CN110750728A - Prediction method and prediction device for browsing resource heat and readable storage medium - Google Patents
Prediction method and prediction device for browsing resource heat and readable storage medium Download PDFInfo
- Publication number
- CN110750728A CN110750728A CN201911029099.7A CN201911029099A CN110750728A CN 110750728 A CN110750728 A CN 110750728A CN 201911029099 A CN201911029099 A CN 201911029099A CN 110750728 A CN110750728 A CN 110750728A
- Authority
- CN
- China
- Prior art keywords
- analyzed
- score
- browsing
- heat
- determining
- 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
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Medical Informatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The application provides a prediction method and a prediction device for browsing resource heat and a readable storage medium. Wherein, the prediction method comprises the following steps: acquiring internal associated information related to browsing resources to be analyzed during manufacturing and external associated information related to browsing resources to be analyzed during broadcasting; determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed based on the internal correlation information and the external correlation information; determining an information characteristic matrix of the browsing resources to be analyzed according to the attribute characteristics and the score characteristics; and inputting the information characteristic matrix into a heat prediction model, and determining a heat prediction value of the browsing resource to be analyzed. The method can predict the heat of the resources to be analyzed and browsed more accurately from two aspects of the internal associated information and the external associated information of the resources to be analyzed and browsed, and is beneficial to improving the rationality of resource throwing, reducing the waste of resources and improving the utilization rate of the resources.
Description
Technical Field
The present application relates to the field of big data processing technologies, and in particular, to a method and an apparatus for predicting browsing resource popularity, and a readable storage medium.
Background
With the increase of economy and the improvement of living standard of people, people can watch more browsing resources in the network. In order to meet the preference of people, the network platform can predict the heat of browsing resources to be released, so that more popular browsing resources can be released according to the interest of people.
Currently, for the prediction of the popularity of the browsing resources, only relevant information related to the browsing resources when the browsing resources are manufactured, such as director information, drama information, actor information involved in the browsing resources, and the like, is mostly considered, and external relevant information of the browsing resources, such as associated information of a launching platform and a launching platform of the browsing resources, is not considered.
Disclosure of Invention
In view of this, an object of the present application is to provide a method, a device and a readable storage medium for predicting the popularity of browsing resources to be analyzed, which can combine the internal related information and the external related information of the browsing resources to be analyzed to more comprehensively and accurately predict the popularity of the browsing resources to be analyzed, thereby improving the rationality of delivering the browsing resources, reducing the waste of resources and improving the utilization rate of the resources.
The embodiment of the application provides a method for predicting browsing resource heat, which comprises the following steps:
acquiring internal associated information related to browsing resources to be analyzed during manufacturing and external associated information related to the browsing resources to be analyzed during broadcasting;
determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed based on the internal correlation information and the external correlation information;
generating an information characteristic matrix of the browsing resources to be analyzed by using the attribute characteristics and the score characteristics;
and inputting the information characteristic matrix into a heat prediction model, and determining a heat prediction value of the browsing resource to be analyzed.
Further, the inputting the information feature matrix into a heat prediction model to determine a heat prediction value of the browsing resource to be analyzed includes:
inputting the information characteristic matrix into a time series model in the heat prediction model, and determining a first heat value of the browsing resource to be analyzed and a residual error characteristic matrix of the browsing resource to be analyzed;
inputting the residual error feature matrix into a machine learning model in the heat prediction model, and determining a second heat value of the browsing resource to be analyzed;
and determining a heat degree predicted value of the browsing resource to be analyzed based on the first heat degree value and the second heat degree value.
Further, the generating an information characteristic matrix of the browsing resource to be analyzed by using the plurality of attribute characteristics and the plurality of score characteristics includes:
determining an attribute feature value corresponding to each attribute feature in the plurality of attribute features;
determining a rating score corresponding to each of the plurality of scoring features based on the plurality of scoring features;
and generating an information characteristic matrix of the browsing resources to be analyzed based on the attribute characteristic values and the evaluation scores.
Further, the determining, based on the plurality of scoring features, a rating score corresponding to each scoring feature of the plurality of scoring features includes:
detecting whether the plurality of score features belong to a process class score feature;
if the score features belong to the processing class score features, determining at least one first feature value corresponding to each score feature belonging to the processing class score features;
and determining the evaluation score corresponding to each score feature belonging to the processing class score features based on the at least one first feature value.
