CN113343021A - Audio recommendation method, device, equipment and storage medium - Google Patents
Audio recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113343021A CN113343021A CN202110739029.1A CN202110739029A CN113343021A CN 113343021 A CN113343021 A CN 113343021A CN 202110739029 A CN202110739029 A CN 202110739029A CN 113343021 A CN113343021 A CN 113343021A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- historical
- destination address
- current user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 239000013598 vector Substances 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000014509 gene expression Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/635—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/65—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/687—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses an audio recommendation method, an audio recommendation device, audio recommendation equipment and a storage medium, wherein the audio recommendation method comprises the following steps: acquiring user information of each historical user; clustering historical users according to the user information to generate a user clustering result comprising a clustering category set; acquiring recommended audio contents of all historical users corresponding to the target clustering category, and adding the recommended audio contents of all historical users corresponding to the target clustering category into a recommended audio content set corresponding to the target clustering category; comparing the user historical information of the current user with the user information of each historical user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs; and recommending the audio content in the audio content set to be recommended corresponding to the target cluster category to which the current user belongs to the current user. The audio content recommendation of the current user is more accurate, and is obtained through the recommended audio content set corresponding to the cluster type of the user information of the current user.
Description
Technical Field
The present application relates to the field of vehicle technologies, and in particular, to an audio recommendation method, apparatus, device, and storage medium.
Background
Typically, a user will choose to drive a car for travel in a variety of situations. Such as eating, working, traveling, etc. In the driving and traveling process, a user can select an audio platform on a vehicle to play audio, so that the mood is relaxed. Users tend to be fatigued to make selections of audio content, wasting a great deal of time and effort in selecting particular audio content.
With the development of vehicle intelligence, more and more users have strong demands for intelligent audio content recommendation of vehicles.
Disclosure of Invention
In view of this, embodiments of the present application provide an audio recommendation method, apparatus, device, and storage medium, which perform intelligent recommendation of audio content by determining historical users of the same cluster category of a current user and based on recommended audio content of each historical user in the category, so that time and energy of the user are saved, and accurate recommendation can be achieved.
In order to solve the above problem, the technical solution provided by the embodiment of the present application is as follows:
in a first aspect, an embodiment provides an audio recommendation method, where the method includes:
acquiring user history information of a current user, wherein the user history information of the current user comprises current user identity information, a historical trip destination address of the current user, attribute information corresponding to the historical trip destination address and a destination address type corresponding to the historical trip destination address;
comparing the user historical information of the current user with the user information of each historical user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs;
and determining the recommended audio content set corresponding to the target clustering category to which the current user belongs as an audio content set to be recommended.
In an optional embodiment, before the step of obtaining the user history information of the current user, the method further includes:
acquiring user information of each historical user, wherein each piece of user information comprises user identity information, a trip destination address, attribute information corresponding to the trip destination address, a trip time period corresponding to the trip destination address and a destination address type corresponding to the trip destination address;
clustering the historical users according to the user information to generate a user clustering result comprising a clustering category set, wherein the clustering category set comprises at least one clustering category, and the clustering category corresponds to at least one historical user;
acquiring recommended audio contents of all historical users corresponding to a target clustering category, and adding the recommended audio contents of all historical users corresponding to the target clustering category to a recommended audio content set corresponding to the target clustering category; the target cluster category is each of the set of cluster categories.
In an alternative embodiment, the method further comprises:
and acquiring the recommended audio content of the current user, and adding the recommended audio content of the current user into the audio content set to be recommended.
In an alternative embodiment, the method further comprises:
acquiring operation information of the current user when playing the audio content in the audio content set to be recommended;
and adjusting the audio content recommended to the current user according to the operation information.
In an alternative embodiment, the method further comprises:
first target information corresponding to a first historical travel destination address of the current user and acquired from a third-party platform and second target information of a second historical travel destination address of the current user and acquired from a vehicle-mounted terminal;
according to the first target information and the second target information, one or more of the following parameter information is corrected, wherein the parameter information comprises attribute information corresponding to the first historical travel destination address, a destination address type corresponding to the first historical travel destination address, attribute information corresponding to the second historical travel destination address or a destination address type corresponding to the second historical travel destination address.
In an optional implementation manner, the step of obtaining recommended audio content of each historical user corresponding to the target cluster category includes:
and acquiring recommended audio contents of each historical user corresponding to the target clustering category from the cloud platform or the third-party audio platform.
In an optional embodiment, the step of clustering the historical users according to the user information to generate a user clustering result including a cluster category set includes:
extracting the features of the user information to generate a feature vector of the user information;
and clustering the historical users according to the characteristic vectors of the user information to generate a user clustering result comprising a clustering category set.
In an optional embodiment, the step of comparing the user history information of the current user with the user information of each history user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs includes:
extracting the characteristics of the user history information of the current user to generate a characteristic vector of the user history information of the current user;
and comparing the feature vector of the user historical information of the current user with the user information of each historical user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs.
