CN112000821A - Multimedia information pushing method, device, server and storage medium - Google Patents

Multimedia information pushing method, device, server and storage medium Download PDF

Info

Publication number
CN112000821A
CN112000821A CN202010848523.7A CN202010848523A CN112000821A CN 112000821 A CN112000821 A CN 112000821A CN 202010848523 A CN202010848523 A CN 202010848523A CN 112000821 A CN112000821 A CN 112000821A
Authority
CN
China
Prior art keywords
information
multimedia information
sorting
model
account
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.)
Granted
Application number
CN202010848523.7A
Other languages
Chinese (zh)
Other versions
CN112000821B (en
Inventor
张志伟
林靖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Dajia Internet Information Technology Co Ltd
Original Assignee
Beijing Dajia Internet Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Dajia Internet Information Technology Co Ltd filed Critical Beijing Dajia Internet Information Technology Co Ltd
Priority to CN202010848523.7A priority Critical patent/CN112000821B/en
Publication of CN112000821A publication Critical patent/CN112000821A/en
Application granted granted Critical
Publication of CN112000821B publication Critical patent/CN112000821B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F16/438—Presentation of query results
    • 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
    • G06F16/44—Browsing; Visualisation therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present disclosure relates to a multimedia information pushing method, apparatus, server and storage medium, the method comprising: acquiring candidate multimedia information corresponding to an account to be pushed; obtaining a ranking label of each candidate multimedia information through a target ranking model; the target ordering model is obtained by fusing tree models selected from at least two information ordering models and is used for outputting an ordering label of the multimedia information; sequencing all candidate multimedia information according to the sequencing tag to obtain sequenced candidate multimedia information; and pushing the sorted candidate multimedia information to an account to be pushed. By adopting the method, the target ordering model for ordering the candidate multimedia information is obtained by fusing the tree models selected from at least two information ordering models, and the model structure of the model is not redundant, so that the overall operation efficiency of the target ordering model is higher, and the pushing efficiency of the multimedia information is improved.