Further, after the detecting whether the plurality of score features belong to the processing class score features, the prediction method further includes:
and if the score features do not belong to the processing class score features, determining a second feature value of each score feature not belonging to the processing class score features, and determining the second feature value as the evaluation score of each score feature not belonging to the processing class score features.
The embodiment of the present application further provides a device for predicting browsing resource heat, where the device includes:
the information acquisition module is used for acquiring internal associated information related to the browsing resources to be analyzed during manufacturing and external associated information related to the browsing resources to be analyzed during broadcasting;
the characteristic determining module is used for determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed based on the internal associated information and the external associated information;
the matrix determination module is used for generating an information characteristic matrix of the browsing resource to be analyzed by using the attribute characteristics and the score characteristics;
and the heat prediction module is used for inputting the information characteristic matrix into a heat prediction model and determining a heat prediction value of the browsing resource to be analyzed.
Further, when the heat prediction module is configured to input the information feature matrix into a heat prediction model and determine a heat prediction value of the browsing resource to be analyzed, the heat prediction module is further configured to:
inputting the information characteristic matrix into a time series model in the heat prediction model, and determining a first heat value of the browsing resource to be analyzed and a residual error characteristic matrix of the browsing resource to be analyzed;
inputting the residual error feature matrix into a machine learning model in the heat prediction model, and determining a second heat value of the browsing resource to be analyzed;
and determining a heat degree predicted value of the browsing resource to be analyzed based on the first heat degree value and the second heat degree value.
Further, when the matrix determination module is configured to generate the information feature matrix of the browsing resource to be analyzed by using the plurality of attribute features and the plurality of score features, the matrix determination module is further configured to:
determining an attribute feature value corresponding to each attribute feature in the plurality of attribute features;
determining a rating score corresponding to each of the plurality of scoring features based on the plurality of scoring features;
and determining an information characteristic matrix of the browsing resource to be analyzed based on the attribute characteristic values and the evaluation scores.
Further, when the matrix determination module is configured to determine, based on the plurality of scoring features, a rating score corresponding to each scoring feature of the plurality of scoring features, the matrix determination module is further configured to:
detecting whether the plurality of score features belong to a process class score feature;
if the score features belong to the processing class score features, determining at least one first feature value corresponding to each score feature belonging to the processing class score features;
and determining the evaluation score corresponding to each score feature belonging to the processing class score features based on the at least one first feature value.
Further, after the matrix determination module is configured to detect whether the plurality of scoring features belong to a processing class scoring feature, the matrix determination module is further configured to:
and if the score features do not belong to the processing class score features, determining a second feature value of each score feature not belonging to the processing class score features, and determining the second feature value as the evaluation score of each score feature not belonging to the processing class score features.
An embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine readable instructions when executed by the processor performing the steps of the method for predicting browsing resource heat as described above.
The embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method for predicting the popularity of browsing resources as described above are performed.
The method, the device and the readable storage medium for predicting the popularity of browsing resources provided by the embodiment of the application acquire internal associated information related to browsing resources to be analyzed during manufacturing and external associated information related to the browsing resources to be analyzed during broadcasting; determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed based on the internal correlation information and the external correlation information; generating an information characteristic matrix of the browsing resources to be analyzed by using the attribute characteristics and the score characteristics; and inputting the information characteristic matrix into a heat prediction model, and determining a heat prediction value of the browsing resource to be analyzed.
Therefore, the method and the device for predicting the popularity of the browsing resources to be analyzed obtain the internal associated information and the external associated information of the browsing resources to be analyzed, determine a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed from the internal associated information and the external associated information, form an information characteristic matrix, and finally determine the popularity prediction value of the browsing resources to be analyzed through the information characteristic matrix and the popularity prediction model. The method can predict the heat of the resources to be analyzed and browsed more accurately from two aspects of the internal associated information and the external associated information of the resources to be analyzed and browsed, and is beneficial to improving the rationality of resource throwing, reducing the waste of resources and improving the utilization rate of the resources.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
FIG. 1 is a system architecture diagram of one possible application scenario of the present application;
fig. 2 is a flowchart of a method for predicting browsing resource heat according to an embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating a method for predicting browsing resource popularity according to another embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an apparatus for predicting browsing resource heat according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. Every other embodiment that can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present application falls within the protection scope of the present application.
First, a possible application scenario of the present application will be described. The method and the device can be applied to the technical field of big data processing, obtain internal associated information and external associated information of the browsing resources to be analyzed, form an information characteristic matrix, and predict the heat of the browsing resources to be analyzed through a heat prediction model. Referring to fig. 1, fig. 1 is a system architecture diagram illustrating a possible application scenario of the present application. As shown in fig. 1, the system includes an information storage device and a prediction device, where the prediction device is capable of obtaining internal correlation information and external correlation information of browsing resources to be analyzed from the information storage device, determining a plurality of attribute features and a plurality of score features of the browsing resources to be analyzed according to the internal correlation information and the external correlation information, determining an information feature matrix of the browsing resources to be analyzed according to the attribute features and the score features, inputting the information feature matrix into a heat prediction model, and determining a heat prediction value of the browsing resources to be analyzed.
Research shows that currently, most of predictions of browsing resource popularity are related to relevant information of browsing resources, such as director information, drama information, actor information involved in the browsing resources, and the like, and external relevant information of the browsing resources, such as a launch platform of the browsing resources, relevant information of the launch platform of the browsing resources, and the like, is not considered, so that the predictions of the browsing resources are not accurate enough.
Based on this, the embodiment of the application provides a method for predicting the popularity of browsing resources, which can more accurately predict the popularity of browsing resources to be analyzed from two aspects of the internal relevant information and the external relevant information of the browsing resources to be analyzed by acquiring the internal relevant information related to the production information of the browsing resources to be analyzed and the external relevant information related to the playing information of the browsing resources to be analyzed, thereby being beneficial to improving the rationality of the launching of the browsing resources, reducing the waste of the resources and improving the utilization rate of the resources.
Referring to fig. 2, fig. 2 is a flowchart illustrating a method for predicting browsing resource heat according to an embodiment of the present disclosure. As shown in fig. 2, a method for predicting browsing resource popularity provided in the embodiment of the present application includes:
s201, obtaining internal associated information related to browsing resources to be analyzed during production and external associated information related to the browsing resources to be analyzed during broadcasting.
In this step, for a browsing resource to be analyzed, the information capable of affecting the heat value thereof includes internal related information related to the production information of the browsing resource to be analyzed, that is, internal related information related to the browsing resource itself involved in the production process of the browsing resource to be analyzed, such as: the director corresponding subject score, the drama corresponding subject score, the production team corresponding subject score, the actor influence, the actor exposure index, and the like, and the external related information related to the playing information of the browsing resource to be analyzed, that is, the external related information related to the browsing resource in the future playing process of the browsing resource to be analyzed, for example: playing date, playing platform influence, competitive product programs and the like; therefore, in order to predict the heat of the browsing resource to be analyzed more accurately, it is first necessary to obtain the internal related information related to the browsing resource to be analyzed at the time of production and the external related information related to the browsing resource to be analyzed at the time of playback.
S202, determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed based on the internal correlation information and the external correlation information.
In this step, a plurality of attribute features and a plurality of score features of the browsing resource to be analyzed are determined from the obtained internal associated information and the external associated information, and are used for constructing an information feature matrix of the browsing resource to be analyzed.
The attribute feature is feature information capable of indicating an attribute of the browsing resource to be analyzed, for example, a type of the browsing resource: drama/heddles/animation, etc.; source of browsing resources: china/singapore/indonesia, etc.; the broadcasting form is as follows: on-line single broadcast/multi-platform broadcast/network station linkage, etc.; broadcasting date: ordinary workday/ordinary weekends/special holidays/summer holidays/cold holidays and the like.
The score feature is feature information that can be used to evaluate the influence effect of the browsing resource to be analyzed, such as influence of program type, influence of playing platform, influence of actors, and audience fitness.
S203, generating an information characteristic matrix of the browsing resource to be analyzed by using the attribute characteristics and the score characteristics.
In the step, the determined multiple attribute characteristics and the multiple score characteristics of the browsing resources to be analyzed are combined to form an information characteristic matrix which can be used for determining the browsing resources to be analyzed according to a preset rule form.
The preset rule form may be specifically set according to actual conditions, for example, the nth row and the mth column should be an attribute feature (corresponding attribute feature value) a, and the like.
And S204, inputting the information characteristic matrix into a heat prediction model, and determining a heat prediction value of the browsing resource to be analyzed.
Inputting the information characteristic matrix into a pre-trained heat prediction model, determining parameter values of the browsing resources to be analyzed in the heat prediction model according to the attribute characteristics of the browsing resources to be analyzed in the input information characteristic matrix, and predicting the playing heat of the browsing resources to be analyzed through the heat prediction model according to the information characteristic matrix.
Illustratively, according to the attribute characteristics included in the input information characteristic matrix, it is determined that the browsing resources to be analyzed are "china" or "drama", and then, according to the two attribute characteristics, the parameter value of the heat prediction model when the browsing resources to be analyzed are predicted is determined, and then, the heat value of the browsing resources to be analyzed is predicted according to the information characteristic matrix.
The method for predicting the popularity of the browsing resources, provided by the embodiment of the application, acquires internal associated information related to the browsing resources to be analyzed during manufacturing and external associated information related to the browsing resources to be analyzed during broadcasting; determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed based on the internal correlation information and the external correlation information; generating an information characteristic matrix of the browsing resources to be analyzed by using the attribute characteristics and the score characteristics; and inputting the information characteristic matrix into a heat prediction model, and determining a heat prediction value of the browsing resource to be analyzed.
Therefore, the method and the device for predicting the heat of the browsing resources to be analyzed form an information characteristic matrix by acquiring the internal associated information and the external associated information of the browsing resources to be analyzed and determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed from the internal associated information and the external associated information, and finally determine the predicted heat value of the browsing resources to be analyzed through the information characteristic matrix and a pre-trained heat prediction model. The method can predict the heat of the resources to be analyzed and browsed more accurately from two aspects of the internal associated information and the external associated information of the resources to be analyzed and browsed, and is beneficial to improving the rationality of resource throwing, reducing the waste of resources and improving the utilization rate of the resources.
Referring to fig. 3, fig. 3 is a flowchart illustrating a method for predicting browsing resource heat according to another embodiment of the present application. As shown in fig. 3, a method for predicting browsing resource popularity provided in the embodiment of the present application includes:
s301, obtaining internal associated information related to browsing resources to be analyzed during production and external associated information related to the browsing resources to be analyzed during broadcasting.
S302, determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed based on the internal correlation information and the external correlation information.
S303, generating an information characteristic matrix of the browsing resource to be analyzed by using the attribute characteristics and the score characteristics.
S304, inputting the information characteristic matrix into a time series model in the heat prediction model, and determining a first heat value of the browsing resource to be analyzed and a residual error characteristic matrix of the browsing resource to be analyzed.
In this step, the information feature matrix is firstly input into a time series model in the heat prediction model, and a first heat value of the browsing resource to be analyzed and a residual error feature matrix which can be input into a machine learning model in the heat prediction model are determined through the time series model.
The residual error feature matrix is a matrix formed by features which are not linearized and are affected by random factors, and the features which are not linearized and are affected by the random factors can be screened out through a time sequence model to form the residual error feature matrix.
S305, inputting the residual error feature matrix into a machine learning model in the heat prediction model, and determining a second heat value of the browsing resource to be analyzed.
In this step, the residual error feature matrix is input into a machine learning model in the heat prediction model, and a second heat value of the browsing resource to be analyzed is determined.
The machine learning model may be a neural network, a deep neural network, a conditional random field, a markov model, or the like.
S306, determining a heat degree predicted value of the browsing resource to be analyzed based on the first heat degree value and the second heat degree value.
In the step, the obtained first heat value and the second heat value of the browsing resource to be analyzed are summed, and the obtained sum value is determined as a heat prediction value of the browsing resource to be analyzed.
The descriptions of S301 to S303 may refer to the descriptions of S201 to S203, and the same technical effects can be achieved, which are not described in detail.
Further, step S303 includes: determining an attribute feature value corresponding to each attribute feature in the plurality of attribute features; determining a rating score corresponding to each of the plurality of scoring features based on the plurality of scoring features; and generating an information characteristic matrix of the browsing resources to be analyzed based on the attribute characteristic values and the evaluation scores.
In this step, based on the attribute features, an attribute feature value corresponding to each attribute feature is determined, for example, the type of browsing resource may be: when the type of the browsed resources is TV play, determining that the attribute characteristic value corresponding to the browsed resources to be analyzed at the moment is 0 according to a preset attribute characteristic value; when the type of the browsing resource is a comprehensive art, determining that the attribute characteristic value corresponding to the browsing resource to be analyzed is 1 according to a preset attribute characteristic value; and when the type of the browsing resource is animation, determining that the attribute characteristic value corresponding to the browsing resource to be analyzed at the moment is 2 according to the preset attribute characteristic value. Meanwhile, determining an evaluation score corresponding to the browsing resource to be analyzed under each score characteristic according to the plurality of score characteristics, for example, determining the evaluation score '95' corresponding to the score characteristic in the influence of the actor, wherein the score characteristic is the influence of the actor; the influence of the playing platform, and the evaluation score of '90'. And then generating an information characteristic matrix of the browsing resources to be analyzed according to the attribute characteristic values of the browsing resources to be analyzed and the evaluation scores of the browsing resources to be analyzed.
Further, the determining, based on the plurality of scoring features, a rating score corresponding to each scoring feature of the plurality of scoring features includes: detecting whether the plurality of score features belong to a process class score feature; if the score features belong to the processing class score features, determining at least one first feature value corresponding to each score feature belonging to the processing class score features; and determining the evaluation score corresponding to each score feature belonging to the processing class score features based on the at least one first feature value.
Detecting the determined plurality of score features, detecting whether each score feature is a processing class score feature, if the score feature is the processing class score feature, determining at least one first feature value corresponding to each score feature belonging to the processing class score feature from internal associated information or external associated information, and calculating an evaluation score of the processing class score feature through the at least one first feature value according to the class of the score feature.
The processing class score feature comprises a score feature with a plurality of feature values, a calculation method is determined according to the class corresponding to the feature, the evaluation score of the score feature is calculated through the calculation method and at least one first feature value, and the evaluation score can comprehensively represent the score feature.
The calculation method may be calculating a weighted average of a plurality of feature values, and may also be an average, a variance, or the like, and may also select a suitable calculation method according to a category of the score feature, for example, when the score feature is "a score of a subject corresponding to a director", the score feature is considered as a class a according to a preset rule, and then the weighted average thereof is calculated; and when the score feature is the social exposure index, if the score feature is considered as a B class according to a preset rule, calculating the average value of the social exposure indexes and the like.
For example, the score feature is "score of subject corresponding to director", and the scores given by evaluators with different score features are different, that is, the score feature of "score of subject corresponding to director" may correspond to a plurality of feature values, and then the score feature is a processing class score feature, and further calculation is performed on the score feature, so as to determine the evaluation score of the score feature.
Further, after the detecting whether the plurality of score features belong to the processing class score features, the prediction method further includes: and if the score features do not belong to the processing class score features, determining a second feature value of each score feature not belonging to the processing class score features, and determining the second feature value as the evaluation score of each score feature not belonging to the processing class score features.
In the step, the determined plurality of score features are detected, whether each score feature is a processing class score feature is detected, if the score feature does not belong to the processing class score feature, a second feature value of the score feature is obtained, and the second feature value is used as an evaluation score of the score feature not belonging to the processing class score feature.
Illustratively, the score feature is "number of contest programs", and since the number of contest programs of the browsing resources to be analyzed is fixed in a preset time period, the "number of contest programs" does not belong to the processing class score feature, and the feature value is directly determined as the evaluation score of the score feature, i.e., the "number of contest programs".
The method for predicting the popularity of the browsing resources, provided by the embodiment of the application, acquires internal associated information related to the browsing resources to be analyzed during manufacturing and external associated information related to the browsing resources to be analyzed during broadcasting; determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed based on the internal correlation information and the external correlation information; generating an information characteristic matrix of the browsing resources to be analyzed by using the attribute characteristics and the score characteristics; inputting the information characteristic matrix into a time series model in the heat prediction model, and determining a first heat value of the browsing resource to be analyzed and a residual error characteristic matrix of the browsing resource to be analyzed; inputting the residual error feature matrix into a machine learning model in the heat prediction model, and determining a second heat value of the browsing resource to be analyzed; and determining a heat degree predicted value of the browsing resource to be analyzed based on the first heat degree value and the second heat degree value.
Therefore, the method comprises the steps of obtaining internal associated information and external associated information of browsing resources to be analyzed, determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed from the internal associated information and the external associated information to form an information characteristic matrix, finally performing heat prediction on the browsing resources to be analyzed according to different characteristics in the information characteristic matrix through the information characteristic matrix and a pre-trained heat prediction model and through a time sequence model and a machine learning model in the heat prediction model, and determining a heat prediction value of the browsing resources to be analyzed. The method can predict the heat of the resources to be analyzed and browsed more accurately from two aspects of the internal associated information and the external associated information of the resources to be analyzed and browsed, and is beneficial to improving the rationality of resource throwing, reducing the waste of resources and improving the utilization rate of the resources.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a device for predicting browsing resource heat according to an embodiment of the present disclosure. As shown in fig. 4, the prediction apparatus 400 includes:
an information obtaining module 410, configured to obtain internal association information related to browsing resources to be analyzed during manufacturing and external association information related to browsing resources to be analyzed during broadcasting;
a feature determining module 420, configured to determine, based on the internal association information and the external association information, a plurality of attribute features and a plurality of score features of the browsing resource to be analyzed;
a matrix determining module 430, configured to generate an information feature matrix of the browsing resource to be analyzed by using the plurality of attribute features and the plurality of score features;
and the heat prediction module 440 is configured to input the information feature matrix into a heat prediction model, and determine a heat prediction value of the browsing resource to be analyzed.
Further, when the heat prediction module 440 is configured to input the information feature matrix into a heat prediction model and determine a heat prediction value of the browsing resource to be analyzed, the heat prediction module 440 is further configured to:
inputting the information characteristic matrix into a time series model in the heat prediction model, and determining a first heat value of the browsing resource to be analyzed and a residual error characteristic matrix of the browsing resource to be analyzed;
inputting the residual error feature matrix into a machine learning model in the heat prediction model, and determining a second heat value of the browsing resource to be analyzed;
and determining a heat degree predicted value of the browsing resource to be analyzed based on the first heat degree value and the second heat degree value.
Further, when the matrix determining module 430 is configured to generate the information feature matrix of the browsing resource to be analyzed by using the plurality of attribute features and the plurality of score features, the matrix determining module 430 is further configured to:
determining an attribute feature value corresponding to each attribute feature in the plurality of attribute features;
determining a rating score corresponding to each of the plurality of scoring features based on the plurality of scoring features;
and determining an information characteristic matrix of the browsing resource to be analyzed based on the attribute characteristic values and the evaluation scores.
Further, when the matrix determination module 430 is configured to determine, based on the plurality of scoring features, the rating score corresponding to each scoring feature of the plurality of scoring features, the matrix determination module 430 is further configured to:
detecting whether the plurality of score features belong to a process class score feature;
if the score features belong to the processing class score features, determining at least one first feature value corresponding to each score feature belonging to the processing class score features;
and determining the evaluation score corresponding to each score feature belonging to the processing class score features based on the at least one first feature value.
Further, after the matrix determination module 430 is configured to detect whether the plurality of scored features belong to a process class scored feature, the matrix determination module 430 is further configured to:
and if the score features do not belong to the processing class score features, determining a second feature value of each score feature not belonging to the processing class score features, and determining the second feature value as the evaluation score of each score feature not belonging to the processing class score features.
The device for predicting the popularity of browsing resources, provided by the embodiment of the application, acquires internal associated information related to browsing resources to be analyzed during manufacturing and external associated information related to the browsing resources to be analyzed during broadcasting; determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed based on the internal correlation information and the external correlation information; generating an information characteristic matrix of the browsing resources to be analyzed by using the attribute characteristics and the score characteristics; and inputting the information characteristic matrix into a heat prediction model, and determining a heat prediction value of the browsing resource to be analyzed.
Therefore, the method and the device for predicting the heat of the browsing resources to be analyzed form an information characteristic matrix by acquiring the internal associated information and the external associated information of the browsing resources to be analyzed and determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed from the internal associated information and the external associated information, and finally determine the predicted heat value of the browsing resources to be analyzed through the information characteristic matrix and a pre-trained heat prediction model. The method can predict the heat of the resources to be analyzed and browsed more accurately from two aspects of the internal associated information and the external associated information of the resources to be analyzed and browsed, and is beneficial to improving the rationality of resource throwing, reducing the waste of resources and improving the utilization rate of the resources.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 5, the electronic device 500 includes a processor 510, a memory 520, and a bus 530.
The memory 520 stores machine-readable instructions executable by the processor 510, when the electronic device 500 runs, the processor 510 communicates with the memory 520 through the bus 530, and when the machine-readable instructions are executed by the processor 510, the steps of the method for predicting the browsing resource heat degree in the method embodiments shown in fig. 2 and fig. 3 may be performed.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the step of the method for predicting the browsing resource heat in the method embodiments shown in fig. 2 and fig. 3 may be executed.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application, and are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A prediction method for browsing resource heat degree is characterized by comprising the following steps:
acquiring internal associated information related to browsing resources to be analyzed during manufacturing and external associated information related to the browsing resources to be analyzed during broadcasting;
determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed based on the internal correlation information and the external correlation information;
generating an information characteristic matrix of the browsing resources to be analyzed by using the attribute characteristics and the score characteristics;
and inputting the information characteristic matrix into a heat prediction model, and determining a heat prediction value of the browsing resource to be analyzed.
2. The prediction method according to claim 1, wherein the inputting the information feature matrix into a heat prediction model to determine a heat prediction value of the browsing resource to be analyzed comprises:
inputting the information characteristic matrix into a time series model in the heat prediction model, and determining a first heat value of the browsing resource to be analyzed and a residual error characteristic matrix of the browsing resource to be analyzed;
inputting the residual error feature matrix into a machine learning model in the heat prediction model, and determining a second heat value of the browsing resource to be analyzed;
and determining a heat degree predicted value of the browsing resource to be analyzed based on the first heat degree value and the second heat degree value.
3. The prediction method according to claim 1, wherein the generating an information characteristic matrix of the browsing resource to be analyzed by using the plurality of attribute characteristics and the plurality of score characteristics comprises:
determining an attribute feature value corresponding to each attribute feature in the plurality of attribute features;
determining a rating score corresponding to each of the plurality of scoring features based on the plurality of scoring features;
and generating an information characteristic matrix of the browsing resources to be analyzed based on the attribute characteristic values and the evaluation scores.
4. The prediction method of claim 3, wherein the determining a rating score for each of the plurality of scoring features based on the plurality of scoring features comprises:
detecting whether the plurality of score features belong to a process class score feature;
if the score features belong to the processing class score features, determining at least one first feature value corresponding to each score feature belonging to the processing class score features;
and determining the evaluation score corresponding to each score feature belonging to the processing class score features based on the at least one first feature value.
5. The prediction method according to claim 4, wherein after said detecting whether said plurality of scoring features belong to a process class scoring feature, said prediction method further comprises:
and if the score features do not belong to the processing class score features, determining a second feature value of each score feature not belonging to the processing class score features, and determining the second feature value as the evaluation score of each score feature not belonging to the processing class score features.
6. An apparatus for predicting a browsing resource heat, the apparatus comprising:
the information acquisition module is used for acquiring internal associated information related to the browsing resources to be analyzed during manufacturing and external associated information related to the browsing resources to be analyzed during broadcasting;
the characteristic determining module is used for determining a plurality of attribute characteristics and a plurality of score characteristics of the browsing resources to be analyzed based on the internal associated information and the external associated information;
the matrix determination module is used for generating an information characteristic matrix of the browsing resource to be analyzed by using the attribute characteristics and the score characteristics;
and the heat prediction module is used for inputting the information characteristic matrix into a heat prediction model and determining a heat prediction value of the browsing resource to be analyzed.
7. The prediction device according to claim 6, wherein the heat prediction module, when configured to input the information feature matrix into a heat prediction model to determine a heat prediction value of the browsing resource to be analyzed, is further configured to:
inputting the information characteristic matrix into a time series model in the heat prediction model, and determining a first heat value of the browsing resource to be analyzed and a residual error characteristic matrix of the browsing resource to be analyzed;
inputting the residual error feature matrix into a machine learning model in the heat prediction model, and determining a second heat value of the browsing resource to be analyzed;
and determining a heat degree predicted value of the browsing resource to be analyzed based on the first heat degree value and the second heat degree value.
8. The prediction apparatus according to claim 6, wherein the matrix determination module, when configured to generate the information feature matrix of the browsing resource to be analyzed using the plurality of attribute features and the plurality of score features, is further configured to:
determining an attribute feature value corresponding to each attribute feature in the plurality of attribute features;
determining a rating score corresponding to each of the plurality of scoring features based on the plurality of scoring features;
and determining an information characteristic matrix of the browsing resource to be analyzed based on the attribute characteristic values and the evaluation scores.
9. An electronic device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over the bus when an electronic device is running, the machine-readable instructions when executed by the processor performing the steps of the method of predicting browsing resource heat of any of claims 1 to 5.
10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the prediction method of browsing resource heat according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911029099.7A CN110750728A (en) | 2019-10-28 | 2019-10-28 | Prediction method and prediction device for browsing resource heat and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911029099.7A CN110750728A (en) | 2019-10-28 | 2019-10-28 | Prediction method and prediction device for browsing resource heat and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110750728A true CN110750728A (en) | 2020-02-04 |
Family
ID=69280338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911029099.7A Pending CN110750728A (en) | 2019-10-28 | 2019-10-28 | Prediction method and prediction device for browsing resource heat and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110750728A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110055223A1 (en) * | 2009-02-04 | 2011-03-03 | Popular Mechanics, Inc. | Internet based system and method for wagering on an artist |
| CN109104301A (en) * | 2018-07-19 | 2018-12-28 | 国政通科技有限公司 | A kind of method and system carrying out the prediction of network temperature for variety show based on deep learning model |
| CN109451352A (en) * | 2018-12-11 | 2019-03-08 | 北京奇艺世纪科技有限公司 | A kind of video playing method for predicting and device |
| CN109495318A (en) * | 2018-12-17 | 2019-03-19 | 广东宜通世纪科技股份有限公司 | A kind of mobile communications network method for predicting, device and readable storage medium storing program for executing |
| CN109522470A (en) * | 2018-11-06 | 2019-03-26 | 汪浩 | A kind of video temperature prediction technique, device, equipment and storage medium |
| CN110298515A (en) * | 2019-07-03 | 2019-10-01 | 山东浪潮人工智能研究院有限公司 | Coil of strip storage throughput time sequence prediction method and system based on residual error thought |
-
2019
- 2019-10-28 CN CN201911029099.7A patent/CN110750728A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110055223A1 (en) * | 2009-02-04 | 2011-03-03 | Popular Mechanics, Inc. | Internet based system and method for wagering on an artist |
| CN109104301A (en) * | 2018-07-19 | 2018-12-28 | 国政通科技有限公司 | A kind of method and system carrying out the prediction of network temperature for variety show based on deep learning model |
| CN109522470A (en) * | 2018-11-06 | 2019-03-26 | 汪浩 | A kind of video temperature prediction technique, device, equipment and storage medium |
| CN109451352A (en) * | 2018-12-11 | 2019-03-08 | 北京奇艺世纪科技有限公司 | A kind of video playing method for predicting and device |
| CN109495318A (en) * | 2018-12-17 | 2019-03-19 | 广东宜通世纪科技股份有限公司 | A kind of mobile communications network method for predicting, device and readable storage medium storing program for executing |
| CN110298515A (en) * | 2019-07-03 | 2019-10-01 | 山东浪潮人工智能研究院有限公司 | Coil of strip storage throughput time sequence prediction method and system based on residual error thought |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10335690B2 (en) | Automatic video game highlight reel | |
| CN107832437B (en) | Audio/video pushing method, device, equipment and storage medium | |
| TW202007178A (en) | Method, device, apparatus, and storage medium of generating features of user | |
| CN110727868B (en) | Object recommendation method, device and computer-readable storage medium | |
| US9569536B2 (en) | Identifying similar applications | |
| CN111242310B (en) | Feature validity evaluation method and device, electronic equipment and storage medium | |
| CN111126495B (en) | Model training method, information prediction device, storage medium and equipment | |
| US9421470B2 (en) | Player model | |
| CA3150500A1 (en) | Uploader matching method and device | |
| US11547945B2 (en) | Content generation system | |
| US20150310498A1 (en) | Computer-Implemented Systems and Methods for Generating Media Content Recommendations for Subsequent Works | |
| CN110743169A (en) | Anti-cheating method and system based on block chain | |
| CN117575687A (en) | Method and device for monitoring new media operation effect of automobile based on big data | |
| CN117312628A (en) | Method and device for recommending exercise course, storage medium and electronic equipment | |
| US8663017B1 (en) | Matrix judging systems and methods | |
| CN115834959B (en) | Video recommendation information determining method and device, electronic equipment and medium | |
| WO2021048902A1 (en) | Learning model application system, learning model application method, and program | |
| CN110750728A (en) | Prediction method and prediction device for browsing resource heat and readable storage medium | |
| CN115018471B (en) | Data processing method and related device | |
| CN113268589A (en) | Key user identification method and device, readable storage medium and computer equipment | |
| CN111340540A (en) | Monitoring method, recommendation method and device of advertisement recommendation model | |
| CN107820125B (en) | Method and device for optimizing video application experience based on user behavior | |
| CN115269919A (en) | Method and device for determining quality of short video, electronic equipment and storage medium | |
| CN111659125A (en) | Game-based friend recommendation method and device and computer-readable storage medium | |
| CN115422918A (en) | Narrative capability evaluation method and device for narrative object |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201222 Address after: A108, 1 / F, curling hall, winter training center, 68 Shijingshan Road, Shijingshan District, Beijing 100041 Applicant after: Beijing second hand Artificial Intelligence Technology Co.,Ltd. Address before: Room 9014, 9 / F, building 3, yard 30, Shixing street, Shijingshan District, Beijing Applicant before: ADMASTER TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200204 |