In a second aspect, an embodiment provides an audio recommendation apparatus, including:
a third obtaining unit, configured to obtain user history information of a current user, where the user history information of the current user includes current user identity information, a historical trip destination address of the current user, attribute information corresponding to the historical trip destination address, and a destination address type corresponding to the historical trip destination address;
the comparison unit is used for comparing the user historical information of the current user with the user information of each historical user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs;
and the determining unit is used for determining the recommended audio content set corresponding to the target cluster category to which the current user belongs as an audio content set to be recommended.
In a third aspect, an embodiment provides an electronic device, including a memory and a processor, where the memory stores a computer program operable on the processor, and the processor implements the steps of the method described in any one of the foregoing embodiments when executing the computer program. In a fourth aspect, embodiments provide a machine-readable storage medium having stored thereon machine-executable instructions that, when invoked and executed by a processor, cause the processor to carry out the steps of the method of any preceding embodiment.
Therefore, the embodiment of the application has the following beneficial effects:
the embodiment of the application provides an audio recommendation method, an audio recommendation device and audio recommendation equipment, wherein the method comprises the following steps:
acquiring user information of each historical user, wherein each piece of user information comprises user identity information, a trip destination address, attribute information corresponding to the trip destination address and a destination address type corresponding to the trip destination address; clustering historical users according to the user information to generate a user clustering result comprising a clustering category set, wherein the clustering category set comprises at least one clustering category, and the clustering category corresponds to at least one historical user; acquiring recommended audio contents of all historical users corresponding to the target clustering category, and adding the recommended audio contents of all historical users corresponding to the target clustering category into a recommended audio content set corresponding to the target clustering category; the target clustering category is respectively each of the clustering category sets; acquiring user history information of a current user, wherein the user history information of the current user comprises current user identity information, a historical trip destination address of the current user, attribute information corresponding to the historical trip destination address, a trip time period corresponding to the historical trip destination address and a destination address type corresponding to the historical trip destination address; comparing the user historical information of the current user with the user information of each historical user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs; determining a recommended audio content set corresponding to a target clustering category to which a current user belongs as an audio content set to be recommended; and recommending the audio content in the audio content set to be recommended to the current user. By intelligently recommending the audio content to the current user, the time and energy of the user are saved. The cluster category is obtained through a clustering algorithm, the recommended audio content set corresponding to the cluster category is obtained, and the audio content recommendation of the current user, which is obtained through the recommended audio content set corresponding to the cluster category of the user information of the current user, is more accurate.
Drawings
Fig. 1 is an exemplary application scenario of an audio recommendation method provided in an embodiment of the present application;
fig. 2 is a flowchart of an audio recommendation method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of another audio recommendation method provided in an embodiment of the present application;
fig. 4 is a schematic diagram of an audio recommendation apparatus according to an embodiment of the present application.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments accompanying the drawings are described in detail below.
In order to facilitate understanding of an audio recommendation method provided in the embodiments of the present application, an exemplary application scenario of the audio recommendation method provided in the embodiments of the present application is described below with reference to fig. 1. Fig. 1 is an exemplary application scenario of an audio recommendation method provided in an embodiment of the present application. The audio recommendation method provided by the embodiment of the application can be applied to the vehicle-mounted terminal 10.
The cloud platform 20 stores user information of a large number of historical users, and each user corresponds to at least one piece of user information. The user information is used for representing the trip condition of the corresponding user, and each piece of user information comprises user identity information, a trip destination address, attribute information corresponding to the trip destination address, a trip time period corresponding to the trip destination address and a destination address type corresponding to the trip destination address.
The vehicle-mounted terminal 10 acquires the user information of a large number of historical users stored by the vehicle-mounted terminal from the cloud platform 20, and performs clustering operation on the large number of historical users according to the acquired user information to generate a user clustering result including at least one clustering category. The in-vehicle terminal 10 sequentially determines each category in the cluster category set as a target cluster category. The vehicle-mounted terminal 10 acquires the recommended audio content of each user corresponding to the target cluster category, and adds the recommended audio content of each user corresponding to the target cluster category to the recommended audio content set corresponding to the target cluster category, wherein each target cluster category is operated according to the above.
As an optional embodiment, the cloud platform 20 may also perform the user clustering operation, and obtain recommended music content corresponding to each historical user in each target cluster category, at this time, the vehicle-mounted terminal 10 may directly obtain the recommended music content corresponding to each historical user in each target cluster category from the cloud platform 20, and use the recommended music content as a recommended audio content set corresponding to each target cluster category, and judge the user historical information of the current user based on the user information of each historical user in each target cluster category, so that resource consumption of the vehicle-mounted terminal 10 may be reduced, which is specifically as follows:
the in-vehicle terminal 10 acquires user history information of the current user. The user history information of the current user comprises current user identity information, a historical trip destination address of the current user, attribute information corresponding to the historical trip destination address, a trip time period corresponding to the historical trip destination address and a destination address type corresponding to the historical trip destination address. The in-vehicle terminal 10 compares the user history information of the current user with the user information of each history user corresponding to the target cluster category, and obtains the target cluster category to which the current user belongs. And determining a recommended audio content set corresponding to the cluster category to which the current user belongs as an audio content set to be recommended. Finally, the vehicle-mounted terminal 10 recommends the audio content in the set of audio content to be recommended to the current user.
Those skilled in the art will appreciate that the block diagram shown in fig. 1 is merely an example in which embodiments of the present application may be implemented. The scope of applicability of the embodiments of the present application is not limited in any way by this framework.
Referring to fig. 2, fig. 2 is a flowchart of an audio recommendation method according to an embodiment of the present application. As shown in fig. 2, the method includes S201-S207:
s201: the method comprises the steps of obtaining user information of each historical user, wherein each piece of user information can comprise user identity information, a trip destination address, attribute information corresponding to the trip destination address, a trip time period corresponding to the trip destination address and a destination address type corresponding to the trip destination address.
Specifically, the in-vehicle terminal needs to acquire user information of a large number of history users for subsequent clustering in S202. Each piece of user information comprises user identity information, a trip destination address, attribute information corresponding to the trip destination address, a trip time period corresponding to the trip destination address and a destination address type corresponding to the trip destination address.
The user identity information is the identity information of the user to which the vehicle belongs. The user identity information may include information of user age, user gender, user driving age, vehicle price, vehicle age, etc. Specifically, the user identification information may be provided by the user to which the vehicle belongs.
The travel destination address is an address reached by the user driving in historical travel, such as a park, a restaurant and the like. Specifically, the user travel destination address may be determined by a global positioning system installed on the vehicle.
The attribute information corresponding to the travel destination address is some of the travel destination address with attributes, such as average consumption of the travel destination address.
The trip time period corresponding to the trip destination address is a time period where the user trips, such as a certain time period of the monday or a certain time period of the weekend.
The user information can be acquired through manual input of a user, or the vehicle information is acquired through analysis based on vehicle condition data acquired by a vehicle-mounted terminal, and the driving age information, the destination address, the current driving time period and other user information corresponding to the user can be acquired according to parameters such as vehicle tire wear, battery loss, vehicle pressure signals, positioning information and the like.
From the travel destination addresses acquired from the user information, the destination address type corresponding to the travel destination address can be determined. The type of the destination address corresponding to the travel destination address is a category to which the destination address belongs, such as an address of an entertainment category, an address of a catering category, an address of a leisure category, an address of an education category, and an address of a department category. As an example, if the travel destination address is "xx restaurant", the category to which the travel destination address belongs is the address of the restaurant category.
It should be noted that, in order to make the attribute information corresponding to the travel destination address and the destination address type corresponding to the travel destination address in the obtained user information more accurate and perfect, the attribute information and the destination address type may be corrected by using related information obtained from other information sources. It can be understood that, by the correction method, attribute information corresponding to a travel destination address and a destination address type corresponding to the travel destination address in the user information of the historical user acquired in the cloud platform can be corrected, and attribute information corresponding to the travel destination address and a destination address type corresponding to the travel destination address in the user historical information of the current user can also be corrected.
As an example, first target information corresponding to a first historical travel destination address of a current user is acquired from a third-party platform (such as an xx group purchase platform, an xx commenting platform and the like); and according to the first target information corresponding to the first historical travel destination address, correcting one or more items of attribute information corresponding to the first historical travel destination address and a destination address type corresponding to the first historical travel destination address. In specific implementation, the third-party platform acquires the first target information corresponding to the first travel destination address according to the consumption condition of the destination address concerned by the user or already traveled and the type of the destination address traveled. The target information corresponding to the travel destination address acquired from the third-party platform is attribute information corresponding to the travel destination address acquired from the third-party platform and a destination address type corresponding to the travel destination address.
S202: and clustering the historical users according to the user information to generate a user clustering result comprising a clustering category set, wherein the clustering category set comprises at least one clustering category, and the clustering category corresponds to at least one historical user.
The vehicle-mounted terminal clusters the acquired user information of a large number of historical users to generate a user clustering result comprising at least one clustering category, wherein each clustering category may comprise a plurality of historical users, each historical user may comprise a plurality of user information, and each user information may comprise a plurality of travel destination addresses, travel time periods and the like. It should be noted that the clustering process may be performed by using a common clustering algorithm, and a specific clustering algorithm is not limited herein. As an example, a K-nearest neighbor clustering algorithm is used for clustering the user information.
In specific implementation, the step of clustering the historical users according to the user information to generate a user clustering result comprising a clustering category set includes:
extracting the characteristics of the user information to generate a characteristic vector of the user information;
and clustering the historical users according to the characteristic vectors of the user information to generate a user clustering result comprising a clustering category set.
The user information is subjected to feature extraction, and the feature vector is used for representing the user information, so that the user information expression is simplified, and the implementation of a subsequent clustering algorithm is facilitated.
It will be appreciated that clustering user information may categorize users of the same category into one category. Further, a category label for each cluster category may be defined to indicate common traits that are possessed by users having user information within the cluster category. For example, the user information of going to work, going to a weekend, going out in the morning and at a high consumption place, the user information of work in a scientific park, the user information of a restaurant, and the like.
S203: acquiring recommended audio contents of all historical users corresponding to the target clustering category, and adding the recommended audio contents of all historical users corresponding to the target clustering category into a recommended audio content set corresponding to the target clustering category; the target cluster category is each of a set of cluster categories.
And sequentially determining each cluster category in the cluster category set as a target cluster category. And acquiring the recommended audio content of each user corresponding to the target clustering category, and adding the recommended audio content of each user corresponding to the target clustering category into the recommended audio content set corresponding to the target clustering category. Namely, each target cluster category corresponds to the recommended audio content of all the historical users belonging to the target cluster category, and for one target cluster category, the recommended audio content of the historical users corresponding to the target cluster category is integrated to determine the recommended audio content set corresponding to the target cluster category. The historical user in the target cluster category may be interested in and recommendable by the recommended audio content in the set of recommended audio content corresponding to the target cluster category. In specific implementation, the obtaining of recommended audio content of each historical user corresponding to the target cluster category includes:
and acquiring recommended audio contents of each historical user corresponding to the target clustering category from the cloud platform or the third-party audio platform.
In other words, in specific implementation, recommended audio content for each user in the target cluster category can be acquired through the third-party audio platform, so that the set of recommended audio content corresponding to the acquired target cluster category is more accurate.
As an optional embodiment, the number of recommended audio contents of each historical user may be different, and the recommended audio contents may be manually entered into the vehicle-mounted terminal by the historical user and then uploaded to the cradle head, or the vehicle-mounted terminal may analyze audio operation records of the historical user to obtain recommended audio contents and then upload to the cradle head, or recommended audio contents obtained by the historical user from a third-party audio platform thereof.
S204: the method comprises the steps of obtaining user historical information of a current user, wherein the user historical information of the current user comprises current user identity information, a historical trip destination address of the current user, attribute information corresponding to the historical trip destination address, a trip time period corresponding to the historical trip destination address and a destination address type corresponding to the historical trip destination address.
And acquiring user history information of the current user, and finally performing audio recommendation for the current user. The user history information of the current user comprises current user identity information, a historical trip destination address of the current user, attribute information corresponding to the historical trip destination address, a trip time period corresponding to the historical trip destination address and a destination address type corresponding to the historical trip destination address.
The current user identity information comprises information such as the current user age, the current user gender, the current user driving age, the vehicle price and the like. Specifically, the current user identity information is provided by the current user. As an example, the in-vehicle terminal prompts the user to input user identity information.
In addition, as for the historical trip destination address of the current user, the attribute information corresponding to the historical trip destination address, the trip time period corresponding to the historical trip destination address, and the destination address type corresponding to the historical trip destination address, reference may be made to the content in the foregoing S201, and details are not repeated here.
It should be noted that, in order to make the acquired user information of the current user more accurate and complete, the relevant information acquired by other information sources may be used for correction.
As an example, second target information of a second historical travel destination address of the current user is acquired from the third-party platform; and according to second target information of a second historical travel destination address of the current user, correcting one or more items of attribute information corresponding to the second historical travel destination address of the current user or destination address types corresponding to the second historical travel destination address. In specific implementation, the third-party platform acquires target information corresponding to the travel destination address according to the consumption condition of the history destination address which has been traveled by the current user and the type of the history destination address which has been traveled. The target information of the historical travel destination address of the current user, which is acquired from the third-party platform, is attribute information corresponding to the second historical travel destination address of the current user, which is acquired from the third-party platform, or a destination address type corresponding to the second historical travel destination address.
S205: and comparing the user historical information of the current user with the user information of each historical user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs.
After the user history information of the current user is obtained, comparing the user history information of the current user with the user information of each history user corresponding to the target cluster category to obtain the target cluster category to which the user of the current user belongs.
In specific implementation, comparing the user history information of the current user with the user information of each history user corresponding to the target cluster category to obtain the target cluster category to which the user of the current user belongs, includes:
extracting the characteristics of the user history information of the current user to generate a characteristic vector of the user history information of the current user;
and comparing the feature vector of the user historical information of the current user with the user information of each historical user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs.
As an example, based on the feature vector of the user history information of the current user, the similarity between the feature vector of the user history information of the current user and the user information of each historical user corresponding to each target cluster category is calculated, and the cluster category with the highest similarity is used as the target cluster category to which the user history information of the current user belongs.
The similarity of the user information is determined by comparing a determination formula formed by the above factors according to the travel times of the same or similar travel destination addresses, the similarity of travel time periods of the same or similar travel destination addresses, and the similarity of destination address types corresponding to the most frequent travel destination addresses. Each factor is provided with a corresponding adjustable coefficient, and a user can adjust the adjustable coefficient according to more intentional conditions of the user, so that the finally determined destination address is more accurate, and the adjustable coefficient is a coefficient smaller than 1. For example, if the user more desires to determine the pushed audio recommendation content according to the historical travel destination address of the current travel time period, the adjustable coefficient corresponding to the factor is adjusted and increased according to the preset level. As an alternative embodiment, the adjustment level of the adjustable coefficient can be divided into several gears, and the user can easily adjust to the corresponding gear according to the desired intensity.
S206: and determining a recommended audio content set corresponding to the target clustering category to which the current user belongs as an audio content set to be recommended.
After the target cluster category to which the user history information of the current user belongs is determined, a recommended audio content set corresponding to the target cluster category to which the user history information of the current user belongs is obtained and determined as an audio content set to be recommended. The audio content in the audio content set to be recommended is the audio content which may be interested by the current user, and is recommendable. And the audio content which the user is interested in is determined and recommended by determining the cluster type to which the user information of the current user belongs, so that the audio content recommended to the current user is more accurate and meets the requirements of the current user.
In addition, in order to enrich the audio content in the audio content set to be recommended, the recommended audio content of the current user is acquired, and the recommended audio content of the current user is added to the audio content set to be recommended. As an example, the recommended audio content of the current user may be obtained through a third-party application, such as an audio sharing platform like xxFM. Usually, the third-party application program gives the audio content recommendation of the current user according to the user information of the current user, and determines the audio content recommended by the third-party application program as the recommended audio content of the current user.
S207: and recommending the audio content in the audio content set to be recommended to the current user.
And after the audio content set to be recommended is determined, recommending the audio content in the audio content set to be recommended to the current user.
It should be noted that, in order to make the recommended audio content more flexible, the recommended audio content may be adjusted in real time.
Specifically, acquiring operation information of a current user when playing audio content in an audio content set to be recommended; and adjusting the audio content recommended to the current user according to the operation information. The operation information is an operation triggered by the current user, such as a pause operation, a next operation, a forward operation, a backward operation, a collection operation, a volume adjustment operation, and the like. The vehicle-mounted terminal can adjust the audio content according to the currently played audio content and the user operation information of corresponding playing time in the playing process, before playing and after playing. For example, if the currently played audio content is one of the set of audio contents to be recommended, and the playing time is less than a first preset time, the user triggers the next operation, and the vehicle-mounted terminal can determine the audio content as a song that is not interested by the user, and then reduce the playing times or delete the audio content from the set of audio contents to be recommended.
In addition, the vehicle-mounted terminal can also indicate the current user to grade the recommended audio content, and the recommended audio content of the current user is automatically adjusted according to the grade.
According to the audio recommendation method provided by the embodiment of the application, a large amount of user information of historical users is obtained, and the historical users are clustered through the user information to obtain various clustering categories. And determining the recommended audio content of each historical user corresponding to each cluster category, and adding the recommended audio content of each user corresponding to the target cluster category into the recommended audio content set corresponding to the target cluster category. And determining a target cluster category to which the current user belongs according to the user history information of the current user, and determining a recommended audio content set corresponding to the cluster category to which the current user belongs as an audio content set to be recommended. And recommending the audio content in the audio content set to be recommended to the current user. By intelligently recommending the audio content to the current user, the time and energy of the user are saved. The cluster category is obtained through a clustering algorithm, the recommended audio content set corresponding to the cluster category is obtained, and the audio content recommendation of the current user, which is obtained through the recommended audio content set corresponding to the cluster category of the user information of the current user, is more accurate.
In order to facilitate understanding of the point of interest location pushing method provided by the embodiment of the present application, the point of interest location pushing method provided by the embodiment of the present application is comprehensively described below with reference to fig. 3.
As shown in fig. 3, first, user information of a historical user is obtained, where each piece of user information includes user identity information, a trip destination address, attribute information corresponding to the trip destination address, a trip period corresponding to the trip destination address, and a destination address type corresponding to the trip destination address.
Secondly, clustering the user information through a K nearest neighbor clustering algorithm to generate a user clustering result comprising at least one clustering category. And each cluster category in the user cluster results is determined as a target cluster category. And determining a recommended audio content set corresponding to the target clustering category according to the target clustering category. Specifically, the recommended audio content set corresponding to the target cluster category can be obtained by obtaining the recommended audio content of each user corresponding to the target cluster category and adding the recommended audio content of each user corresponding to the target cluster category to the recommended audio content set corresponding to the target cluster category.
Further, according to the acquired user history information of the current user, determining a set of audio contents to be recommended of the current user. And the audio contents in the audio content set to be recommended of the current user are the audio contents which are possibly interested by the current user. The user history information of the current user comprises current user identity information, a historical trip destination address of the current user, attribute information corresponding to the historical trip destination address, a trip time period corresponding to the historical trip destination address and a destination address type corresponding to the historical trip destination address. And in specific implementation, comparing the acquired user history information of the current user with the user information of each history user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs. And determining a recommended audio content set corresponding to the target clustering category to which the current user belongs as an audio content set to be recommended.
In order to enrich the audio content in the audio content set to be recommended, acquiring the recommended audio content of the current user in the third-party application program, and adding the recommended audio content of the current user into the audio content set to be recommended.
And finally, recommending the audio content in the audio content set to be recommended to the current user.
In addition, in order to make the obtained attribute information corresponding to the trip destination address, the destination address type corresponding to the trip destination address, the attribute information corresponding to the historical trip destination address of the current user, or the destination address type corresponding to the historical trip destination address more accurate, first target information corresponding to a first historical trip destination address of the current user and second target information corresponding to a second historical trip destination address of the current user, which are obtained from the vehicle-mounted terminal, need to be obtained from a third party platform. And correcting one or more items of attribute information corresponding to the first historical travel destination address, a destination address type corresponding to the first historical travel destination address, attribute information corresponding to the second historical travel destination address of the current user or a destination address type corresponding to the second historical travel destination address by using the information acquired from the third party platform.
By the audio recommendation method provided by the embodiment of the application, the audio content is intelligently recommended when the current user goes out, so that the time and energy of the user are saved, and the use experience of the user is improved. The audio content in the audio content set to be recommended corresponding to the target clustering category to which the current user belongs is recommended to the current user, so that the audio content recommended to the current user meets the requirements of the current user.
Referring to fig. 4, fig. 4 is a schematic diagram of an audio recommendation apparatus according to an embodiment of the present application. As shown in fig. 4, the apparatus includes:
a first obtaining unit 401, configured to obtain user information of each historical user, where each piece of user information includes user identity information, a trip destination address, attribute information corresponding to the trip destination address, a trip time period corresponding to the trip destination address, and a destination address type corresponding to the trip destination address;
a clustering unit 402, configured to cluster the historical users according to the user information, and generate a user clustering result including a cluster category set, where the cluster category set includes at least one cluster category, and the cluster category corresponds to at least one historical user;
a second obtaining unit 403, configured to obtain recommended audio content of each historical user corresponding to a target cluster category, and add the recommended audio content of each historical user corresponding to the target cluster category to a recommended audio content set corresponding to the target cluster category; the target cluster category is each of the cluster category sets;
a third obtaining unit 404, configured to obtain user history information of a current user, where the user history information of the current user includes current user identity information, a historical trip destination address of the current user, attribute information corresponding to the historical trip destination address, a trip time period corresponding to the historical trip destination address, and a destination address type corresponding to the historical trip destination address;
a comparing unit 405, configured to compare the user history information of the current user with the user information of each history user corresponding to the target cluster category, to obtain a target cluster category to which the current user belongs;
a determining unit 406, configured to determine a recommended audio content set corresponding to the target cluster category to which the current user belongs as an audio content set to be recommended;
a recommending unit 407, configured to recommend, to the current user, the audio content in the set of audio content to be recommended.
Optionally, in some implementations of embodiments of the present application, the apparatus further includes:
and the fourth obtaining unit is used for obtaining the recommended audio content of the current user and adding the recommended audio content of the current user into the audio content set to be recommended.
Optionally, in some implementations of embodiments of the present application, the apparatus further includes:
a fifth obtaining unit, configured to obtain operation information of the current user when playing the audio content in the set of audio content to be recommended;
and the adjusting unit is used for adjusting the audio content recommended to the current user according to the operation information.
Optionally, in some implementations of embodiments of the present application, the apparatus further includes:
a sixth obtaining unit, configured to obtain, from a third party platform, first target information corresponding to a first historical travel destination address of the current user, and obtain, from a vehicle-mounted terminal, second target information of a second historical travel destination address of the current user;
a correcting unit, configured to correct one or more of the following parameter information according to the first target information and the second target information, where the parameter information includes attribute information corresponding to the first historical travel destination address, a destination address type corresponding to the first historical travel destination address, attribute information corresponding to the second historical travel destination address, or a destination address type corresponding to the second historical travel destination address.
Optionally, in some implementations of the embodiment of the application, the second obtaining unit 403 is specifically configured to obtain, from a cloud platform or a third-party audio platform, recommended audio content of each historical user corresponding to a target cluster category, and add the recommended audio content of each user corresponding to the target cluster category to a recommended audio content set corresponding to the target cluster category.
Optionally, in some implementations of embodiments of the present application, the clustering unit 402 includes:
the first feature extraction subunit is used for performing feature extraction on the user information to generate a feature vector of the user information;
and the clustering subunit is used for clustering the historical users according to the characteristic vectors of the user information to generate a user clustering result comprising a clustering category set.
Optionally, in some implementations of the embodiments of the present application, the comparing unit 405 includes:
the second feature extraction subunit is configured to perform feature extraction on the user history information of the current user, and generate a feature vector of the user information of the current user;
and the comparison subunit is used for comparing the feature vector of the user history information of the current user with the user information of each history user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs.
The audio recommendation device provided by the embodiment of the invention can be used for acquiring a large amount of user information of historical users, and clustering the historical users according to the user information to acquire various clustering categories. And determining the recommended audio content of each historical user corresponding to each cluster category, and adding the recommended audio content of each user corresponding to the target cluster category into the recommended audio content set corresponding to the target cluster category. And determining the target clustering category of the current user according to the user history information of the current user, and determining a recommended audio content set corresponding to the target clustering category of the current user as an audio content set to be recommended. And recommending the audio content in the audio content set to be recommended to the current user. By intelligently recommending the audio content to the current user, the time and energy of the user are saved. The cluster category is obtained through a clustering algorithm, the recommended audio content set corresponding to the cluster category is obtained, and the audio content recommendation of the current user, which is obtained through the recommended audio content set corresponding to the cluster category of the user information of the current user, is more accurate.
An embodiment of the present application further provides an audio recommendation device, including: the audio recommendation method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the computer program, the audio recommendation method is realized according to the embodiment of the application.
The embodiment of the application also provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and the computer program is used for executing the audio recommendation method according to the embodiment of the application.
It should be noted that, in the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the system or the device disclosed by the embodiment, the description is simple because the system or the device corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (11)
1. An audio recommendation method, characterized in that the method comprises:
acquiring user history information of a current user, wherein the user history information of the current user comprises current user identity information, a historical trip destination address of the current user, attribute information corresponding to the historical trip destination address and a destination address type corresponding to the historical trip destination address;
comparing the user historical information of the current user with the user information of each historical user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs;
and determining the recommended audio content set corresponding to the target clustering category to which the current user belongs as an audio content set to be recommended.
2. The method of claim 1, wherein the step of obtaining user history information of the current user is preceded by the method further comprising:
acquiring user information of each historical user, wherein each piece of user information comprises user identity information, a trip destination address, attribute information corresponding to the trip destination address, a trip time period corresponding to the trip destination address and a destination address type corresponding to the trip destination address;
clustering the historical users according to the user information to generate a user clustering result comprising a clustering category set, wherein the clustering category set comprises at least one clustering category, and the clustering category corresponds to at least one historical user;
acquiring recommended audio contents of all historical users corresponding to a target clustering category, and adding the recommended audio contents of all historical users corresponding to the target clustering category to a recommended audio content set corresponding to the target clustering category; the target cluster category is each of the set of cluster categories.
3. The method of claim 1, further comprising:
and acquiring the recommended audio content of the current user, and adding the recommended audio content of the current user into the audio content set to be recommended.
4. The method according to claim 1 or 3, characterized in that the method further comprises:
acquiring operation information of the current user when playing the audio content in the audio content set to be recommended;
and adjusting the audio content recommended to the current user according to the operation information.
5. The method of claim 1, further comprising:
first target information corresponding to a first historical travel destination address of the current user and acquired from a third-party platform and second target information of a second historical travel destination address of the current user and acquired from a vehicle-mounted terminal;
according to the first target information and the second target information, one or more of the following parameter information is corrected, wherein the parameter information comprises attribute information corresponding to the first historical travel destination address, a destination address type corresponding to the first historical travel destination address, attribute information corresponding to the second historical travel destination address or a destination address type corresponding to the second historical travel destination address.
6. The method according to claim 2, wherein the step of obtaining the recommended audio content of each historical user corresponding to the target cluster category comprises:
and acquiring recommended audio contents of each historical user corresponding to the target clustering category from the cloud platform or the third-party audio platform.
7. The method according to claim 1, wherein the step of clustering the historical users according to the user information to generate a user clustering result comprising a set of clustering categories comprises:
extracting the features of the user information to generate a feature vector of the user information;
and clustering the historical users according to the characteristic vectors of the user information to generate a user clustering result comprising a clustering category set.
8. The method according to claim 7, wherein the step of comparing the user history information of the current user with the user information of each historical user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs comprises:
extracting the characteristics of the user history information of the current user to generate a characteristic vector of the user history information of the current user;
and comparing the feature vector of the user historical information of the current user with the user information of each historical user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs.
9. An audio recommendation apparatus, characterized in that the apparatus comprises:
a third obtaining unit, configured to obtain user history information of a current user, where the user history information of the current user includes current user identity information, a historical trip destination address of the current user, attribute information corresponding to the historical trip destination address, and a destination address type corresponding to the historical trip destination address;
the comparison unit is used for comparing the user historical information of the current user with the user information of each historical user corresponding to the target cluster category to obtain the target cluster category to which the current user belongs;
and the determining unit is used for determining the recommended audio content set corresponding to the target cluster category to which the current user belongs as an audio content set to be recommended.
