CN116248931A - Resource information pushing method and device, electronic equipment and readable storage medium - Google Patents

Resource information pushing method and device, electronic equipment and readable storage medium Download PDF

Info

Publication number
CN116248931A
CN116248931A CN202310270592.8A CN202310270592A CN116248931A CN 116248931 A CN116248931 A CN 116248931A CN 202310270592 A CN202310270592 A CN 202310270592A CN 116248931 A CN116248931 A CN 116248931A
Authority
CN
China
Prior art keywords
video
users
preset age
historical
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202310270592.8A
Other languages
Chinese (zh)
Other versions
CN116248931B (en
Inventor
汪山人
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 QIYI Century Science and Technology Co Ltd
Original Assignee
Beijing QIYI Century Science and 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 QIYI Century Science and Technology Co Ltd filed Critical Beijing QIYI Century Science and Technology Co Ltd
Priority to CN202310270592.8A priority Critical patent/CN116248931B/en
Publication of CN116248931A publication Critical patent/CN116248931A/en
Application granted granted Critical
Publication of CN116248931B publication Critical patent/CN116248931B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73—Querying
    • G06F16/735—Filtering based on additional data, e.g. user or group profiles
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/24—Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream requests
    • H04N21/2407—Monitoring of transmitted content, e.g. distribution time, number of downloads
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H04N21/25866—Management of end-user data
    • H04N21/25883—Management of end-user data being end-user demographical data, e.g. age, family status or address
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H04N21/25866—Management of end-user data
    • H04N21/25891—Management of end-user data being end-user preferences

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Computer Graphics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The embodiment of the invention provides a method, a device, electronic equipment and a readable storage medium for pushing resource information, wherein the method comprises the following steps: acquiring N first historical play videos in target equipment, wherein each first historical play video in the N first historical play videos corresponds to a first distribution sequence, the first distribution sequence is used for representing the corresponding percentage of first test users distributed in at least two preset age groups, the first test users are users watching the first historical play videos, and N is a positive integer; determining a user portrait using the target device based on a first distribution sequence corresponding to each first historical play video, wherein the user portrait comprises preset age groups corresponding to the user in the at least two preset age groups; and pushing resource information to the target equipment based on the user portrait. The method provided by the embodiment of the invention can improve the accuracy and efficiency of the resource information pushing.

