CN116343771A - Music on-demand voice instruction recognition method and device based on knowledge graph - Google Patents
Music on-demand voice instruction recognition method and device based on knowledge graph Download PDFInfo
- Publication number
- CN116343771A CN116343771A CN202310241322.4A CN202310241322A CN116343771A CN 116343771 A CN116343771 A CN 116343771A CN 202310241322 A CN202310241322 A CN 202310241322A CN 116343771 A CN116343771 A CN 116343771A
- Authority
- CN
- China
- Prior art keywords
- music
- demand
- fuzzy
- content
- knowledge
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000004891 communication Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 3
- 241000616862 Belliella Species 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000007858 starting material Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L2015/088—Word spotting
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a music on-demand voice command recognition method and a device based on a knowledge graph, wherein the music on-demand voice command recognition method based on the knowledge graph comprises the following steps: acquiring a demand voice signal of a user on demand music; carrying out semantic analysis on the demand voice signals to obtain fuzzy demand characteristics; acquiring accurate music demand content from a preset music knowledge graph according to the fuzzy demand characteristics; generating search keywords according to the accurate music demand content or the fuzzy demand characteristics and the accurate music demand content; and acquiring the content to be played according to the search keyword. According to the invention, the voice on-demand instruction with the meaning sent by the user is identified by combining the music knowledge graph, the accurate music demand content is obtained according to the identification result, and then the music resource actually wanted to be heard by the user is obtained according to the accurate music demand content, so that the understanding capability and accuracy of the voice instruction indicating entity are improved, and the user experience is optimized.
Description
Technical Field
The invention relates to the technical field of voice command recognition, in particular to a music on-demand voice command recognition method based on a knowledge graph, a music on-demand voice command recognition device based on the knowledge graph and electronic equipment.
Background
With the development of artificial intelligence technology, more and more fields introduce voice as a new interaction mode, and people are gradually used to order songs, voices, audio books and the like through voice assistants. In order to meet the demand of users on demand, the current common implementation method is to identify medium type information and condition information in an NLU identification link, search the content meeting the condition by adopting a search interface of an entertainment application, and play the content to be played by the entertainment application. The NLU identifies the media type (e.g., song, audio program, video) of the on-demand content; for different media types, key information of the media is identified, such as information of singer name, song name, genre of song, etc. for song media, and information of presenter, album name, classification, etc. for voiced program media. For example, when the user says "XXX of play singer a", it can be recognized that: the media type is song, condition 1 is singer name a, condition 2 is song name XXX; through a certain search rule definition, the keyword XXX A is searched for in a search interface of the music application, a search result is obtained, and a song meeting the condition is played.
However, with the intelligent expectations of voice assistants, when a user requests a song, the voice assistant is often expected to understand what the user speaks like a human being in a relatively spoken expression. For example, the user may say "I want to hear the original version of song XXX" expecting the voice assistant to be able to play a satisfactory song. At present, NLU (non-line unit) identification in the field of music mainly identifies information such as song names, singer names, labels and the like, can not complement related information, is equivalent to only mechanically extracting keywords, and can only identify at present: the user intends to "listen to the song", the name of the song is "XXX", and the condition is "original version"; when a music application searches by using a search keyword 'XXX original singing edition', the obtained search results basically do not meet the search conditions, so that a technical scheme for accurately identifying a user voice instruction containing indicative information is needed to solve the problems.
Disclosure of Invention
The invention aims to provide a music on-demand voice command recognition method based on a knowledge graph and a music on-demand voice command recognition device based on the knowledge graph, so as to at least solve one technical problem.
The invention provides the following scheme:
a music on-demand voice instruction recognition method based on a knowledge graph comprises the following steps:
acquiring a demand voice signal of a user on demand music;
carrying out semantic analysis on the demand voice signals to obtain fuzzy demand characteristics;
acquiring accurate music demand content from a preset music knowledge graph according to the fuzzy demand characteristics;
generating search keywords according to the accurate music demand content or the fuzzy demand characteristics and the accurate music demand content;
and acquiring the content to be played according to the search keyword.
Optionally, the performing semantic analysis on the demand speech signal includes:
performing voice recognition on the required voice signal to obtain a voice recognition text;
and extracting the characteristics of the voice recognition text to obtain fuzzy demand characteristics.