Description

Multimedia information pushing method, device, server and storage medium
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a multimedia information pushing method, an apparatus, a server, and a storage medium.
Background
With the development of computer technology, various applications for browsing multimedia information are on the verge, and more users choose to browse multimedia information, such as videos, pictures and the like, through the applications; in order to realize accurate pushing of multimedia information, generally, the recalled information needs to be sorted.
In the related art, in order to integrate the advantages of different information ranking models in information ranking, the current multimedia information pushing method generally trains and obtains another information ranking model (the model structure of the information ranking model comprises the model structure of the trained information ranking model) on the basis of one information ranking model, continues to train and obtain another information ranking model on the basis of the trained information ranking model, and so on until the last information ranking model is obtained by training and is used as a final fusion model, performs ranking processing on multimedia information through the fusion model, and then pushes the ranked multimedia information to a corresponding account; however, if the number of the information ranking models is large, the model structure of the fusion model obtained by gradual accumulation training is more and more complex, redundancy is likely to occur, the ranking processing time of the multimedia information is long, and the pushing efficiency of the multimedia information is low.
Disclosure of Invention
The present disclosure provides a multimedia information pushing method, apparatus, server and storage medium, so as to at least solve the problem of low multimedia information pushing efficiency in the related art. The technical scheme of the disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, there is provided a multimedia information pushing method, including:
acquiring candidate multimedia information corresponding to an account to be pushed;
obtaining a ranking label of each candidate multimedia information through a target ranking model; the target ordering model is obtained by fusing tree models selected from at least two information ordering models and used for outputting ordering labels of multimedia information, and the number of the tree models selected from each information ordering model is determined according to the information ordering accuracy of each information ordering model;
according to the sorting label, sorting each candidate multimedia information to obtain sorted candidate multimedia information;
and pushing the sorted candidate multimedia information to the account to be pushed.
In an exemplary embodiment, the obtaining of candidate multimedia information corresponding to an account to be pushed includes:
receiving an information pushing request of the account to be pushed; the information pushing request comprises key information triggered and input by the account to be pushed;
and recalling multimedia information with the information matching degree higher than the preset matching degree from an information base, wherein the multimedia information is used as candidate multimedia information corresponding to the account to be pushed.
In an exemplary embodiment, the obtaining candidate multimedia information corresponding to an account to be pushed further includes:
acquiring account characteristics of an account to be pushed;
acquiring multimedia information categories according with the account characteristics;
and screening out the multimedia information which accords with the account characteristics from the multimedia information corresponding to the multimedia information category, and taking the multimedia information as candidate multimedia information corresponding to the account to be pushed.
In an exemplary embodiment, the filtering out multimedia information that meets the account characteristics from the multimedia information corresponding to the multimedia information category includes:
acquiring information characteristics of the multimedia information corresponding to the multimedia information category;
acquiring feature similarity between the account features and each information feature;
and screening out the multimedia information with the characteristic similarity larger than the preset similarity from the multimedia information corresponding to the multimedia information category as the multimedia information according with the account characteristics.
In an exemplary embodiment, the pushing the ranked candidate multimedia information to the account to be pushed includes:
sequentially screening out a preset number of candidate multimedia information from the sorted candidate multimedia information as target multimedia information corresponding to the account to be pushed;
and pushing the target multimedia information to the account to be pushed according to a preset pushing frequency.
In an exemplary embodiment, the target ranking model is obtained by fusing:
obtaining information sorting accuracy of at least two information sorting models, and determining the number of tree models selected from each information sorting model according to the information sorting accuracy;
according to a preset selection sequence, correspondingly selecting tree models corresponding to the number of the tree models from the tree models contained in the information sorting models to obtain the tree models correspondingly selected from the information sorting models;
and carrying out fusion processing on the tree models correspondingly selected from the information sorting models to obtain the target sorting model.
In an exemplary embodiment, the obtaining information ranking accuracies of at least two information ranking models includes:
collecting a test sample set; the test sample set comprises sample multimedia information and an actual sequencing label corresponding to the sample multimedia information;
respectively inputting the sample multimedia information into each information sorting model to obtain a prediction sorting label of each information sorting model for the sample multimedia information;
and respectively obtaining the error between the predicted sorting label of the sample multimedia information and the actual sorting label of the sample multimedia information of each information sorting model, and obtaining the information sorting accuracy of each information sorting model according to the error.
According to a second aspect of the embodiments of the present disclosure, there is provided a multimedia information pushing apparatus, including:
the multimedia message information acquisition unit is configured to execute acquisition of candidate multimedia message information corresponding to the account to be pushed;
the sequencing label determining unit is configured to execute a target sequencing model to obtain a sequencing label of each candidate multimedia message; the target ordering model is obtained by fusing tree models selected from at least two information ordering models and used for outputting ordering labels of multimedia information, and the number of the tree models selected from each information ordering model is determined according to the information ordering accuracy of each information ordering model;
the multimedia information sorting unit is configured to execute sorting of the candidate multimedia information according to the sorting label to obtain sorted candidate multimedia information;
and the multimedia information pushing unit is configured to execute pushing of the sorted candidate multimedia information to the account to be pushed.
In an exemplary embodiment, the multimedia information obtaining unit is further configured to execute receiving an information push request of the account to be pushed; the information pushing request comprises key information triggered and input by the account to be pushed; and recalling multimedia information with the information matching degree higher than the preset matching degree from an information base, wherein the multimedia information is used as candidate multimedia information corresponding to the account to be pushed.
In an exemplary embodiment, the multimedia information obtaining unit is further configured to perform obtaining an account feature of an account to be pushed; acquiring multimedia information categories according with the account characteristics; and screening out the multimedia information which accords with the account characteristics from the multimedia information corresponding to the multimedia information category, and taking the multimedia information as candidate multimedia information corresponding to the account to be pushed.
In an exemplary embodiment, the multimedia information obtaining unit is further configured to perform obtaining information characteristics of the multimedia information corresponding to the multimedia information category; acquiring feature similarity between the account features and each information feature; and screening out the multimedia information with the characteristic similarity larger than the preset similarity from the multimedia information corresponding to the multimedia information category as the multimedia information according with the account characteristics.
In an exemplary embodiment, the multimedia information pushing unit is further configured to perform filtering out a preset number of candidate multimedia information in sequence from the sorted candidate multimedia information as target multimedia information corresponding to the account to be pushed; and pushing the target multimedia information to the account to be pushed according to a preset pushing frequency.
In an exemplary embodiment, the apparatus further includes a model fusion unit configured to perform obtaining information sorting accuracies of at least two information sorting models, and determine the number of tree models selected from each of the information sorting models according to the information sorting accuracies; according to a preset selection sequence, correspondingly selecting tree models corresponding to the number of the tree models from the tree models contained in the information sorting models to obtain the tree models correspondingly selected from the information sorting models; and carrying out fusion processing on the tree models correspondingly selected from the information sorting models to obtain the target sorting model.
In an exemplary embodiment, the model fusion unit is further configured to perform acquiring a set of test samples; the test sample set comprises sample multimedia information and an actual sequencing label corresponding to the sample multimedia information; respectively inputting the sample multimedia information into each information sorting model to obtain a prediction sorting label of each information sorting model for the sample multimedia information; and respectively obtaining the error between the predicted sorting label of the sample multimedia information and the actual sorting label of the sample multimedia information of each information sorting model, and obtaining the information sorting accuracy of each information sorting model according to the error.