Description

Resource information pushing method and device, electronic equipment and readable storage medium
Technical Field
The present invention relates to the field of video technologies, and in particular, to a method and apparatus for pushing resource information, an electronic device, and a readable storage medium.
Background
The personalized resource information pushing algorithm is widely applied to the field of online videos, and the distribution efficiency of video contents to video users is improved through personalized resource information pushing. The personalized resource information pushing is based on the information data of the video user, wherein the age data of the video user is one of important parameters of personalized recommendation.
However, in actual usage scenarios (e.g., web browsing, movie viewing, service purchasing, etc.), age data is not involved, and no authority is available to directly obtain information data of a video user, so that the existing resource information pushing method has the problems of poor recommendation accuracy and low efficiency.
Disclosure of Invention
The embodiment of the invention aims to provide a resource information pushing method, a device, electronic equipment and a readable storage medium, so as to solve the problems of poor recommending accuracy and low efficiency of the existing resource information pushing method. The specific technical scheme is as follows:
in a first aspect of the present invention, there is first provided a method for pushing resource information, including:
acquiring N first historical play videos in target equipment, wherein each first historical play video in the N first historical play videos corresponds to a first distribution sequence, the first distribution sequence is used for representing the corresponding percentage of first test users distributed in at least two preset age groups, the first test users are users watching the first historical play videos, and N is a positive integer;
Determining a user portrait using the target device based on a first distribution sequence corresponding to each first historical play video, wherein the user portrait comprises preset age groups corresponding to the user in the at least two preset age groups;
and pushing resource information to the target equipment based on the user portrait.
In a second aspect of the present invention, there is provided a resource information pushing apparatus, including:
the first acquisition module is used for acquiring N first historical play videos in the target device, each first historical play video in the N first historical play videos corresponds to a first distribution sequence, the first distribution sequence is used for representing the corresponding percentage of first test users distributed in at least two preset age groups, the first test users are users watching the first historical play videos, and N is a positive integer;
the determining module is used for determining a user portrait using the target device based on a first distribution sequence corresponding to each first historical play video, wherein the user portrait comprises a preset age bracket corresponding to a user in the at least two preset age brackets;
and the pushing module is used for pushing the resource information to the target equipment based on the user portrait.
In a third aspect of the present invention, there is provided an electronic device including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory perform communication with each other through the communication bus;
a memory for storing a program;
a processor for implementing the method according to the first aspect when executing a program stored on a memory.
In a fourth aspect of the invention, there is provided a readable storage medium having stored thereon a program which, when executed by a processor, implements a method as described in the first aspect.
In the embodiment of the application, under the condition of lacking user identity information, the user portraits of the target equipment are determined by acquiring the first historical play video in the target equipment and based on the first distribution sequence corresponding to the first historical play video, so that the age bracket distribution condition of the user using the target equipment is determined, and when the resource information is pushed to the target equipment, personalized recommendation can be carried out according to the preset age bracket corresponding to the user portraits, so that the potential demands of users in different age brackets are met, and the accuracy and the efficiency of the resource information pushing are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
Fig. 1 is a flow chart of a method for pushing resource information according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a resource information pushing device according to an embodiment of the present invention;
fig. 3 is a block diagram of an electronic device in an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts steps as a sequential process, many of the steps may be implemented in parallel, concurrently, or with other steps. Furthermore, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Furthermore, the terms "first," "second," and the like, may be used herein to describe various directions, acts, steps, or elements, etc., but these directions, acts, steps, or elements are not limited by these terms. These terms are only used to distinguish one direction, action, step or element from another direction, action, step or element. For example, a first historically played video may be a second historically played video, and similarly, the second historically played video may be referred to as the first historically played video, without departing from the scope of the present application. Both the first historical play video and the second historical play video are historical play videos, but they are not the same historical play video. The terms "first," "second," and the like, are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
The embodiment of the application provides a method for pushing resource information, as shown in fig. 1, the method comprises the following steps:
Step 101, acquiring N first historical play videos in a target device, wherein each first historical play video in the N first historical play videos corresponds to a first distribution sequence, the first distribution sequence is used for representing the corresponding percentage of first test users distributed in at least two preset age groups, the first test users are users watching the first historical play videos, and N is a positive integer;
the target device may be a Virtual Reality (VR) device, projector, television, computer, etc. N first historical play videos (i.e., historical video watching records) in the target device can be obtained through a server in communication connection with the target device, wherein the N first historical play videos can comprise different types of videos, such as animation types, science fiction types, history types and the like. Through the first distribution sequence corresponding to each first historical playing video, the percentage of each first historical playing video in each preset age group in at least two preset age groups can be known.
In an example, the at least two preset age groups may include a first preset age group (e.g., under 18 years old), a second preset age group (e.g., 18 years old to 30 years old), a third preset age group (e.g., 31 years old to 40 years old), a fourth preset age group (e.g., over 40 years old), and the first historically played video may include video a of an animation class, etc., video B of a science fiction class, etc.
The first distribution sequence corresponding to the video a may be expressed as [0.9,0.07,0.02,0.01], in other words, in the first test user group viewing the video a, the ages of 90% of the first test users are distributed in a first preset age group (under 18 years), 7% of the first test users are distributed in a second preset age group (18 years to 30 years), 2% of the first test users are distributed in a third preset age group (31 years to 40 years), and 1% of the first test users are distributed in a fourth preset age group (over 40 years);
the first distribution sequence corresponding to the video B may be represented as [0.2,0.3,0.3,0.2], in other words, in the first test user group viewing the video B, the ages of 20% of the first test users are distributed in the first preset age group (under 18 years), 30% of the first test users are distributed in the second preset age group (18 years to 30 years), 30% of the first test users are distributed in the third preset age group (31 years to 40 years), and 20% of the first test users are distributed in the fourth preset age group (over 40 years).
Thus, through the first distribution sequence corresponding to each first historical playing video, the percentage of the users who watch the first historical playing video in each preset age group in at least two preset age groups can be known. The user representation is further determined, via step 102.
It should be noted that, the at least two preset age groups may further include other number of preset age groups, for example, a preset age group may be set for every 5 years, so as to improve the refinement degree of the user age in the generated user portrait.
It should be noted that, the animation class may further include videos of other different first distribution sequences, the science fiction class may further include videos of other different first distribution sequences, and the first history playing video may further include other types of videos (such as action class, music class, etc.), which may also achieve the same technical effects, and are not described herein again.
102, determining a user portrait using the target device based on a first distribution sequence corresponding to each first historical play video, wherein the user portrait comprises a preset age group corresponding to a user in the at least two preset age groups;
the object to use the target device may be a single user or a family, that is, a plurality of users belonging to a family. In the step, based on the first distribution sequence corresponding to each first historical play video, the number of users using the target device and the age groups corresponding to the users are determined, so that the user portraits using the target device are judged through the video watching records of the users on the target device under the condition that the user identity information is not required to be acquired, and the resource information matched with the user portraits is pushed through the step 103, so that the accuracy and the efficiency of distributing video contents to video users are improved.