Optionally, the preset music knowledge graph includes at least one first music knowledge node and at least one second music knowledge node, wherein the first music knowledge node has an association relationship with at least one second music knowledge node,
each music knowledge node includes one of the following:
song basic information, song related movie information, song related singer information;
the association relationship comprises one of a relationship between songs and singers and a relationship between songs and film and television works.
Optionally, the obtaining the accurate music demand content from the preset music knowledge graph according to the fuzzy demand feature includes:
matching the fuzzy demand characteristics with each music knowledge node in a preset music knowledge graph according to the fuzzy demand characteristics, so as to obtain first music knowledge nodes corresponding to the fuzzy demand characteristics;
and acquiring at least one of second music knowledge nodes with association relations with the first music knowledge nodes corresponding to the fuzzy demand features according to the association relations with the first music knowledge nodes corresponding to the fuzzy demand features and the fuzzy demand features, wherein the acquired second music knowledge nodes are the accurate music demand contents.
Optionally, the generating a search keyword according to the accurate music demand content or according to the fuzzy demand characteristics and the accurate music demand content:
combining the fuzzy demand characteristics with accurate music demand contents to obtain a combined search text;
and extracting the search keywords in the combined search text according to a preset search interface protocol.
Optionally, the obtaining the accurate music demand content from the preset music knowledge graph according to the fuzzy demand feature includes:
matching the fuzzy demand characteristics with each music knowledge node in a preset music knowledge graph according to the fuzzy demand characteristics, so as to obtain first music knowledge nodes corresponding to the fuzzy demand characteristics;
and acquiring one of second music knowledge nodes with association relation with the first music knowledge node corresponding to the fuzzy demand feature according to each association relation with the first music knowledge node corresponding to the fuzzy demand feature and the fuzzy demand feature, wherein the acquired second music knowledge nodes and the first music knowledge nodes form the accurate music demand content.
Optionally, the obtaining the content to be played according to the search keyword includes:
acquiring the content to be played meeting the search condition from a preset music database or the Internet according to the search keyword;
and adding the content to be played to a list to be played.
Optionally, the obtaining the content to be played meeting the search condition from a preset music database or the internet according to the search keyword includes:
obtaining the search type of the search keyword;
and acquiring the content to be played meeting the conditions from a preset music database or the Internet according to the search keywords and the search types of the search keywords.
The invention also provides a music on-demand voice instruction recognition device based on the knowledge graph, which comprises:
the system comprises a demand voice signal acquisition module, a control module and a control module, wherein the demand voice signal acquisition module is used for acquiring a demand voice signal of user on-demand music;
the fuzzy demand characteristic acquisition module is used for carrying out semantic analysis on the demand voice signals to obtain fuzzy demand characteristics;
the accurate music demand content acquisition module is used for acquiring accurate music demand content from a preset music knowledge graph according to the fuzzy demand characteristics;
the search keyword generation module is used for generating search keywords according to the accurate music demand content or the fuzzy demand characteristics and the accurate music demand content;
and the content to be played obtaining module is used for obtaining the content to be played according to the search keywords.
The invention provides an electronic device, comprising: the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory has stored therein a computer program which, when executed by the processor, causes the processor to perform the steps of the method as described above.
Compared with the prior art, the invention has the following advantages:
according to the method, the voice on-demand instruction with the fuzzy requirement sent by the user is identified, the identified voice identification text information is combined with the preset music knowledge graph to obtain accurate music requirement content, search keywords are generated through the accurate music requirement content, and then music resources actually wanted to be heard by the user are provided for the user according to the search keywords; according to the invention, the voice instruction with the meaning is identified and the indicated entity information is supplemented, so that the understanding capability and accuracy of the voice instruction with the fuzzy requirement, which is sent by the user, are improved, the intelligent degree of voice instruction identification and the accuracy of song playing are further enhanced, and the user experience is optimized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a music on demand voice command recognition method based on a knowledge graph according to an embodiment of the invention;
fig. 2 is a schematic diagram of a preset music knowledge graph of a music on demand voice command recognition method based on a knowledge graph according to an embodiment of the invention;
fig. 3 is a schematic structural diagram of a music on demand voice command recognition device based on a knowledge graph according to an embodiment of the invention;
fig. 4 is a block diagram of an electronic device in which the knowledge-graph-based music-on-demand voice command recognition method of the present invention may be implemented.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a flowchart of a music on demand voice command recognition method based on a knowledge graph according to an embodiment of the invention;
as shown in fig. 1, a music on demand voice instruction recognition method based on a knowledge graph includes:
step 1: acquiring a demand voice signal of a user on demand music;
step 2: carrying out semantic analysis on the demand voice signals to obtain fuzzy demand characteristics;
step 3: acquiring accurate music demand content from a preset music knowledge graph according to the fuzzy demand characteristics;
step 4: generating search keywords according to the accurate music demand content or according to the fuzzy demand characteristics and the accurate music demand content;
step 5: and obtaining the content to be played according to the search keywords.
