2015-08-05 | 深圳市掌翼星通科技有限公司 | The online song system of a kind of vehicle-carried sound-controlled playing speech on demand |
| CN104679855A (en) * | 2015-02-13 | 2015-06-03 | 广东欧珀移动通信有限公司 | Playlist creation method and terminal device |
| EP3144825A1 (en) * | 2015-09-16 | 2017-03-22 | Valossa Labs Oy | Enhanced digital media indexing and retrieval |
| WO2018020275A1 (en) * | 2016-07-29 | 2018-02-01 | Unifai Holdings Limited | Computer vision systems |
| CN107247769A (en) * | 2017-06-05 | 2017-10-13 | 北京智能管家科技有限公司 | Method for ordering song by voice, device, terminal and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111128168A (en) * | 2019-12-30 | 2020-05-08 | 斑马网络技术有限公司 | Voice control method, device and storage medium |
| CN111198965A (en) * | 2019-12-31 | 2020-05-26 | 腾讯科技（深圳）有限公司 | Song retrieval method, device, server and storage medium |
| CN111198965B (en) * | 2019-12-31 | 2024-04-19 | 腾讯科技（深圳）有限公司 | Song retrieval method, song retrieval device, server and storage medium |
| CN112148848A (en) * | 2020-08-28 | 2020-12-29 | 出门问问(苏州)信息科技有限公司 | Question and answer processing method and device |
| CN112751635A (en) * | 2020-12-16 | 2021-05-04 | 北京百度网讯科技有限公司 | Method, device and equipment for playing vehicle radio station and storage medium |
| CN112751635B (en) * | 2020-12-16 | 2023-03-24 | 阿波罗智联(北京)科技有限公司 | Method, device and equipment for playing vehicle radio station and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210240763A1 (en) | Generating and Distributing Playlists with Music and Stories Having Related Moods | |
| CN100495536C (en) | System and method of access and retrieval for media file using speech recognition | |
| US9190052B2 (en) | Systems and methods for providing information discovery and retrieval | |
| KR101326897B1 (en) | Device and Method for Providing a Television Sequence | |
| CN107526809B (en) | Method and device for pushing music based on artificial intelligence | |
| CN109165302A (en) | Multimedia file recommendation method and device | |
| CN110309345A (en) | Online song search method and search engine based on vehicle-mounted radio | |
| CN102567447A (en) | Information processing device and method, information processing system, and program | |
| EP3664461A1 (en) | Content playback system | |
| CN109237740A (en) | A kind of control method of electric appliance, device, storage medium and electric appliance | |
| KR20030059503A (en) | User made music service system and method in accordance with degree of preference of user's | |
| US20040193649A1 (en) | Method and apparatus for searching recommended music in the internet, and a computer-readable medium encoded with a plurality of processor-executable instruction sequences for searching recommended music in the internet | |
| CN111427444B (en) | Control method and device of intelligent device | |
| KR101715070B1 (en) | System and method for providong digital sound transmission based music radio service | |
| US20120304064A1 (en) | Software Method to Create a Music Playlist and a Video Playlist from Upcoming Concerts | |
| JP5474591B2 (en) | Image selection apparatus, image selection method, and image selection program | |
| JP2011180271A (en) | Karaoke music selection reservation device connected to host system through cradle | |
| JPH08127187A (en) | Quick sample of karaoke melody | |
| KR100978382B1 (en) | System and its method for providing advertisement of contents using entertainer's voice pattern | |
| JP2007072316A (en) | Retrieval method of recorded song pieces, database structure of the recorded song pieces | |
| CN112836083A (en) | Selection method based on RTOS system and convenient for randomly searching played content | |
| KR20040066598A (en) | Method for searching music using a refrain listen and computer readable record medium on which a program therefor is recorded | |
| JP2017161815A (en) | Response system and response program | |
| JP2005233986A (en) | Music data downloading method and music data reproducing device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |