CN113868443A - Multimedia resource recommendation method, device and storage medium - Google Patents
Multimedia resource recommendation method, device and storage medium Download PDFInfo
- Publication number
- CN113868443A CN113868443A CN202010623962.8A CN202010623962A CN113868443A CN 113868443 A CN113868443 A CN 113868443A CN 202010623962 A CN202010623962 A CN 202010623962A CN 113868443 A CN113868443 A CN 113868443A
- Authority
- CN
- China
- Prior art keywords
- multimedia resources
- candidate
- multimedia
- resources
- candidate multimedia
- 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 46
- 238000012216 screening Methods 0.000 claims abstract description 51
- 238000001914 filtration Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 10
- 230000002787 reinforcement Effects 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 5
- 238000005728 strengthening Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000002860 competitive effect Effects 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000013179 statistical model Methods 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
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/435—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
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/438—Presentation of query results
Abstract
The disclosure discloses a multimedia resource recommendation method, a multimedia resource recommendation device and a storage medium, relates to the technical field of mobile internet, and at least solves the problem that the accuracy of recommending multimedia resources is low in the related technology. According to the method, the multimedia resources are selected in multiple dimensions according to the characteristic information of the candidate multimedia resources, a multimedia resource set under different dimensions is obtained, and the multimedia resources selected in each dimension are comprehensively sequenced to obtain a final screening result. Therefore, the multimedia resources are selected in multiple dimensions, and high-quality candidate multimedia resources can be prevented from being filtered out, so that the accuracy of recommending the multimedia resources is improved.
Description
Technical Field
The present disclosure relates to the field of mobile internet technologies, and in particular, to a multimedia resource recommendation method, apparatus, and storage medium.
Background
With the development of the times, electronic devices have become a part of life, and various application software is generally downloaded and installed in the electronic devices in order to meet the use requirements of users. The user can watch videos, listen to music, etc. through the application software. In order to recommend multimedia resources such as videos, music or news which are interesting to the user, the application software screens the multimedia resources which are interesting to the user from a resource library through a recommendation algorithm.
However, the existing recommendation algorithm obtains a candidate multimedia resource set, then filters the candidate multimedia resources according to a uniform rule, and determines a recommendation result, for example, filters according to the number of times of displaying the candidate multimedia resources. However, as the candidate multimedia resources are filtered by using a strong rule, a part of high-quality candidate multimedia resources are killed by mistake, and the proportion of killing by mistake is higher in experiments, the accuracy of recommending the multimedia resources by the conventional recommendation method is lower.
Disclosure of Invention
The embodiment of the disclosure provides a multimedia resource recommendation method, a multimedia resource recommendation device and a storage medium, so as to improve the accuracy of recommending multimedia resources.
According to a first aspect of the embodiments of the present disclosure, a multimedia resource recommendation method is provided, including:
acquiring a candidate multimedia resource set; wherein the candidate multimedia resource set comprises at least two candidate multimedia resources;
screening the candidate multimedia resource set by at least two dimensions according to the characteristic information of the candidate multimedia resources to obtain a multimedia resource set to be recommended corresponding to each dimension; wherein the feature information is used for characterizing state information and attribute information of the candidate multimedia resources;
correcting the weight of the multimedia resources in each multimedia resource set to be recommended by using a preset weight factor to obtain a screening parameter of each multimedia resource;
and screening the multimedia resources according to the screening parameters.
In a possible implementation manner, the at least two dimensions include the historical display times of the candidate multimedia resources, and then the set of multimedia resources to be recommended corresponding to the dimension is obtained by the following method:
acquiring historical display times of the candidate multimedia resources from the characteristic information of the candidate multimedia resources;
classifying the candidate multimedia resources according to preset historical display times and the historical display times of the candidate multimedia resources;
carrying out Bayesian statistical calculation on the historical display times of the candidate multimedia resources in each class, and determining a first threshold value of each class;
and taking the set of candidate multimedia resources with the history display times of each type larger than the first threshold value as a first set of multimedia resources to be recommended.
In a possible implementation manner, the at least two dimensions include the characteristic parameters of the candidate multimedia resources, and then the set of multimedia resources to be recommended corresponding to the dimension is obtained by the following method:
determining the characteristic parameters of the candidate multimedia resources by performing characteristic extraction on the characteristic information of the candidate multimedia resources;
and taking the set of candidate multimedia resources with the characteristic parameter larger than the second threshold value as a second set of multimedia resources to be recommended.
In a possible implementation manner, the at least two dimensions include the enhancement parameters of the candidate multimedia resources, and then the set of multimedia resources to be recommended corresponding to the dimension is obtained by the following method:
acquiring the life cycle state of the candidate multimedia resource from the characteristic information of the candidate multimedia resource;
inputting the life cycle state of the candidate multimedia resource into a life cycle reinforcement learning neural network model to obtain reinforcement parameters of the candidate multimedia resource;
and taking the set of candidate multimedia resources with the strengthening parameters larger than the third threshold value as a third set of multimedia resources to be recommended.
In a possible implementation manner, if the same multimedia resource exists in each set of multimedia resources to be recommended, modifying the weight of the multimedia resource in each set of multimedia resources to be recommended by using a preset weight factor to obtain a screening parameter of each multimedia resource, including:
correcting the weight of the multimedia resources in the multimedia resource set to be recommended corresponding to each dimension screening condition by using a preset weight factor to obtain a correction parameter of each multimedia resource;
and summing the correction parameters of the same multimedia resources in each multimedia resource set to be recommended to obtain the screening parameters of the multimedia resources.
According to a second aspect of the embodiments of the present disclosure, there is provided a multimedia resource recommendation apparatus, including:
a first acquisition unit configured to perform acquisition of a set of candidate multimedia resources; wherein the candidate multimedia resource set comprises at least two candidate multimedia resources;
the first screening unit is configured to perform screening on the candidate multimedia resource set in at least two dimensions according to the feature information of the candidate multimedia resources to obtain a multimedia resource set to be recommended corresponding to each dimension; wherein the feature information is used for characterizing state information and attribute information of the candidate multimedia resources;
the correcting unit is configured to correct the weight of the multimedia resource in each set of multimedia resources to be recommended by using a preset weight factor to obtain a screening parameter of each multimedia resource;
a second filtering unit configured to perform filtering of the multimedia resource according to the filtering parameter.
In a possible implementation manner, at least two dimensions include the historical display times of the candidate multimedia resources, and then the set of multimedia resources to be recommended corresponding to the dimension is obtained by the following means:
the obtaining unit is configured to obtain the historical showing times of the candidate multimedia resources from the characteristic information of the candidate multimedia resources;
the classification unit is configured to classify the candidate multimedia resources according to preset historical display times and the historical display times of the candidate multimedia resources;
the computing unit is configured to perform Bayesian statistical computation on the historical display times of the candidate multimedia resources in each class and determine a first threshold value of each class;
and the first determining unit is configured to perform the step of taking the set of candidate multimedia resources with the history showing times larger than the first threshold value in each category as the first set of multimedia resources to be recommended.
In a possible implementation manner, the at least two dimensions include the feature parameters of the candidate multimedia resources, and then the set of multimedia resources to be recommended corresponding to the dimension is obtained by the following means:
a feature extraction unit configured to perform feature extraction on feature information of the candidate multimedia resource to determine a feature parameter of the candidate multimedia resource;
and the second determining unit is configured to execute the set of candidate multimedia resources with the characteristic parameter larger than a second threshold value as a second set of multimedia resources to be recommended.
In a possible implementation manner, the at least two dimensions include the enhancement parameters of the candidate multimedia resources, and then the set of multimedia resources to be recommended corresponding to the dimension is obtained by the following means:
a second obtaining unit configured to perform obtaining a life cycle state of the candidate multimedia resource from feature information of the candidate multimedia resource;
the input unit is configured to input the life cycle state of the candidate multimedia resource into a life cycle reinforcement learning neural network model to obtain reinforcement parameters of the candidate multimedia resource;
and the third determining unit is configured to execute the set of candidate multimedia resources with the strengthening parameter larger than the third threshold as a third set of multimedia resources to be recommended.
In a possible implementation manner, if the same multimedia resource exists in each set of multimedia resources to be recommended, the modifying unit includes:
the multimedia resource weighting subunit is configured to modify the weight of the multimedia resource in the to-be-recommended multimedia resource set corresponding to each dimension screening condition by using a preset weight factor to obtain a modification parameter of each multimedia resource;
and the summation subunit is configured to sum the correction parameters of the same multimedia resource in each to-be-recommended multimedia resource set to obtain the screening parameters of the multimedia resource.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement a multimedia resource recommendation method;
according to a fourth aspect of the embodiments of the present disclosure, there is provided a storage medium having instructions that, when executed by a processor of an electronic device, enable the electronic device to perform a multimedia resource recommendation method;
according to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the multimedia resource recommendation method provided by the embodiment of the disclosure.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
according to the characteristic information of the candidate multimedia resources, the multimedia resources are selected through multiple dimensions to obtain multimedia resource sets under different dimensions, and the multimedia resources selected through the dimensions are comprehensively sequenced to obtain a final screening result. Therefore, the multimedia resources are selected in multiple dimensions, and high-quality candidate multimedia resources can be prevented from being filtered out, so that the accuracy of recommending the multimedia resources is improved.