In an example, the first distribution sequence corresponding to the video a may be [0.9,0.07,0.02,0.01], that is, in the first test user group watching the video a, the ages of 90% of the first test users are in the first preset age range (for example, under 18 years old), 7% of the first test users are in the second preset age range (for example, 18 years old to 30 years old), 2% of the first test users are in the third preset age range (for example, 31 years old to 40 years old), 1% of the first test users are in the fourth preset age range (for example, over 40 years old), and the age range of the main audience group of the video a may be determined to be in the first preset age range through the first distribution sequence [0.9,0.07,0.02,0.01 ]. In this way, in the case where the server acquires that the video a is included in the first historically played video of the target device, it may determine that the user portrait using the target device includes the user of the first preset age group (for example, 18 years or less) based on the first distribution sequence corresponding to the video a.
And step 103, pushing resource information to the target equipment based on the user portrait.
The server pushes resource information to the target device based on the user portrayal, which may include video content resources and/or advertising resources, etc. In an example, the user images determined in the step 102 may include the user of the first preset age group (e.g., under 18 years old) and the user of the fourth preset age group (e.g., over 40 years old), so when pushing the resource information to the target device, the video content resources of the animation class may be increased to conform to the preference of the user of the first preset age group, the video content resources of the history class may be increased to conform to the preference of the user of the first preset age group, and the advertisement resources such as learning articles and education courses may be increased to conform to the requirement of the user of the first preset age group, and the advertisement resources such as health maintenance products may be increased to conform to the requirement of the user of the fourth preset age group. The resource information pushed to the target equipment can meet the potential requirements of one or more users corresponding to the user image, so that the accuracy and the efficiency of the resource information pushing are improved.
In the embodiment of the application, under the condition of lacking user identity information, the user portraits of the target equipment are determined by acquiring the first historical play video in the target equipment and based on the first distribution sequence corresponding to the first historical play video, so that the age bracket distribution condition of the user using the target equipment is determined, and when the resource information is pushed to the target equipment, personalized recommendation can be carried out according to the preset age bracket corresponding to the user portraits, so that the potential requirements of users in different age brackets are met, and the accuracy and the efficiency of the resource information pushing are improved.
Optionally, in step 102, the determining, based on the first distribution sequence corresponding to each first historical playing video, a user portrait using the target device includes:
calculating error values of different numbers of users according to a first distribution sequence corresponding to each first historical play video, wherein the error values are used for representing the confidence coefficient of the different numbers of users using the target equipment, and the error values are inversely proportional to the confidence coefficient, namely, the smaller the error values are, the higher the confidence coefficient is, and the higher the accuracy of the number of users corresponding to the error values is indicated; conversely, the larger the error value is, the lower the confidence coefficient is, which indicates that the accuracy of the number of users corresponding to the error value is poor;
Determining a target number of preset age groups in the at least two preset age groups to determine a user portrait using the target device, wherein the target number is the number of users corresponding to the minimum error value, the user portrait comprises the target number of users and the target number of preset age groups, and each user in the target number of users corresponds to a different preset age group respectively.
As an alternative implementation manner, in a scenario that family members share one target device, there is a situation that the same target device corresponds to users in multiple age groups, and a more chaotic playing record is left in the same target device, at this time, if it is determined that the user portrait using the target device only includes one preset age group, the actual use situation may not be met, or the age span in the preset age group is larger, so that it is difficult to achieve the requirement of subdividing the user ages, and therefore, the user portraits using the target device need to be considered for distinguishing and identifying.
For example, the server obtains that the first historical playing video of the target device includes video a, video B and video C, where the at least two preset age groups may include a first preset age group (for example, under 18 years old), a second preset age group (for example, 18 years old to 30 years old), a third preset age group (for example, 31 years old to 40 years old), and a fourth preset age group (for example, over 40 years old), and the percentages of the video a in the first preset age group, the second preset age group, the third preset age group and the fourth preset age group are 0.9,0.07,0.02 and 0.01, that is, the first distribution sequence corresponding to the video a may be represented as [0.9,0.07,0.02,0.01], and similarly, the first distribution sequence corresponding to the video B may be represented as [0.2,0.3,0.3,0.2], and the first distribution sequence corresponding to the video C may be represented as [0.05,0.15,0.2,0.7]. Through the first distribution sequence corresponding to each first historical playing video in the historical video watching record of the target device, the error value when the number of calculated users is 1 can be 0.52, the error value when the number of calculated users is 2 can be 0.42, the error value when the number of calculated users is 3 can be 0.3, and the target number can be determined to be 3 because 0.3 in the error values is the minimum value, namely, the user portraits can comprise 3 types of users in preset age groups. Therefore, when the resource information is pushed to the target equipment, personalized recommendation can be performed according to the preset age groups corresponding to the user images, so that potential requirements of users in different age groups are met, and the accuracy and the efficiency of pushing the resource information are improved.
The calculating the error value of different user numbers according to the first distribution sequence corresponding to each first historical playing video comprises the following steps:
according to punishment values corresponding to the number of 1 to N users and first distribution sequences corresponding to each first historical playing video in the N first historical playing videos, calculating error values corresponding to the number of 1 to N users, wherein the numerical value of the punishment values is in direct proportion to the numerical value of the number of 1 to N users.
Alternatively, calculating error values for the number of n users can be described as follows:
calculating the square of the difference between the first distribution sequences corresponding to any two first historical play videos in the N first historical play videos, and then summing the squares of the difference between the first distribution sequences corresponding to any two first historical play videos in the first historical play videos to obtain a first difference value; and calculating to obtain error values of the number n of users according to the first difference value, the penalty value corresponding to the number n of users and the number of the first historical play videos.
In an example, taking N first historical play videos including video a, video B and video C as an illustration, assuming that the user portrait using the target device includes only one preset age group (i.e. only one user), that is, video a, video B and video C are all histories watched by the user, an error value when the number of users is 1 can be calculated by equation 1 to be 0.52. Equation 1 can be expressed as:
Figure BDA0004134572480000091
The method comprises the steps that a is a first distribution sequence corresponding to video A, B is a first distribution sequence corresponding to video B, C is a first distribution sequence corresponding to video C, alpha is a penalty term of the number of users, alpha can be set to be 0.1, the value of the penalty term can be adjusted according to actual conditions, N is a penalty value corresponding to 1 to N users, the more the number of users is, the larger the penalty value corresponding to 1 to N users is, and therefore the smallest number of users corresponding to the error value exists when the error value of different numbers of users is calculated.
Wherein (a-b)/(2) may be the square of the difference of a group of squares of the differences of the first distribution sequences corresponding to any two first historically played videos, and the first distribution sequence corresponding to video A may be represented as [0.9,0.07,0.02,0.01 ]]The first distribution sequence corresponding to video B may be represented as [0.2,0.3,0.3,0.2 ]]Then (a-b) 2 ＝(0.9-0.2) 2 +(0.07-0.3) 2 +(0.02-0.3) 2 +(0.01-0.2) 2 . Similarly, the squares of the differences between the first distribution sequences corresponding to any two other first historical playing videos are not described herein.
The user portrait using the target device is assumed to only include two preset age groups (i.e. only two users), and the age range of the main audience group of the video a can be determined to be in a first preset age group through the first distribution sequences respectively corresponding to the video a, the video B and the video C, the age range of the main audience group of the video B is determined to be in a second preset age group and a third preset age group, and the age range of the main audience group of the video C is determined to be in a fourth preset age group. The videos A, B and C are ranked according to the differences among the age groups, and as the differences among the age ranges of the main audience groups of the videos A and C are larger, the user portrait using the target device can be preliminarily determined to comprise the user of the first preset age group and the user of the fourth preset age group, and then the condition that the video B belongs to one of the first preset age group and the fourth preset age group is judged. Then, when the number of users is 2 through the calculation of the formula 2.1, the error value of the video B belonging to the first preset age group is 0.42. Equation 2.1 can be expressed as:
Figure BDA0004134572480000101
When the number of users is 2, and the error value of the video B belonging to the fourth preset age group is 0.33, the number of users can be calculated by the formula 2.2. Equation 2.2 can be expressed as:
Figure BDA0004134572480000102
since the error value of video B belonging to the fourth preset age group is 0.33 less than the error value of video B belonging to the first preset age group is 0.42, video B can be attributed to the user of the fourth preset age group.
The user portraits using the target device only include three preset age groups (i.e., only three users), and at this time, the number of the first historical playing videos is the same as the number of the preset age groups corresponding to the users included in the user portraits, and then an error value when the number of the users is 3 can be calculated by using the formula 3 to be 0.3. Equation 3 can be expressed as:
3*alpha；
according to the penalty value corresponding to the number of 1 to 3 users and the first distribution sequence corresponding to each first historical playing video in the 3 first historical playing videos, error values corresponding to the number of 1 to 3 users are respectively 0.52, 0.42 or 0.33 and 0.3, and 0.3 in the error values is the minimum value, so that the target number can be determined to be 3, namely, the user portraits can comprise 3 types of users in preset age groups.
Further, determining a target number of preset age groups among the at least two preset age groups to determine a user representation using the target device, comprising:
Acquiring preset age groups corresponding to the maximum percentage of the first test users distributed in the at least two preset age groups in a first distribution sequence corresponding to the N first historical play videos, and acquiring the preset age groups of the target number;
and determining the user portrait using the target equipment according to the target number of users and the preset age groups of the target number.
In an example, the error values corresponding to the 1 to N numbers of users are sequentially calculated, and when the number of users is 3, the target number is 3 with the smallest error value. The first historically played video includes video a, video B, and video C. The first distribution sequence corresponding to the video a is represented as [0.9,0.07,0.02,0.01], and according to [0.9,0.07,0.02,0.01], the percentage of the first test users distributed in the first preset age group can be obtained to have the maximum value, so that the preset age groups with the target number comprise the first preset age group, that is, the user image can comprise the users in the first preset age group; the first distribution sequence corresponding to the video B is represented as [0.2,0.3,0.3,0.2], and according to [0.2,0.3,0.3,0.2], the percentage of the first test users distributed in the second preset age group and the third preset age group can be obtained to have the maximum value, so that the preset age groups with the target number comprise the second preset age group and/or the third preset age group, that is, the user images can comprise the users in the second preset age group and/or the third preset age group; the first distribution sequence corresponding to the video C is denoted as [0.05,0.15,0.2,0.7], and according to [0.05,0.15,0.2,0.7], the percentage of the first test users distributed in the fourth preset age group may be obtained to have the maximum value, so that the preset age groups with the target number include the fourth preset age group, that is, the user image may include the users in the fourth preset age group.
In this way, the user portraits comprise the target number of users and the target number of preset age groups, the number of users using the target equipment and the age groups corresponding to the users are considered, and when resource information is pushed to the target equipment, personalized recommendation can be carried out according to the preset age groups corresponding to the user portraits, so that potential demands of users in different age groups are met, and accuracy and efficiency of resource information pushing are improved.
Optionally, in step 102, after determining, based on the first distribution sequence corresponding to each first historical play video, a user portrait using the target device, the method further includes:
acquiring a second historical playing video in the target equipment, wherein the second historical playing video corresponds to a second distribution sequence, the second distribution sequence is used for representing the corresponding percentage of second test users distributed in the at least two preset age groups, and the second test users are users playing the second historical playing video;
cosine similarity between the second distribution sequence and the first distribution sequence is calculated to obtain a similarity sequence, wherein the similarity sequence comprises the similarity between the second historical playing video and each first historical playing video in the N first historical playing videos;
Executing step 102 of determining a user representation using the target device, in the case where the target similarity in the similarity sequence is less than or equal to a similarity threshold;
wherein the target similarity is greater than other similarities in the similarity sequence.
As an alternative embodiment, by acquiring N first historical play videos in the target device, taking three first historical play videos (i.e., video a, video B, and video C described above) as an example, and taking at least two preset age groups may include a first preset age group (e.g., under 18 years old), a second preset age group (e.g., 18 years old to 30 years old), a third preset age group (e.g., 31 years old to 40 years old), and a fourth preset age group (e.g., over 40 years old) as examples. After the error values corresponding to the 1-3 user numbers are calculated in sequence, the error is minimum when the user portrait comprises 3 types of users with different preset age groups, and the actual use condition of the target equipment is met. After a period of time, the target device uploads a video playing record to the server again, that is, the server acquires a second historical playing video (video D) in the target device, wherein the percentages of the video D in the first preset age group, the second preset age group, the third preset age group and the fourth preset age group are 0.8,0.1,0.05 and 0.05 respectively, that is, the second distribution sequence corresponding to the video D can be represented as [0.8,0.1,0.05,0.05]. Cosine similarities between the second distribution sequence [0.8,0.1,0.05,0.05] and the first distribution sequences respectively corresponding to 3 types of users (marked as user 1, user 2 and user 3) with different preset age groups are calculated, so that the similarity between the second distribution sequence corresponding to the video D and the preset age group corresponding to the user 1 is 0.8, the similarity between the second distribution sequence corresponding to the user 2 and the preset age group corresponding to the user 2 is 0.52, and the similarity between the second distribution sequence corresponding to the user 3 and the preset age group corresponding to the user 3 is 0.16, and the similarity sequence can be represented as [0.8,0.52,0.16].
The target similarity may be the similarity with the largest value in [0.8,0.52,0.16], the similarity threshold (threshold) may be preset, here may be set to 0.9, and the similarity threshold may be adjusted according to the actual situation, which is not limited herein.
Under the condition that the target similarity 0.8 in the similarity sequence [0.8,0.52,0.16] is smaller than or equal to the similarity threshold 0.9, indicating that the difference between the preset age group corresponding to the video D and the preset age group corresponding to any one of the current users 1 to 3 is large, returning to the step 102 of determining the user portraits using the target equipment so as to redetermine the number of users in the user portraits and the corresponding preset age groups.
Optionally, the step 102 of executing the user representation of determining to use the target device includes:
and determining the user portrait using the target device based on the second distribution sequence corresponding to the second historical playing video and the first distribution sequence corresponding to each first historical playing video.
And determining the user portrait using the target device based on the second distribution sequence corresponding to the second historical playing video and the first distribution sequence corresponding to each first historical playing video. Therefore, the user portraits can comprise the preset age groups corresponding to the users 1 to 3 and the preset age groups corresponding to the users 4, wherein the preset age groups corresponding to the users 4 are the preset age groups corresponding to the videos D, and personalized recommendation can be carried out according to the preset age groups corresponding to the user portraits when the resource information is pushed to the target equipment, so that the potential demands of users in different age groups are met, and the accuracy and the efficiency of the resource information pushing are improved.
Optionally, after the calculating the cosine similarity between the second distribution sequence and the first distribution sequence, the method further includes:
and under the condition that the target similarity in the similarity sequence is larger than the similarity threshold, associating the first historical playing video corresponding to the target similarity in the N first historical playing videos with the second historical playing video so as to determine that the users using the target equipment have the same preset age range.
In an example, the percentages of the video D in the first preset age group, the second preset age group, the third preset age group and the fourth preset age group are 0.8,0.1,0.05 and 0.05, respectively, i.e. the second distribution sequence corresponding to the video D may be represented as [0.8,0.1,0.05,0.05]. Cosine similarities between the second distribution sequence [0.8,0.1,0.05,0.05] and the first distribution sequences respectively corresponding to 3 types of users (marked as user 1, user 2 and user 3) with different preset age groups are calculated, if the similarity between the second distribution sequence corresponding to the video D and the preset age group corresponding to the user 1 is 0.99, the similarity between the preset age group corresponding to the user 2 is 0.52, and the similarity between the preset age group corresponding to the user 3 is 0.16, the similarity sequence can be represented as [0.99,0.52,0.16].
Under the condition that the target similarity 0.99 in the similarity sequence [0.99,0.52,0.16] is larger than the similarity threshold value 0.9, the preset age range corresponding to the video D is the same as or similar to the preset age range corresponding to the user 1, and then the video A and the video D corresponding to the target similarity in the first historical playing video can be associated so as to determine that the users watching the video A and the video D by using the target equipment have the same preset age range, namely the user playing the video D and the user playing the video A can be considered to be the same user 1, and the accuracy of the target quantity is improved.
In an optional embodiment, in step 102, the determining, based on the first distribution sequence corresponding to each of the first historical play videos, a user portrait using the target device includes:
clustering the N first historical play videos according to a first distribution sequence corresponding to each first historical play video in the N first historical play videos to obtain M first historical play videos, wherein M is a positive integer smaller than or equal to N;
and determining the user portrait using the target equipment according to the first distribution sequences corresponding to the M first historical play videos.
Multiple users of different ages can share the same target device, and more video records can be recorded on the same target device under the condition that the times of using the target device are frequent. According to a first distribution sequence corresponding to each first historical play video in N first historical play videos uploaded by a target device, determining the age range of a main audience of each first historical play video, and clustering the first historical play videos with the same age range of the audience in the N first historical play videos so as to reduce the number of the first historical play videos and facilitate the follow-up distinguishing and identifying according to refinement.
For example, video A 1 The corresponding first distribution sequence may be denoted as [0.9,0.07,0.02,0.01 ]]Video A 2 The corresponding first distribution sequence may be denoted as [0.8,0.1,0.05,0.05 ]]Video A 3 The corresponding first distribution sequence may be denoted as [0.6,0.1,0.2,0.1 ]]Video A 4 The corresponding first distribution sequence may be denoted as [0.95,0.02,0.02,0.01 ]]Through video A 1 Corresponding first distribution sequence [0.9,0.07,0.02,0.01 ]]Video a can be determined 1 The age range of the main audience group is in a first preset age range, and the audience group is recorded by video A 2 Corresponding first distribution sequence [0.8,0.1,0.05,0.05 ]]Video a can be determined 2 The age range of the main audience group of (2) is also in the first preset age range, through video A 3 Corresponding first distribution sequence [0.6,0.1,0.2,0.1 ]]Video a can be determined 3 The age range of the main audience group of (2) is also in the first preset age range, through video A 4 Corresponding first distribution sequence [0.95,0.02,0.02,0.01 ]]Video a can be determined 4 The age range of the primary audience population is also within the first predetermined age range. Video a of the same age range of the major audience group may be presented 1 Video A 2 Video A 3 And video A 4 Clustering to obtain clustered video A 1-4 Video A 1-4 The corresponding first distribution sequence may be denoted as [0.8125,0.0725,0.0725,0.0425 ]]。
Wherein video A 1-4 The corresponding percentage of the first test user distribution in the corresponding first distribution sequence in the first preset age group is 0.8125, which can be seen in the following calculation manner:
computing video A 1 Video A 2 Video A 3 And video A 4 The average value of the percentages of the first test users distributed in the first preset age group in the first distribution sequence corresponding to the first distribution sequence is calculated, namely the average values of 0.9, 0.8, 0.6 and 0.95 are calculated, and video A is obtained 1-4 The corresponding percentage of the first test user distribution in the corresponding first distribution sequence in the first preset age group is 0.8125. Similarly, video A can be obtained 1-4 And the corresponding percentages of the first test users distributed in other preset age groups in the corresponding first distribution sequence.
In this way, based on the first distribution sequence corresponding to each first historical play video in the N first historical play videos, the N first historical play videos are clustered to obtain M first historical play videos, M is a positive integer smaller than or equal to N, the number of the first historical play videos is reduced, and the user portrait using the target device can be distinguished and identified in a fine mode conveniently according to the first distribution sequence corresponding to the M first historical play videos. The accuracy of the age prediction of each user in the user portrait is improved, and the accuracy and the efficiency of the resource information pushing are further improved.
In an optional embodiment, before the obtaining N first historical play videos in the target device in step 101, the method further includes:
constructing at least two preset age groups, wherein each of the at least two preset age groups is a different age group;
dividing the first test user into corresponding preset age groups in the at least two preset age groups according to the age data of the first test user so as to obtain a first distribution sequence corresponding to each first historical play video in the N first historical play videos.
In this embodiment, at least two preset age groups may be pre-constructed according to the resource information to be pushed, for example, the resource information to be pushed includes resource information 1, resource information 2, resource information 3 and resource information 4, where the age of the main audience group of resource information 1 is under 18 years old, the age of the main audience group of resource information 2 is between 18 years old and 30 years old, the age of the main audience group of resource information 3 is between 31 years old and 40 years old, the age of the main audience group of resource information 4 is above 40 years old, and then a first preset age group, a second preset age group, a third preset age group and a fourth preset age group may be constructed, the first preset age group may be set under 18 years old, the second preset age group may be set under 18 years old, the third preset age group may be set under 31 years old and 40 years old, and the fourth preset age group may be set above 40 years old.
Then, the corresponding percentages of each first historical playing video in the N first historical playing videos in the first preset age group, the second preset age group, the third preset age group and the fourth preset age group can be obtained through an online web data crawler mode or an offline questionnaire mode. Taking video a as an example, the video a is a certain historical playing video of the N first historical playing videos. A questionnaire is performed on a number of first test users, in this example, 100 first test users who have watched the video a, and the questionnaire includes age data of the first test users. It should be understood that other numbers of first test users may be subjected to questionnaires, and the same technical effects may be achieved, which will not be described herein.
The results of the questionnaire survey may be: the ages of 90 first test users are in a first preset age group, and then the 90 first test users are divided into constructed first preset age groups; the ages of the 7 first test users are in a second preset age group, and the 7 first test users are divided into constructed second preset age groups; the ages of the 2 first test users are in three preset age groups, and the 2 first test users are divided into a constructed third preset age group; and if the ages of the 1 first test users are in the fourth preset age group, dividing the 1 first test users into the constructed fourth preset age group. Thus, the first distribution sequence corresponding to video a may be [0.9,0.07,0.02,0.01]. Similarly, the age group (i.e., the first distribution sequence) of the viewing corresponding to each of the N first historical playing videos may be obtained and stored in the server. The first distribution sequence corresponding to each of the N first historical playing videos obtained through the step 101 is obtained, that is, age distributions of users appearing on different contents are obtained, and the distributions are clustered, so that user portraits using the target device (that is, the number of users existing on the target device and the respective corresponding preset age groups) are determined, and when resource information is pushed to the target device, personalized recommendation can be performed according to the corresponding preset age groups of the user portraits, so that potential demands of users in different age groups are met, and accuracy and efficiency of resource information pushing are improved.
As shown in fig. 2, an embodiment of the present invention further provides a resource information pushing device 200, including:
the first obtaining module 201 is configured to obtain N first historical play videos in the target device, where each first historical play video in the N first historical play videos corresponds to a first distribution sequence, the first distribution sequence is used to characterize a corresponding percentage of first test users distributed in at least two preset age groups, the first test users are users who have watched the first historical play videos, and N is a positive integer;
a determining module 202, configured to determine, based on a first distribution sequence corresponding to each first historical play video, a user portrait using the target device, where the user portrait includes a preset age bracket corresponding to a user in the at least two preset age brackets;
and the pushing module 203 is configured to push resource information to the target device based on the user portrait.
Optionally, the determining module 202 includes:
the computing sub-module is used for computing error values of different user numbers according to the first distribution sequences corresponding to each first historical play video, wherein the error values are used for representing the confidence that different numbers of users use the target equipment;
The first determining submodule determines a target number of preset age groups in the at least two preset age groups to determine the number of users corresponding to the minimum error value by using the target equipment, wherein the user representation comprises the target number of users and the target number of preset age groups, and each user in the target number of users corresponds to different preset age groups respectively.
Optionally, the calculating submodule includes:
the calculating unit is used for calculating error values corresponding to the 1 to N user numbers according to penalty values corresponding to the 1 to N user numbers and first distribution sequences corresponding to each first historical play video in the N first historical play videos, and the penalty values are proportional to the 1 to N user numbers.
Optionally, the first determining submodule includes:
the acquisition unit is used for acquiring preset age groups corresponding to the maximum percentage of the first test users distributed in the at least two preset age groups in a first distribution sequence corresponding to the N first historical play videos, so as to obtain the preset age groups of the target number;
And the determining unit is used for determining the user portrait using the target equipment according to the target number of users and the preset age bracket of the target number.
Optionally, the resource information pushing device 200 further includes:
the second acquisition module is used for acquiring a second historical playing video in the target device, the second historical playing video corresponds to a second distribution sequence, the second distribution sequence is used for representing the corresponding percentage of second test users distributed in the at least two preset age groups, and the second test users are users playing the second historical playing video;
the calculation module is used for calculating the similarity between the second distribution sequence and the first distribution sequence to obtain a similarity sequence, wherein the similarity sequence comprises the similarity between the second historical playing video and each first historical playing video in the N first historical playing videos;
an execution module, configured to execute a step of determining a user portrait using the target device, in a case where a target similarity in the similarity sequence is equal to or less than a similarity threshold;
wherein the target similarity is greater than other similarities in the similarity sequence.
Optionally, the execution module includes:
and the second determining submodule is used for determining the user portrait using the target equipment based on the second distribution sequence corresponding to the second historical playing video and the first distribution sequence corresponding to each first historical playing video.
Optionally, the resource information pushing device 200 further includes:
the association module is configured to associate, when the target similarity in the similarity sequence is greater than the similarity threshold, a first historical playing video corresponding to the target similarity in the N first historical playing videos with the second historical playing video, so as to determine that users using the target device have the same preset age group.
Optionally, the determining module 202 includes:
the clustering sub-module is used for clustering the N first historical play videos according to a first distribution sequence corresponding to each first historical play video in the N first historical play videos to obtain M first historical play videos, wherein M is a positive integer smaller than or equal to N;
and the fourth determining submodule is used for determining the user portrait using the target equipment according to the first distribution sequences corresponding to the M first historical playing videos.
Optionally, the resource information pushing device 200 further includes:
the building module is used for building at least two preset age groups, wherein each preset age group in the at least two preset age groups is a different age group;
the dividing module is used for dividing the first test user to a corresponding preset age bracket in the at least two preset age brackets according to the age data of the first test user so as to obtain a first distribution sequence corresponding to each first historical play video in the N first historical play videos.
The resource information pushing device 200 provided in the embodiment of the present invention can implement each process implemented by the method embodiment shown in fig. 1, and can obtain the same beneficial effects, so that repetition is avoided, and no further description is provided here.
The embodiment of the invention also provides an electronic device, as shown in fig. 3, which comprises a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302 and the memory 303 complete communication with each other through the communication bus 304;
a memory 303 for storing a computer program; the processor 301 is configured to execute the program stored in the memory 303, and implement the following steps:
Acquiring N first historical play videos in target equipment, wherein each first historical play video in the N first historical play videos corresponds to a first distribution sequence, the first distribution sequence is used for representing the corresponding percentage of first test users distributed in at least two preset age groups, the first test users are users watching the first historical play videos, and N is a positive integer;
determining a user portrait using the target device based on a first distribution sequence corresponding to each first historical play video, wherein the user portrait comprises preset age groups corresponding to the user in the at least two preset age groups;
and pushing resource information to the target equipment based on the user portrait.
Optionally, the determining, based on the first distribution sequence corresponding to each first historical playing video, a user portrait using the target device includes:
calculating error values of different numbers of users according to first distribution sequences corresponding to each first historical play video, wherein the error values are used for representing the confidence level of the different numbers of users using the target equipment;
determining a target number of preset age groups in the at least two preset age groups to determine a user portrait using the target device, wherein the target number is the number of users corresponding to the minimum error value, the user portrait comprises the target number of users and the target number of preset age groups, and each user in the target number of users corresponds to a different preset age group respectively.
Optionally, calculating the error value of different numbers of users according to the first distribution sequence corresponding to each first historical playing video includes:
according to punishment values corresponding to the number of 1 to N users and first distribution sequences corresponding to each first historical playing video in the N first historical playing videos, calculating error values corresponding to the number of 1 to N users, wherein the numerical value of the punishment values is in direct proportion to the numerical value of the number of 1 to N users.
Optionally, determining a target number of preset age groups among the at least two preset age groups to determine a user representation using the target device includes:
acquiring preset age groups corresponding to the maximum percentage of the first test users distributed in the at least two preset age groups in a first distribution sequence corresponding to the N first historical play videos, and acquiring the preset age groups of the target number;
and determining the user portrait using the target equipment according to the target number of users and the preset age groups of the target number.
Optionally, after determining, based on the first distribution sequence corresponding to each first historical play video, that the user portrait using the target device, the processor 301 is further configured to execute the program stored on the memory 303, to implement the following steps:
Acquiring a second historical playing video in the target equipment, wherein the second historical playing video corresponds to a second distribution sequence, the second distribution sequence is used for representing the corresponding percentage of second test users distributed in the at least two preset age groups, and the second test users are users playing the second historical playing video;
calculating the similarity between the second distribution sequence and the first distribution sequence to obtain a similarity sequence, wherein the similarity sequence comprises the similarity between the second historical playing video and each first historical playing video in the N first historical playing videos;
executing a step of determining a user representation using the target device in the case where the target similarity in the similarity sequence is equal to or less than a similarity threshold;
wherein the target similarity is greater than other similarities in the similarity sequence.
Optionally, the step of executing the user representation of determining to use the target device comprises:
and determining the user portrait using the target device based on the second distribution sequence corresponding to the second historical playing video and the first distribution sequence corresponding to each first historical playing video.
Optionally, after the calculating the cosine similarity between the second distribution sequence and the first distribution sequence to obtain a similarity sequence, the processor 301 is further configured to implement the following steps when executing the program stored in the memory 303:
and under the condition that the target similarity in the similarity sequence is larger than the similarity threshold, associating the first historical playing video corresponding to the target similarity in the N first historical playing videos with the second historical playing video so as to determine that the users using the target equipment have the same preset age range.
Optionally, the determining, based on the first distribution sequence corresponding to each first historical playing video, a user portrait using the target device includes:
clustering the N first historical play videos according to a first distribution sequence corresponding to each first historical play video in the N first historical play videos to obtain M first historical play videos, wherein M is a positive integer smaller than or equal to N;
and determining the user portrait using the target equipment according to the first distribution sequences corresponding to the M first historical play videos.
Optionally, before the capturing N first historical play videos in the target device, the processor 301 is further configured to execute the program stored in the memory 303, to implement the following steps:
Constructing at least two preset age groups, wherein each of the at least two preset age groups is a different age group;
dividing the first test user into corresponding preset age groups in the at least two preset age groups according to the age data of the first test user so as to obtain a first distribution sequence corresponding to each first historical play video in the N first historical play videos.
The communication bus mentioned by the above electronic device may be a peripheral component interconnect standard (Peripheral Component Interconnect, abbreviated as PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated as EISA) bus, or the like. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the terminal and other devices.
The memory may include random access memory (Random Access Memory, RAM) or non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
In yet another embodiment of the present invention, a computer readable storage medium is provided, where instructions are stored, which when executed on a computer, cause the computer to perform the resource information pushing method according to any of the foregoing embodiments.
In yet another embodiment of the present invention, a computer program product containing instructions that, when run on a computer, cause the computer to perform the resource information pushing method of any of the above embodiments is also provided.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk Sol id State Disk (SSD)), etc.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims (12)

1. The method for pushing the resource information is characterized by comprising the following steps:
acquiring N first historical play videos in target equipment, wherein each first historical play video in the N first historical play videos corresponds to a first distribution sequence, the first distribution sequence is used for representing the corresponding percentage of first test users distributed in at least two preset age groups, the first test users are users watching the first historical play videos, and N is a positive integer;
determining a user portrait using the target device based on a first distribution sequence corresponding to each first historical play video, wherein the user portrait comprises preset age groups corresponding to the user in the at least two preset age groups;
and pushing resource information to the target equipment based on the user portrait.
2. The method of claim 1, wherein determining a user representation using the target device based on the first distribution sequence corresponding to each first historically played video comprises:
Calculating error values of different numbers of users according to first distribution sequences corresponding to each first historical play video, wherein the error values are used for representing the confidence level of the different numbers of users using the target equipment;
determining a target number of preset age groups in the at least two preset age groups to determine a user portrait using the target device, wherein the target number is the number of users corresponding to the minimum error value, the user portrait comprises the target number of users and the target number of preset age groups, and each user in the target number of users corresponds to a different preset age group respectively.
3. The method according to claim 2, wherein calculating the error value for the different number of users according to the first distribution sequence corresponding to each of the first historically played videos comprises:
according to punishment values corresponding to the number of 1 to N users and first distribution sequences corresponding to each first historical playing video in the N first historical playing videos, calculating error values corresponding to the number of 1 to N users, wherein the numerical value of the punishment values is in direct proportion to the numerical value of the number of 1 to N users.
4. The method of claim 2, wherein determining a target number of preset age groups among the at least two preset age groups to determine a representation of a user using the target device comprises:
acquiring preset age groups corresponding to the maximum percentage of the first test users distributed in the at least two preset age groups in a first distribution sequence corresponding to the N first historical play videos, and acquiring the preset age groups of the target number;
and determining the user portrait using the target equipment according to the target number of users and the preset age groups of the target number.
5. The method of claim 1, wherein after determining a user representation using the target device based on the first distribution sequence corresponding to each first historically played video, the method further comprises:
acquiring a second historical playing video in the target equipment, wherein the second historical playing video corresponds to a second distribution sequence, the second distribution sequence is used for representing the corresponding percentage of second test users distributed in the at least two preset age groups, and the second test users are users playing the second historical playing video;
Calculating the similarity between the second distribution sequence and the first distribution sequence to obtain a similarity sequence, wherein the similarity sequence comprises the similarity between the second historical playing video and each first historical playing video in the N first historical playing videos;
executing a step of determining a user representation using the target device in the case where the target similarity in the similarity sequence is equal to or less than a similarity threshold;
wherein the target similarity is greater than other similarities in the similarity sequence.
6. The method of claim 5, wherein the step of performing the determination of the user representation using the target device comprises:
and determining the user portrait using the target device based on the second distribution sequence corresponding to the second historical playing video and the first distribution sequence corresponding to each first historical playing video.
7. The method of claim 5, wherein after said calculating the similarity between the second distribution sequence and the first distribution sequence to obtain a similarity sequence, the method further comprises:
and under the condition that the target similarity in the similarity sequence is larger than the similarity threshold, associating the first historical playing video corresponding to the target similarity in the N first historical playing videos with the second historical playing video so as to determine that the users using the target equipment have the same preset age range.
8. The method of claim 1, wherein determining a user representation using the target device based on the first distribution sequence corresponding to each first historically played video comprises:
clustering the N first historical play videos according to a first distribution sequence corresponding to each first historical play video in the N first historical play videos to obtain M first historical play videos, wherein M is a positive integer smaller than or equal to N;
and determining the user portrait using the target equipment according to the first distribution sequences corresponding to the M first historical play videos.
9. The method of claim 1, wherein prior to the capturing N first historically played videos in the target device, the method further comprises:
constructing at least two preset age groups, wherein each of the at least two preset age groups is a different age group;
dividing the first test user into corresponding preset age groups in the at least two preset age groups according to the age data of the first test user so as to obtain a first distribution sequence corresponding to each first historical play video in the N first historical play videos.
10. A resource information pushing apparatus, comprising:
the first acquisition module is used for acquiring N first historical play videos in the target device, each first historical play video in the N first historical play videos corresponds to a first distribution sequence, the first distribution sequence is used for representing the corresponding percentage of first test users distributed in at least two preset age groups, the first test users are users watching the first historical play videos, and N is a positive integer;
the determining module is used for determining a user portrait using the target device based on a first distribution sequence corresponding to each first historical play video, wherein the user portrait comprises a preset age bracket corresponding to a user in the at least two preset age brackets;
and the pushing module is used for pushing the resource information to the target equipment based on the user portrait.
11. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a program;
a processor for implementing the method according to any one of claims 1-9 when executing a program stored on a memory.
12. A readable storage medium having stored thereon a program, which when executed by a processor, implements the method according to any of claims 1-9.
CN202310270592.8A 2023-03-16 2023-03-16 Resource information pushing method and device, electronic equipment and readable storage medium Active CN116248931B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310270592.8A CN116248931B (en) 2023-03-16 2023-03-16 Resource information pushing method and device, electronic equipment and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310270592.8A CN116248931B (en) 2023-03-16 2023-03-16 Resource information pushing method and device, electronic equipment and readable storage medium

Publications (2)

Publication Number Publication Date
CN116248931A true CN116248931A (en) 2023-06-09
CN116248931B CN116248931B (en) 2024-07-12

Family

ID=86626123

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310270592.8A Active CN116248931B (en) 2023-03-16 2023-03-16 Resource information pushing method and device, electronic equipment and readable storage medium

Country Status (1)

Country Link
CN (1) CN116248931B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107239456A (en) * 2016-03-28 2017-10-10 阿里巴巴集团控股有限公司 Age bracket recognition methods and device
CN110941738A (en) * 2019-11-27 2020-03-31 北京奇艺世纪科技有限公司 Recommendation method and device, electronic equipment and computer-readable storage medium
CN111046230A (en) * 2019-12-06 2020-04-21 北京奇艺世纪科技有限公司 Content recommendation method and device, electronic equipment and storable medium
CN111080401A (en) * 2019-11-25 2020-04-28 苏宁云计算有限公司 Age estimation method and device
WO2022017001A1 (en) * 2020-07-21 2022-01-27 百果园技术(新加坡)有限公司 Recommendation method, and method and device for publishing online prediction model
CN114818982A (en) * 2022-05-25 2022-07-29 深圳市酷开网络科技股份有限公司 User portrait generation method and device and electronic equipment
CN115134668A (en) * 2022-03-14 2022-09-30 深圳市酷开网络科技股份有限公司 OTT-based family member age group and family structure dividing method and device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107239456A (en) * 2016-03-28 2017-10-10 阿里巴巴集团控股有限公司 Age bracket recognition methods and device
CN111080401A (en) * 2019-11-25 2020-04-28 苏宁云计算有限公司 Age estimation method and device
CN110941738A (en) * 2019-11-27 2020-03-31 北京奇艺世纪科技有限公司 Recommendation method and device, electronic equipment and computer-readable storage medium
CN111046230A (en) * 2019-12-06 2020-04-21 北京奇艺世纪科技有限公司 Content recommendation method and device, electronic equipment and storable medium
WO2022017001A1 (en) * 2020-07-21 2022-01-27 百果园技术(新加坡)有限公司 Recommendation method, and method and device for publishing online prediction model
CN115134668A (en) * 2022-03-14 2022-09-30 深圳市酷开网络科技股份有限公司 OTT-based family member age group and family structure dividing method and device
CN114818982A (en) * 2022-05-25 2022-07-29 深圳市酷开网络科技股份有限公司 User portrait generation method and device and electronic equipment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李佳琪;刘红岩;何军;王蓓;杜小勇: "应用商城中用户年龄的推断及在推荐中的应用", 《计算机科学与探索》, vol. 12, no. 11, 2 April 2018 (2018-04-02), pages 1729 - 1739 *

Also Published As

Publication number Publication date
CN116248931B (en) 2024-07-12

Similar Documents

Publication Publication Date Title
CN106294497B (en) Information recommendation method and device
CN109241425B (en) Resource recommendation method, device, equipment and storage medium
US10997229B2 (en) Content recommendation system
CN108322829B (en) Personalized anchor recommendation method and device and electronic equipment
CN110929052A (en) Multimedia resource recommendation method and device, electronic equipment and storage medium
CN108335131B (en) Method and device for estimating age bracket of user and electronic equipment
KR20160113685A (en) Method, apparatus and system for content recommendation
CN108134944B (en) Identification method and device for anchor user with abnormal income and electronic equipment
CN110941738A (en) Recommendation method and device, electronic equipment and computer-readable storage medium
CN111046230B (en) Content recommendation method and device, electronic equipment and storable medium
EP3346396A1 (en) Multimedia resource quality assessment method and apparatus
US20230269432A1 (en) System, method and computer-readable medium for recommending streaming data
CN109379608A (en) A kind of recommended method and relevant device of direct broadcasting room
CN111753239A (en) Resource distribution method and device, electronic equipment and storage medium
CN111291217A (en) Content recommendation method and device, electronic equipment and computer readable medium
CN105956061B (en) Method and device for determining similarity between users
CN107730271B (en) Similar user determination method and device based on virtual interaction object and electronic equipment
CN116248931B (en) Resource information pushing method and device, electronic equipment and readable storage medium
CN111597380B (en) Recommended video determining method and device, electronic equipment and storage medium
CN111079061B (en) Data processing method and electronic equipment
US20100205041A1 (en) Determining the interest of individual entities based on a general interest
CN109963174B (en) Flow related index estimation method and device and computer readable storage medium
CN111565322B (en) User emotional tendency information obtaining method and device and electronic equipment
CN110996177B (en) Video recommendation method, device and equipment for video-on-demand cinema
CN111104582B (en) Fault tolerance method and device for search page 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