According to the method, the voice on-demand instruction with the fuzzy requirement sent by the user is identified, the identified voice identification text information is combined with the preset music knowledge graph to obtain accurate music requirement content, search keywords are generated through the accurate music requirement content, and then music resources actually wanted to be heard by the user are provided for the user according to the search keywords; according to the invention, the voice instruction with the meaning is identified and the indicated entity information is supplemented, so that the understanding capability and accuracy of the voice instruction with the fuzzy requirement, which is sent by the user, are improved, the intelligent degree of voice instruction identification and the accuracy of song playing are further enhanced, and the user experience is optimized.
In this embodiment, performing semantic analysis on the demand speech signal includes:
performing voice recognition on the required voice signal to obtain a voice recognition text;
and extracting features of the voice recognition text to obtain fuzzy demand features.
In this embodiment, feature extraction of the speech recognition text includes:
acquiring a preset feature extraction model;
inputting the voice recognition text into a preset feature extraction model, and performing word segmentation operation, stop word removal operation and feature extraction operation on the voice recognition text.
In this embodiment, after a sound pickup device recognizes a user's required voice signal, voice recognition is performed to generate a voice recognition text, where the user's voice signal is "play an original singing version of belleville lake side"; the method comprises the steps of inputting a voice recognition text 'play Begals lake side' original singing version 'into a preset feature extraction model to perform word segmentation operation to obtain' play ',' Begals lake side ',' original singing version ', performing stop word removal operation on text information after word segmentation to obtain' play ',' Begals lake side ',' original singing version ', performing feature extraction on text after stop word removal operation, and recognizing fuzzy demand features, such as song=' Begals lake side ',' tags= 'original singing', wherein the fuzzy demand features are recognized, and the recognition is realized because the recognized tags= 'original singing' has no determined target in the system, and can only be obtained through matching of preset music knowledge patterns of the system so as to find the determined target of tags= 'original singing'.
It will be appreciated that the rules for feature extraction of speech recognition text are updated as the user requests the text, including but not limited to the following:
fig. 2 is a schematic diagram of a preset music knowledge graph of a music on demand voice command recognition method based on a knowledge graph according to an embodiment of the invention;
as shown in fig. 2, in this embodiment, the preset music knowledge graph includes at least one first music knowledge node and at least one second music knowledge node, where the first music knowledge node and the second music knowledge node have an association relationship, and the second music knowledge node has a function of generating a music file,
each music knowledge node includes one of the following:
song basic information, song related movie information, song related singer information;
the association relationship includes one of a relationship between a song and a singer and a relationship between a song and a movie work.
In this embodiment, the construction of the preset music knowledge graph mainly includes the following links:
(1) Song knowledge representation
(2) Selecting information sources for constructing knowledge graphs
(3) Information extraction
(4) Information deduplication
(5) Generating a knowledge graph
In this embodiment, a manner of predefining basic types and attributes is adopted to determine a representation manner of song information, and labeling information of a knowledge graph directly adopts the predefined representation manner.
Because the source of song information is wider and the complexity of knowledge is low, the song information can be obtained by adopting information source modes such as manual annotation, knowledge base containing song information for a third party, encyclopedia knowledge capture, website capture containing song information and the like.
The information extraction link adopts different processing methods aiming at different types of information sources, mainly reads corresponding information for manual annotation and a knowledge base containing song information of a third party, normalizes and expresses attributes and entities, and recognizes song information by natural language understanding for encyclopedia knowledge and information captured by a website containing the song information.
Because repeated information exists in the music information from different sources, the duplicate removal operation is performed before the music information is added to the preset music knowledge graph, and the efficiency is improved.
In this embodiment, the preset music knowledge graph is iteratively maintained according to the data source, including but not limited to the following parts:
the music knowledge node includes: singer name, word maker, composer, album name, song name, time, number, television play name, movie name;
the relationship map of the music knowledge node comprises points, edges and points, and the specific point, edge and point relationship can be set by adopting the following relationship:
the song basic information includes:
album name → album release time → time information;
album name → number of songs included → number of songs;
album name → album recorded song → specific song name;
song name → the song composer → the composer;
song name → the song composer → composer;
song name → song composer → composer;
the song-related movie information includes:
song name → song performance occasion → performance time of performance occasion → time;
TV title- & gt the TV theme song- & gt song title;
TV title- & gtthe title of the TV album- & gtsong title;
TV play name- & gtthe TV play tail song- & gtsong name;
the song-related singer information includes:
artist name → album to which album pertains → album name;
singer name- & gt singing single song- & gt song name;
song name → original singing of the song → singer name;
song name → turn-over of the song → singer name.
As shown in FIG. 2, the music knowledge nodes associated with the songs "Begale's lakeside" include basic information of the songs such as "still" →the album records the songs "→the heart rising moon", "Color Me Love
I always stay here, go back to former, get around, deep loving, stay on the road, begarter side, love, two am points, thank you, still, the album release time
2011-12-10, still, including song number-11, etc., song related movie information such as "centreless artist", tail song of the TV series "→" bella lake side ", song related singer information such as" bella lake side "→" original singing of the song → Li Jian ".
In this embodiment, obtaining accurate music demand content from a preset music knowledge graph according to the fuzzy demand features includes:
matching the fuzzy demand characteristics with each music knowledge node in a preset music knowledge graph according to the fuzzy demand characteristics, so as to obtain first music knowledge nodes corresponding to the fuzzy demand characteristics;
and acquiring at least one of second music knowledge nodes with association relations with the first music knowledge nodes corresponding to the fuzzy demand features according to the association relations with the first music knowledge nodes corresponding to the fuzzy demand features and the fuzzy demand features, wherein the acquired second music knowledge nodes are accurate music demand contents.
Specifically, when the fuzzy demand features have texts which can be used as search information, the method adopting the predefined rules judges that the user designates part of information, and the search is performed in a preset music knowledge graph according to the fuzzy demand features, and the search can be performed in the following cases:
when the fuzzy demand feature contains singer name information, the singer name information is searched through a preset music knowledge graph,
scene 1: there is "song", "tags = original singing" no "singer";
scene 2: there is "song", "tags = singing" no "singer";
for example, when the "song name" exists and the "original singing" exists in the fuzzy demand feature, the corresponding first music knowledge node in the preset music knowledge graph is searched according to the "song name", then the association relation of the first music knowledge node is searched according to the "original singing", the second music knowledge node corresponding to the "original singing" association relation of the first music knowledge node can be obtained through such an reasoning search mode, namely, which singer the "original singing" corresponding to the "song name" is, and finally the searched singer name is supplemented as singer.
When the fuzzy demand characteristic contains 'song name' information, searching the song name information through a preset music knowledge graph,
scene 1: with "singer" & with "time=latest" & with "type=song" & without "song";
scene 2: with "singer" & with "source" & without "song";
scene 3: there are "Source" & there are "tags = subject curves" & there are no "song";
scene 4: there were "Source" & there were "tags = headpiece" & there was no "song";
scene 5: there were "Source" & there was "tags = tail starter" & there was no "song";
scene 6: there is "singer" & there is "time" & there is no "source_type=album" & there is no "song".
For example, when the fuzzy demand features include "television play name" and "piece top song", the corresponding first music knowledge node in the preset music knowledge graph is searched according to the "television play name", then the association relationship of the first music knowledge node is searched according to the "piece top song", the second music knowledge node "song name" corresponding to the association relationship of the "piece top song" of the first music knowledge node can be obtained through such an reasoning search mode, and finally the searched song name is supplemented as "song".
When the fuzzy demand characteristic contains 'album name' information, the album name information is searched through a preset music knowledge graph,
scene 1: there is "singer" & there is "time" & there is "source_type=album" & there is no "album".
For example, when the fuzzy demand features include a "singer name" and a "latest album", a corresponding first music knowledge node in the preset music knowledge graph is searched according to the "singer name", and then the association relationship of the first music knowledge node is searched according to the "album" pointed by the "latest album", and a second music knowledge node "album name" with the latest release time is screened and supplemented as "album".
The above scenes can be adjusted and supplemented according to the actual use effect.
In one embodiment, the fuzzy requirement is characterized in that when song= "bellar lake side" and tags= "original singing", all relevant music knowledge nodes are searched according to the "bellar lake side" and the "original singing" in a preset music knowledge graph, the music information of the first music knowledge node which is obtained to be matched is "bellar lake side", and the association relation of the first music knowledge node is searched according to the "original singing", and finally the second music knowledge node "Li Jian" corresponding to the association relation is obtained.
In this embodiment, the search keyword is generated according to the accurate music demand content or according to the fuzzy demand feature and the accurate music demand content:
combining the fuzzy demand characteristics with the accurate music demand content to obtain a combined search text;
and extracting search keywords in the combined search text according to a preset search interface protocol.
In this embodiment, the preset search interface protocol includes:
the search type of the search keyword includes any one of singer name, album name, song name.
It can be understood that, after the combined search text is generated according to the fuzzy requirement characteristics and the accurate music requirement contents, the embodiment ignores redundant information which may affect the search result in the combined search text according to the search characteristics of the music playing software, and performs the operation of extracting the search keywords from the combined search text according to the search types of the search keywords.
For example, the user's demand voice signal is "play Zhou Jielun latest album", the obtained fuzzy demand characteristic is "singer= Zhou Jielun, tag=latest, the fuzzy demand characteristic is matched with a music knowledge node in a preset music knowledge graph, the accurate music demand content corresponding to the fuzzy demand characteristic is obtained, so that" album=maximum work "is obtained, the user can hear the album which is" maximum work ", but when we use the work which is" Zhou Jielun latest album maximum work "for searching, the most accurate corresponding content is not obtained, so that search keywords in the combined search text are extracted according to a preset search interface protocol to obtain search keywords, the set of preset search interface protocol iterates according to the condition of actually using data, and when one set of protocol does not meet the search characteristics of different music playing software, different music playing software are distinguished for adjustment.
The preset search interface protocol comprises the following steps:
(1) Singer name, song name information
When the combination search text comprises 'singer' & gt 'song', the search word is '[ song'
(singer), ignoring other information (other information in fuzzy demand characteristics, other music information matched with a preset music knowledge graph);
(2) Album name information
When the combined search text comprises 'album' and 'singer', the search word is 'album', other information (other information in the fuzzy demand characteristics and other music information matched with the preset music knowledge graph) is ignored.
According to the preset search interface protocol, the combined search text "Zhou Jielun is the most-great work of the latest album", and the search keyword obtained after extracting the search keyword from the combined search text is "Zhou Jielun the most-great work".
In another embodiment, the content to be played may be obtained by using the retrieved first music knowledge node and the second music knowledge node as search keywords, and specifically, in this embodiment, obtaining accurate music demand content in the preset music knowledge graph according to the fuzzy demand feature includes:
matching the fuzzy demand characteristics with each music knowledge node in a preset music knowledge graph according to the fuzzy demand characteristics, so as to obtain first music knowledge nodes corresponding to the fuzzy demand characteristics;
and acquiring one of the second music knowledge nodes with the association relation with the first music knowledge node corresponding to the fuzzy demand feature according to the association relation with the first music knowledge node corresponding to the fuzzy demand feature and the fuzzy demand feature, wherein the acquired second music knowledge node and the first music knowledge node form accurate music demand content.
Specifically, in this embodiment, the search keyword "bellar lake side Li Jian" may be generated according to the combination of the first music knowledge node "bellar lake side" and the second music knowledge node "Li Jian", and it may be understood that the search keyword generated according to the music knowledge node does not include redundant information, so that an operation of extracting the search keyword is not required for the search keyword, and the content to be played may be searched directly according to the search keyword.
In this embodiment, obtaining the content to be played according to the search keyword includes:
acquiring content to be played meeting search conditions from a preset music database or the Internet according to the search keywords;
and adding the content to be played to the to-be-played list.
In this embodiment, obtaining, from a preset music database or the internet, content to be played that satisfies the search condition according to the search keyword includes:
obtaining the search type of the search keyword;
and acquiring the content to be played meeting the conditions from a preset music database or the Internet according to the search keywords and the search types of the search keywords.
Specifically, when the obtained search keyword is "Zhou Jielun maximum work", the search type of the search keyword is obtained, the search type corresponding to the obtained search term is "Zhou Jielun" = [ singer ], the "maximum work" = [ album ], and the content to be played satisfying the condition may be obtained in the preset music database or the internet according to "Zhou Jielun" = [ singer ], and all the obtained songs contained in the album may be added to the playlist to be played.
Fig. 3 is a schematic structural diagram of a music on demand voice command recognition device based on a knowledge graph according to an embodiment of the invention;
as shown in fig. 3, the invention provides a music on demand voice command recognition device based on a knowledge graph, which comprises a demand voice signal acquisition module, a fuzzy demand characteristic acquisition module, an accurate music demand content acquisition module, a search keyword generation module and a content to be played acquisition module; wherein, the liquid crystal display device comprises a liquid crystal display device,
the demand voice signal acquisition module is used for acquiring demand voice signals of music on demand of users;
the fuzzy demand characteristic acquisition module is used for carrying out semantic analysis on the demand voice signals to acquire fuzzy demand characteristics;
the accurate music demand content acquisition module is used for acquiring accurate music demand content from a preset music knowledge graph according to the fuzzy demand characteristics;
the search keyword generation module is used for generating search keywords according to the accurate music demand content or according to the fuzzy demand characteristics and the accurate music demand content;
and the content to be played obtaining module is used for obtaining the content to be played according to the search keywords.
It should be noted that, although the system only discloses basic functional modules such as a required voice signal acquisition module, a fuzzy required feature acquisition module, an accurate music required content acquisition module, a search keyword generation module and a content to be played acquisition module, the present invention is not limited to the basic functional modules, and on the contrary, the present invention is intended to express that, on the basis of the basic functional modules, one or more functional modules can be added arbitrarily by a person skilled in the art to form an infinite number of embodiments or technical solutions, that is, the system is open rather than closed, and the protection scope of the claims of the present invention is not limited to the basic functional modules disclosed above because the present embodiment only discloses individual basic functional modules.
FIG. 4 is a block diagram of an electronic device in which the knowledge-based music-on-demand voice command recognition method of the present invention can be implemented
As shown in fig. 4, the electronic device includes: the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; the memory stores a computer program which, when executed by the processor, causes the processor to perform the steps of the knowledge-graph-based music-on-demand voice instruction recognition method.
The present application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which when run on the electronic device causes the electronic device to perform the steps of a knowledge-graph-based music-on-demand voice instruction recognition method.
The communication bus mentioned above for the electronic devices may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The electronic device includes a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on top of the operating system. The hardware layer includes hardware such as a central processing unit (CPU, central Processing Unit), a memory management unit (MMU, memory Management Unit), and a memory. The operating system may be any one or more computer operating systems that implement electronic device control via processes (processes), such as a Linux operating system, a Unix operating system, an Android operating system, an iOS operating system, or a windows operating system, etc. In addition, in the embodiment of the present invention, the electronic device may be a handheld device such as a smart phone, a tablet computer, or an electronic device such as a desktop computer, a portable computer, which is not particularly limited in the embodiment of the present invention.
The execution body controlled by the electronic device in the embodiment of the invention can be the electronic device or a functional module in the electronic device, which can call a program and execute the program. The electronic device may obtain firmware corresponding to the storage medium, where the firmware corresponding to the storage medium is provided by the vendor, and the firmware corresponding to different storage media may be the same or different, which is not limited herein. After the electronic device obtains the firmware corresponding to the storage medium, the firmware corresponding to the storage medium can be written into the storage medium, specifically, the firmware corresponding to the storage medium is burned into the storage medium. The process of burning the firmware into the storage medium may be implemented by using the prior art, and will not be described in detail in the embodiment of the present invention.
The electronic device may further obtain a reset command corresponding to the storage medium, where the reset command corresponding to the storage medium is provided by the provider, and the reset commands corresponding to different storage media may be the same or different, which is not limited herein.
At this time, the storage medium of the electronic device is a storage medium in which the corresponding firmware is written, and the electronic device may respond to a reset command corresponding to the storage medium in which the corresponding firmware is written, so that the electronic device resets the storage medium in which the corresponding firmware is written according to the reset command corresponding to the storage medium. The process of resetting the storage medium according to the reset command may be implemented in the prior art, and will not be described in detail in the embodiments of the present invention.
For convenience of description, the above devices are described as being functionally divided into various units and modules. Of course, the functions of each unit, module, etc. may be implemented in one or more pieces of software and/or hardware when implementing the present application.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
For the purposes of simplicity of explanation, the methodologies are shown and described as a series of acts, it is to be understood and appreciated by one of ordinary skill in the art that the methodologies are not limited by the order of acts, as some acts may, in accordance with the methodologies, take place in other order or concurrently. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.
From the above description of embodiments, it will be apparent to those skilled in the art that the present application may be implemented in software plus a necessary general purpose hardware platform. Based on such understanding, the technical solutions of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server or a network device, etc.) to perform the methods described in the embodiments or some parts of the embodiments of the present application.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (10)
1. A music on-demand voice instruction recognition method based on a knowledge graph is characterized by comprising the following steps:
acquiring a demand voice signal of a user on demand music;
carrying out semantic analysis on the demand voice signals to obtain fuzzy demand characteristics;
acquiring accurate music demand content from a preset music knowledge graph according to the fuzzy demand characteristics;
generating search keywords according to the accurate music demand content or the fuzzy demand characteristics and the accurate music demand content;
and acquiring the content to be played according to the search keyword.
2. The knowledge-based music-on-demand voice instruction recognition method of claim 1, wherein the performing semantic analysis on the demand voice signal comprises:
performing voice recognition on the required voice signal to obtain a voice recognition text;
and extracting the characteristics of the voice recognition text to obtain fuzzy demand characteristics.
3. The music on-demand voice instruction recognition method based on a knowledge graph of claim 2, wherein the preset music knowledge graph comprises at least one first music knowledge node and at least one second music knowledge node, wherein the first music knowledge node has an association relationship with the at least one second music knowledge node,
each music knowledge node includes one of the following:
song basic information, song related movie information, song related singer information;
the association relationship comprises one of a relationship between songs and singers and a relationship between songs and film and television works.
4. The knowledge-based music-on-demand voice instruction recognition method of claim 3, wherein the obtaining accurate music demand content in a preset music knowledge graph according to the fuzzy demand features comprises:
matching the fuzzy demand characteristics with each music knowledge node in a preset music knowledge graph according to the fuzzy demand characteristics, so as to obtain first music knowledge nodes corresponding to the fuzzy demand characteristics;
and acquiring at least one of second music knowledge nodes with association relations with the first music knowledge nodes corresponding to the fuzzy demand features according to the association relations with the first music knowledge nodes corresponding to the fuzzy demand features and the fuzzy demand features, wherein the acquired second music knowledge nodes are the accurate music demand contents.
5. The knowledge-based music-on-demand voice instruction recognition method of claim 4, wherein the generating search keywords based on the exact music demand content or based on the fuzzy demand features and exact music demand content:
combining the fuzzy demand characteristics with accurate music demand contents to obtain a combined search text;
and extracting the search keywords in the combined search text according to a preset search interface protocol.
6. The knowledge-based music-on-demand voice instruction recognition method of claim 3, wherein the obtaining accurate music demand content in a preset music knowledge graph according to the fuzzy demand features comprises:
matching the fuzzy demand characteristics with each music knowledge node in a preset music knowledge graph according to the fuzzy demand characteristics, so as to obtain first music knowledge nodes corresponding to the fuzzy demand characteristics;
and acquiring one of second music knowledge nodes with association relation with the first music knowledge node corresponding to the fuzzy demand feature according to each association relation with the first music knowledge node corresponding to the fuzzy demand feature and the fuzzy demand feature, wherein the acquired second music knowledge nodes and the first music knowledge nodes form the accurate music demand content.
7. The knowledge-graph-based music-on-demand voice instruction recognition method of claim 1, wherein the obtaining the content to be played according to the search keyword comprises:
acquiring the content to be played meeting the search condition from a preset music database or the Internet according to the search keyword;
and adding the content to be played to a list to be played.
8. The knowledge-graph-based music-on-demand voice instruction recognition method of claim 7, wherein the obtaining the content to be played meeting the search condition from a preset music database or the internet according to the search keyword comprises:
obtaining the search type of the search keyword;
and acquiring the content to be played meeting the conditions from a preset music database or the Internet according to the search keywords and the search types of the search keywords.
9. The music on-demand voice instruction recognition device based on the knowledge graph is characterized by comprising:
the system comprises a demand voice signal acquisition module, a control module and a control module, wherein the demand voice signal acquisition module is used for acquiring a demand voice signal of user on-demand music;
the fuzzy demand characteristic acquisition module is used for carrying out semantic analysis on the demand voice signals to obtain fuzzy demand characteristics;
the accurate music demand content acquisition module is used for acquiring accurate music demand content from a preset music knowledge graph according to the fuzzy demand characteristics;
the search keyword generation module is used for generating search keywords according to the accurate music demand content or the fuzzy demand characteristics and the accurate music demand content;
and the content to be played obtaining module is used for obtaining the content to be played according to the search keywords.
10. An electronic device, comprising: the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory has stored therein a computer program which, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310241322.4A CN116343771A (en) | 2023-03-14 | 2023-03-14 | Music on-demand voice instruction recognition method and device based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310241322.4A CN116343771A (en) | 2023-03-14 | 2023-03-14 | Music on-demand voice instruction recognition method and device based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116343771A true CN116343771A (en) | 2023-06-27 |
Family
ID=86888808
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310241322.4A Pending CN116343771A (en) | 2023-03-14 | 2023-03-14 | Music on-demand voice instruction recognition method and device based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116343771A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113823281A (en) * | 2020-11-24 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Voice signal processing method, device, medium and electronic equipment |
-
2023
- 2023-03-14 CN CN202310241322.4A patent/CN116343771A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113823281A (en) * | 2020-11-24 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Voice signal processing method, device, medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220214775A1 (en) | Method for extracting salient dialog usage from live data | |
| US9824150B2 (en) | Systems and methods for providing information discovery and retrieval | |
| US8321414B2 (en) | Hybrid audio-visual categorization system and method | |
| CN109165302B (en) | Multimedia file recommendation method and device | |
| TWI553494B (en) | Multi-modal fusion based Intelligent fault-tolerant video content recognition system and recognition method | |
| EP3579140A1 (en) | Method and apparatus for processing video | |
| US9972340B2 (en) | Deep tagging background noises | |
| US20120131060A1 (en) | Systems and methods performing semantic analysis to facilitate audio information searches | |
| WO2018045646A1 (en) | Artificial intelligence-based method and device for human-machine interaction | |
| CN107145509B (en) | Information searching method and equipment thereof | |
| US20220093082A1 (en) | Automatically Adding Sound Effects Into Audio Files | |
| CN109710799B (en) | Voice interaction method, medium, device and computing equipment | |
| CN108153875B (en) | Corpus processing method and device, intelligent sound box and storage medium | |
| CN108710653B (en) | On-demand method, device and system for reading book | |
| JP2019091416A5 (en) | ||
| CN116343771A (en) | Music on-demand voice instruction recognition method and device based on knowledge graph | |
| JP2023027749A (en) | Method and apparatus for determining broadcasting style, equipment, and computer storage medium | |
| CN114661939A (en) | Song matching method, medium, device and computing equipment | |
| CN114547373A (en) | Method for intelligently identifying and searching programs based on audio | |
| CN113407775B (en) | Video searching method and device and electronic equipment | |
| CN115329125A (en) | Song skewer burning splicing method and device | |
| US20200250220A1 (en) | Methods and Apparatuses for Enhancing User Interaction with Audio and Visual Data Using Emotional and Conceptual Content | |
| CN115602154B (en) | Audio identification method, device, storage medium and computing equipment | |
| Kothawade et al. | Retrieving instructional video content from speech and text information | |
| TWI220206B (en) | System and method for searching a single word in accordance with speech |
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 |