Additional features and advantages of the disclosure will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the disclosure. The objectives and other advantages of the disclosure may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and not to limit the disclosure. In the drawings:
FIG. 1 is a flow chart of a recommendation method in the prior art;
FIG. 2 is a flowchart illustrating a multimedia resource recommendation method according to an embodiment of the disclosure;
FIG. 3 is a schematic flow chart of a first screening method according to an embodiment of the present disclosure;
FIG. 4 is a schematic flow chart of a second screening method according to an embodiment of the present disclosure;
FIG. 5 is a schematic flow chart of a third screening method according to an embodiment of the present disclosure;
FIG. 6 is a schematic structural diagram of a multimedia resource recommendation apparatus according to an embodiment of the disclosure;
fig. 7 is a schematic structural diagram of a terminal device in an embodiment of the present disclosure.
Detailed Description
In order to improve the accuracy of recommending multimedia resources to a user, the embodiment of the disclosure provides a multimedia resource recommending method, a multimedia resource recommending device and a storage medium. In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The technical scheme provided by the embodiment of the disclosure is described below with reference to the accompanying drawings.
In the context of the information age, both information consumers and information producers have met with significant challenges. As information consumers, it is difficult to find out the information which is interested by the consumers from a large amount of information; it is also difficult for information producers to pay attention to their own information, which is a matter of concern to users. The recommendation system is the main tool to solve this contradiction.
The recommendation system can recommend multimedia information preferred by the information consumer to the information consumer, and also recommend high-quality multimedia resources produced by the information producer to the information consumer. By taking short videos as an example, in a mature video community, a producer can continuously upload videos shot by the producer, a recommendation system needs to filter out some works with low quality and not conforming to the main stream of the community under the complex condition of information overload, reasonably screen out high-quality works as a candidate set of a recommendation model, and further realize pushing the works which are liked by users, and meanwhile, the personalized interest and the diversity experience of the users are met.
An industrial recommendation system mainly comprises two stages of recalling and sorting, wherein a screening process exists between the two stages, the multimedia resources in the recall source are screened, and the screened multimedia resources are sorted.
The existing recommendation algorithm obtains a candidate multimedia resource set from a recall source, then filters the candidate multimedia resources according to a uniform rule, determines a recommendation result, and recommends a user by sequencing the recommendation result. As shown in fig. 1, which is a recommendation method in the prior art. After receiving the recommendation request, screening the multimedia resources from the i2i recall source, the u2i recall source and the FM recall source according to a uniform rule, and sequencing the screened multimedia resources to obtain a recommendation result. However, as the candidate multimedia resources are filtered by using a strong rule, a part of high-quality candidate multimedia resources are killed by mistake, and the proportion of killing by mistake is higher in experiments, the accuracy of recommending the multimedia resources by the conventional recommendation method is lower.
In view of this, the present disclosure provides a multimedia resource recommendation method for solving the above problems, in which multimedia resources are selected in multiple dimensions to obtain multimedia resource sets in different dimensions, and the multimedia resources selected in each dimension are comprehensively sorted to obtain a final screening result. By selecting the multimedia resources in multiple dimensions, high-quality candidate multimedia resources can be prevented from being filtered, and therefore the accuracy of recommending the multimedia resources is improved.
For the convenience of understanding, the technical solutions provided by the present disclosure are further described below with reference to the accompanying drawings.
Fig. 2 is a flowchart illustrating a multimedia resource recommendation method according to an exemplary embodiment, as shown in fig. 2, including the following steps.
In step S21, a candidate multimedia resource set is obtained; wherein the candidate multimedia resource set comprises at least two candidate multimedia resources.
The multimedia resources comprise multimedia information such as music, video, news and the like.
And the candidate multimedia resource set is a multimedia resource set obtained by roughly sequencing the multimedia resources in the recall source.
In step S22, according to the feature information of the candidate multimedia resources, the candidate multimedia resource set is screened in at least two dimensions to obtain a multimedia resource set to be recommended corresponding to each dimension; wherein the feature information is used for characterizing state information and attribute information of the candidate multimedia resources.
In the embodiment of the disclosure, after the candidate multimedia resource set is obtained, the candidate multimedia resource set is screened in multiple dimensions according to the feature information of the candidate multimedia resource. The characteristic information of the candidate multimedia resources comprises attribute class characteristics and statistic class characteristics; the attribute class features can extract different dimensional classes of the multimedia resource (taking a video as an example, the different dimensional classes include various portrait features of the video, such as content class features including landscapes, people, animals and the like, such as behavior class features including dancing, driving, sports and the like), producer attributes (the producer attributes refer to portrait features of a video author, including gender, age and region of the video author) and the like. The statistical type features can extract the features of historical display times, click quantity, forwarding quantity, praise quantity, playing completion degree and the like.
In an embodiment of the present disclosure, the dimension includes any one of:
the historical display times of the candidate multimedia resources are firstly counted;
in the embodiment of the present disclosure, when the candidate multimedia resources are screened by using the historical display times of the candidate multimedia resources as the dimension, the candidate multimedia resources may be classified according to the historical display times of the candidate multimedia resources, and the candidate multimedia resources meeting the condition in each class may be obtained, which may be specifically implemented as steps a1-a 4:
step A1: and acquiring the historical display times of the candidate multimedia resources from the characteristic information of the candidate multimedia resources.
Step A2: and classifying the candidate multimedia resources according to the preset historical display times and the historical display times of the candidate multimedia resources.
Wherein the preset historical display times are at least one. And dividing competitive tracks according to preset historical display times, wherein the preset historical display times are determined based on a statistical learning method.
For example, if there are two preset historical display times, which are 100 and 1000 respectively, three competitive tracks are divided according to the preset historical display times, and the range of each track is 0 to 100, 100 to 1000, and 1000 to infinity respectively. And the candidate multimedia resources are divided into corresponding tracks according to the historical display times of the candidate multimedia resources.
Step A3: and carrying out Bayesian statistical calculation on the historical display times of the candidate multimedia resources in each class, and determining a first threshold value of each class.
Wherein each track has a first threshold.
Step A4: and taking the set of candidate multimedia resources with the history display times of each type larger than the first threshold value as a first set of multimedia resources to be recommended.
In the embodiment of the disclosure, the candidate multimedia resources are screened according to the comparison between the first threshold and the historical display times of the candidate multimedia resources. For example: the method is characterized in that the method is divided into three tracks, the range of each track is 0-100, 100-1000 and 1000-infinity, and the first threshold of each track is 80, 860 and 5000 respectively. Selecting multimedia resources with historical display times larger than 80 from the first track during screening; selecting multimedia resources with historical display times larger than 860 from the second track; and selecting multimedia resources with historical display times larger than 5000 from the third track, and taking the multimedia resources screened from the three tracks as a first to-be-recommended multimedia resource set.
FIG. 3 is a schematic flow chart of the first screening method. The candidate multimedia resources are obtained by roughly sequencing the multimedia resources in various recall sources.
By developing a plurality of tracks, calculating a first threshold value in each track by using a Bayesian statistical model, and screening out multimedia resources to be recommended according to the first threshold values of the tracks. Therefore, the candidate multimedia resources with different display times are screened by different standards, the quality of the multimedia resources to be recommended can be improved, and the accuracy of recommending the multimedia resources is further improved.
Second, characteristic parameters of candidate multimedia resources;
the characteristic parameters are obtained by extracting the characteristics of the characteristic information of the candidate multimedia resources.
In the embodiment of the present disclosure, when the candidate multimedia resources are screened according to the feature parameters of the candidate multimedia resources, the multimedia resources to be recommended are screened according to the size relationship between the feature parameters of the candidate multimedia resources and the second threshold, which may be specifically implemented as steps B1-B2:
step B1: and determining the characteristic parameters of the candidate multimedia resources by performing characteristic extraction on the characteristic information of the candidate multimedia resources.
The feature information of the candidate multimedia resources is subjected to feature extraction to obtain a feature vector representing the feature information of the candidate multimedia resources, and the feature vector is scored through a scoring formula trained by a supervised learning method to obtain feature parameters of the candidate multimedia resources.
Along with the increase of platform flow, the interest of the user is continuously evolved and mined, and the fluctuation of historical statistical indexes of multimedia resources is obvious; meanwhile, in some stages of the product cycle, the introduction of special feature competitive content is also expected to adjust the sensory tone of the multimedia resources. By using the collected multimedia resource quality marking data and a part of manually labeled characteristic competitive product data, a scoring formula is trained by using a supervised learning algorithm, and the result of the formula can be used as the characteristic parameter of the multimedia resource. The learning algorithm may use rulefit (rule fitting) which is highly interpretable.
Step B2: and taking the set of candidate multimedia resources with the characteristic parameter larger than the second threshold value as a second set of multimedia resources to be recommended.
FIG. 4 is a schematic flow chart of a second screening method. And obtaining a characteristic parameter by performing characteristic extraction on the candidate multimedia resources, and comparing the characteristic parameter with a second threshold value to determine a second multimedia resource set to be recommended.
Therefore, the characteristic parameters of the candidate multimedia resources are used as important judgment bases for screening the multimedia resources, the generalization performance of the original algorithm is improved, and the long-term effect stability is ensured, so that the quality of the multimedia resources to be recommended is improved, and the accuracy of recommending the multimedia resources is further improved.
Thirdly, enhancing parameters of the candidate multimedia resources;
wherein the enhancement parameters are obtained according to the life cycle state of the candidate multimedia resources.
In the embodiment of the present disclosure, when the candidate multimedia resources are screened according to the enhancement parameters of the candidate multimedia resources, the multimedia resources to be recommended are screened according to the size relationship between the enhancement parameters of the candidate multimedia resources and the third threshold, which may be specifically implemented as steps C1-C3:
step C1: and acquiring the life cycle state of the candidate multimedia resource from the characteristic information of the candidate multimedia resource.
Like any thing, a multimedia resource also undergoes stages of induction, birth, growth, maturity, decline and the like, generally called the life cycle of the multimedia resource, and it can be determined which stage of the life cycle the candidate multimedia resource is in through the feature information of the candidate multimedia resource.
Step C2: and inputting the life cycle state of the candidate multimedia resource into a life cycle reinforcement learning neural network model to obtain reinforcement parameters of the candidate multimedia resource.
Step C3: and taking the set of candidate multimedia resources with the strengthening parameters larger than the third threshold value as a third set of multimedia resources to be recommended.
FIG. 5 is a schematic flow chart of the third screening method. And finally, comparing the enhancement parameters with a third threshold value to determine a third multimedia resource set to be recommended.
In step S23, the weights of the multimedia resources in each set of multimedia resources to be recommended are modified by a preset weight factor, so as to obtain the filtering parameters of each multimedia resource.
In step S24, the multimedia resource is filtered according to the filtering parameters.
In the embodiment of the present disclosure, after the first to-be-recommended multimedia resource set, the second to-be-recommended multimedia resource set, and the third to-be-recommended multimedia resource set are obtained, the three sets need to be filtered again.
The preset weight may be preset or determined empirically. The weight of the multimedia asset is considered to be 1 before being unmodified.
In the embodiment of the present disclosure, the preset weight factor is multiplied by the weight of the multimedia resource to obtain the screening parameter of the multimedia resource. For example: if there are 3 multimedia assets, a1, a2 and a3 respectively, and their corresponding weighting factors are w1, w2 and w3 respectively, then the filter parameters of the 3 multimedia assets are modified to be a1w1, a2w2 and a3w3 respectively. And screening the multimedia resources according to the obtained screening parameters. The multimedia resource can be selected according to the value of the screening parameter, for example: and selecting the multimedia resources in the front order according to the sequence from large to small. The multimedia resource may also be selected from multimedia resources whose filtering parameter exceeds a threshold, and this disclosure is not limited thereto.
In the screening, multimedia resources in all dimensions are screened.
Therefore, the quality of the multimedia resources can be further improved through re-screening, and the accuracy of recommending the multimedia resources is improved.
However, in the embodiment of the present disclosure, in the to-be-recommended multimedia resource set determined by the three dimensions, there may be a multimedia resource existing in multiple to-be-recommended multimedia resource sets at the same time, at this time, the multimedia resource needs to be weighted and summed, so as to obtain a final screening parameter, which may be specifically implemented as:
correcting the weight of the multimedia resources in the multimedia resource set to be recommended corresponding to each dimension screening condition by using a preset weight factor to obtain a correction parameter of each multimedia resource; and summing the correction parameters of the same multimedia resources in each multimedia resource set to be recommended to obtain the screening parameters of the multimedia resources.
For example: if one multimedia resource exists and all appears in the multimedia resource set to be recommended in three dimensions, firstly, determining correction parameters under all dimensions, and summing the correction parameters under all dimensions to obtain screening parameters. Such as: if the preset weight of a multimedia asset a1 in the first dimension is w1, the preset weight in the second dimension is w2, and the preset weight in the third dimension is w3, the filtering parameters of the multimedia asset are (w1+ w2+ w3) a 1.
Therefore, the same multimedia resources in different sets are subjected to weighted summation calculation, so that high-quality multimedia resources can be determined more accurately, and the accuracy of recommending the multimedia resources can be improved.
Multimedia resources are selected in multiple dimensions to obtain multimedia resource sets in different dimensions, and the multimedia resources selected in all dimensions are comprehensively sequenced to obtain a final screening result. Therefore, the multimedia resources are selected in multiple dimensions, and high-quality candidate multimedia resources can be prevented from being filtered, so that the overall quality of the multimedia resources is improved, and the accuracy of recommending the multimedia resources is further improved.
Based on the same inventive concept, the disclosure also provides a multimedia resource recommendation device. Fig. 6 is a schematic diagram of a multimedia resource recommendation apparatus according to the present disclosure. The device includes:
a first obtaining unit 601 configured to perform obtaining a candidate multimedia resource set; wherein the candidate multimedia resource set comprises at least two candidate multimedia resources;
a first screening unit 602, configured to perform screening on the candidate multimedia resource set in at least two dimensions according to the feature information of the candidate multimedia resource, so as to obtain a to-be-recommended multimedia resource set corresponding to each dimension; wherein the feature information is used for characterizing state information and attribute information of the candidate multimedia resources;
a correcting unit 603 configured to correct the weight of the multimedia resource in each set of multimedia resources to be recommended by using a preset weight factor, so as to obtain a screening parameter of each multimedia resource;
a second filtering unit 604 configured to perform filtering of the multimedia resource according to the filtering parameter.
In a possible implementation manner, at least two dimensions include the historical display times of the candidate multimedia resources, and then the set of multimedia resources to be recommended corresponding to the dimension is obtained by the following means:
the obtaining unit is configured to obtain the historical showing times of the candidate multimedia resources from the characteristic information of the candidate multimedia resources;
the classification unit is configured to classify the candidate multimedia resources according to preset historical display times and the historical display times of the candidate multimedia resources;
the computing unit is configured to perform Bayesian statistical computation on the historical display times of the candidate multimedia resources in each class and determine a first threshold value of each class;
and the first determining unit is configured to perform the step of taking the set of candidate multimedia resources with the history showing times larger than the first threshold value in each category as the first set of multimedia resources to be recommended.
In a possible implementation manner, the at least two dimensions include the feature parameters of the candidate multimedia resources, and then the set of multimedia resources to be recommended corresponding to the dimension is obtained by the following means:
a feature extraction unit configured to perform feature extraction on feature information of the candidate multimedia resource to determine a feature parameter of the candidate multimedia resource;
and the second determining unit is configured to execute the set of candidate multimedia resources with the characteristic parameter larger than a second threshold value as a second set of multimedia resources to be recommended.
In a possible implementation manner, the at least two dimensions include the enhancement parameters of the candidate multimedia resources, and then the set of multimedia resources to be recommended corresponding to the dimension is obtained by the following means:
a second obtaining unit configured to perform obtaining a life cycle state of the candidate multimedia resource from feature information of the candidate multimedia resource;
the input unit is configured to input the life cycle state of the candidate multimedia resource into a life cycle reinforcement learning neural network model to obtain reinforcement parameters of the candidate multimedia resource;
and the third determining unit is configured to execute the set of candidate multimedia resources with the strengthening parameter larger than the third threshold as a third set of multimedia resources to be recommended.
In a possible implementation manner, if the same multimedia resource exists in each set of multimedia resources to be recommended, the modifying unit 603 includes:
the multimedia resource weighting subunit is configured to modify the weight of the multimedia resource in the to-be-recommended multimedia resource set corresponding to each dimension screening condition by using a preset weight factor to obtain a modification parameter of each multimedia resource;
and the summation subunit is configured to sum the correction parameters of the same multimedia resource in each to-be-recommended multimedia resource set to obtain the screening parameters of the multimedia resource.
As shown in fig. 7, based on the same technical concept, the embodiment of the present disclosure also provides an electronic device 70, which may include a memory 701 and a processor 702.
The memory 701 is used for storing a computer program executed by the processor 702. The memory 701 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to use of the task management device, and the like. The processor 702 may be a Central Processing Unit (CPU), a digital processing unit, or the like. The specific connection medium between the memory 701 and the processor 702 is not limited in the embodiments of the present disclosure. In fig. 7, the memory 701 and the processor 702 are connected by a bus 703, the bus 703 is represented by a thick line in fig. 7, and the connection manner between other components is merely illustrative and not limited. The bus 703 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 7, but this is not intended to represent only one bus or type of bus.
The memory 701 may be a volatile memory (volatile memory), such as a random-access memory (RAM); the memory 701 may also be a non-volatile memory (non-volatile memory) such as, but not limited to, a read-only memory (rom), a flash memory (flash memory), a Hard Disk Drive (HDD) or a solid-state drive (SSD), or any other medium which can be used to carry or store desired program code in the form of instructions or data structures and which can be accessed by a computer. Memory 701 may be a combination of the above.
A processor 702 for executing the method performed by the apparatus in the embodiment shown in fig. 2 when invoking the computer program stored in said memory 701.
In some possible embodiments, various aspects of the methods provided by the present disclosure may also be implemented in the form of a program product including program code for causing a computer device to perform the steps of the methods according to various exemplary embodiments of the present disclosure described above in this specification when the program product is run on the computer device, for example, the computer device may perform the methods performed by the devices in the embodiments shown in fig. 2-6.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
While preferred embodiments of the present disclosure have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A method for recommending multimedia resources, the method comprising:
acquiring a candidate multimedia resource set; wherein the candidate multimedia resource set comprises at least two candidate multimedia resources;
screening the candidate multimedia resource set by at least two dimensions according to the characteristic information of the candidate multimedia resources to obtain a multimedia resource set to be recommended corresponding to each dimension; wherein the feature information is used for characterizing state information and attribute information of the candidate multimedia resources;
correcting the weight of the multimedia resources in each multimedia resource set to be recommended by using a preset weight factor to obtain a screening parameter of each multimedia resource;
and screening the multimedia resources according to the screening parameters.
