CN115658914A - Music knowledge map construction method, electronic equipment, storage medium and air conditioner - Google Patents

Abstract

The application relates to a music knowledge graph construction method, electronic equipment, a storage medium and an air conditioner, wherein the method comprises the following steps: acquiring a target music attribute of target music according to a target scene corresponding to a target air conditioner type, wherein the target music is music of an air conditioner type to be associated, and the target air conditioner type is an air conditioner type to be determined whether to be matched with the target music; determining a target matching result according to the target music attribute, wherein the target matching result is used for indicating whether the target air conditioner type is matched with the target music; and associating the air conditioner type for the target music according to the target matching result to obtain the music knowledge graph. The method and the device solve the technical problem that music in adaptive scenes cannot be recommended to the user aiming at different use scenes of the air conditioner by directly using universal music resources for music recommendation.

Description

Music knowledge map construction method, electronic equipment, storage medium and air conditioner

Technical Field

The application relates to the technical field of intelligent air conditioners, in particular to a music knowledge graph construction method, electronic equipment, a storage medium and an air conditioner.

Background

With the development of smart homes, many smart home devices currently have a music playing function, such as a voice air conditioner. Generally, the music playing process of the voice air conditioner includes: the user's voice command is first speech recognized and the recognized text is then used to request the music interface of the third party. The intelligent household equipment aims at specific crowds and environments in the house, music recommendation is directly performed by using general music resources, a large number of cases that recommendation results are not matched with user requirements exist, and music recommendation in adaptive scenes cannot be achieved for users according to different use scenes of the air conditioner.

Aiming at the problem that music recommendation is carried out by directly using general music resources in the related technology and music of adaptive scenes cannot be recommended for users aiming at different use scenes of an air conditioner, an effective solution is not provided at present.

Disclosure of Invention

The application provides a music knowledge graph construction method, electronic equipment, a storage medium and an air conditioner, which at least solve the technical problem that music in adaptive scenes cannot be recommended to a user for different use scenes of the air conditioner by directly using universal music resources to perform music recommendation in related technologies.

According to an aspect of an embodiment of the present application, there is provided a music knowledge base construction method, including: acquiring a target music attribute of target music according to a target scene corresponding to a target air conditioner type, wherein the target music is music of an air conditioner type to be associated, and the target air conditioner type is an air conditioner type to be determined whether to be matched with the target music; determining a target matching result according to the target music attribute, wherein the target matching result is used for indicating whether the type of the target air conditioner is matched with the target music; and associating the air conditioner type for the target music according to the target matching result to obtain the music knowledge graph.

According to another aspect of the embodiments of the present application, there is also provided an air conditioner music playing method, including: acquiring a target voice instruction, wherein the target voice instruction is used for requesting a specified air conditioner to play music; performing semantic analysis on the target voice command to obtain a semantic analysis result; under the condition that the semantic analysis result does not contain the name of the music, determining the music to be played of the specified air conditioner from preset music in a music knowledge graph according to the specified air conditioner type to which the specified air conditioner belongs, wherein all air conditioner types related to the preset music comprise the specified air conditioner type, and the music knowledge graph is constructed according to the music knowledge graph construction method; and instructing a specified music player to play the music to be played, wherein the specified music player is a music player associated with the specified air conditioner.

According to another aspect of the embodiments of the present application, there is also provided a music knowledge base constructing apparatus, including: the acquisition module is used for acquiring the target music attribute of the target music according to the target scene corresponding to the target air conditioner type, wherein the target music is the music of the air conditioner type to be associated, and the target air conditioner type is the air conditioner type to be determined whether to be matched with the target music; the matching module is used for determining a target matching result according to the target music attribute, wherein the target matching result is used for indicating whether the type of the target air conditioner is matched with the target music; and the association module is used for associating the air conditioner type with the target music according to the target matching result to obtain the music knowledge graph.

According to another aspect of the embodiments of the present application, there is also provided an electronic device, including: the system 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 is used for storing a computer program; the processor, when executing the computer program, is configured to implement the method according to any of the preceding claims.

According to an aspect of the application, there is provided a computer readable storage medium comprising a stored program, wherein the program when executed performs the method of any of the preceding claims.

According to another aspect of the embodiment of the application, an air conditioner is further provided, and the air conditioner comprises the electronic equipment.

In the embodiment of the application, a target music attribute of target music is obtained according to a target scene corresponding to a target air conditioner type, wherein the target music is music of an air conditioner type to be associated, and the target air conditioner type is an air conditioner type to be determined whether to be matched with the target music; determining a target matching result according to the target music attribute, wherein the target matching result is used for indicating whether the type of the target air conditioner is matched with the target music; the method comprises the steps of associating an air conditioner type with target music according to a target matching result to obtain a music knowledge graph mode, determining whether music is matched with the target air conditioner type or not by obtaining music attributes which need to be considered in a target scene corresponding to the target air conditioner type, associating the air conditioner type with the music according to the matching result, and associating the air conditioner type with the music in the obtained music knowledge graph, so that the use scene of the air conditioner can be adapted when music is recommended according to the music knowledge graph, more accurate music recommendation service is provided for users, and the technical problem that the music which is adapted to the use scene of the air conditioner cannot be recommended for the users according to different use scenes of the air conditioner when the music is recommended by directly using universal music resources in the related technology is solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

FIG. 1 is a schematic diagram of a hardware environment for a music knowledge graph construction method according to an embodiment of the present application;

FIG. 2 is a flow diagram of an alternative music knowledge base construction method according to an embodiment of the present application;

FIG. 3 is a flow diagram of an alternative music knowledge map construction method according to an embodiment of the present application;

FIG. 4 is a schematic diagram of an alternative music knowledge map construction apparatus according to an embodiment of the present application; and the number of the first and second groups,

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

First, partial nouns or terms appearing in the description of the embodiments of the present application are applicable to the following explanations:

knowledge graph: is a structured semantic knowledge base used for describing concepts and their interrelations in the physical world in symbolic form. The knowledge graph is converted into a simple and clear triple of entities, relations and entities by effectively processing, processing and integrating the data of the complicated document, and finally a great deal of knowledge is aggregated, so that the quick response and reasoning of the knowledge are realized.

The attributes are as follows: attributes are entity-specific labels that may represent what the entity itself owns or may represent relationships between the entity and other entities.

According to an aspect of an embodiment of the present application, an embodiment of a method for music knowledge graph construction is provided.

Alternatively, in the present embodiment, the above music knowledge base construction method may be applied to a hardware environment constituted by the terminal 101 and the server 103 as shown in fig. 1. As shown in fig. 1, a server 103 is connected to a terminal 101 through a network, which may be used to provide a music knowledge graph building service for the terminal or a client installed on the terminal, and a database 105 may be provided on the server or separately from the server, and may be used to provide a data storage service for the server 103, and the network includes but is not limited to: the terminal 101 is not limited to a PC, a mobile phone, a tablet computer, and the like. The music knowledge graph construction method according to the embodiment of the present application may be executed by the server 103, by the terminal 101, or by both the server 103 and the terminal 101. The terminal 101 executing the music knowledge base construction method according to the embodiment of the present application may be executed by a client installed thereon. The following description will be given taking an example of a music knowledge base construction method executed on a server according to an embodiment of the present application.

Fig. 2 is a flowchart of an alternative music knowledge base construction method according to an embodiment of the present application, which may include the following steps, as shown in fig. 2:

step S104, acquiring target music attributes of target music according to a target scene corresponding to a target air conditioner type, wherein the target music is music of an air conditioner type to be associated, and the target air conditioner type is an air conditioner type to be determined whether to be matched with the target music;

step S106, determining a target matching result according to the target music attribute, wherein the target matching result is used for indicating whether the type of the target air conditioner is matched with the target music;

and step S108, associating the air conditioner type with the target music according to the target matching result to obtain the music knowledge graph.

Through the steps S104 to S108, whether the music is matched with the target air conditioner type or not is determined by acquiring the music attribute which needs to be considered in the target scene corresponding to the target air conditioner type, and the air conditioner type is associated with the music according to the matching result, so that a music knowledge graph is obtained; the air conditioners with different air conditioner types have different use scenes, and the music is associated with the air conditioner type in the music knowledge graph, namely the use scene adapted to the music is indicated, so that the use scene of the air conditioner can be adapted when the music is recommended according to the music knowledge graph, more accurate music recommendation service is provided for users, and the technical problem that the music with the adapted scene can not be recommended for the users according to the different use scenes of the air conditioners by directly using universal music resources in the related technology is solved.

In the technical solution provided in step S104, the server obtains a target music attribute of the target music according to a target scene corresponding to the target air conditioner type.

The musical attributes of the music may include an emotional attribute, a lyric attribute, a style attribute, a song list attribute, a time attribute, a singer attribute, a list attribute, and the like, wherein the emotional attribute is an emotional type of the music, the lyric attribute is a lyric text of the music, the style attribute is a music style type of the music, the list attribute is a list name of the list where the music is located, the time attribute is a release time of the music, the singer attribute is a name of the singer of the music, and the list attribute is a list name where the music is located. The music has music attributes that are not limited by the above examples, and may be more or less.

For different use scenes of the air conditioner, different music attributes need to be analyzed to judge whether the music can be adapted to the use scenes of the air conditioner. The target scene corresponding to the target air conditioner type is a use scene of the air conditioner of the target air conditioner type.

The target air conditioner type air conditioner is used to provide a music playing function in a target scene.

The target music can be any music to be associated with the air conditioner type in the music library.

The music attribute can comprise an emotional attribute, a lyric attribute, a style attribute, a song list attribute, a time attribute, a singer attribute, a song list attribute and the like, wherein the emotional attribute is the emotional type of music, the lyric attribute is the lyric text of the music, the style attribute is the music style type of the music, the song list attribute is the name of the song list where the music is located, the time attribute is the release time of the music, the singer attribute is the name of the singer of the music, and the song list attribute is the name of the song list where the music is located. The type of music attribute is not limited by the above examples and may be more or less.

In different air conditioner use scenes, a user has different music playing requirements, whether music is matched with the air conditioner type is judged, different judgment bases are provided for different air conditioner types, therefore, the music playing requirements of different scenes need to be mined, music attributes which are used as judgment bases need to be extracted are determined according to the music playing requirements, then, according to a target scene corresponding to the target air conditioner type, the music attributes corresponding to the target scene are determined, and according to the music attributes corresponding to the target scene, the target music attributes of target music are obtained. For example, if the target scene is a guest scene, and the music attribute corresponding to the target scene is an emotion attribute and a style attribute, acquiring a target emotion attribute and a target style attribute of the target music, where the target music attribute includes the target emotion attribute and the target style attribute, the target emotion attribute is the emotion attribute of the target music, and the target style attribute is the style attribute of the target music. For another example: (1) The target air conditioner type corresponds to a guest-meeting scene, and the music playing requirement of the user in the guest-meeting scene is generally as follows: music cannot be too noisy and the emotion of the music cannot be too negative. Whether the music is noisy or not and whether the emotion is negative or not can be judged according to the style attribute and the emotion attribute of the music respectively, and then the target music attribute can be a target style attribute and a target emotion attribute under the condition that the target scene is a guest-meeting scene. (2) The target air conditioner type corresponds to a rest scenario, and the music playing requirement of the user in the rest scenario is generally as follows: quiet, soothing, music to aid sleep. Whether the music meets the playing requirements of the user in the rest scene or not can be judged according to the attribute of the song list of the music, whether the music is in the sleep song list or not can be determined according to the name of the song list where the music is located, and then the attribute of the target music can be the attribute of the target song list under the condition that the target scene is the rest scene. (3) The target air conditioner type corresponds to a child usage scenario, and the music playing requirement of a user in the child usage scenario is generally as follows: positively upward music. Whether the music meets the user playing requirements in the use scene of the children or not can be judged according to the emotion attribute and the lyric attribute of the music, and then the target music attribute can be a target emotion attribute and a target lyric attribute under the condition that the target scene is the use scene of the children. (4) The target air conditioner type corresponds to the old people use scene, and the music playing requirement of the user under the old people use scene is generally as follows: classic music that matches the background of the age in which the elderly grow. Whether the music meets the playing requirements of users in the old people use scene or not can be judged according to the attribute and the time attribute of the song list of the music, whether the music is classical song list or not can be determined according to the name of the song list where the music is located, whether the music is in the time range which is consistent with the era background of the growth of the old people or not can be determined according to the time attribute, and then the target music attribute can be target song list attribute or target time attribute under the condition that the target scene is the old people use scene.

There are various ways to obtain the target music attribute of the target music, including but not limited to the following: (1) obtaining from a music database of a music platform; (2) obtaining from an existing general knowledge graph; and (3) acquiring from the network music resource.

As an alternative embodiment, in step S104, obtaining the target music attribute of the target music according to the target scene corresponding to the target air conditioner type, the method may include the following steps:

step S1041, when the target air conditioner type is the first air conditioner type corresponding to the attended scene, obtaining a target emotion attribute and a target style attribute of the target music, where the target music attribute includes the target emotion attribute and the target style attribute.

Optionally, in this embodiment, in step S106, determining a target matching result according to the target music attribute may include the following steps:

step S1061, when a first preset requirement is met, determining that the target matching result is that the first air conditioner type is not matched with the target music, wherein the first preset requirement is that the target emotion attribute indicates that the emotion type of the target music is a negative emotion type, or the target style attribute indicates that the music style of the target music is a noisy music style.

The first air conditioner type is an air conditioner type corresponding to a meeting scene, the air conditioner of the first air conditioner type is an air conditioner which is usually used in the meeting scene, the division mode of the air conditioner type is not limited, the first air conditioner type can also comprise a plurality of air conditioner types, for example, (1) the air conditioner type is divided into a cabinet air conditioner, a hanging air conditioner and the like, if the cabinet air conditioner is usually installed in a meeting room and a living room and used in the meeting scene, the first air conditioner type can be a cabinet air conditioner type; (2) The air-conditioning types may also be classified into a living room air-conditioning type, a bedroom air-conditioning type, a meeting room air-conditioning type, a washroom air-conditioning type, and the like, wherein the living room air-conditioning type and the meeting room air-conditioning type are often used in a meeting scene, and the first air-conditioning type may also be the living room air-conditioning type and the meeting room air-conditioning type.

As an alternative embodiment, in step S104, obtaining the target music attribute of the target music according to the target scene corresponding to the target air conditioner type may include the following steps:

step S1042, under the condition that the type of the target air conditioner is a second air conditioner type corresponding to the rest scene, obtaining the target song list attribute of the target music, wherein the target music attribute comprises the target song list attribute which is used for indicating the song list name of the song list where the target music is located;

optionally, in this embodiment, in step S106, determining a target matching result according to the target music attribute may include the following steps:

step S1062, when the attribute of the target song list indicates that the song list name of the song list in which the target music is located contains a preset keyword, determining that the target matching result is that the second air conditioner type is matched with the target music, wherein the preset keyword comprises a vocabulary associated with a rest scene.

The second air conditioner type is an air conditioner type corresponding to the rest scene, the air conditioner of the second air conditioner type is an air conditioner which is generally used in the rest scene, the division manner of the air conditioner types is not limited, the second air conditioner type may also include a plurality of air conditioner types, for example, the second air conditioner type may be a hanging air conditioner type, and may also be a bedroom air conditioner type.

As an alternative embodiment, in step S104, obtaining the target music attribute of the target music according to the target scene corresponding to the target air conditioner type, the method may include the following steps:

step S1043, under the condition that the target air conditioner type is a third air conditioner type corresponding to the usage scene of the children, acquiring a target emotion attribute and a target lyric attribute of the target music, wherein the target music attribute comprises the target emotion attribute and the target lyric attribute;

optionally, in this embodiment, in step S106, determining a target matching result according to the target music attribute may include the following steps:

step S1063, when a second preset requirement is met, determining that the target matching result is that the third air conditioner type is not matched with the target music, where the second preset requirement is: the target emotion attribute indicates that the emotion type of the target music is a negative emotion type, or the target lyric attribute indicates that the lyric text of the target music contains preset negative words.

The third air conditioner type is an air conditioner type corresponding to a child use scene, the air conditioner of the third air conditioner type is an air conditioner commonly used in the child use scene, a user in the child use scene is a child generally, the air conditioner type is not limited in dividing manner, the third air conditioner type may also include a plurality of air conditioner types, for example, the third air conditioner type may be a child air conditioner type, and may also be a child room air conditioner type.

As an alternative embodiment, in step S104, obtaining the target music attribute of the target music according to the target scene corresponding to the target air conditioner type, the method may include the following steps:

and step S1044, acquiring a target song list attribute and a target time attribute of the target music under the condition that the target air conditioner type is a fourth air conditioner type corresponding to the usage scene of the old people, wherein the target music attribute comprises the target song list attribute and the target time attribute, the target song list attribute is used for indicating the song list name of the target music, and the target time attribute is used for indicating the issuing time of the target music.

Optionally, in this embodiment, in the step S106, determining the target matching result according to the target music attribute may include the following steps:

step S1064, when a third preset requirement is met, determining that the target matching result is that the fourth air conditioner type is matched with the target music, where the third preset requirement is: the target song list attribute indicates that the song list name of the song list where the target music is located contains a specified keyword, or the target time attribute indicates that the release time of the target music is within a preset time range.

The fourth air conditioner type is an air conditioner type corresponding to a scene of use of the elderly people, the air conditioner of the fourth air conditioner type is an air conditioner which is usually used in the scene of use of the elderly people, a user in the scene of use of the elderly people is usually the elderly people, and the division manner of the air conditioner types is not limited, and the fourth air conditioner type may also include a plurality of air conditioner types, for example, the third air conditioner type may be a senior citizen air conditioner type or an elderly room air conditioner type.

As an alternative embodiment, step S108, associating the air conditioner type for the target music according to the target matching result to obtain the music knowledge graph, may include the following steps:

and step S1081, associating the specified target air conditioner type in all the target air conditioner types with the target music according to each target matching result to obtain a music knowledge graph, wherein the specified target air conditioner type is the air conditioner type matched with the target music.

As an alternative embodiment, after the music knowledge base is obtained by associating the air conditioner type for the target music according to the target matching result in step S108, the method may further include the following steps:

step S1091, obtaining a target voice instruction, wherein the target voice instruction is used for requesting an appointed air conditioner to play music;

step S1092, performing semantic analysis on the target voice command to obtain a semantic analysis result;

step S1093, determining music to be played of the designated air conditioner from preset music in a music knowledge graph according to the designated air conditioner type to which the designated air conditioner belongs under the condition that the semantic analysis result does not contain the music name, wherein all air conditioner types related to the preset music comprise the designated air conditioner type, and the music knowledge graph is constructed according to the music knowledge graph construction method in the step;

step S1094, the designated music player is instructed to play the music to be played, wherein the designated music player is the music player associated with the designated air conditioner.

The above semantic analysis process for the target voice instruction can be implemented by using technologies such as a voice recognition technology (ASR) and a natural language processing technology. And the semantic analysis result is used for expressing the meaning of the target voice instruction obtained after the target voice instruction is analyzed.

Whether the semantic analysis result contains the music name or not means whether a specific music name can be obtained or not after the semantic analysis is carried out on the voice command.

For example, if the semantic analysis result is "request to play music", it indicates that the semantic analysis result does not include a music name. If the semantic analysis result is "request to play" song by joy ", it indicates that the semantic analysis result includes the music name song by joy".

As an optional embodiment, step S104 is to obtain a target music attribute of a target music according to a target scene corresponding to a target air conditioner type, and may include the following steps:

step S202, acquiring all candidate music attributes of target music in the general knowledge base, wherein the target music is music of an air conditioner type to be associated in the general knowledge base;

step S204, according to a target scene corresponding to a target air conditioner type in all air conditioner types, extracting a target music attribute from all candidate music attributes of the target music, wherein the target air conditioner type is an air conditioner type to be determined whether the target music is matched with the target music, and an air conditioner of the target air conditioner type is used for providing a music playing function in the target scene.

Optionally, in this embodiment, in step S108, associating the air conditioner type with the target music according to the target matching result to obtain the music knowledge base, the steps may include:

and step S208, associating the air conditioner type for the target music in the general knowledge graph according to the target matching result to obtain the music knowledge graph.

Through the steps S202 to S204 and S208, it is determined whether the music matches each air conditioner type according to the music attribute of the music in the general knowledge base and the usage scenario corresponding to the air conditioner of each air conditioner type, and the air conditioner type is associated with the music in the general knowledge base according to the matching result, so that the usage scenario of the air conditioner can be adapted when music recommendation is performed according to the music knowledge base, a more accurate music recommendation service is provided for a user, and the technical problem that the general knowledge base cannot implement the music recommendation of the adapted scenario for the user according to different usage scenarios of the air conditioner in the related art is solved.

In the technical solution provided in step S202, the server obtains all candidate music attributes of the target music in the generic knowledge base, where the target music is music to be associated with an air conditioner type in the generic knowledge base, and the music associated with the air conditioner type is used to indicate an air conditioner type to which the music is applicable.

The general knowledge graph refers to a knowledge graph which comprises attributes of music and music names, singers, lyrics and the like and can be used for music knowledge question answering, music search recommendation, music question answering service and the like. The music attribute in the general knowledge map may include an emotion attribute, a lyric attribute, a style attribute, a song list attribute, a time attribute, a singer attribute, a list attribute, and the like, wherein the emotion attribute is an emotion type of music, the lyric attribute is a lyric text of the music, the style attribute is a music style type of the music, the list attribute is a list name of the list where the music is located, the time attribute is a release time of the music, the singer attribute is a list name of the music, and the list attribute is a list name where the music is located. The musical attributes contained in the generic knowledge graph are not limited by the above examples and may be more or less.

The candidate music attribute is an attribute used for constructing the music knowledge graph in all music attributes of the target music in the common knowledge graph, and all the candidate music attributes can be all the music attributes of the target music in the common knowledge graph or part of the music attributes of the target music in the common knowledge graph. The candidate music attributes may be attributes associated with the scene requirements, such as an emotion attribute, a lyric attribute, a style attribute, a song menu attribute, a time attribute, and the like.

Generic knowledge graph the target music may be any music in the generic knowledge graph that is to be associated with an air conditioner type.

Optionally, in this embodiment, different air conditioner types correspond to different usage scenarios, and the air conditioner type associated with the music is used to indicate that the music can be used to be played in the usage scenario of the air conditioner type.

For example, if the air conditioner type associated with music a is air conditioner type a, it indicates that music a can be used for playing in the usage scenario of the air conditioner of air conditioner type a.

In the technical solution provided in step S204, the server extracts a target music attribute from all candidate music attributes of the target music according to a target scene corresponding to a target air conditioner type of all air conditioner types, where the target air conditioner type is an air conditioner type to be determined whether to match the target music, and an air conditioner of the target air conditioner type is used to provide a music playing function in the target scene.

Air conditioners of different air conditioner types have different use scenes, for example, a cabinet air conditioner is generally installed in a living room, then the cabinet air conditioner can correspond to a guest-meeting scene, an on-hook air conditioner is generally installed in a bedroom, then the on-hook air conditioner can correspond to a rest scene, and if the child air conditioner is generally installed in a child room, then the child air conditioner can correspond to a child use scene, a senior citizen air conditioner is generally installed in a room of an elderly person, and then the senior citizen air conditioner can correspond to an elderly person use scene.

The above-mentioned target air conditioner type may be any one of all air conditioner types to be determined whether to match the target music.

In different air conditioner use scenes, a user has different music playing requirements, whether music is matched with the air conditioner type is judged, different judgment bases are provided for different air conditioner types, therefore, the music playing requirements of different scenes need to be mined, music attributes which are used as judgment bases need to be extracted are determined according to the music playing requirements, and then target music attributes are extracted from all candidate music attributes of target music according to target scenes corresponding to target air conditioner types in all air conditioner types. The target music attribute is a music attribute associated with the music playing requirement of the user in the target scene among all the candidate music attributes.

For example: (1) The target air conditioner type corresponds to a guest-meeting scene, and the music playing requirement of the user in the guest-meeting scene is generally as follows: the music cannot be too noisy and the emotion of the music cannot be too negative. Whether the music is noisy or not and whether the emotion is negative or not can be judged according to the style attribute and the emotion attribute of the music respectively, and then the target music attribute can be a target style attribute and a target emotion attribute under the condition that the target scene is a guest-meeting scene. (2) The target air conditioner type corresponds to a rest scenario, and the music playing requirement of the user in the rest scenario is generally as follows: quiet, soothing, music to aid sleep. Whether the music meets the playing requirements of the user in the rest scene or not can be judged according to the attribute of the song list of the music, whether the music is in the sleeping song list or not can be determined according to the name of the song list where the music is located, and then the attribute of the target music can be the attribute of the target song list under the condition that the target scene is the rest scene. (3) The target air conditioner type corresponds to a child usage scenario, and the music playing requirement of a user in the child usage scenario is generally as follows: positive upward music. Whether the music meets the user playing requirements in the use scene of the children or not can be judged according to the emotional attribute and the lyric attribute of the music, and then the target music attribute can be a target emotional attribute and a target lyric attribute under the condition that the target scene is the use scene of the children. (4) The type of the target air conditioner corresponds to the usage scene of the old, and the music playing requirement of a user under the usage scene of the old is as follows: classic music that matches the background of the age in which the elderly grow. Whether the music meets the playing requirements of users in the old people use scene or not can be judged according to the attribute and the time attribute of the song list of the music, whether the music is classical song list or not can be determined according to the name of the song list where the music is located, whether the music is in the time range which is consistent with the era background of the growth of the old people or not can be determined according to the time attribute, and then the target music attribute can be target song list attribute or target time attribute under the condition that the target scene is the old people use scene.

In the technical solution provided in step S106, the server determines a target matching result according to the target music attribute, where the target matching result is used to indicate whether the target air conditioner type matches the target music.

And determining whether the target music meets the music playing requirement of the user in the target scene or not by taking the target music attribute as a basis, thereby determining a target matching result whether the target air conditioner type is matched with the target music or not.

For example: (1) The target air conditioner type corresponds to the guest meeting scene, if the target style attribute indicates that the music style of the target music is a noisy music style (the noisy music style can comprise music styles such as electronic music, rock music, metal music and rap music, the music of the music styles is noisy and is not suitable for being played in the guest meeting scene), or if the target emotion attribute indicates that the emotion type of the target music is a negative emotion type (the negative emotion type can comprise angry, sadness and the like), the target matching result is that the target air conditioner type is not matched with the target music. (2) The target air conditioner type corresponds to a rest scene, and if the target song list attribute indicates that at least one song list name of the song list where the target music is located contains preset keywords (the preset keywords can be vocabularies such as 'sleep', 'rest', 'quiet', 'slow', and the like), the target matching result is that the target air conditioner type is matched with the target music. (3) The target air conditioner type corresponds to a child use scene, and if the target emotion attribute indicates that the emotion type of the target music is a negative emotion type (the negative emotion type can comprise angry, sadness and the like), or the target lyric attribute indicates that the lyric text of the target music contains preset negative words (the preset negative words can comprise pain, fall and the like), the target matching result is that the target air conditioner type is not matched with the target music. (4) The target air conditioner type corresponds to a usage scene of the old people, and if the target song list attribute indicates that at least one song list name of the song list where the target music is located contains a specified keyword (the specified keyword can be words such as 'classic memory', '90 years' and the like), or the target time attribute indicates that the release time of the target music is within a preset time range (for example, the preset time range is 1980 to 2010), the target matching result is that the target air conditioner type is matched with the target music.

Optionally, the target matching result may further include a matching degree in addition to the information indicating whether the target air conditioner type and the target music are matched, for example, the matching degree is classified into 6 levels, the 1 st level indicates a considerable match, the 2 nd level indicates a perfect match, the 3 rd level indicates a general match, the 4 th level indicates a general mismatch, the 5 th level indicates a very mismatch, and the 6 th level indicates a considerable mismatch.

In the technical solution provided in step S108, the server associates the air conditioner type with the target music according to the target matching result, and obtains a music knowledge graph.

There are several ways to associate the type of air conditioner to the target music: (1) And taking the air conditioner type matched with the target music as the air conditioner type of the target music, and taking the air conditioner type not matched with the target music as the air conditioner type of the target music. (2) The air conditioner type matching with the target music is taken as a first air conditioner type of the target music, the air conditioner type not matching with the target music is taken as a second air conditioner type of the target music, for example, air conditioner type 01 matches with the target music, air conditioner type 02 does not match with the target music, the first air conditioner type is identified by letter Y, the second air conditioner type is identified by letter N, and then the air conditioner type of the target music comprises: y air conditioner type 01, N air conditioner type 02. (3) The matching result includes a matching degree, and different level identifiers are determined for the air conditioner type of the target music according to the matching degree, for example, the matching degree of the air conditioner type 01 is level 1, the matching degree of the air conditioner type 02 is level 2, the matching degree of the air conditioner type 03 is level 3, the matching degree of the air conditioner type is level 1 by using a letter a, the matching degree of the air conditioner type is level 2 by using a letter B, and the matching degree of the air conditioner type of the target music is level 3 by using a letter C, and then the air conditioner type of the target music includes: air conditioner type 01 a, air conditioner type 02B, air conditioner type 03C.

After the matching of all the air conditioner types is completed, one or more air conditioner types related to the target music can be obtained, so that the association of the air conditioner types of the target music is completed, and a complete music knowledge graph with better universality is obtained. The music recommendation is carried out by utilizing the music knowledge graph, so that the adaptation with the use scene of the air conditioner can be realized.

In the technical solution provided in step S208, the server associates the air conditioner type for the target music in the general knowledge base according to the target matching result, so as to obtain a music knowledge base.

There are a number of ways to associate the type of air conditioner for the target music in the generic knowledge graph: (1) And taking the air conditioner type matched with the target music as the air conditioner type of the target music, and taking the air conditioner type not matched with the target music as the air conditioner type of the target music. (2) The air conditioner type matched with the target music is used as a first air conditioner type of the target music, the air conditioner type not matched with the target music is used as a second air conditioner type of the target music, for example, the air conditioner type 01 is matched with the target music, the air conditioner type 02 is not matched with the target music, the first air conditioner type is identified by letter Y, the second air conditioner type is identified by letter N, and the air conditioner type of the target music comprises: y air conditioner type 01, N air conditioner type 02. (3) The matching result includes a matching degree, and different level identifiers are determined for the air conditioner type of the target music according to the matching degree, for example, the matching degree of the air conditioner type 01 is level 1, the matching degree of the air conditioner type 02 is level 2, the matching degree of the air conditioner type 03 is level 3, the matching degree of the air conditioner type is level 1 by using a letter a, the matching degree of the air conditioner type is level 2 by using a letter B, and the matching degree of the air conditioner type of the target music is level 3 by using a letter C, and then the air conditioner type of the target music includes: air conditioner type a 01, air conditioner type B02, and air conditioner type C03.

After the matching of all the air conditioner types is completed, one or more air conditioner types associated with the target music can be obtained, so that the association of the air conditioner types with the target music is completed.

And after the association of the air conditioner types of all the music in the general knowledge graph is completed, the complete music knowledge graph with better universality can be obtained. The music recommendation is carried out by utilizing the music knowledge graph, so that the adaptation with the use scene of the air conditioner can be realized.

As an alternative embodiment, step S204 is to extract the target music attribute from all candidate music attributes of the target music according to the target scene corresponding to the target air conditioner type in all air conditioner types, and may further include the following steps:

step S41, under the condition that the target air conditioner type is a first air conditioner type corresponding to the participated scene, extracting target emotion attributes and target style attributes of target music from all candidate music attributes, wherein the target music attributes comprise the target emotion attributes and the target style attributes;

step S42, under the condition that the target air conditioner type is a second air conditioner type corresponding to the rest scene, extracting target song list attributes from all candidate music attributes of the target music, wherein the target music attributes comprise the target song list attributes which are used for indicating the name of the song list where the target music is located;

step S43, under the condition that the target air conditioner type is a third air conditioner type corresponding to a child use scene, extracting a target emotion attribute and a target lyric attribute of the target music from all candidate music attributes, wherein the target music attribute comprises the target emotion attribute and the target lyric attribute;

step S44, under the condition that the target air conditioner type is a fourth air conditioner type corresponding to the usage scene of the old people, extracting a target song list attribute and a target time attribute of the target music from all candidate music attributes, wherein the target music attribute comprises the target song list attribute and the target time attribute, the target song list attribute is used for indicating the song list name of the song list where the target music is located, and the target time attribute is used for indicating the release time of the target music.

The air-conditioning types can be classified into various types, for example, according to the type of the air-conditioning, the air-conditioning types can be classified into a cabinet air-conditioning type, a hanging air-conditioning type and the like, according to the applicable group, the air-conditioning types can be classified into a child air-conditioning type, a senior citizen air-conditioning type and the like, according to the installation scene, and the air-conditioning types can be classified into a bedroom air-conditioning type, a living room air-conditioning type and the like.

The first air conditioner type is an air conditioner type corresponding to a participatory scene, and can be a cabinet air conditioner type or a living room air conditioner type; the second air conditioner type is an air conditioner type corresponding to a rest scene, can be a hanging air conditioner type and can also be a bedroom air conditioner type; the third air conditioner type is an air conditioner type corresponding to a child use scene, and can be a child air conditioner type or a child room air conditioner type; the fourth air conditioner type is an air conditioner type corresponding to the use scene of the old people, and can be a long air conditioner type or an air conditioner type in a room of the old people.

Different air conditioner types can correspond to different use scenes, music playing requirements under different air conditioner use scenes can be determined according to actual conditions, steps S41 to S44 in the present application are only one implementation manner, and more complex music playing requirements can be actually customized for each use scene, so that a greater number of target music attributes are selected from all candidate music attributes as a judgment basis to determine whether the target music matches with the music playing requirements of the target scene, and thus determine whether the target air conditioner type corresponding to the target scene matches with the target music.

Optionally, in this embodiment, in S106, determining a target matching result according to the target music attribute, which may further include the following steps:

step S61, under the condition that the target air conditioner type is a first air conditioner type, when a first preset requirement is met, determining that a target matching result is that the first air conditioner type is not matched with the target music, wherein the first preset requirement is that the target emotion attribute indicates that the emotion type of the target music is a negative emotion type, or the target style attribute indicates that the music style of the target music is a noisy music style;

step S62, when the target type of the air conditioner is a second type of the air conditioner, and when the attribute of the target song list indicates that the song list name of the song list where the target music is located contains a preset keyword, determining that the target matching result is that the second type of the air conditioner is matched with the target music, wherein the preset keyword comprises words associated with a rest scene;

step S63, when the target air conditioner type is the third air conditioner type and a second preset requirement is met, determining that the target matching result is that the third air conditioner type is not matched with the target music, where the second preset requirement is: the target emotion attribute indicates that the emotion type of the target music is a negative emotion type, or the target lyric attribute indicates that a lyric text of the target music contains preset negative words;

step S64, when the target air conditioner type is a fourth air conditioner type and a third preset requirement is met, determining that the target matching result is that the fourth air conditioner type matches the target music, where the third preset requirement is: the target song list attribute indicates that the song list name of the song list where the target music is located contains a specified keyword, or the target time attribute indicates that the release time of the target music is within a preset time range.

In the case that the target air conditioner type is the first air conditioner type, the first air conditioner type corresponds to the guest meeting scene, if the target style attribute indicates that the music style of the target music is a noisy music style (the noisy music style may include electronic music, rock music, metallic music, rap music, etc., and the music of these music styles is usually more noisy music), or the target emotion attribute indicates that the emotion type of the target music is a negative emotion type (the negative emotion type may include anger, sadness, etc.), the target matching result is that the target air conditioner type is not matched with the target music. And if the target style attribute indicates that the music style of the target music is not the music style in the noisy music style and the target emotion attribute indicates that the emotion type of the target music is not the emotion type in the negative emotion types, the target matching result is that the target air conditioner type is matched with the target music.

And under the condition that the target air conditioner type is the second air conditioner type, the second air conditioner type corresponds to a rest scene, if the attribute of the target song list indicates that the song list name of the song list where the target music is located contains preset keywords (the preset keywords can be vocabularies such as 'sleep', 'rest', 'quiet', 'relax', and the like), the target matching result is that the target air conditioner type is matched with the target music.

Optionally, in this embodiment, the target music may be included in one or more vocabularies, the target vocabularies attribute of the target music may include a plurality of vocabularies, and in a case that at least one vocabularies name includes a preset keyword, the target matching result is determined to be that the target air conditioner type matches the target music. And if the attribute of the target song list indicates that no song list with the name containing the preset keyword exists in all the song lists of the target music, determining that the target matching result is that the type of the target air conditioner is not matched with the target music.

If the target type of the air conditioner is the third type of the air conditioner, the third type of the air conditioner corresponds to a usage scenario of the child, and if the target emotion attribute indicates that the emotion type of the target music is a negative emotion type (the negative emotion type may include angry, sadness, etc.), or the target lyric attribute indicates that the lyric text of the target music contains a preset negative vocabulary (the preset negative vocabulary may include "pain", "fall", etc.), the target matching result is that the target type of the air conditioner does not match the target music. And if the target emotion attribute indicates that the emotion type of the target music is not the emotion type in the negative emotion types and the lyric text indicated by the target lyric attribute does not contain preset negative words, the target matching result is that the target air conditioner type is matched with the target music.

Alternatively, in the present embodiment, the negative emotion types may include more emotion types than the above examples.

Alternatively, in this embodiment, a preset negative vocabulary library may be established in advance before step S204, and the preset negative vocabulary library may include vocabularies related to emotional negatives, vulgars, violence, and the like.

If the target type of air conditioner is a fourth type of air conditioner, the fourth type of air conditioner corresponds to a scene of usage of the elderly people, and if the attribute of the target song list indicates that the song list name of the song list where the target music is located contains a specified keyword (the specified keyword may be words such as "classic memory", "90 years", and the like), or the attribute of the target time indicates that the release time of the target music is within a preset time range (for example, the preset time range is 1980 to 2010), the target matching result is that the target type of air conditioner is matched with the target music.

Optionally, in this embodiment, the target music may be included in one or more vocabularies, the target vocabularies attribute of the target music may include one or more vocabularies, and in a case that at least one vocabularies name includes a preset keyword, it is determined that the target matching result is that the target air conditioner type matches the target music.

And if the target song list attribute indicates that no song list with the name containing the specified keyword exists in all the song lists of the target music, and the release time indicated by the target time attribute is not within the preset time range, the target matching result is that the type of the target air conditioner is not matched with the target music.

As an alternative embodiment, step S208, associating the air conditioner type for the target music in the generic knowledge graph according to the target matching result to obtain a music knowledge graph, and may further include the following steps:

and S81, under the condition that the target air conditioner type is matched with the target music, taking the target air conditioner type as the air conditioner type of the target music in the general knowledge graph to obtain the music knowledge graph.

As an alternative embodiment, after obtaining the music knowledge map, the method further comprises performing music recommendation according to the following steps:

step S91, acquiring a target voice instruction, wherein the target voice instruction is used for requesting the appointed air conditioner to play music;

step S92, carrying out semantic analysis on the target voice command to obtain a semantic analysis result;

and S93, determining the music to be played of the specified air conditioner from the music knowledge graph according to the semantic analysis result.

The designated air conditioner is a voice air conditioner capable of playing music according to a voice instruction given by a user.

Optionally, in this embodiment, the designated air conditioner may receive a target voice instruction sent by the user through a self intelligent voice module or an intelligent device in communication connection with the designated air conditioner, and transmit the target voice instruction to the server, and after the server acquires the target voice instruction, the server identifies an intention of the voice instruction sent by the user, and executes a subsequent operation according to the intention indicated by the voice instruction.

Optionally, in this embodiment, in step S93, according to the semantic analysis result, the music to be played of the specified air conditioner is determined from the music knowledge graph, and the method may further include the following steps:

step S931, under the condition that the semantic analysis result does not include the music name, determining, according to the specified air conditioner type to which the specified air conditioner belongs, music to be played of the specified air conditioner from preset music in the music knowledge graph, where all air conditioner types associated with the preset music include the specified air conditioner type.

Step 932, finding out the designated music corresponding to the designated music name and the air conditioner type of the designated music in the music knowledge map according to the designated music name under the condition that the semantic analysis result contains the designated music name; sending preset prompting information under the condition that the air conditioner type of the specified music does not include the specified air conditioner type to which the specified air conditioner belongs, wherein the preset prompting information is used for prompting that the specified music is not suitable for playing of the specified air conditioner; and in the case that the air conditioner type of the designated music comprises the designated air conditioner type, the designated music is used as the music to be played of the designated air conditioner.

If the voice command sent by the user is a fuzzy music playing command, such as 'play music', 'play a song', etc., after semantic analysis is performed on the voice command, a specific music name cannot be obtained, and one or more pieces of music suitable for being played in the current air conditioner use scene need to be determined in the music knowledge base as the music to be played in the specified air conditioner. If the voice command sent by the user is a specific music playing command, such as "i want to listen, good luck", the voice command is subjected to semantic analysis to obtain a specific music name, and then the music name can be obtained according to the music knowledge map. Determining whether the music corresponding to the music name is suitable for playing in the current air conditioner use scene, if so, taking the music corresponding to the music name as the music to be played in the specified air conditioner, if not, sending a prompt to a user to prompt that the music is not suitable for the current air conditioner use scene, inquiring whether the user still needs to play, and if obtaining a play instruction confirmed by the user, taking the music as the music to be played in the specified air conditioner.

Optionally, in this embodiment, if the play confirmation instruction of the user is not obtained within the preset time period, one or more pieces of music that are suitable for being played in the current air conditioner usage scene are determined in the music knowledge base as the to-be-played music of the specified air conditioner.

Optionally, in this embodiment, in step S93, after determining, according to the semantic analysis result, music to be played of the specified air conditioner from the music knowledge graph, the method further includes the following steps:

step S94, generating a music playing instruction according to the music to be played of the specified air conditioner;

and step S95, sending a music playing instruction to a designated music player, wherein the designated music player is used for playing the music to be played of the designated air conditioner.

The designated music player can be a music playing module of the designated air conditioner or a music playing device connected with the designated air conditioner.

When the music to be played is a plurality of pieces of music, the designated music player may play the plurality of pieces of music according to a preset sequence, or randomly play the plurality of pieces of music.

Through the steps S91 to S95 and the steps S931 to S932, a decision can be made for different voice instructions of the user according to the music knowledge map, and the music to be played of the designated air conditioner is determined, so that the music playing module of the designated air conditioner or the music playing device connected with the designated air conditioner can play the music to be played, the requirements of the user are met, the scene is adapted, and the user experience is improved.

As an alternative example, the following describes the technical solution of the present application in combination with the specific embodiments:

currently, many smart home voice devices, such as a voice air conditioner, have a music playing function. Generally, the music playing process includes: firstly, voice recognition is carried out on a voice instruction of a user, and then the recognized text is directly taken to request a music interface of a third party. Thus, there is a problem that the devices are directed to specific groups of people and environments in the home, and there is a certain mismatch in directly using general music resources. Therefore, it is necessary to construct a music knowledge base suitable for a voice air conditioner.

(I) mining of different voice air-conditioning music playing requirements

The voice air conditioners can be divided into a cabinet air conditioner and an on-hook air conditioner; the voice air conditioner can be classified into a general air conditioner, a child air conditioner and a senior air conditioner according to the use of people. The requirements of different devices for playing music are shown in the following table:

(II) converting equipment requirements into music knowledge graph

The general knowledge map mainly includes song information (song name, lyrics, distribution time, play amount, music type, music style, etc.), singer information, album information, song list information, and list information. The music knowledge graph (namely the music knowledge graph in the application) in the field of voice air conditioning can be constructed based on the existing general knowledge graph, and different music is labeled with equipment on the basis of the existing content. The following labels are marked on music according to the requirements of different voice air conditioners, and a piece of music can have a plurality of labels, so that the labeling process is actually a process of performing two classifications many times, a specific flow is shown in fig. 3, and a specific classification mode is as follows:

1. cabinet air conditioner

Firstly, emotion polarity analysis is needed to be carried out on lyrics of music, a general text classification method can be adopted, such as an LSTM (long short term memory network), a TextCNN (text convolution network) and a BERT (text based notation) model, and if the emotion of the lyrics tends to be negative, a label of a cabinet air conditioner cannot be marked; secondly, the audio frequency of the music can be analyzed, if the music is too noisy, the tag of the cabinet air conditioner cannot be played, and judgment can also be carried out according to the music style, for example, music with music styles such as rock, electronic, rap, metal and the like is not suitable for being played in a living room.

2. On-hook air conditioner

Music of the on-hook air conditioner mainly considers music recommendation in sleep time periods, and the music can be labeled according to music song list attributes, such as sleep music song lists shared by a plurality of people. This requires that we first identify the name of the song list by keyword, and identify whether it is a song list of sleeping music.

3. Air conditioner for children

Establishing a dictionary of negative words, traversing the lyrics, and filtering the corresponding songs as long as negative words appear in the lyrics of the music; meanwhile, emotion polarity analysis of the text is carried out, and music with negative emotion is filtered out. And (4) putting child air conditioner labels on music which has no negative words and positive emotion.

4. Air conditioner for the elder

The music label of the air conditioner of the elder can be marked according to the distribution time of the music and the song list information. For example, a song with a song list name containing keywords such as "chinese love song in the 90 s", "classic", "recall song list" and the like may be labeled with a senior air conditioner.

The method has the advantages that different requirements of different voice air conditioner types on music resources are mined, music playing requirements of different equipment are considered when the music knowledge graph is constructed, the requirements of the equipment are converted into the music knowledge graph, and more accurate music recommendation can be carried out when a user proposes a fuzzy music playing intention. If the music requirement expressed by the user is not a specific certain song, such as 'I want to listen to music', the user can be recommended by selecting one from suitable songs; if the user speaks the name of the song that the user wants to listen to, whether the user is suitable for the current equipment to play or not can be judged, if so, the user can be played, and if not, the user is reminded. For example, if a user requests a song on a child's air conditioner that is not suitable for the child to listen to, the user will audibly prompt and recommend another song to be played if confirmed.

According to the scheme, music playing requirements of different types of voice air conditioners are refined, and then the requirements are stored in the knowledge map, so that more accurate music recommendation can be performed when a user proposes a fuzzy music playing intention.

According to another aspect of the embodiments of the present application, there is also provided an air conditioner music playing method, which may include:

step S302, a target voice instruction is obtained, wherein the target voice instruction is used for requesting the appointed air conditioner to play music;

step S304, carrying out semantic analysis on the target voice command to obtain a semantic analysis result;

step S306, under the condition that the semantic analysis result does not contain the music name, determining the music to be played of the specified air conditioner from the preset music in the music knowledge graph according to the specified air conditioner type to which the specified air conditioner belongs, wherein all the air conditioner types related to the preset music comprise the specified air conditioner type, and the music knowledge graph is constructed according to the music knowledge graph construction method;

step S308, indicating a designated music player to play music to be played, wherein the designated music player is a music player associated with a designated air conditioner.

Through the steps S302 to S308, music to be played that can adapt to the use scene of the air conditioner is determined according to the music attribute of the music in the general knowledge graph and the type of the specified air conditioner to which the air conditioner belongs, so that a more accurate music recommendation service is provided for the user, and further the technical problem that music in the adaptation scene cannot be recommended for the user for different use scenes of the air conditioner by directly using general music resources for music recommendation in the related art is solved.

Alternatively, in the present embodiment, the air-conditioning music playing method described above may be applied to a hardware environment constituted by the terminal 101 and the server 103 as shown in fig. 1. The air conditioning music playing method according to the embodiment of the present application may be executed by the server 103, may be executed by the terminal 101, or may be executed by both the server 103 and the terminal 101. The terminal 101 executing the air conditioner music playing method according to the embodiment of the present application may also be executed by a client installed thereon. The following description will be given taking an example in which an air conditioner music playing method according to an embodiment of the present application is executed on a server.

In the technical solution provided in step S302, the server obtains a target voice instruction, where the target voice instruction is used to request a specified air conditioner to play music.

The designated air conditioner is a voice air conditioner which can enable a music player associated with the designated air conditioner to play music according to a voice instruction sent by a user.

The designated air conditioner can receive a target voice instruction sent by a user through the intelligent voice module of the designated air conditioner or the intelligent equipment in communication connection with the designated air conditioner, and transmit the target voice instruction to the server.

In the technical solution provided in step S302, the server performs semantic analysis on the target voice instruction to obtain a semantic analysis result.

In the technical solution provided in step S306, the server determines, according to the specified air conditioner type to which the specified air conditioner belongs, music to be played of the specified air conditioner from preset music in a music knowledge graph when the semantic analysis result does not include the music name, where all air conditioner types associated with the preset music include the specified air conditioner type, and the music knowledge graph is constructed according to the music knowledge graph construction method.

If the voice instruction sent by the user is a fuzzy music playing instruction, such as 'i want to listen to music', 'play a song', and the like, a specific music name cannot be obtained after semantic analysis is performed on the voice instruction, and one or more pieces of music which are suitable for being played in the current air conditioner use scene need to be determined in the music knowledge base to be used as the music to be played in the specified air conditioner.

Optionally, in this embodiment, in step S304, after performing semantic analysis on the target voice instruction to obtain a semantic analysis result, and in step S308, before playing music to be played, the air conditioning music playing method may further include the following steps:

step S307, under the condition that the semantic analysis result contains the designated music name, searching the designated music corresponding to the designated music name and the air conditioner type of the designated music in the music knowledge map according to the designated music name; sending preset prompting information under the condition that the air conditioner type of the specified music does not include the specified air conditioner type to which the specified air conditioner belongs, wherein the preset prompting information is used for prompting that the specified music is not suitable for playing of the specified air conditioner; and in the case that the air conditioner type of the designated music comprises the designated air conditioner type, the designated music is used as the music to be played of the designated air conditioner.

If the voice command sent by the user is a specific music playing command, such as "i want to listen, good luck", the voice command is subjected to semantic analysis to obtain a specific music name, and then the music name can be obtained according to the music knowledge map. Determining whether the music corresponding to the music name is suitable for playing in the current air conditioner use scene, if so, taking the music corresponding to the music name as the music to be played in the specified air conditioner, if not, sending a prompt to a user to prompt that the music is not suitable for the current air conditioner use scene, inquiring whether the user still needs to play, and if obtaining a play instruction confirmed by the user, taking the music as the music to be played in the specified air conditioner.

Optionally, in this embodiment, if the play confirmation instruction of the user is not obtained within the preset time period, one or more pieces of music suitable for being played in the current air conditioner usage scene are determined in the music knowledge graph, and are used as the music to be played in the specified air conditioner.

In the technical solution provided in step S308, the server instructs a designated music player to play music to be played, where the designated music player is a music player associated with a designated air conditioner.

The designated music player can be a music playing module of the designated air conditioner or a music playing device connected with the designated air conditioner.

By the mode, the music is matched with the air conditioner using scene as much as possible, and the personalized music playing requirement of a user can be met while the scene requirement is met.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present application.

According to another aspect of the embodiment of the application, a music knowledge graph construction device for implementing the music knowledge graph construction method is further provided. Fig. 4 is a schematic diagram of an alternative music knowledge base constructing apparatus according to an embodiment of the present application, which may include, as shown in fig. 4:

the obtaining module 24 is configured to obtain a target music attribute of the target music according to a target scene corresponding to a target air conditioner type, where the target music is music of an air conditioner type to be associated, and the target air conditioner type is an air conditioner type to be determined whether to be matched with the target music;

the matching module 26 is configured to determine a target matching result according to the target music attribute, where the target matching result is used to indicate whether the target air conditioner type is matched with the target music;

and the association module 28 is used for associating the air conditioner type with the target music according to the target matching result to obtain the music knowledge graph.

It should be noted that the obtaining module 24 in this embodiment may be configured to execute step S104 in this embodiment, the matching module 26 in this embodiment may be configured to execute step S106 in this embodiment, and the associating module 28 in this embodiment may be configured to execute step S108 in this embodiment.

It should be noted here that the modules described above are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the above embodiments. It should be noted that the modules described above as a part of the apparatus may operate in a hardware environment as shown in fig. 1, and may be implemented by software or hardware.

Through the modules, the technical problem that music in a matched scene cannot be recommended to a user for different use scenes of the air conditioner by directly using universal music resources to recommend the music in the related art can be solved.

As an alternative embodiment, the obtaining module 24 further includes: the music processing device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring all candidate music attributes of target music in a general knowledge graph, the target music is music of an air conditioner type to be associated in the general knowledge graph, and the air conditioner type associated with the music is used for representing the air conditioner type to which the music is applicable; and the extracting unit is used for extracting the target music attribute from all candidate music attributes of the target music according to a target scene corresponding to a target air conditioner type in all air conditioner types, wherein the target air conditioner type is an air conditioner type to be determined whether the target music is matched with the target music, and an air conditioner of the target air conditioner type is used for providing a music playing function in the target scene.

Optionally, the associating module 28 is further configured to associate the air conditioner type for the target music in the general knowledge base according to the target matching result, so as to obtain a music knowledge base.

As an alternative embodiment, the extraction unit further comprises:

the first extraction unit is used for extracting a target emotion attribute and a target style attribute of the target music from all candidate music attributes under the condition that the target air conditioner type is a first air conditioner type corresponding to the participated scene, wherein the target music attribute comprises the target emotion attribute and the target style attribute;

and the second extraction unit is used for extracting a target song list attribute from all candidate music attributes of the target music under the condition that the target air conditioner type is a second air conditioner type corresponding to the rest scene, wherein the target music attribute comprises the target song list attribute which is used for indicating the song list name of the song list where the target music is located.

Optionally, in this embodiment, the matching module 26 further includes:

the first matching unit is used for determining that the target matching result is that the first air conditioner type is not matched with the target music when a first preset requirement is met under the condition that the target air conditioner type is the first air conditioner type, wherein the first preset requirement is that the target emotion attribute indicates that the emotion type of the target music is a negative emotion type, or the target style attribute indicates that the music style of the target music is a noisy music style;

and the second matching unit is used for determining that the target matching result is that the second air-conditioning type is matched with the target music when the attribute of the target song list indicates that the song list name of the song list where the target music is located contains a preset keyword under the condition that the target air-conditioning type is the second air-conditioning type, wherein the preset keyword comprises words associated with the rest scene.

As an alternative embodiment, the extraction unit further comprises:

the third extraction unit is used for extracting a target emotion attribute and a target lyric attribute of the target music from all candidate music attributes under the condition that the target air conditioner type is a third air conditioner type corresponding to the using scene of the child, wherein the target music attribute comprises the target emotion attribute and the target lyric attribute;

and the fourth extraction unit is used for extracting a target song list attribute and a target time attribute of the target music from all candidate music attributes under the condition that the target air conditioner type is a fourth air conditioner type corresponding to the usage scene of the old people, wherein the target music attribute comprises the target song list attribute and the target time attribute, the target song list attribute is used for indicating the song list name of the target music, and the target time attribute is used for indicating the release time of the target music.

Optionally, in this embodiment, the matching module 26 further includes:

the third matching unit is used for determining that the target matching result is that the third air conditioner type is not matched with the target music when a second preset requirement is met under the condition that the target air conditioner type is the third air conditioner type, wherein the second preset requirement is as follows: the target emotion attribute indicates that the emotion type of the target music is a negative emotion type, or the target lyric attribute indicates that a lyric text of the target music contains preset negative words;

the fourth matching unit is configured to determine that the target matching result is that the fourth air conditioner type is matched with the target music when a third preset requirement is met under the condition that the target air conditioner type is the fourth air conditioner type, where the third preset requirement is that: the target song sheet attribute indicates that the song sheet name of the song sheet in which the target music is located contains a specified keyword, or the target time attribute indicates that the release time of the target music is within a preset time range.

As an alternative embodiment, the association module 28 is further configured to: and under the condition that the target air conditioner type is matched with the target music, taking the target air conditioner type as the air conditioner type of the target music in the general knowledge graph to obtain the music knowledge graph.

As an alternative embodiment, the apparatus further comprises an air conditioner music playing unit for: acquiring a target voice instruction, wherein the target voice instruction is used for requesting a specified air conditioner to play music; performing semantic analysis on the target voice instruction to obtain a semantic analysis result; and under the condition that the semantic analysis result does not contain the music name, determining the music to be played of the specified air conditioner from the preset music in the music knowledge graph according to the specified air conditioner type to which the specified air conditioner belongs, wherein all air conditioner types related to the preset music comprise the specified air conditioner type.

Optionally, in this embodiment, the air conditioner music playing unit is further configured to: under the condition that the semantic analysis result contains the designated music name, searching the designated music corresponding to the designated music name and the air conditioner type of the designated music in the music knowledge map according to the designated music name; sending preset prompting information under the condition that the air conditioner type of the specified music does not include the specified air conditioner type to which the specified air conditioner belongs, wherein the preset prompting information is used for prompting that the specified music is not suitable for playing of the specified air conditioner; and in the case that the air conditioner type of the designated music comprises the designated air conditioner type, the designated music is used as the music to be played of the designated air conditioner.

Optionally, in this embodiment, the air conditioner music playing unit is further configured to: and instructing a designated music player to play music to be played, wherein the designated music player is a music player associated with the designated air conditioner.

It should be noted here that the modules described above are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the above embodiments. It should be noted that the modules described above as a part of the apparatus may be operated in a hardware environment as shown in fig. 1, and may be implemented by software, or may be implemented by hardware, where the hardware environment includes a network environment.

According to another aspect of the embodiment of the application, an electronic device for implementing the music knowledge base construction method and/or the air conditioner music playing method is further provided.

The embodiment of the application provides a scheme for constructing the music knowledge graph and a scheme for playing the air conditioner music. The method comprises the steps of determining whether music is matched with a target air conditioner type or not by obtaining a music attribute which is required to be considered in a target scene corresponding to the target air conditioner type, associating the air conditioner type with the music according to a matching result, and enabling the music to be matched with the use scene of the air conditioner when music recommendation is carried out according to the music knowledge map, so that more accurate music recommendation service is provided for a user, and the technical problem that music matched with the scene cannot be recommended for the user according to different use scenes of the air conditioner when music recommendation is directly carried out by using general music resources in the related technology is solved.

Optionally, for a specific example in this embodiment, reference may be made to the example described in the foregoing embodiment, and this embodiment is not described herein again.

Specifically, the specific process of implementing the functions of each module in the apparatus according to the embodiment of the present invention may refer to the related description in the method embodiment, and details are not described herein again.

According to another embodiment of the present application, there is also provided an electronic apparatus, as shown in fig. 5, the electronic apparatus may include: the system comprises a processor 1501, a communication interface 1502, a memory 1503 and a communication bus 1504, wherein the processor 1501, the communication interface 1502 and the memory 1503 complete communication with each other through the communication bus 1504.

A memory 1503 for storing a computer program;

the processor 1501 is configured to implement the steps of the above-described method embodiments when executing the program stored in the memory 1503.

The bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

The communication interface is used for communication between the electronic equipment and other equipment.

The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.

The embodiment of the present application further provides a computer-readable storage medium, where the storage medium includes a stored program, and when the program runs, the method steps of the above method embodiment are executed.

According to another aspect of the embodiment of the application, an air conditioner comprising the electronic equipment is also provided. Furthermore, the music knowledge map construction method and/or the air-conditioning music playing method can be implemented through an air conditioner.

The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.

The integrated unit in the above embodiments, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a storage medium, and including instructions for causing one or more computer devices (which may be personal computers, servers, network devices, or the like) to execute all or part of the steps of the method described in the embodiments of the present application.

In the embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to the related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims (11)

1. A music knowledge graph construction method is characterized by comprising the following steps:

acquiring a target music attribute of target music according to a target scene corresponding to a target air conditioner type, wherein the target music is music of an air conditioner type to be associated, and the target air conditioner type is an air conditioner type to be determined whether to be matched with the target music;

determining a target matching result according to the target music attribute, wherein the target matching result is used for indicating whether the target air conditioner type is matched with the target music;

and associating the air conditioner type for the target music according to the target matching result to obtain a music knowledge graph.

2. The method according to claim 1, wherein the obtaining of the target music attribute of the target music according to the target scene corresponding to the target air conditioner type comprises:

under the condition that the target air conditioner type is a first air conditioner type corresponding to a participatory scene, acquiring a target emotion attribute and a target style attribute of the target music, wherein the target music attribute comprises the target emotion attribute and the target style attribute;

the determining a target matching result according to the target music attribute comprises:

when a first preset requirement is met, determining that the target matching result is that the first air conditioner type is not matched with the target music, wherein the first preset requirement is that the target emotion attribute indicates that the emotion type of the target music is a negative emotion type, or the target style attribute indicates that the music style of the target music is a noisy music style.

3. The method according to claim 1, wherein the obtaining of the target music attribute of the target music according to the target scene corresponding to the target air conditioner type comprises:

under the condition that the target air conditioner type is a second air conditioner type corresponding to a rest scene, acquiring a target song list attribute of the target music, wherein the target music attribute comprises the target song list attribute which is used for indicating the name of the song list where the target music is located;

the determining a target matching result according to the target music attribute comprises:

and when the target song list attribute indicates that the song list name of the song list where the target music is located contains a preset keyword, determining that the target matching result is that the second air conditioner type is matched with the target music, wherein the preset keyword comprises a vocabulary associated with the rest scene.

4. The method according to claim 1, wherein the obtaining of the target music attribute of the target music according to the target scene corresponding to the target air conditioner type comprises:

under the condition that the target air conditioner type is a third air conditioner type corresponding to a use scene of the children, acquiring a target emotion attribute and a target lyric attribute of the target music, wherein the target music attribute comprises the target emotion attribute and the target lyric attribute;

the determining a target matching result according to the target music attribute comprises:

when a second preset requirement is met, determining that the target matching result is that the third air conditioner type is not matched with the target music, wherein the second preset requirement is as follows: the target emotion attribute indicates that the emotion type of the target music is a negative emotion type, or the target lyric attribute indicates that the lyric text of the target music contains preset negative words.

5. The method according to claim 1, wherein the obtaining of the target music attribute of the target music according to the target scene corresponding to the target air conditioner type comprises:

under the condition that the target air conditioner type is a fourth air conditioner type corresponding to the usage scene of the old people, acquiring a target song list attribute and a target time attribute of the target music, wherein the target music attribute comprises the target song list attribute and the target time attribute, the target song list attribute is used for indicating the song list name of the song list where the target music is located, and the target time attribute is used for indicating the issuing time of the target music;

the determining a target matching result according to the target music attribute comprises:

when a third preset requirement is met, determining that the target matching result is that the fourth air conditioner type is matched with the target music, wherein the third preset requirement is that: the target song list attribute indicates that the song list name of the song list where the target music is located contains a specified keyword, or the target time attribute indicates that the release time of the target music is within a preset time range.

6. The method of claim 1, wherein associating an air conditioner type for the target music according to the target matching result to obtain a music knowledge graph comprises:

and according to each target matching result, associating a specified target air conditioner type in all the target air conditioner types with the target music to obtain the music knowledge graph, wherein the specified target air conditioner type is the air conditioner type matched with the target music.

7. An air conditioner music playing method is characterized by comprising the following steps:

acquiring a target voice instruction, wherein the target voice instruction is used for requesting a specified air conditioner to play music;

performing semantic analysis on the target voice instruction to obtain a semantic analysis result;

under the condition that the semantic analysis result does not contain a music name, determining music to be played of the specified air conditioner from preset music in a music knowledge graph according to the specified air conditioner type to which the specified air conditioner belongs, wherein all air conditioner types related to the preset music comprise the specified air conditioner type, and the music knowledge graph is constructed according to the music knowledge graph construction method of any one of claims 1 to 6;

and instructing a specified music player to play the music to be played, wherein the specified music player is a music player associated with the specified air conditioner.

8. A music knowledge base construction apparatus, comprising:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring a target music attribute of target music according to a target scene corresponding to a target air conditioner type, and the target air conditioner type is an air conditioner type to be determined whether to be matched with the target music;

the matching module is used for determining a target matching result according to the target music attribute, wherein the target matching result is used for indicating whether the target air conditioner type is matched with the target music;

and the association module is used for associating the air conditioner type with the target music according to the target matching result to obtain a music knowledge graph.

9. An electronic device, comprising: the system 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 is used for storing a computer program;

the processor, when executing the computer program, implementing the method of any of claims 1 to 7.

10. A computer-readable storage medium, characterized in that the storage medium comprises a stored program, wherein the program when executed performs the method of any of the preceding claims 1 to 7.

11. An air conditioner characterized by comprising the electronic apparatus according to claim 9.

Images