According to a third aspect of the embodiments of the present disclosure, there is provided a server, including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the multimedia information pushing method as described in any embodiment of the first aspect.
According to a fourth aspect of embodiments of the present disclosure, there is provided a storage medium including: the instructions in the storage medium, when executed by a processor of a server, enable the server to perform the multimedia information push method described in any of the embodiments of the first aspect.
According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product, the program product comprising a computer program, the computer program being stored in a readable storage medium, from which the at least one processor of the device reads and executes the computer program, so that the device performs the multimedia information pushing method described in any one of the embodiments of the first aspect.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
acquiring candidate multimedia information corresponding to an account to be pushed; then, obtaining a ranking label of each candidate multimedia information through a target ranking model; the target ordering model is obtained by fusing tree models selected from at least two information ordering models and used for outputting ordering labels of the multimedia information, and the number of the tree models selected from each information ordering model is determined according to the information ordering accuracy of each information ordering model; finally, according to the sorting labels, sorting the candidate multimedia information to obtain the sorted candidate multimedia information; pushing the sorted candidate multimedia information to an account to be pushed; the aim of sorting the candidate multimedia information according to the target sorting model obtained by fusing the tree models selected from the at least two information sorting models is fulfilled, and as the model structure of the target sorting model obtained by fusing the tree models selected from the at least two information sorting models is not redundant, the overall operation efficiency of the target sorting model is higher, the sorting efficiency of the multimedia information is improved, and the pushing efficiency of the multimedia information is improved; meanwhile, the defect that the model structure of the fusion model obtained by gradual accumulation training is easy to generate redundancy, so that the sequencing processing time of the multimedia information is long, and the pushing efficiency of the multimedia information is low is overcome.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
Fig. 1 is a diagram illustrating an application environment of a multimedia information push method according to an exemplary embodiment.
Fig. 2 is a flowchart illustrating a multimedia information push method according to an exemplary embodiment.
FIG. 3 is a flowchart illustrating the fusion steps of the target ranking model according to an exemplary embodiment.
Fig. 4 is a flowchart illustrating another multimedia information push method according to an exemplary embodiment.
Fig. 5 is a block diagram illustrating a multimedia information push apparatus according to an exemplary embodiment.
Fig. 6 is an internal block diagram of a server according to an example embodiment.
Detailed Description
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 multimedia information pushing method provided by the present disclosure can be applied to the application environment shown in fig. 1. The terminal 110 interacts with the server 120 through a network, and the server 120 obtains candidate multimedia information corresponding to an account to be pushed and logged in the terminal 110; obtaining a ranking label of each candidate message through a target ranking model; the target ordering model is obtained by fusing tree models selected from at least two information ordering models and used for outputting ordering labels of the multimedia information, and the number of the tree models selected from each information ordering model is determined according to the information ordering accuracy of each information ordering model; sequencing all candidate multimedia information according to the sequencing tag to obtain sequenced candidate multimedia information; and pushing the sorted candidate multimedia information to a terminal 110 corresponding to the account to be pushed, wherein the terminal 110 displays the sorted candidate multimedia information through a terminal interface. The terminal 110 may be, but is not limited to, various smart phones, tablet computers, notebook computers, or the like, and the server 120 may be implemented by an independent server or a server cluster formed by a plurality of servers.
Fig. 2 is a flowchart illustrating a multimedia information push method according to an exemplary embodiment, where, as shown in fig. 2, the multimedia information push method is used in the server shown in fig. 1, and includes the following steps:
in step S210, candidate multimedia information corresponding to the account to be pushed is acquired.
The account refers to a registered account of an application program in the terminal, such as a registered account of a short video application program, a registered account of a video browsing program, and the like. The account to be pushed refers to an authorized account which needs to be processed and analyzed, and specifically refers to a pushing object of the candidate multimedia information; in an actual scene, the account to be pushed may refer to a pushed object of a video or a pushed object of a picture.
The candidate multimedia information refers to multimedia information which is preliminarily screened from mass multimedia information and accords with the account to be pushed, such as favorite videos and pictures of the account to be pushed; in an actual scene, the candidate multimedia information may refer to multimedia information such as videos and pictures recalled based on a recall algorithm such as a hotspot recall algorithm, a theme recall algorithm, a collaborative recall algorithm, a related recall algorithm, an environmental recall algorithm, and the like.
Specifically, the server receives a multimedia information pushing request of an account to be pushed, and screens out multimedia information conforming to the account to be pushed from a local database or a network according to the multimedia information pushing request of the account to be pushed, wherein the multimedia information is used as candidate multimedia information corresponding to the account to be pushed. Therefore, the candidate multimedia information corresponding to the account to be pushed is obtained, the candidate multimedia information corresponding to the account to be pushed can be conveniently sequenced subsequently, all the multimedia information does not need to be sequenced, the sequencing processing time of the multimedia information is reduced, and the efficiency of subsequently pushing the multimedia information is further improved.
For example, in a video search scene, a terminal responds to a video search operation of a currently logged account to be pushed on a terminal interface to obtain a keyword, such as AAA, input by the account to be pushed; generating an information pushing request according to a keyword input by an account to be pushed, and sending the information pushing request to a corresponding server; the server analyzes the received information pushing request to obtain keywords input by the account to be pushed, and screens out videos conforming to the account to be pushed from an information base in which a plurality of videos are stored to serve as candidate multimedia information corresponding to the account to be pushed.
Further, the server may further obtain an account feature code of the account to be pushed and information feature codes of each piece of information in the information base, respectively determine feature similarities between the account feature codes and the information feature codes, and screen out multimedia information with the feature similarity greater than a preset similarity (for example, 0.6) from each piece of multimedia information in the information base, as candidate multimedia information corresponding to the account to be pushed. The account characteristics refer to attribute characteristics of the account to be pushed, such as gender, age, region, occupation, interest and the like, and the information characteristics refer to attribute characteristics of information, such as information content, information author, information tag and the like; the account feature coding refers to a low-dimensional feature vector which is subjected to compression coding and used for representing low-level semantics of account features, the information feature coding refers to a low-dimensional feature vector which is subjected to compression coding and used for representing low-level semantics of information features, and the low-dimensional feature vector and the information feature coding are obtained through pre-trained feature coding generation model learning.
In step S220, obtaining a ranking label of each candidate multimedia information through the target ranking model; the target ordering model is obtained by fusing tree models selected from at least two information ordering models and used for outputting ordering labels of the multimedia information, and the number of the tree models selected from each information ordering model is determined according to the information ordering accuracy of each information ordering model.
Wherein, the ranking label refers to the ranking basis of the candidate multimedia information, and can be CTR (Click-Through-Rate), relevancy, and the like; in an actual scene, the higher the CTR or the correlation of the candidate multimedia information is, the higher the ranking position of the candidate multimedia information is.
The information sorting model is a decision forest model which is used for sorting multimedia information and comprises a plurality of tree models, such as a model obtained by training data based on artificial labeling, a model obtained by training data based on posterior behavior, and the like; the model obtained based on the data training of the artificial labeling has a better effect on the relevance, and the model obtained based on the data training of the posterior behavior has a better effect on the online index.
The Tree model is a model with a Tree-shaped branch structure based on feature space division, such as a GBDT (Gradient Boost Decision Tree) model, an XGBoost (eXtreme Gradient Boost) Tree model, a LightGBM (Light Gradient Boost Machine) Tree model, and the like.
The information sorting accuracy is used for measuring the accuracy of the sorting label output by the information sorting model, and the information sorting accuracies corresponding to different information sorting models are different; and if the information sorting accuracy of the information sorting model is higher, the larger the number of the tree models selected from the information sorting model is.
The target ordering model is a fusion model which is obtained by fusing tree models selected from at least two information ordering models and is used for ordering the multimedia information so as to output an ordering label of the multimedia information; it should be noted that the at least two information ranking models refer to two or more information ranking models, and the disclosure is not limited in this respect.
Specifically, the server inputs candidate multimedia information into a target sorting model, and outputs an initial sorting label of the candidate multimedia information through each information sorting model in the target sorting model; screening out the initial sorting label with the largest ratio from the initial sorting labels of the candidate multimedia information output by each information sorting model to serve as the sorting label of the candidate multimedia information; with reference to this method, the ranking label of each candidate multimedia message can be obtained. Therefore, the target ordering model for ordering the candidate multimedia information is obtained by fusing the tree models selected from the at least two information ordering models, and the model structure of the model is not redundant, so that the overall operation efficiency of the target ordering model is high, the ordering processing of the candidate multimedia information is fast, and the subsequent multimedia information pushing efficiency is improved.
For example, if there are 6 information ranking models, if the initial ranking labels of the candidate multimedia information output by each information ranking model are a1, a2, A3, a1, a2, and a1, respectively, the ratio of the initial ranking label to a1 is the largest, and the final ranking label of the candidate multimedia information is a 1.
Furthermore, the server can input the candidate multimedia information into the target sorting model and output the initial sorting label of the candidate multimedia information through each information sorting model in the target sorting model; acquiring weights corresponding to the information sorting accuracy of each information sorting model, wherein the weights correspond to the initial sorting labels of the candidate multimedia information output by each information sorting model; according to the weight of the initial sorting label of the candidate multimedia information output by each information sorting model, carrying out weighting processing on the initial sorting label of the candidate multimedia information output by each information sorting model to obtain the sorting label of the candidate multimedia information; with reference to this method, the ranking label of each candidate multimedia message can be obtained.
For example, if the initial ranking tag is the initial click rate, the server may perform weighting processing on the initial click rates of the candidate multimedia information output by each information ranking model according to the weight of the initial click rate of the candidate multimedia information output by each information ranking model, to obtain a target click rate of the candidate multimedia information, which is used as the ranking tag of the candidate multimedia information.
In step S230, the candidate multimedia information is ranked according to the ranking label, so as to obtain ranked candidate multimedia information.
For example, the server sorts each candidate multimedia information according to the order of the click rate or the degree of correlation from high to low, so as to obtain the sorted candidate multimedia information. Therefore, the efficiency of outputting the sorting labels through the target sorting model is high, so that the sorting time of the candidate multimedia information is greatly shortened, the sorting efficiency of the multimedia information is improved, and the subsequent multimedia information pushing efficiency is further improved.
In step S240, the sorted candidate multimedia information is pushed to an account to be pushed.
Specifically, the server pushes the sorted candidate multimedia information to a corresponding account to be pushed; therefore, accurate pushing of the multimedia information is facilitated.
In the multimedia information pushing method, candidate multimedia information corresponding to an account to be pushed is obtained; then, obtaining a ranking label of each candidate multimedia information through a target ranking model; the target ordering model is obtained by fusing tree models selected from at least two information ordering models and used for outputting ordering labels of the multimedia information, and the number of the tree models selected from each information ordering model is determined according to the information ordering accuracy of each information ordering model; finally, according to the sorting labels, sorting the candidate multimedia information to obtain the sorted candidate multimedia information; pushing the sorted candidate multimedia information to an account to be pushed; the aim of sorting the candidate multimedia information according to the target sorting model obtained by fusing the tree models selected from the at least two information sorting models is fulfilled, and as the model structure of the target sorting model obtained by fusing the tree models selected from the at least two information sorting models is not redundant, the overall operation efficiency of the target sorting model is higher, the sorting efficiency of the multimedia information is improved, and the pushing efficiency of the multimedia information is improved; meanwhile, the defect that the model structure of the fusion model obtained by gradual accumulation training is easy to generate redundancy, so that the sequencing processing time of the multimedia information is long, and the pushing efficiency of the multimedia information is low is overcome.
In an exemplary embodiment, in step S210, acquiring candidate multimedia information corresponding to an account to be pushed includes: receiving an information push request of an account to be pushed; the information pushing request comprises key information triggered and input by an account to be pushed; and recalling multimedia information with the information matching degree higher than the preset matching degree from the information base, wherein the multimedia information is used as candidate multimedia information corresponding to the account to be pushed.
The information matching degree between the multimedia information and the key information is used for measuring the correlation degree between the multimedia information and the key information; the higher the information matching degree, the higher the correlation degree.
For example, in a video search scene, a terminal responds to a video search operation of a currently logged account to be pushed on a terminal interface to obtain a keyword, such as AAA, input by the account to be pushed; generating an information pushing request according to a keyword input by an account to be pushed, and sending the information pushing request to a corresponding server; the server analyzes the received information pushing request to obtain keywords triggered and input by the account to be pushed; and respectively counting the information matching degrees between the keywords and each video in the information base, and screening out the videos with the information matching degree higher than the preset matching degree from each video in the information base to serve as candidate multimedia information corresponding to the account to be pushed.
According to the technical scheme provided by the embodiment of the disclosure, the candidate multimedia information corresponding to the account to be pushed is obtained, so that the candidate multimedia information corresponding to the account to be pushed can be conveniently sequenced in the following process, and all the multimedia information does not need to be sequenced, so that the sequencing processing time of the multimedia information is reduced, and the sequencing processing efficiency of the multimedia information is further improved.
In an exemplary embodiment, in step S210, acquiring candidate multimedia information corresponding to an account to be pushed further includes: acquiring account characteristics of an account to be pushed; acquiring multimedia information categories according with account characteristics; and screening out multimedia information which accords with the account characteristics from the multimedia information corresponding to the multimedia information category, and taking the multimedia information as candidate multimedia information corresponding to the account to be pushed.
The multimedia information category refers to the information type to which the multimedia information belongs; for example, if the multimedia information is a video, the information type may be a fun video, a variety video, a food video, a travel video, and the like.
Specifically, the server acquires account characteristics of an account to be pushed and category characteristics of multimedia information categories, wherein the category characteristics refer to attribute characteristics of the multimedia information categories, such as category contents; secondly, the server calculates the feature similarity between the account features and each multimedia information category, and screens out the multimedia information categories with the feature similarity larger than a preset threshold value from each multimedia information category as the multimedia information categories according with the account features; the method comprises the steps of obtaining information characteristics of multimedia information corresponding to multimedia information categories, screening out the multimedia information with the information characteristics matched with account characteristics from the multimedia information corresponding to the multimedia information categories, using the multimedia information as the multimedia information conforming to the account characteristics, and using the multimedia information as candidate multimedia information corresponding to an account to be pushed.
According to the technical scheme provided by the embodiment of the disclosure, the multimedia information category which accords with the account characteristics of the account to be pushed is obtained, and then the multimedia information which accords with the account characteristics is screened out from the multimedia information corresponding to the multimedia information category and is used as candidate multimedia information corresponding to the account to be pushed, so that the determined candidate multimedia information is more accurate, and the determination accuracy of the candidate multimedia information is improved.
In an exemplary embodiment, screening out multimedia information meeting account characteristics from multimedia information corresponding to multimedia information categories comprises: acquiring information characteristics of multimedia information corresponding to the multimedia information category; acquiring feature similarity between the account features and each information feature; and screening out the multimedia information with the characteristic similarity larger than the preset similarity from the multimedia information corresponding to the multimedia information category as the multimedia information according with the account characteristics.
The characteristic similarity between the account characteristics and the information characteristics is used for measuring the correlation between the account characteristics and the information characteristics; generally, the greater the feature similarity, the greater the correlation between the representation account features and the information features.
Specifically, the server inputs multimedia information corresponding to the multimedia information category into a pre-trained information feature extraction model, and performs information feature extraction processing on the multimedia information corresponding to the multimedia information category through the pre-trained information feature extraction model to obtain information features of the multimedia information corresponding to the multimedia information category; according to a preset feature similarity counting instruction, counting feature similarities between the account features and the information features, and correspondingly taking the feature similarities as the feature similarity of each piece of multimedia information; if the feature similarity of the multimedia information is larger than the preset similarity, the multimedia information is used as the multimedia information conforming to the account feature; therefore, the multimedia information which is in accordance with the account characteristics can be screened from the multimedia information corresponding to the multimedia information types.
According to the technical scheme provided by the embodiment of the disclosure, the multimedia information with the characteristic similarity between the information characteristic and the account characteristic larger than the preset similarity is screened out from the multimedia information corresponding to the multimedia information category and is used as the multimedia information conforming to the account characteristic, so that the purpose of determining the multimedia information conforming to the account characteristic according to the characteristic similarity between the information characteristic of the multimedia information and the account characteristic of the account to be pushed is achieved, and the accuracy of the determined multimedia information is improved.
In an exemplary embodiment, in step S240, pushing the sorted candidate multimedia information to the account to be pushed includes: sequentially screening out a preset number of candidate multimedia information from the sorted candidate multimedia information as target multimedia information corresponding to the account to be pushed; and pushing the target multimedia information to an account to be pushed according to a preset pushing frequency.
The preset push frequency refers to a push frequency of the target multimedia information, for example, 5 pieces of target multimedia information are pushed at a time.
For example, the server screens out the top 20 pieces of candidate multimedia information from the sorted candidate multimedia information as target multimedia information corresponding to the account to be pushed; and pushing the target multimedia information to a terminal corresponding to the account to be pushed according to a preset pushing frequency, and displaying the received target multimedia information through a terminal interface.
According to the technical scheme provided by the embodiment of the disclosure, the candidate multimedia information with the preset number is screened out, and then the screened candidate multimedia information is pushed to the corresponding account to be pushed, so that the defect that the information pushing accuracy is low due to the fact that all candidate multimedia information is pushed to the account to be pushed is overcome, and accurate pushing of the multimedia information is achieved.
In an exemplary embodiment, as shown in fig. 3, the target ranking model is obtained by fusing:
in step S310, information ranking accuracies of at least two information ranking models are obtained, and the number of tree models selected from each information ranking model is determined according to the information ranking accuracies.
Specifically, the server acquires the information sorting accuracy of at least two information sorting models from a local database, and determines the quantity proportion of tree models selected from each information sorting model according to the information sorting accuracy; and determining the number of the tree models selected from each information sorting model according to the preset number of the tree models and the number proportion of the tree models selected from each information sorting model.
In step S320, according to a preset selection sequence, the tree models corresponding to the number of the tree models are correspondingly selected from the tree models included in each information ranking model, so as to obtain the tree models correspondingly selected from each information ranking model.
The preset selection sequence refers to a selection sequence of a tree model in the information sorting model, and specifically refers to an interception sequence of the tree model in the information sorting model; in an actual scene, the tree models corresponding to the number of the tree models are correspondingly selected from the tree models contained in the information sorting model, and the tree models corresponding to the number of the tree models before are intercepted from the tree models contained in the information sorting model according to the sequence from left to right.
In step S330, a fusion process is performed on the tree models correspondingly selected from the information ranking models to obtain a target ranking model.
Specifically, the server obtains a preset model fusion instruction, and performs fusion processing on the tree models correspondingly selected from the information sorting models according to the preset model fusion instruction to obtain fused models serving as target sorting models.
For example, assume that there are two information sorting models, namely an information sorting model a and an information sorting model B, the number of tree models included in the information sorting model a is I, the number of tree models included in the information sorting model B is J, and the number of tree models selected from the information sorting model a is treeAThe number of the tree models selected from the information sorting model B is treeBThen, from the I tree models included in the information sorting model A, the front tree is intercepted from left to rightAThe tree model is marked as i; intercepting front tree from left to right from J tree models included in the information sequencing model BBIndividual tree model, memoryIs j; fusing the tree models correspondingly intercepted from the information sequencing models A and B to obtain a target sequencing model treefusion＝i∪j。
According to the technical scheme provided by the embodiment of the disclosure, according to the information sorting accuracy of the information sorting models, the corresponding number of tree models are correspondingly selected from the tree models contained in each information sorting model, and then the corresponding selected tree models in each information sorting model are subjected to fusion processing, so that the purpose of dynamically fusing the tree models is realized, and the defects that the model structure of the fusion model obtained by gradual accumulation training is easy to generate redundancy, the sorting processing time of multimedia information is long, and the subsequent multimedia information pushing efficiency is low are avoided.
In an exemplary embodiment, in step S330, the tree models correspondingly selected from the information ranking models are fused to obtain a target ranking model, which specifically includes the following contents: respectively carrying out fusion processing on the tree models correspondingly selected from the information sorting models to obtain new information sorting models; the information sorting accuracy of each new information sorting model corresponds to the information sorting accuracy of each information sorting model respectively; carrying out fusion processing on each new information sequencing model to obtain a target sequencing model; in the target ranking model, the weights of the ranking labels output by each new information ranking model are matched with the information ranking accuracy of each new information ranking model.
The information sorting accuracy of each new information sorting model is in one-to-one correspondence with the information sorting accuracy of each information sorting model, and the information sorting accuracy of each information sorting model can be correspondingly used as the information sorting accuracy of each new information sorting model.
The weight of the ranking label output by each new information ranking model is matched with the information ranking accuracy of each new information ranking model, which means that the weight of the ranking label output by each new information ranking model and the information ranking accuracy of each new information ranking model have a one-to-one correspondence relationship, for example, the higher the information ranking accuracy of the new information ranking model is, the higher the weight of the ranking label output by the new information ranking model is; it should be noted that the sum of the weights of the ranking labels output by each new information ranking model is constantly equal to 1.
Specifically, the server performs fusion processing on the tree models correspondingly selected from the information sequencing models respectively according to a preset model fusion instruction to obtain new information sequencing models, and correspondingly takes the information sequencing accuracy of the information sequencing models as the information sequencing accuracy of the new information sequencing models; then, according to a preset model fusion instruction, continuously carrying out fusion processing on each new information sorting model to obtain a target sorting model; and meanwhile, determining the weight of the sorting label output by each new information sorting model based on the information sorting accuracy of each new information sorting model according to the corresponding relation between the information sorting accuracy and the weight.
According to the technical scheme provided by the embodiment of the disclosure, the target sorting model for sorting the candidate information is obtained by fusing the tree models selected from the at least two information sorting models, and the model structures are not redundant, so that the overall operation efficiency of the target sorting model is high, the information sorting is fast, and the subsequent information pushing efficiency is improved.
In an exemplary embodiment, in the step S310, the information ranking accuracies of the at least two information ranking models are obtained, which specifically include the following: collecting a test sample set; the test sample set comprises sample multimedia information and an actual sequencing label corresponding to the sample multimedia information; respectively inputting the sample multimedia information into each information sorting model to obtain a prediction sorting label of each information sorting model for the sample multimedia information; and respectively obtaining the error between the predicted sorting label of each information sorting model to the sample multimedia information and the actual sorting label of the sample multimedia information, and obtaining the information sorting accuracy of each information sorting model according to the error.
The sample multimedia information refers to multimedia information labeled with an actual sorting label, and specifically may refer to pictures, videos and the like labeled with an actual click rate or an actual relevance.
The error between the predicted sorting label of the sample multimedia information and the actual sorting label of the sample multimedia information is used for measuring the deviation degree between the predicted sorting label of the sample multimedia information and the actual sorting label of the sample multimedia information; the larger the error, the lower the accuracy of the information ranking representing the information ranking model.
Specifically, the server obtains the error between the predicted sorting label and the actual sorting label of each sample multimedia information by the information sorting model, and adds the error between the predicted sorting label and the actual sorting label of each sample multimedia information by the information sorting model to obtain the target error of the information sorting model on the test sample set; obtaining the information sorting accuracy of the information sorting model according to the corresponding relation between the target error and the information sorting accuracy; with reference to this method, the information ranking accuracy of each information ranking model can be obtained.
For example, assuming that there are two information ranking models, namely an information ranking model a and an information ranking model B, on a given test sample set, the positive sequence pair number pos corresponding to the two models can be obtainedA、posBAnd then the information sequencing accuracy of the two models is obtained. If the classification model A and the classification model B are adopted, the prediction accuracy acc corresponding to the two models can be obtained on a given test sample setA、accBAnd then the information sequencing accuracy of the two models is obtained. If the regression model A and the regression model B are adopted, the root mean square error rmse corresponding to the two models can be obtained on a given test sample setA、rmseBAnd then the information sequencing accuracy of the two models is obtained. It should be noted that, according to the type of the model, the evaluation index of the model on a given test sample set is obtained, and then the information ranking accuracy of the model is obtained.
According to the technical scheme provided by the embodiment of the disclosure, the information sorting accuracy of the at least two information sorting models is obtained, so that the quantity of the tree models selected from each information sorting model is determined according to the information sorting accuracy of the information sorting models, the tree models corresponding to the quantity of the tree models are selected from each information sorting model, and the dynamic fusion of the tree models is realized.
In an exemplary embodiment, in step S310, the number of tree models selected from each information ranking model is determined according to the information ranking accuracy, and the method specifically includes the following steps: normalizing the information sorting accuracy of each information sorting model to obtain the quantity proportion of the tree models selected from each information sorting model; and obtaining the number of the tree models selected from each information sorting model according to the preset number of the tree models and the number proportion of the tree models selected from each information sorting model.
The preset number of the tree models refers to the total number of the tree models which need to be dynamically fused, and can be adjusted according to actual conditions, and is not specifically limited.
Specifically, the server obtains a product between a preset tree model number and a tree model number ratio selected from each information sorting model as the tree model number selected from each information sorting model.
For example, assume that there are two information sorting models, namely an information sorting model a and an information sorting model B, and the corresponding information sorting accuracies are respectively indicatorsA、indicatorBThen, the tree model quantity ratios of the information sorting model a and the information sorting model B are respectively:
Figure BDA0002643916110000151
Figure BDA0002643916110000152
if the preset number of the tree models is N, the number of the tree models selected from the information sorting model A and the information sorting model B is respectively as follows:
Figure BDA0002643916110000153
Figure BDA0002643916110000154
wherein the content of the first and second substances,
Figure BDA0002643916110000155
representing fracAAn integer of x N, or a combination thereof,
Figure BDA0002643916110000156
representing fracBInteger of XN.
According to the technical scheme provided by the embodiment of the disclosure, the number of the tree models selected from each information sequencing model is determined according to the information sequencing accuracy, so that the number of the tree models selected from each information sequencing model can be determined accurately, the overall operation efficiency of the target sequencing model obtained by subsequent fusion is higher, and the sequencing processing efficiency of the multimedia information is further improved.
Fig. 4 is a flowchart illustrating another multimedia information push method according to an exemplary embodiment, where, as shown in fig. 4, the multimedia information push method is used in the server shown in fig. 1, and includes the following steps:
in step S410, information ranking accuracies of at least two information ranking models are obtained, and the number of tree models selected from each information ranking model is determined according to the information ranking accuracies.
In step S420, according to a preset selection sequence, the tree models corresponding to the number of the tree models are correspondingly selected from the tree models included in each information ranking model, so as to obtain the tree models correspondingly selected from each information ranking model.
In step S430, the tree models correspondingly selected from the information ranking models are fused to obtain a target ranking model.
In step S440, receiving an information push request of an account to be pushed; the information pushing request comprises key information triggered and input by an account to be pushed; and recalling multimedia information with the information matching degree higher than the preset matching degree from the information base, wherein the multimedia information is used as candidate multimedia information corresponding to the account to be pushed.
In step S450, the ranking label of each candidate multimedia message is obtained through the target ranking model.
In step S460, the candidate multimedia information is ranked according to the ranking label, so as to obtain ranked candidate multimedia information.
In step S470, sequentially screening out a preset number of candidate multimedia information from the sorted candidate multimedia information as target multimedia information corresponding to the account to be pushed; and pushing the target multimedia information to an account to be pushed according to a preset pushing frequency.
In the multimedia information pushing method, candidate multimedia information corresponding to an account to be pushed is obtained; then, obtaining a ranking label of each candidate multimedia information through a target ranking model; the target ordering model is obtained by fusing tree models selected from at least two information ordering models and used for outputting ordering labels of the multimedia information, and the number of the tree models selected from each information ordering model is determined according to the information ordering accuracy of each information ordering model; finally, according to the sorting labels, sorting the candidate multimedia information to obtain the sorted candidate multimedia information; pushing the sorted candidate multimedia information to an account to be pushed; the aim of sorting the candidate multimedia information according to the target sorting model obtained by fusing the tree models selected from the at least two information sorting models is fulfilled, and as the model structure of the target sorting model obtained by fusing the tree models selected from the at least two information sorting models is not redundant, the overall operation efficiency of the target sorting model is higher, the sorting efficiency of the multimedia information is improved, and the pushing efficiency of the multimedia information is improved; meanwhile, the defect that the model structure of the fusion model obtained by gradual accumulation training is easy to generate redundancy, so that the sequencing processing time of the multimedia information is long, and the pushing efficiency of the multimedia information is low is overcome.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
Fig. 5 is a block diagram illustrating a multimedia information push apparatus according to an exemplary embodiment. Referring to fig. 5, the apparatus includes a multimedia information acquiring unit 510, a sorting label determining unit 520, a multimedia information sorting unit 530, and a multimedia information pushing unit 540.
A multimedia information obtaining unit 510 configured to perform obtaining candidate multimedia information corresponding to the account to be pushed.
A ranking label determination unit 520 configured to perform ranking label obtaining of each candidate multimedia information through the target ranking model; the target ordering model is obtained by fusing tree models selected from at least two information ordering models and used for outputting ordering labels of the multimedia information, and the number of the tree models selected from each information ordering model is determined according to the information ordering accuracy of each information ordering model.
The multimedia information sorting unit 530 is configured to perform sorting of the candidate multimedia information according to the sorting label, so as to obtain sorted candidate multimedia information.
And the multimedia information pushing unit 540 is configured to execute pushing of the sorted candidate pair media information to the account to be pushed.
In an exemplary embodiment, the multimedia information obtaining unit 510 is further configured to perform receiving an information push request of an account to be pushed; the information pushing request comprises key information triggered and input by an account to be pushed; and recalling multimedia information with the information matching degree higher than the preset matching degree from the information base, wherein the multimedia information is used as candidate multimedia information corresponding to the account to be pushed.
In an exemplary embodiment, the multimedia information obtaining unit 510 is further configured to perform obtaining the account feature of the account to be pushed; acquiring multimedia information categories according with account characteristics; and screening out multimedia information which accords with the account characteristics from the multimedia information corresponding to the multimedia information category, and taking the multimedia information as candidate multimedia information corresponding to the account to be pushed.
In an exemplary embodiment, the multimedia information obtaining unit 510 is further configured to perform obtaining information characteristics of multimedia information corresponding to multimedia information categories; acquiring feature similarity between the account features and each information feature; and screening out the multimedia information with the characteristic similarity larger than the preset similarity from the multimedia information corresponding to the multimedia information category as the multimedia information according with the account characteristics.
In an exemplary embodiment, the multimedia information pushing unit 540 is further configured to perform filtering out a preset number of candidate multimedia information from the sorted candidate multimedia information in sequence, and take the candidate multimedia information as target multimedia information corresponding to the account to be pushed; and pushing the target multimedia information to an account to be pushed according to a preset pushing frequency.
In an exemplary embodiment, the multimedia information pushing apparatus of the present disclosure further includes a model fusion unit configured to perform obtaining information sorting accuracies of at least two information sorting models, and determine the number of tree models selected from each information sorting model according to the information sorting accuracies; according to a preset selection sequence, correspondingly selecting tree models corresponding to the number of the tree models from the tree models contained in the information sorting models to obtain the tree models correspondingly selected from the information sorting models; and carrying out fusion processing on the tree models correspondingly selected from the information sorting models to obtain a target sorting model.
In an exemplary embodiment, the model fusion unit is further configured to perform acquiring a set of test samples; the test sample set comprises sample multimedia information and an actual sequencing label corresponding to the sample multimedia information; respectively inputting the sample multimedia information into each information sorting model to obtain a prediction sorting label of each information sorting model for the sample multimedia information; and respectively obtaining the error between the predicted sorting label of each information sorting model to the sample multimedia information and the actual sorting label of the sample multimedia information, and obtaining the information sorting accuracy of each information sorting model according to the error.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 6 is a block diagram illustrating an apparatus 600 for performing the above-described multimedia information push method according to an exemplary embodiment. For example, the device 600 may be a server. Referring to fig. 6, device 600 includes a processing component 620 that further includes one or more processors and memory resources, represented by memory 622, for storing instructions, such as applications, that are executable by processing component 620. The application programs stored in memory 622 may include one or more modules that each correspond to a set of instructions. Further, the processing component 620 is configured to execute the instructions to perform the multimedia information pushing method described above.
The device 600 may also include a power component 624 configured to perform power management for the device 600, a wired or wireless network interface 626 configured to connect the device 600 to a network, and an input/output (I/O) interface 628. The device 600 may operate based on an operating system stored in the memory 622, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
In an exemplary embodiment, a storage medium comprising instructions, such as the memory 622 comprising instructions, executable by the processor of the device 600 to perform the method described above is also provided. The storage medium may be a non-transitory computer readable storage medium, for example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, there is also provided a computer program product, the program product including a computer program, the computer program being stored in a readable storage medium, from which at least one processor of a device reads and executes the computer program, so that the device performs the multimedia information push method in any one of the embodiments of the present 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 multimedia information pushing method is characterized by comprising the following steps:
acquiring candidate multimedia information corresponding to an account to be pushed;
obtaining a ranking label of each candidate multimedia information through a target ranking model; the target ordering model is obtained by fusing tree models selected from at least two information ordering models and used for outputting ordering labels of multimedia information, and the number of the tree models selected from each information ordering model is determined according to the information ordering accuracy of each information ordering model;
according to the sorting label, sorting each candidate multimedia information to obtain sorted candidate multimedia information;
and pushing the sorted candidate multimedia information to the account to be pushed.
2. The method for pushing multimedia information according to claim 1, wherein the obtaining of candidate multimedia information corresponding to an account to be pushed comprises:
receiving an information pushing request of the account to be pushed; the information pushing request comprises key information triggered and input by the account to be pushed;
and recalling multimedia information with the information matching degree higher than the preset matching degree from an information base, wherein the multimedia information is used as candidate multimedia information corresponding to the account to be pushed.
3. The method according to claim 1, wherein the obtaining of candidate multimedia information corresponding to an account to be pushed further comprises:
acquiring account characteristics of an account to be pushed;
acquiring multimedia information categories according with the account characteristics;
and screening out the multimedia information which accords with the account characteristics from the multimedia information corresponding to the multimedia information category, and taking the multimedia information as candidate multimedia information corresponding to the account to be pushed.
4. The method according to claim 3, wherein the screening out the multimedia information that matches the account feature from the multimedia information corresponding to the multimedia information category comprises:
acquiring information characteristics of the multimedia information corresponding to the multimedia information category;
acquiring feature similarity between the account features and each information feature;
and screening out the multimedia information with the characteristic similarity larger than the preset similarity from the multimedia information corresponding to the multimedia information category as the multimedia information according with the account characteristics.
5. The method according to claim 1, wherein the pushing the ranked candidate multimedia information to the account to be pushed comprises:
sequentially screening out a preset number of candidate multimedia information from the sorted candidate multimedia information as target multimedia information corresponding to the account to be pushed;
and pushing the target multimedia information to the account to be pushed according to a preset pushing frequency.
6. The method for pushing multimedia information according to any one of claims 1 to 5, wherein the target ranking model is obtained by fusing:
obtaining information sorting accuracy of at least two information sorting models, and determining the number of tree models selected from each information sorting model according to the information sorting accuracy;
according to a preset selection sequence, correspondingly selecting tree models corresponding to the number of the tree models from the tree models contained in the information sorting models to obtain the tree models correspondingly selected from the information sorting models;
and carrying out fusion processing on the tree models correspondingly selected from the information sorting models to obtain the target sorting model.
7. The method for pushing multimedia information according to claim 6, wherein said obtaining information ranking accuracy of at least two information ranking models comprises:
collecting a test sample set; the test sample set comprises sample multimedia information and an actual sequencing label corresponding to the sample multimedia information;
respectively inputting the sample multimedia information into each information sorting model to obtain a prediction sorting label of each information sorting model for the sample multimedia information;
and respectively obtaining the error between the predicted sorting label of the sample multimedia information and the actual sorting label of the sample multimedia information of each information sorting model, and obtaining the information sorting accuracy of each information sorting model according to the error.
8. A multimedia information push apparatus, comprising:
the multimedia information acquisition unit is configured to execute acquisition of candidate multimedia information corresponding to the account to be pushed;
the sequencing label determining unit is configured to execute a target sequencing model to obtain a sequencing label of each candidate multimedia information; the target ordering model is obtained by fusing tree models selected from at least two information ordering models and used for outputting ordering labels of multimedia information, and the number of the tree models selected from each information ordering model is determined according to the information ordering accuracy of each information ordering model;
the multimedia information sorting unit is configured to execute sorting of the candidate multimedia information according to the sorting label to obtain sorted candidate multimedia information;
and the multimedia information pushing unit is configured to execute pushing of the sorted candidate multimedia information to the account to be pushed.
9. A server, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the multimedia information pushing method according to any one of claims 1 to 7.
10. A storage medium in which instructions, when executed by a processor of a server, enable the server to perform the multimedia information push method according to any one of claims 1 to 7.
CN202010848523.7A 2020-08-21 2020-08-21 Multimedia information pushing method, device, server and storage medium Active CN112000821B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010848523.7A CN112000821B (en) 2020-08-21 2020-08-21 Multimedia information pushing method, device, server and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010848523.7A CN112000821B (en) 2020-08-21 2020-08-21 Multimedia information pushing method, device, server and storage medium

Publications (2)

Publication Number Publication Date
CN112000821A true CN112000821A (en) 2020-11-27
CN112000821B CN112000821B (en) 2024-03-26

Family

ID=73474028

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010848523.7A Active CN112000821B (en) 2020-08-21 2020-08-21 Multimedia information pushing method, device, server and storage medium

Country Status (1)

Country Link
CN (1) CN112000821B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190042585A1 (en) * 2017-08-01 2019-02-07 Yandex Europe Ag Method of and system for recommending media objects
CN110263235A (en) * 2019-06-05 2019-09-20 深圳市腾讯计算机系统有限公司 Information pushes object updating method, device and computer equipment
CN110457534A (en) * 2019-07-30 2019-11-15 深圳市腾讯网域计算机网络有限公司 A kind of data processing method based on artificial intelligence, device, terminal and medium
CN111339327A (en) * 2020-02-20 2020-06-26 北京达佳互联信息技术有限公司 Work recommendation method and device, server and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190042585A1 (en) * 2017-08-01 2019-02-07 Yandex Europe Ag Method of and system for recommending media objects
CN110263235A (en) * 2019-06-05 2019-09-20 深圳市腾讯计算机系统有限公司 Information pushes object updating method, device and computer equipment
CN110457534A (en) * 2019-07-30 2019-11-15 深圳市腾讯网域计算机网络有限公司 A kind of data processing method based on artificial intelligence, device, terminal and medium
CN111339327A (en) * 2020-02-20 2020-06-26 北京达佳互联信息技术有限公司 Work recommendation method and device, server and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
智能推荐系统: "推荐系统系列教程之十四：经典模型融合方法----线性模型和树模型的组合拳-CSDN博客", Retrieved from the Internet <URL:https://blog.csdn.net/m0_37586850/article/details/103342361> *

Also Published As

Publication number Publication date
CN112000821B (en) 2024-03-26

Similar Documents

Publication Publication Date Title
CN110909182B (en) Multimedia resource searching method, device, computer equipment and storage medium
JP7104244B2 (en) User tag generation method and its devices, computer programs and computer equipment
CN112364204B (en) Video searching method, device, computer equipment and storage medium
US11741094B2 (en) Method and system for identifying core product terms
CN112749330B (en) Information pushing method, device, computer equipment and storage medium
CN111191133B (en) Service search processing method, device and equipment
CN111783712A (en) Video processing method, device, equipment and medium
CN112989212B (en) Media content recommendation method, device and equipment and computer storage medium
CN112052387A (en) Content recommendation method and device and computer readable storage medium
CN109858024B (en) Word2 vec-based room source word vector training method and device
CN113254711A (en) Interactive image display method and device, computer equipment and storage medium
CN112364184A (en) Method, device, server and storage medium for ordering multimedia data
CN115712780A (en) Information pushing method and device based on cloud computing and big data
CN112883265A (en) Information recommendation method and device, server and computer readable storage medium
CN107368923B (en) Scenic spot heat prediction method and device
CN113032676A (en) Recommendation method and system based on micro-feedback
CN110351183B (en) Resource collection method and device in instant messaging
CN116823410A (en) Data processing method, object processing method, recommending method and computing device
CN116955591A (en) Recommendation language generation method, related device and medium for content recommendation
CN112000821B (en) Multimedia information pushing method, device, server and storage medium
CN115269998A (en) Information recommendation method and device, electronic equipment and storage medium
CN114449342A (en) Video recommendation method and device, computer readable storage medium and computer equipment
CN112000888B (en) Information pushing method, device, server and storage medium
CN113763084A (en) Product recommendation processing method, device, equipment and storage medium
CN111414538A (en) Text recommendation method and device based on artificial intelligence and electronic equipment

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