2. The method according to claim 1, wherein the at least two dimensions include the historical display times of the candidate multimedia resources, and the set of multimedia resources to be recommended corresponding to the dimension is obtained as follows:
acquiring historical display times of the candidate multimedia resources from the characteristic information of the candidate multimedia resources;
classifying the candidate multimedia resources according to preset historical display times and the historical display times of the candidate multimedia resources;
carrying out Bayesian statistical calculation on the historical display times of the candidate multimedia resources in each class, and determining a first threshold value of each class;
and taking the set of candidate multimedia resources with the history display times of each type larger than the first threshold value as a first set of multimedia resources to be recommended.
3. The method according to claim 1, wherein the at least two dimensions include feature parameters of the candidate multimedia resources, and a set of multimedia resources to be recommended corresponding to the dimension is obtained as follows:
determining the characteristic parameters of the candidate multimedia resources by performing characteristic extraction on the characteristic information of the candidate multimedia resources;
and taking the set of candidate multimedia resources with the characteristic parameter larger than the second threshold value as a second set of multimedia resources to be recommended.
4. The method according to claim 1, wherein the at least two dimensions include enhancement parameters of the candidate multimedia resources, and a set of multimedia resources to be recommended corresponding to the dimension is obtained as follows:
acquiring the life cycle state of the candidate multimedia resource from the characteristic information of the candidate multimedia resource;
inputting the life cycle state of the candidate multimedia resource into a life cycle reinforcement learning neural network model to obtain reinforcement parameters of the candidate multimedia resource;
and taking the set of candidate multimedia resources with the strengthening parameters larger than the third threshold value as a third set of multimedia resources to be recommended.
5. The method of claim 1, wherein if the same multimedia resource exists in each set of multimedia resources to be recommended, modifying the weight of the multimedia resource in each set of multimedia resources to be recommended by a preset weight factor to obtain a filtering parameter of each multimedia resource, the method comprises:
correcting the weight of the multimedia resources in the multimedia resource set to be recommended corresponding to each dimension screening condition by using a preset weight factor to obtain a correction parameter of each multimedia resource;
and summing the correction parameters of the same multimedia resources in each multimedia resource set to be recommended to obtain the screening parameters of the multimedia resources.
6. A multimedia resource recommendation apparatus, comprising:
a first acquisition unit configured to perform acquisition of a set of candidate multimedia resources; wherein the candidate multimedia resource set comprises at least two candidate multimedia resources;
the first screening unit is configured to perform screening on the candidate multimedia resource set in at least two dimensions according to the feature information of the candidate multimedia resources to obtain a multimedia resource set to be recommended corresponding to each dimension; wherein the feature information is used for characterizing state information and attribute information of the candidate multimedia resources;
the correcting unit is configured to correct the weight of the multimedia resource in each set of multimedia resources to be recommended by using a preset weight factor to obtain a screening parameter of each multimedia resource;
a second filtering unit configured to perform filtering of the multimedia resource according to the filtering parameter.
7. The apparatus according to claim 6, wherein the at least two dimensions include historical presentation times of the candidate multimedia resources, and then the set of multimedia resources to be recommended corresponding to the dimension is obtained by:
the obtaining unit is configured to obtain the historical showing times of the candidate multimedia resources from the characteristic information of the candidate multimedia resources;
the classification unit is configured to classify the candidate multimedia resources according to preset historical display times and the historical display times of the candidate multimedia resources;
the computing unit is configured to perform Bayesian statistical computation on the historical display times of the candidate multimedia resources in each class and determine a first threshold value of each class;
and the first determining unit is configured to perform the step of taking the set of candidate multimedia resources with the history showing times larger than the first threshold value in each category as the first set of multimedia resources to be recommended.
8. The apparatus according to claim 6, wherein the at least two dimensions include feature parameters of the candidate multimedia resources, and then the set of multimedia resources to be recommended corresponding to the dimension is obtained by:
a feature extraction unit configured to perform feature extraction on feature information of the candidate multimedia resource to determine a feature parameter of the candidate multimedia resource;
and the second determining unit is configured to execute the set of candidate multimedia resources with the characteristic parameter larger than a second threshold value as a second set of multimedia resources to be recommended.
9. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the multimedia resource recommendation method of any of claims 1-5.
10. A storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the multimedia asset recommendation method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010623962.8A CN113868443A (en) | 2020-06-30 | 2020-06-30 | Multimedia resource recommendation method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010623962.8A CN113868443A (en) | 2020-06-30 | 2020-06-30 | Multimedia resource recommendation method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113868443A true CN113868443A (en) | 2021-12-31 |
Family
ID=78981023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010623962.8A Pending CN113868443A (en) | 2020-06-30 | 2020-06-30 | Multimedia resource recommendation method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113868443A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663010A (en) * | 2012-03-20 | 2012-09-12 | 复旦大学 | Personalized image browsing and recommending method based on labelling semantics and system thereof |
| US20130028573A1 (en) * | 2011-07-26 | 2013-01-31 | Nimrod Hoofien | Goal-based video delivery system |
| CN106168980A (en) * | 2016-07-26 | 2016-11-30 | 合网络技术（北京）有限公司 | Multimedia resource recommends sort method and device |
| CN106802915A (en) * | 2016-12-09 | 2017-06-06 | 宁波大学 | A kind of academic resources based on user behavior recommend method |
| CN108228824A (en) * | 2017-12-29 | 2018-06-29 | 暴风集团股份有限公司 | Recommendation method, apparatus, electronic equipment, medium and the program of a kind of video |
| CN108665148A (en) * | 2018-04-18 | 2018-10-16 | 腾讯科技（深圳）有限公司 | A kind of e-sourcing quality evaluating method, device and storage medium |
| CN109639786A (en) * | 2018-12-04 | 2019-04-16 | 北京达佳互联信息技术有限公司 | Distribution method, device, server and the storage medium of multimedia resource |
| CN110573837A (en) * | 2017-06-30 | 2019-12-13 | Oppo广东移动通信有限公司 | Navigation method, navigation device, storage medium and server |
| CN110929052A (en) * | 2019-12-03 | 2020-03-27 | 北京奇艺世纪科技有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
-
2020
- 2020-06-30 CN CN202010623962.8A patent/CN113868443A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130028573A1 (en) * | 2011-07-26 | 2013-01-31 | Nimrod Hoofien | Goal-based video delivery system |
| CN102663010A (en) * | 2012-03-20 | 2012-09-12 | 复旦大学 | Personalized image browsing and recommending method based on labelling semantics and system thereof |
| CN106168980A (en) * | 2016-07-26 | 2016-11-30 | 合网络技术（北京）有限公司 | Multimedia resource recommends sort method and device |
| CN106802915A (en) * | 2016-12-09 | 2017-06-06 | 宁波大学 | A kind of academic resources based on user behavior recommend method |
| CN110573837A (en) * | 2017-06-30 | 2019-12-13 | Oppo广东移动通信有限公司 | Navigation method, navigation device, storage medium and server |
| CN108228824A (en) * | 2017-12-29 | 2018-06-29 | 暴风集团股份有限公司 | Recommendation method, apparatus, electronic equipment, medium and the program of a kind of video |
| CN108665148A (en) * | 2018-04-18 | 2018-10-16 | 腾讯科技（深圳）有限公司 | A kind of e-sourcing quality evaluating method, device and storage medium |
| CN109639786A (en) * | 2018-12-04 | 2019-04-16 | 北京达佳互联信息技术有限公司 | Distribution method, device, server and the storage medium of multimedia resource |
| CN110929052A (en) * | 2019-12-03 | 2020-03-27 | 北京奇艺世纪科技有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110704674B (en) | Video playing integrity prediction method and device | |
| CN106651542B (en) | Article recommendation method and device | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| US9684656B2 (en) | Creating personalized and continuous playlists for a content sharing platform based on user history | |
| WO2015188699A1 (en) | Item recommendation method and device | |
| US9495645B2 (en) | Method and system of iteratively autotuning prediction parameters in a media content recommender | |
| CN109753601B (en) | Method and device for determining click rate of recommended information and electronic equipment | |
| CN111816312B (en) | Health state detection method and equipment based on model interpretation and readable storage medium | |
| CN111522724B (en) | Method and device for determining abnormal account number, server and storage medium | |
| CN110856037A (en) | Video cover determination method and device, electronic equipment and readable storage medium | |
| CN108595526B (en) | Resource recommendation method and device | |
| CN111611496A (en) | Product recommendation method and device | |
| CN111241381A (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN112202849A (en) | Content distribution method, content distribution device, electronic equipment and computer-readable storage medium | |
| CN114239697A (en) | Target object classification method and device, electronic equipment and storage medium | |
| CN111784384B (en) | Payment service data processing method, device, equipment and system | |
| CN111177564B (en) | Product recommendation method and device | |
| CN112449002A (en) | Method, device and equipment for pushing object to be pushed and storage medium | |
| CN112565902A (en) | Video recommendation method and device and electronic equipment | |
| CN113868443A (en) | Multimedia resource recommendation method, device and storage medium | |
| CN106445922A (en) | Method and device for determining title of multimedia resource | |
| CN112801053B (en) | Video data processing method and device | |
| CN107220269B (en) | Personalized recommendation method for geographic position sensitive app | |
| CN106445934A (en) | Data processing method and apparatus | |
| CN112822527B (en) | Video recommendation method and device, server and storage medium |
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 |