10. An audio recommendation device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, when executing the computer program, implementing the audio recommendation method of any of claims 1-8.
11. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium for executing the audio recommendation method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110739029.1A CN113343021A (en) | 2021-06-30 | 2021-06-30 | Audio recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110739029.1A CN113343021A (en) | 2021-06-30 | 2021-06-30 | Audio recommendation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113343021A true CN113343021A (en) | 2021-09-03 |
Family
ID=77481822
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110739029.1A Pending CN113343021A (en) | 2021-06-30 | 2021-06-30 | Audio recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113343021A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006003401A (en) * | 2004-06-15 | 2006-01-05 | Equos Research Co Ltd | On-vehicle terminal device |
| CN104750685A (en) * | 2013-12-25 | 2015-07-01 | 上海博泰悦臻网络技术服务有限公司 | Music recommendation method and device of vehicle-mounted system |
| CN105302890A (en) * | 2015-10-16 | 2016-02-03 | 海信集团有限公司 | Multimedia content online recommendation method and multimedia content online recommendation auxiliary method and apparatus |
| CN108628886A (en) * | 2017-03-20 | 2018-10-09 | 中移（杭州）信息技术有限公司 | A kind of audio file recommendation method and device |
| CN111309960A (en) * | 2020-02-26 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Singing bill recommendation method and device |
| CN111797309A (en) * | 2020-06-19 | 2020-10-20 | 一汽奔腾轿车有限公司 | Vehicle-mounted intelligent recommendation device and method based on travel mode |
-
2021
- 2021-06-30 CN CN202110739029.1A patent/CN113343021A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006003401A (en) * | 2004-06-15 | 2006-01-05 | Equos Research Co Ltd | On-vehicle terminal device |
| CN104750685A (en) * | 2013-12-25 | 2015-07-01 | 上海博泰悦臻网络技术服务有限公司 | Music recommendation method and device of vehicle-mounted system |
| CN105302890A (en) * | 2015-10-16 | 2016-02-03 | 海信集团有限公司 | Multimedia content online recommendation method and multimedia content online recommendation auxiliary method and apparatus |
| CN108628886A (en) * | 2017-03-20 | 2018-10-09 | 中移（杭州）信息技术有限公司 | A kind of audio file recommendation method and device |
| CN111309960A (en) * | 2020-02-26 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Singing bill recommendation method and device |
| CN111797309A (en) * | 2020-06-19 | 2020-10-20 | 一汽奔腾轿车有限公司 | Vehicle-mounted intelligent recommendation device and method based on travel mode |
Non-Patent Citations (2)
| Title |
|---|
| 高华玲: "推荐算法及应用", 31 January 2021, 北京邮电大学出版社, pages: 29 - 30 * |
| 龚卫: "大数据挖掘技术与应用研究", 31 March 2021, 吉林文史出版社, pages: 123 - 124 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Baltrunas et al. | Incarmusic: Context-aware music recommendations in a car | |
| US20160253699A1 (en) | Method and apparatus for advertisement screening | |
| CN104731861B (en) | Multi-medium data method for pushing and device | |
| CN106484777B (en) | Multimedia data processing method and device | |
| CN111442778A (en) | Travel scheme recommendation method, device and equipment and computer readable storage medium | |
| US10129314B2 (en) | Media feature determination for internet-based media streaming | |
| CN107577736B (en) | File recommendation method and system based on BP neural network | |
| CN106339504A (en) | Music pushing method and apparatus | |
| CN112488863B (en) | Dangerous seed recommendation method and related equipment in user cold start scene | |
| CN111475714A (en) | Information recommendation method, device, equipment and medium | |
| CN109408710A (en) | Search result optimization method, device, system and storage medium | |
| CN110910180A (en) | Information pushing method and device, electronic equipment and storage medium | |
| US10754902B2 (en) | Information processing system and information processing device | |
| CN110120845B (en) | Radio station playing method and cloud server | |
| CN108932262B (en) | Song recommendation method and device | |
| CN113343021A (en) | Audio recommendation method, device, equipment and storage medium | |
| CN111210274A (en) | Advertisement recommendation method and system | |
| CN110458664B (en) | User travel information prediction method, device, equipment and storage medium | |
| CN117894093A (en) | Vehicle cleaning prompt method, device, computer equipment and storage medium | |
| CN105096161A (en) | Method and device for information display | |
| CN110442746B (en) | Intelligent music pushing method based on random forest algorithm and storage medium | |
| JP2016103107A (en) | Clustering apparatus, information terminal, information providing system, and program | |
| CN113282836A (en) | Travel destination address pushing method, device, equipment and storage medium | |
| CN108959387A (en) | Information acquisition method and device | |
| KR20100022542A (en) | Music recommendation system based on peer to peer network and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |