CN110765310B - Audio album recommendation method and system based on parameter configuration - Google Patents
Audio album recommendation method and system based on parameter configuration Download PDFInfo
- Publication number
- CN110765310B CN110765310B CN201910952294.0A CN201910952294A CN110765310B CN 110765310 B CN110765310 B CN 110765310B CN 201910952294 A CN201910952294 A CN 201910952294A CN 110765310 B CN110765310 B CN 110765310B
- Authority
- CN
- China
- Prior art keywords
- recall
- sequencing
- fusion
- weight
- result
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000004927 fusion Effects 0.000 claims abstract description 72
- 238000012163 sequencing technique Methods 0.000 claims abstract description 71
- 230000001960 triggered effect Effects 0.000 claims abstract description 12
- 238000004590 computer program Methods 0.000 claims description 16
- 230000000717 retained effect Effects 0.000 claims description 6
- 230000006399 behavior Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F16/68—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
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a system, a device and a storage medium for recommending an audio album based on parameter configuration, wherein the method comprises the steps of generating a recall data set of a current Batch in near real time when an ith Batch triggered by a user arrives, and sorting according to number recall scores; fusing recall data sets of the user for n times in the past, and sequencing according to the sequence of the generation time of each recall set; setting a fusion ordering weight parameter of each recall data set according to the distance from the ith recall time, and rearranging all audio albums in the fused recall data set; adjusting the weight of each fusion sorting weight parameter, carrying out data deduplication based on an initial sorting result, and sorting in a descending order again according to a final scoring to obtain a final recall set of the TopN; and carrying out fine sequencing on the final recall set based on a preset fine sequencing model to obtain a recommended result. By configuring parameters, the invention can consider the real-time interest trend and the historical interest of the user, so that the recommendation result is more reasonable.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an audio album recommendation method and system based on parameter configuration.
Background
In the network music platform, the audio album of interest to the user is usually recommended to the user through an audio album recommendation system, and one of the most important links in the audio album recommendation system is a recommendation algorithm, wherein the recommendation algorithm comprises a coarse Ranking recall part and a fine Ranking part. According to different business characteristics, the relation between recall coarse ranking and recall fine ranking needs to be comprehensively considered. In the recall generation section, the long-term behavior of the user, i.e., the historical behavior, needs to be considered, as well as the real-time behavior needs of the user. The method has the advantages that the historical behavior updating time is slow, the data can be considered globally, the real-time behavior updating speed is high, the real-time interest preference of the user can be quickly reflected, and the data is relatively less. However, how to integrate the historical behavior and the real-time behavior makes the recommendation result more reasonable is a problem to be solved urgently at present.
Disclosure of Invention
The invention aims at solving at least one of the technical problems in the prior art, and particularly creatively provides an audio album recommendation method, system, device and storage medium based on parameter configuration, by configuring parameters, the real-time interest trend and the historical interest of a user can be considered, the automatic fusion of different Batch recall results can be realized, the parameter weight based on service understanding can be considered in recall set fusion, the flexibility of recall set generation is greatly improved, the recommendation results are more reasonable, and the user experience is improved.
In order to achieve the above object of the present invention, according to a first aspect of the present invention, there is provided an audio album recommendation method based on parameter configuration, the method comprising the steps of:
s1, when the ith Batch triggered by a user arrives, generating a recall data set of the current Batch in near real time, and sorting audio albums in the recall data set according to the scoring of a recall algorithm, wherein i is a positive integer;
s2, fusing recall data sets of the user, including the current Batch recall data set, for n times in the past, and sequencing according to the sequence of the generation time of each recall set, wherein n is a positive integer greater than 1;
s3, setting a fusion ordering weight parameter of each recall data set according to the distance from the ith recall time, multiplying the original scoring of the ith Batch corresponding to the fusion ordering weight parameter in the step 1 to obtain a new scoring result, and rearranging all audio albums in the fused recall data set in a descending order according to the new scoring result;
s4, adjusting the weight of each fusion sequencing weight parameter to obtain an initial sequencing result;
s5, carrying out data deduplication based on an initial sequencing result, and sequencing in a descending order according to a final scoring to obtain a final recall set of TopN, wherein N is a positive integer;
and S6, carrying out fine sorting on the final recall set based on a preset fine sorting model to obtain a recommended result.
Preferably, the method further comprises:
judging whether current operation information of a user meets a preset condition threshold or not, and triggering a Batch through the current operation information when the current operation information meets the preset condition threshold.
Preferably, the adjusting the weight of each fused ranking weight parameter, to obtain an initial ranking result includes:
and adjusting the weight of each fusion sequencing weight parameter of the parameters, configuring the fusion sequencing weight parameter of the recall data set of the current Batch to be the maximum, and obtaining an initial sequencing result according to the adjusted weight parameters, wherein the fusion sequencing weight parameters of the rest recall data sets are in a descending or fixed state according to the current sequencing.
Preferably, the performing data deduplication based on the initial ordering result includes:
all of the audio albums in the initial ranking result are the same in album name but scored differently, and only the one with the highest score is retained.
According to a second aspect of the present invention, there is provided an audio album recommendation system based on parameter configuration, the system comprising:
the current recall data set generation module is used for generating a recall data set of the current Batch in near real time when the ith Batch triggered by the user arrives when the user operation meets the recommended triggering condition, and sequencing the audio albums in the recall data set according to the scoring of a recall algorithm, wherein i is a positive integer;
the data set fusion module is used for fusing recall data sets of the user, including the recall data set of the current Batch, for n times in the past, and sequencing the recall data sets according to the sequence of the generation time of each recall set, wherein n is a positive integer greater than 1;
the data sorting module is used for setting a fusion sorting weight parameter of each recall data set according to the distance from the ith recall time, multiplying the fusion sorting weight parameter by the corresponding original scoring of the ith Batch to obtain a new scoring result, and rearranging all audio albums in the fused recall data set in a descending order according to the new scoring result;
the weight configuration module is used for adjusting the weight of each fusion ordering weight parameter to obtain an initial ordering result;
the final recall set generation module is used for carrying out data deduplication based on the initial sequencing result, sequencing according to the final scoring and the descending order to obtain the final recall set of the TopN, wherein N is a positive integer;
and the recommendation result generation module is used for carrying out fine ordering on the final recall set based on a preset fine ordering model to obtain a recommendation result.
Preferably, the system further comprises:
the operation information judging module is used for judging whether the current operation information of the user meets a preset condition threshold value or not, and triggering a Batch through the current operation information when the current operation information meets the preset condition threshold value.
Preferably, the adjusting the weight of each fused ranking weight parameter, to obtain an initial ranking result includes:
and adjusting the weight of each fusion sequencing weight parameter of the parameters, configuring the fusion sequencing weight parameter of the recall data set of the current Batch to be the maximum, and obtaining an initial sequencing result according to the adjusted weight parameters, wherein the fusion sequencing weight parameters of the rest recall data sets are in a descending or fixed state according to the current sequencing.
Preferably, the performing data deduplication based on the initial ordering result includes:
all of the audio albums in the initial ranking result are the same in album name but scored differently, and only the one with the highest score is retained.
According to a third aspect of the present invention, there is provided an audio album recommendation apparatus based on parameter configuration, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the audio album recommendation method based on parameter configuration according to the first aspect when executing the computer program.
According to a fourth aspect of the present invention, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the parameter configuration-based audio album recommendation method according to the first aspect.
As can be seen from the above scheme, the present invention provides a method, a system, a device and a storage medium for recommending an audio album based on parameter configuration, wherein the method includes generating a recall data set of a current Batch in near real time when an ith Batch triggered by a user arrives, and sorting the audio albums in the recall data set according to a scoring of a recall algorithm, wherein i is a positive integer; fusing recall data sets of the user, including the recall data set of the current Batch, for n times in the past, and sequencing according to the sequence of the generation time of each recall set, wherein n is a positive integer greater than 1; setting a fusion ordering weight parameter of each recall data set according to the distance from the ith recall time, multiplying the original scoring of the ith Batch corresponding to the fusion ordering weight parameter in the step 1 to obtain a new scoring result, and rearranging all audio albums in the fused recall data set in a descending order according to the new scoring result; adjusting the weight of each fusion sequencing weight parameter to obtain an initial sequencing result; performing data deduplication based on the initial sequencing result, and sequencing in descending order according to the final scoring to obtain a final recall set of TopN, wherein N is a positive integer; and carrying out fine sorting on the final recall set based on a preset fine sorting model to obtain a recommended result. According to the invention, through configuration parameters, real-time interest trend and historical interest of a user can be considered, automatic fusion of different Batch recall results is realized, and parameter weights based on service understanding are considered in recall set fusion, so that flexibility of recall set generation is greatly improved, recommended results are more reasonable, and user experience is improved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
fig. 1 is a flowchart of an audio album recommendation method based on parameter configuration according to a preferred embodiment of the present invention;
fig. 2 is a schematic structural diagram of an audio album recommendation system based on parameter configuration according to a preferred embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
In the description of the present invention, it should be understood that the terms "longitudinal," "transverse," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention.
In the description of the present invention, unless otherwise specified and defined, it should be noted that the terms "mounted," "connected," and "coupled" are to be construed broadly, and may be, for example, mechanical or electrical, or may be in communication with each other between two elements, directly or indirectly through intermediaries, as would be understood by those skilled in the art, in view of the specific meaning of the terms described above.
According to a first aspect of the present invention, the present invention provides a method for recommending an audio album based on parameter configuration, as shown in fig. 1, the method may include the following steps:
s1, when the ith Batch triggered by a user arrives, generating a recall data set of the current Batch in near real time, and sorting audio albums in the recall data set according to the scoring of a recall algorithm, wherein i is a positive integer;
when a user operates on the network music platform, and when the ith Batch triggered by the user operation arrives, a preset recall algorithm is called to generate a recall data set of the current Batch in near real time, the recall data set is set as X (i), the recall audio albums are respectively scored through the recall algorithm in the recall process, and the audio albums in the recall data set are ranked according to the score of the recall algorithm.
S2, fusing recall data sets of the user, including the current Batch recall data set, for n times in the past, and sequencing according to the sequence of the generation time of each recall set, wherein n is a positive integer greater than 1;
fusing recall data sets X (i- (n-1)) of the user for n times including the recall data set X (i) of the current Batch through a preset fusion strategy, wherein X (i-1) and X (i) are sequenced according to the sequence of the recall generation time, n is a positive integer larger than 1, and the value of n can be specifically set according to the requirement.
S3, setting a fusion ordering weight parameter of each recall data set according to the distance from the ith recall time, multiplying the original scoring of the ith Batch corresponding to the fusion ordering weight parameter in the step 1 to obtain a new scoring result, and rearranging all audio albums in the fused recall data set in a descending order according to the new scoring result;
after n times of recall data sets of the user are subjected to fusion sorting through a fusion strategy, setting fusion sorting weight parameters l (i), l (i-1), i (i- (n-2)), and l (i- (n-1)) of each recall data set according to the distance from the ith recall time, multiplying the fusion sorting weight parameters with the original scoring of the corresponding ith Batch in the step S3 to obtain a new scoring result, and rearranging all audio albums in the fused recall data set in a descending order according to the new scoring result.
S4, adjusting the weight of each fusion sequencing weight parameter to obtain an initial sequencing result;
and adjusting the weight size of each fusion ordering weight parameter l (i), l (i-1), i (i- (n-2)), and l (i- (n-1)) through parameter setting to obtain an initial ordering result.
S5, carrying out data deduplication based on an initial sequencing result, and sequencing in a descending order according to a final scoring to obtain a final recall set of TopN, wherein N is a positive integer;
and S6, carrying out fine sorting on the final recall set based on a preset fine sorting model to obtain a recommended result.
After the final recall set is obtained, the final recall set is transmitted to a fine ordering module of a recommendation system, and the fine ordering module carries out fine ordering on the final recall set according to a preset fine ordering model to obtain a recommendation result.
In this embodiment, the method further includes:
judging whether current operation information of a user meets a preset condition threshold or not, and triggering a Batch through the current operation information when the current operation information meets the preset condition threshold.
In this embodiment, the adjusting the weight of each fused ranking weight parameter to obtain the initial ranking result includes:
and adjusting the weight of each fusion sequencing weight parameter of the parameters, configuring the fusion sequencing weight parameter of the recall data set of the current Batch to be the maximum, and obtaining an initial sequencing result according to the adjusted weight parameters, wherein the fusion sequencing weight parameters of the rest recall data sets are in a descending or fixed state according to the current sequencing.
For example, n= 5,l (5) =2, l (4) =1, l (3) =1, l (2) =1, l (1) =1, i.e. the recall set fusion policy, only consider recall set results of past 5 user actions, the last Batch result weight is 2, and the other 4 times weights are 1.
In this embodiment, the performing data deduplication based on the initial ordering result includes:
all of the audio albums in the initial ranking result are the same in album name but scored differently, and only the one with the highest score is retained.
According to the scheme, the audio album recommendation method based on parameter configuration is provided, when the ith Batch triggered by a user arrives, a recall data set of the current Batch is generated in near real time, the audio albums in the recall data set are ordered according to the scoring of a recall algorithm, and i is a positive integer; fusing recall data sets of the user, including the recall data set of the current Batch, for n times in the past, and sequencing according to the sequence of the generation time of each recall set, wherein n is a positive integer greater than 1; setting a fusion ordering weight parameter of each recall data set according to the distance from the ith recall time, multiplying the original scoring of the ith Batch corresponding to the fusion ordering weight parameter in the step 1 to obtain a new scoring result, and rearranging all audio albums in the fused recall data set in a descending order according to the new scoring result; adjusting the weight of each fusion sequencing weight parameter to obtain an initial sequencing result; performing data deduplication based on the initial sequencing result, and sequencing in descending order according to the final scoring to obtain a final recall set of TopN, wherein N is a positive integer; and carrying out fine sorting on the final recall set based on a preset fine sorting model to obtain a recommended result. According to the invention, through configuration parameters, real-time interest trend and historical interest of a user can be considered, automatic fusion of different Batch recall results is realized, and parameter weights based on service understanding are considered in recall set fusion, so that flexibility of recall set generation is greatly improved, recommended results are more reasonable, and user experience is improved.
According to a second aspect of the present invention, there is provided an audio album recommendation system based on parameter configuration, as shown in fig. 2, the system comprising:
the current recall data set generating module 201 is configured to generate, in near real time, a recall data set of a current Batch when the ith Batch triggered by a user arrives when the user operation meets the recommended triggering condition, and rank audio albums in the recall data set according to a score of a recall algorithm, where i is a positive integer;
when a user operates on the network music platform, and when the ith Batch triggered by the user operation arrives, a preset recall algorithm is called to generate a recall data set of the current Batch in near real time, the recall data set is set as X (i), the recall audio albums are respectively scored through the recall algorithm in the recall process, and the audio albums in the recall data set are ranked according to the score of the recall algorithm.
The data set fusion module 202 is configured to fuse recall data sets of the user, including recall data sets of the current Batch, for n times in the past, and sort the recall data sets according to the sequence of the recall set generation times, where n is a positive integer greater than 1;
fusing recall data sets X (i- (n-1)) of the user for n times including the recall data set X (i) of the current Batch through a preset fusion strategy, wherein X (i-1) and X (i) are sequenced according to the sequence of the recall generation time, n is a positive integer larger than 1, and the value of n can be specifically set according to the requirement.
The data sorting module 203 is configured to set a fusion sorting weight parameter of each recall data set according to the distance from the ith recall time, multiply the fusion sorting weight parameter with the corresponding original scoring of the ith Batch to obtain a new scoring result, and reorder all the audio albums in the fused recall data set according to the new scoring result;
after n times of recall data sets of the user are subjected to fusion sorting through a fusion strategy, setting fusion sorting weight parameters l (i), l (i-1), i (i- (n-2)), and l (i- (n-1)) of each recall data set according to the distance from the ith recall time, multiplying the fusion sorting weight parameters with the original scoring of the corresponding ith Batch in the step S3 to obtain a new scoring result, and rearranging all audio albums in the fused recall data set in a descending order according to the new scoring result.
The weight configuration module 204 is configured to adjust the weight of each fused sorting weight parameter to obtain an initial sorting result;
and adjusting the weight size of each fusion ordering weight parameter l (i), l (i-1), i (i- (n-2)), and l (i- (n-1)) through parameter setting to obtain an initial ordering result.
The final recall generation module 205 is configured to perform data deduplication based on the initial sorting result, and sort the data according to a final scoring re-descending order to obtain a final recall of TopN, where N is a positive integer;
the recommendation result generation module 206 is configured to perform a fine ranking on the final recall set based on a preset fine ranking model to obtain a recommendation result.
After the final recall set is obtained, the final recall set is transmitted to a fine ordering module of a recommendation system, and the fine ordering module carries out fine ordering on the final recall set according to a preset fine ordering model to obtain a recommendation result.
In this embodiment, the system further includes:
the operation information judging module is used for judging whether the current operation information of the user meets a preset condition threshold value or not, and triggering a Batch through the current operation information when the current operation information meets the preset condition threshold value.
In this embodiment, the adjusting the weight of each fused ranking weight parameter to obtain the initial ranking result includes:
and adjusting the weight of each fusion sequencing weight parameter of the parameters, configuring the fusion sequencing weight parameter of the recall data set of the current Batch to be the maximum, and obtaining an initial sequencing result according to the adjusted weight parameters, wherein the fusion sequencing weight parameters of the rest recall data sets are in a descending or fixed state according to the current sequencing.
For example, n= 5,l (5) =2, l (4) =1, l (3) =1, l (2) =1, l (1) =1, i.e. the recall set fusion policy, only consider recall set results of past 5 user actions, the last Batch result weight is 2, and the other 4 times weights are 1.
In this embodiment, the performing data deduplication based on the initial ordering result includes:
all of the audio albums in the initial ranking result are the same in album name but scored differently, and only the one with the highest score is retained.
According to the scheme, the audio album recommendation system based on parameter configuration is provided, when the ith Batch triggered by a user arrives, a recall data set of the current Batch is generated in near real time, the audio albums in the recall data set are ordered according to the scoring of a recall algorithm, and i is a positive integer; fusing recall data sets of the user, including the recall data set of the current Batch, for n times in the past, and sequencing according to the sequence of the generation time of each recall set, wherein n is a positive integer greater than 1; setting a fusion ordering weight parameter of each recall data set according to the distance from the ith recall time, multiplying the original scoring of the ith Batch corresponding to the fusion ordering weight parameter in the step 1 to obtain a new scoring result, and rearranging all audio albums in the fused recall data set in a descending order according to the new scoring result; adjusting the weight of each fusion sequencing weight parameter to obtain an initial sequencing result; performing data deduplication based on the initial sequencing result, and sequencing in descending order according to the final scoring to obtain a final recall set of TopN, wherein N is a positive integer; and carrying out fine sorting on the final recall set based on a preset fine sorting model to obtain a recommended result. According to the invention, through configuration parameters, real-time interest trend and historical interest of a user can be considered, automatic fusion of different Batch recall results is realized, and parameter weights based on service understanding are considered in recall set fusion, so that flexibility of recall set generation is greatly improved, recommended results are more reasonable, and user experience is improved.
According to a third aspect of the present invention, there is provided an audio album recommendation apparatus based on parameter configuration, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the audio album recommendation method based on parameter configuration according to the first aspect when executing the computer program.
According to a fourth aspect of the present invention, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the parameter configuration-based audio album recommendation method according to the first aspect.
In this embodiment, the module/unit integrated with the audio album recommendation system based on the parameter configuration may be stored in a computer readable storage medium if implemented in the form of a software function unit and sold or used as a separate product. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-only Memory (ROM), a random access Memory (RAM, randomAccess Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
Those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An audio album recommendation method based on parameter configuration, the method comprising:
s1, when the ith Batch triggered by a user arrives, generating a recall data set of the current Batch in near real time, and sorting audio albums in the recall data set according to the scoring of a recall algorithm, wherein i is a positive integer;
s2, fusing recall data sets of the user, including the current Batch recall data set, for n times in the past, and sequencing according to the sequence of the generation time of each recall set, wherein n is a positive integer greater than 1;
s3, setting a fusion ordering weight parameter of each recall data set according to the distance from the ith recall time, multiplying the original scoring of the ith Batch corresponding to the fusion ordering weight parameter in the step 1 to obtain a new scoring result, and rearranging all audio albums in the fused recall data set in a descending order according to the new scoring result;
s4, adjusting the weight of each fusion sequencing weight parameter to obtain an initial sequencing result;
s5, carrying out data deduplication based on an initial sequencing result, and sequencing in a descending order according to a final scoring to obtain a final recall set of TopN, wherein N is a positive integer;
and S6, carrying out fine sorting on the final recall set based on a preset fine sorting model to obtain a recommended result.
2. The parameter configuration-based audio album recommendation method according to claim 1, further comprising:
judging whether current operation information of a user meets a preset condition threshold or not, and triggering a Batch through the current operation information when the current operation information meets the preset condition threshold.
3. The method for recommending audio albums based on parameter configuration according to claim 1 or 2, wherein the adjusting the weight of each fusion ranking weight parameter to obtain the initial ranking result comprises:
and adjusting the weight of each fusion sequencing weight parameter of the parameters, configuring the fusion sequencing weight parameter of the recall data set of the current Batch to be the maximum, and obtaining an initial sequencing result according to the adjusted weight parameters, wherein the fusion sequencing weight parameters of the rest recall data sets are in a descending or fixed state according to the current sequencing.
4. The parameter configuration-based audio album recommendation method according to claim 1 or 2, wherein said performing data deduplication based on the initial ranking result comprises:
all of the audio albums in the initial ranking result are the same in album name but scored differently, and only the one with the highest score is retained.
5. An audio album recommendation system based on parameter configuration, the system comprising:
the current recall data set generation module is used for generating a recall data set of the current Batch in near real time when the ith Batch triggered by the user arrives when the user operation meets the recommended triggering condition, and sequencing the audio albums in the recall data set according to the scoring of a recall algorithm, wherein i is a positive integer;
the data set fusion module is used for fusing recall data sets of the user, including the recall data set of the current Batch, for n times in the past, and sequencing the recall data sets according to the sequence of the generation time of each recall set, wherein n is a positive integer greater than 1;
the data sorting module is used for setting a fusion sorting weight parameter of each recall data set according to the distance from the ith recall time, multiplying the fusion sorting weight parameter by the corresponding original scoring of the ith Batch to obtain a new scoring result, and rearranging all audio albums in the fused recall data set in a descending order according to the new scoring result;
the weight configuration module is used for adjusting the weight of each fusion ordering weight parameter to obtain an initial ordering result;
the final recall set generation module is used for carrying out data deduplication based on the initial sequencing result, sequencing according to the final scoring and the descending order to obtain the final recall set of the TopN, wherein N is a positive integer;
and the recommendation result generation module is used for carrying out fine ordering on the final recall set based on a preset fine ordering model to obtain a recommendation result.
6. A parameter configuration-based audio album recommendation system as defined in claim 5, further comprising:
the operation information judging module is used for judging whether the current operation information of the user meets a preset condition threshold value or not, and triggering a Batch through the current operation information when the current operation information meets the preset condition threshold value.
7. The parameter configuration-based audio album recommendation system according to claim 5 or 6, wherein said adjusting the weight of each fused ranking weight parameter to obtain an initial ranking result comprises:
and adjusting the weight of each fusion sequencing weight parameter of the parameters, configuring the fusion sequencing weight parameter of the recall data set of the current Batch to be the maximum, and obtaining an initial sequencing result according to the adjusted weight parameters, wherein the fusion sequencing weight parameters of the rest recall data sets are in a descending or fixed state according to the current sequencing.
8. A parameter configuration-based audio album recommendation system according to claim 5 or 6, wherein said data deduplication based on the initial ranking result comprises:
all of the audio albums in the initial ranking result are the same in album name but scored differently, and only the one with the highest score is retained.
9. An audio album recommendation apparatus based on parameter configuration comprising a memory, a processor and a computer program stored in said memory and executable on said processor, wherein said processor implements the steps of the audio album recommendation method based on parameter configuration as claimed in any one of claims 1-4 when said computer program is executed.
10. A computer readable storage medium storing a computer program, which when executed by a processor implements the steps of the parameter configuration based audio album recommendation method as defined in any one of claims 1-4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910952294.0A CN110765310B (en) | 2019-10-09 | 2019-10-09 | Audio album recommendation method and system based on parameter configuration |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910952294.0A CN110765310B (en) | 2019-10-09 | 2019-10-09 | Audio album recommendation method and system based on parameter configuration |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110765310A CN110765310A (en) | 2020-02-07 |
CN110765310B true CN110765310B (en) | 2024-01-30 |
Family
ID=69330966
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910952294.0A Active CN110765310B (en) | 2019-10-09 | 2019-10-09 | Audio album recommendation method and system based on parameter configuration |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110765310B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111625745B (en) * | 2020-05-27 | 2023-12-26 | 抖音视界有限公司 | Recommendation method, recommendation device, electronic equipment and computer readable medium |
CN112115370A (en) * | 2020-09-29 | 2020-12-22 | 贝壳技术有限公司 | Recommendation method and device, computer-readable storage medium and electronic device |
CN112287167A (en) * | 2020-10-29 | 2021-01-29 | 四川长虹电器股份有限公司 | Video recommendation recall method and device |
CN112800325B (en) * | 2021-01-15 | 2024-02-27 | 北京明略软件系统有限公司 | Material recommendation method, system, electronic equipment and storage medium |
CN114676851B (en) * | 2022-04-08 | 2024-03-29 | 中国科学技术大学 | Combined training method, equipment and storage medium for recall and sequence model |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017041484A1 (en) * | 2015-09-08 | 2017-03-16 | 腾讯科技(深圳)有限公司 | Method, apparatus, and system for recommending real-time information |
WO2018010591A1 (en) * | 2016-07-12 | 2018-01-18 | 腾讯科技(深圳)有限公司 | Information push method and apparatus, server, and storage medium |
CN108830689A (en) * | 2018-06-13 | 2018-11-16 | 深圳乐信软件技术有限公司 | Item recommendation method, device, server and storage medium |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100235313A1 (en) * | 2009-03-16 | 2010-09-16 | Tim Rea | Media information analysis and recommendation platform |
US20140278986A1 (en) * | 2013-03-14 | 2014-09-18 | Clipfile Corporation | Tagging and ranking content |
-
2019
- 2019-10-09 CN CN201910952294.0A patent/CN110765310B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017041484A1 (en) * | 2015-09-08 | 2017-03-16 | 腾讯科技(深圳)有限公司 | Method, apparatus, and system for recommending real-time information |
WO2018010591A1 (en) * | 2016-07-12 | 2018-01-18 | 腾讯科技(深圳)有限公司 | Information push method and apparatus, server, and storage medium |
CN108830689A (en) * | 2018-06-13 | 2018-11-16 | 深圳乐信软件技术有限公司 | Item recommendation method, device, server and storage medium |
Non-Patent Citations (3)
Title |
---|
何炜俊 ; 周应堂 ; .结合强弱联系和兴趣的社交网络推荐算法.广东工业大学学报.2019,(03),全文. * |
李燕 ; 张文婧 ; .基于情感分析和改进TOPSIS法的IT服务推荐算法.数学的实践与认识.2019,(09),全文. * |
邬登峰 ; 白琳 ; 王涛 ; 李慧 ; 许舒人 ; .基于多粒度特征和混合算法的文档推荐系统.计算机系统应用.2018,(03),全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN110765310A (en) | 2020-02-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110765310B (en) | Audio album recommendation method and system based on parameter configuration | |
US11449916B2 (en) | Information push method and apparatus, server, and storage medium | |
US11128582B2 (en) | Emoji recommendation method and apparatus | |
CN108287666B (en) | Data storage method and device for cloud storage environment | |
US10846332B2 (en) | Playlist list determining method and device, electronic apparatus, and storage medium | |
CA2765111C (en) | Method and system for estimating age of a user based on mass data | |
US20190220710A1 (en) | Data processing method and data processing device | |
US11630957B2 (en) | Natural language processing method and apparatus | |
CN106130972B (en) | resource access control method and device | |
CN110096617B (en) | Video classification method and device, electronic equipment and computer-readable storage medium | |
CN110781341A (en) | Audio album recommendation method and system fusing multi-strategy recall data sets | |
CN109242593B (en) | Case reasoning-based clothing recommendation method and device and storage medium | |
CN106326388A (en) | Method and device for processing information | |
CN110781340A (en) | Offline evaluation method, system and device for recall strategy of recommendation system and storage medium | |
CN110765309B (en) | Recommendation system recall method and system based on parameter configuration | |
CN110597569A (en) | Software opening page control method and device, storage medium and electronic equipment | |
CN108763506A (en) | A kind of message push processing method and device | |
CN105160003A (en) | Geographic position-based APP retrieving and ordering method and system | |
CN110909200A (en) | Offline and real-time combined audio album recommendation system recall method and system | |
CN108833493A (en) | Selection method, system and the storage medium of best transaction node in peer-to-peer network set | |
CN107301185B (en) | Music recommendation system and method | |
CN108304582A (en) | A kind of network information push method and system | |
CN110825939B (en) | Post score generation and ordering method and device, electronic equipment and storage medium | |
CN109814734B (en) | Method for correcting Chinese pinyin input and processing terminal | |
CN110781342A (en) | Recommendation system recall method and system based on user behavior sequence and data fusion |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |