Preference difference detection method, device, electronic device and computer storage medium

By classifying and detecting user data, determining the difference in video preferences between user groups, the problem of low accuracy of video recommendation in the prior art is solved, and the accuracy and user experience of video delivery are improved.

CN114661947BActive Publication Date: 2024-11-26BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210253490.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-15
Publication Date
2024-11-26
Estimated Expiration
2042-03-15

AI Technical Summary

Technical Problem

When recommending videos by existing video platforms, the recommendation accuracy is low for new users or users with fewer historical viewing records, resulting in poor user viewing experience.

Method used

By obtaining relevant data from users, classifying the data based on classification information, obtaining inspection indicators for testing, and using ANOVA and T test to determine the differences in video preferences between user groups to improve the accuracy of video delivery.

Benefits of technology

It realizes more accurate video recommendations and improves the user's viewing experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114661947B_ABST
    Figure CN114661947B_ABST
Patent Text Reader

Abstract

The present disclosure is about a preference difference detection method, device, electronic device and computer-readable storage medium, and relates to the field of data processing technology. The method includes: obtaining relevant data of users to be detected who watch videos; obtaining classification information, and classifying the relevant data based on the classification information to obtain at least two groups of sub-data; obtaining a test index, and testing any two groups of sub-data in the at least two groups of sub-data based on the test index to obtain at least one test result. In this way, the users to be detected are divided into at least two groups through the classification information, each group corresponds to a group of sub-data, and then each group of sub-data is tested based on the test index to obtain at least one test result of whether there is a difference in viewing preference between each group, so as to realize video delivery to each group based on the test results, which not only improves the accuracy of video delivery, but also improves the user's experience of watching videos.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a preference difference detection method, device, electronic device, and computer-readable storage medium. Background Art

[0002] When users watch videos on a video platform, the video platform can recommend videos to them. However, due to differences in region, gender, age, etc., different users have different preferences for different types of videos.

[0003] In the related art, the video platform will recommend videos based on the user's historical viewing records. However, the accuracy of this recommendation method depends on the number of historical viewing records of the user. The more the number, the more accurate the recommendation. For new users or users with fewer historical viewing records, the accuracy of this recommendation method is low, and the user's video viewing experience is poor. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a preference difference detection method, device, electronic device and storage medium. The technical solution of the present disclosure is as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, a preference difference detection method is provided, comprising:

[0006] Obtain relevant data of the user to be detected who is watching the video;

[0007] Acquire classification information, and classify the relevant data based on the classification information to obtain at least two groups of sub-data; each group of sub-data has a corresponding user group;

[0008] A test index is obtained, and any two groups of sub-data in the at least two groups of sub-data are tested based on the test index to obtain at least one test result; any one of the test results represents the difference in viewing video preferences between two different user groups.

[0009] Optionally, the preset classification information includes: location information, identity information, and preference information;

[0010] The obtaining of classification information and classifying the relevant data based on the classification information to obtain at least two groups of sub-data includes:

[0011] Acquire at least one item of target classification information determined from the preset classification information;

[0012] The relevant data is classified based on the target classification information to obtain at least two groups of sub-data.

[0013] Optionally, the testing any two groups of sub-data among the at least two groups of sub-data based on the inspection index to obtain at least one test result includes:

[0014] Arrange each group of sub-data based on the inspection index to obtain arranged data;

[0015] Performing variance analysis on the sorted data to obtain variance analysis results;

[0016] Detecting whether an inspection is needed based on the variance analysis result;

[0017] If a test is required, any two groups of sub-data among the at least two groups of sub-data are tested to obtain at least one test result.

[0018] Optionally, the data sorting of each group of sub-data based on the inspection index to obtain sorted data includes:

[0019] Obtaining a single group of indicator data corresponding to the inspection indicator in each group of sub-data;

[0020] Calculate the sum of the single group indicator data of each single group indicator data, and calculate the single group indicator data mean of each single group indicator data based on the sum of the single group indicator data;

[0021] Calculate the sum of the complete indicator data including each group of indicator data based on the mean value of each single group of indicator data, and calculate the mean value of the complete indicator data based on the sum of the complete indicator data;

[0022] The sum of the single-group indicator data of each group of sub-data, the mean of the single-group indicator data of each group of sub-data, the sum of the complete indicator data and the mean of the complete indicator data are taken as the sorted data.

[0023] Optionally, performing variance analysis on the sorted data to obtain variance analysis results includes:

[0024] Calculate the sum of squares, the within-group sum of squares, the error sum of squares and the within-group variance of the sorted data respectively;

[0025] Calculate the intra-group square sum and degree of freedom based on the number of groups of the single group indicator data, and use the ratio of the intra-group square sum and the intra-group square sum and degree of freedom as the inter-group mean square value of the sorted data;

[0026] Calculate the error square and degrees of freedom based on the total number of data in all single-group indicator data, and calculate the error mean square value of the sorted data by the ratio of the error square and the error square and degrees of freedom;

[0027] Calculate the F critical value based on the within-group square sum of freedom and the error square sum of freedom, and use the ratio of the between-group mean square value to the error mean square value as the F value of the sorted data;

[0028] The variance analysis results are generated based on the sum of squares, the within-group sum of squares, the error sum of squares, the within-group variance, the between-group mean square value, the error mean square value, the F value, and the F critical value.

[0029] Optionally, the detecting any two groups of sub-data among the at least two groups of sub-data to obtain at least one detection result includes:

[0030] Calculating the error square and degrees of freedom based on the total number of data in each group of sub-data, and calculating the significance level based on the number of groups of sub-data, and calculating the T critical value based on the error square and degrees of freedom and the significance level;

[0031] Calculate the T value between the two groups of sub-data to be detected;

[0032] If the T value exceeds the absolute value of the T critical value, then there is a difference in viewing video preference between the two groups of sub-data to be detected;

[0033] If the T value does not exceed the absolute value of the T critical value, there is no difference in viewing video preference between the two groups of sub-data to be detected.

[0034] According to a second aspect of an embodiment of the present disclosure, there is provided a preference difference detection device, comprising:

[0035] An acquisition unit, configured to acquire relevant data of a user to be detected who is watching a video;

[0036] A classification unit is configured to obtain classification information, and classify the relevant data based on the classification information to obtain at least two groups of sub-data; each group of sub-data has a corresponding user group;

[0037] The detection unit is configured to obtain a detection index, and based on the detection index, detect any two groups of sub-data among the at least two groups of sub-data to obtain at least one detection result; any one of the detection results represents the difference in viewing video preferences between two different user groups.

[0038] Optionally, the preset classification information includes: location information, identity information, and preference information;

[0039] The classification unit includes:

[0040] A first acquisition subunit is configured to acquire at least one target classification information determined from the preset classification information;

[0041] The classification subunit is configured to classify the relevant data based on the target classification information to obtain at least two groups of sub-data.

[0042] Optionally, the detection unit includes:

[0043] A data sorting subunit is configured to sort each group of sub-data based on the inspection index to obtain sorted data;

[0044] A variance analysis subunit is configured to perform variance analysis on the sorted data to obtain a variance analysis result;

[0045] A judgment subunit, configured to detect whether an inspection is required based on the variance analysis result;

[0046] The inspection subunit is configured to inspect any two groups of sub-data among the at least two groups of sub-data to obtain at least one inspection result if inspection is required.

[0047] Optionally, the data sorting subunit is specifically configured as follows:

[0048] Obtaining a single group of indicator data corresponding to the inspection indicator in each group of sub-data;

[0049] Calculate the sum of the single group indicator data of each single group indicator data, and calculate the single group indicator data mean of each single group indicator data based on the sum of the single group indicator data;

[0050] Calculate the sum of the complete indicator data including each group of indicator data based on the mean value of each single group of indicator data, and calculate the mean value of the complete indicator data based on the sum of the complete indicator data;

[0051] The sum of the single-group indicator data of each group of sub-data, the mean of the single-group indicator data of each group of sub-data, the sum of the complete indicator data and the mean of the complete indicator data are taken as the sorted data.

[0052] Optionally, the variance analysis subunit is specifically configured as follows:

[0053] Calculate the sum of squares, the within-group sum of squares, the error sum of squares and the within-group variance of the sorted data respectively;

[0054] Calculate the intra-group square sum and degree of freedom based on the number of groups of the single group indicator data, and use the ratio of the intra-group square sum and the intra-group square sum and degree of freedom as the inter-group mean square value of the sorted data;

[0055] Calculate the error square and degrees of freedom based on the total number of data in all single-group indicator data, and calculate the error mean square value of the sorted data by the ratio of the error square and the error square and degrees of freedom;

[0056] Calculate the F critical value based on the within-group square sum of freedom and the error square sum of freedom, and use the ratio of the between-group mean square value to the error mean square value as the F value of the sorted data;

[0057] The variance analysis results are generated based on the sum of squares, the within-group sum of squares, the error sum of squares, the within-group variance, the between-group mean square value, the error mean square value, the F value, and the F critical value.

[0058] Optionally, the inspection subunit is specifically configured as follows:

[0059] Calculating the error square and degrees of freedom based on the total number of data in each group of sub-data, and calculating the significance level based on the number of groups of sub-data, and calculating the T critical value based on the error square and degrees of freedom and the significance level;

[0060] Calculate the T value between the two groups of sub-data to be detected;

[0061] If the T value exceeds the absolute value of the T critical value, then there is a difference in viewing video preference between the two groups of sub-data to be detected;

[0062] If the T value does not exceed the absolute value of the T critical value, there is no difference in viewing video preference between the two groups of sub-data to be detected.

[0063] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0064] processor;

[0065] a memory for storing processor-executable instructions;

[0066] The processor is configured to execute the instructions to implement the preference difference detection method as described in the first aspect.

[0067] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the storage medium are executed by a processor of a mobile terminal, the electronic device can perform the preference difference detection method as described in the first aspect.

[0068] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, which includes a computer program or computer instructions, and when the computer program or computer instructions are executed by a processor, the preference difference detection method as in the first aspect is implemented.

[0069] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: obtaining relevant data of the user to be detected, and when the classification information is obtained, classifying the relevant data based on the classification information to obtain at least two groups of sub-data, and when the inspection index is obtained, detecting any two groups of sub-data in the at least two groups of sub-data based on the inspection index to obtain at least one detection result, and any detection result characterizes the difference in viewing preference between two different user groups. In this way, the users to be detected are divided into at least two groups through the classification information, each group corresponds to a group of sub-data, and then each group of sub-data is detected based on the inspection index to obtain at least one detection result of whether there is a difference in viewing preference between each group, so as to realize video delivery to each group based on the detection result, which not only improves the accuracy of video delivery, but also improves the user's experience of watching videos.

[0070] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0072] Figure 1 The figure is a flow chart of a method for detecting a preference difference according to an exemplary embodiment.

[0073] Figure 2 It is a block diagram of a preference difference detection device according to an exemplary embodiment.

[0074] Figure 3 It is a block diagram of a device according to an exemplary embodiment (general structure of a mobile terminal). DETAILED DESCRIPTION

[0075] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0076] Figure 1 is a flow chart of a preference difference detection method according to an exemplary embodiment. Figure 1As shown, the preference difference detection method is applied to detect the preference differences between different users in watching videos, for example, detecting the preference differences between users in province A and users in province B, the preference differences between male users and female users, etc. The method includes the following steps.

[0077] In step S11, relevant data of the user to be detected is obtained.

[0078] Specifically, the users to be detected may be all users who watch videos on the video platform, and the relevant data may be the user information of any user to be detected and the video information of the video being watched, the user information includes but is not limited to the user's location, gender, age, etc., and the video information includes but is not limited to the type of video, the author of the video, the play date of the video, the play duration, etc. Of course, in actual applications, the specific information of the user information and the video information can be set according to actual needs, and this embodiment does not limit this.

[0079] In step S12, classification information is obtained, and the relevant data is classified based on the classification information to obtain at least two groups of sub-data; each group of sub-data has a corresponding user group.

[0080] After the relevant data is obtained, classification information for classifying the relevant data may be further obtained, so that the relevant data may be classified according to the classification information to obtain at least two groups of sub-data, each group of sub-data corresponding to one classification.

[0081] In this embodiment, the preset classification information includes: location information, identity information, and preference information;

[0082] The obtaining of classification information and classifying the relevant data based on the classification information to obtain at least two groups of sub-data includes:

[0083] Acquire at least one item of target classification information determined from the preset classification information;

[0084] The relevant data is classified based on the target classification information to obtain at least two groups of sub-data.

[0085] Specifically, before classification, multiple classification information can be preset, including but not limited to: location information, identity information, and preference information. Specifically including but not limited to: the user's resident province, resident city, city level (such as first-tier cities, second-tier cities), town type (such as towns, rural areas), age group, gender, north and south, resident area (such as East China, South China), and commonly used applications (i.e., applications that users often use to watch videos). In this way, when classifying, at least one item can be selected from multiple classification information to classify the relevant data, thereby obtaining at least two groups of sub-data, each group of sub-data corresponds to a classification and a user group, and the collection of all user groups is all the users to be detected.

[0086] For example, assuming that the relevant data are classified according to the province of residence, we can get Group A sub-data and Group B sub-data. Group A sub-data corresponds to Hubei Province, and Group B sub-data corresponds to Hunan Province; assuming that the relevant data are classified according to age segments, we can get Group C sub-data, Group D sub-data and Group E sub-data. Group C sub-data corresponds to 21 to 30 years old, Group D sub-data corresponds to 31 to 40 years old, and Group E sub-data corresponds to 41 to 50 years old.

[0087] In step S13, a test index is obtained, and any two groups of sub-data in the at least two groups of sub-data are tested based on the test index to obtain at least one test result; any one of the test results represents the difference in viewing video preferences between two different user groups.

[0088] Among them, the test index is used to characterize the dimension of testing each group of sub-data. In this embodiment, before the test, multiple test indicators can be preset, and the test indicators include but are not limited to: the proportion of completed broadcasts, the proportion of broadcasts in the same city, and the proportion of viewing time in the same city. In this way, during the test, one item can be selected from multiple test indicators to test any two groups of sub-data in at least two groups of sub-data to obtain at least one test result. Among them, any test result represents the difference in viewing video preferences between two different user groups. For example, there are a total of 3 groups of sub-data A, B, and C, then, testing any two groups of sub-data in the 3 groups of sub-data can be: AB detection, AC detection, and BC detection.

[0089] In this embodiment, the detecting any two groups of sub-data among the at least two groups of sub-data based on the inspection index to obtain at least one detection result includes:

[0090] Arrange each group of sub-data based on the inspection index to obtain arranged data;

[0091] Performing variance analysis on the sorted data to obtain variance analysis results;

[0092] Detecting whether an inspection is needed based on the variance analysis result;

[0093] If a test is required, any two groups of sub-data among the at least two groups of sub-data are tested to obtain at least one test result.

[0094] Specifically, after obtaining the test index, each group of sub-data can be sorted based on the test index to obtain each group of sorted sub-data corresponding to the test index, and then variance analysis is performed on each group of sorted sub-data to obtain variance analysis results, and then based on the variance analysis results, it is detected whether it is necessary to test each group of sorted sub-data. If it is detected that each group of sorted sub-data needs to be tested, then each group of sorted sub-data is tested to obtain at least one test result. Among them, the test can be to detect whether there is a difference between two groups of sorted sub-data, and the test result can be that there is a difference between the two groups of sorted sub-data, or there is no difference between the two groups of sorted sub-data.

[0095] Furthermore, when sorting each group of sub-data, in addition to using the test index, the date can also be used. For example, sorting each group of sub-data within a week, the sorted data obtained includes detailed data for 7 days.

[0096] In this embodiment, the data sorting of each group of sub-data based on the inspection index to obtain sorted data includes:

[0097] Obtaining a single group of indicator data corresponding to the inspection indicator in each group of sub-data;

[0098] Calculate the sum of the single group indicator data of each single group indicator data, and calculate the single group indicator data mean of each single group indicator data based on the sum of the single group indicator data;

[0099] Calculate the sum of the complete indicator data including each group of indicator data based on the mean value of each single group of indicator data, and calculate the mean value of the complete indicator data based on the sum of the complete indicator data;

[0100] The sum of the single-group indicator data of each group of sub-data, the mean of the single-group indicator data of each group of sub-data, the sum of the complete indicator data and the mean of the complete indicator data are taken as the sorted data.

[0101] Specifically, for each group of sub-data, the indicator data corresponding to the test indicator is obtained to obtain multiple single-group indicator data, and then the sum of the single-group indicator data of each single-group indicator data is calculated, and the mean of each single-group indicator data is calculated using the sum of the single-group indicator data, and then the mean of each single-group indicator data is used to calculate the sum of the complete indicator data containing each group of indicator data, and the mean of the complete indicator data is calculated using the sum of the complete indicator data. In this way, the set of the sum of the single-group indicator data of each group of sub-data, the mean of the single-group indicator data of each group of sub-data, the sum of the complete indicator data and the mean of the complete indicator data can be used as the sorted data.

[0102] It should be noted that after calculating the mean value of each single group of indicator data, each single group of indicator data can be sorted in descending order, so as to detect each sorted single group of indicator data in order, thereby reducing the amount of calculation during detection. Of course, subsequent inspections can be performed without sorting. In practical applications, whether sorting is required can be set according to actual needs, and this embodiment does not limit this.

[0103] For example, for the relevant data from October 1st to 7th, age segments are used for classification, and the proportion of completed plays is used as the test indicator to obtain the individual group indicator data shown in Table 1; among them, the age segments are 18-23, 12-17, 24-30, and 31-40.

[0104] Table 1

[0105] Date\Age 12~17(Group 1) 24~30(Group 2) 18~23(Group 3) 31~40(Group 4) 10.1 0.318 0.325 0.3432 0.304 10.2 0.3057 0.3234 0.3389 0.2974 10.3 0.3055 0.3041 0.3408 0.3018 10.4 0.2986 0.3106 0.3296 0.3022 10.5 0.2921 0.3044 0.3288 0.2921 10.6 0.2936 0.3132 0.3241 0.2918 10.7 0.3107 0.3034 0.3347 0.2936

[0106] The sum of the single group indicator data of each single group indicator data is calculated, which is: Group 1 = 2.1242, Group 2 = 2.1841, Group 3 = 2.3401, Group 4 = 2.0829, and the mean of the single group indicator data of each single group indicator data is calculated using the sum of the single group indicator data, which is: Group 1 = 0.303457, Group 2 = 0.312014, Group 3 = 0.3343, Group 4 = 0.297557.

[0107] If sorting is required, then the individual groups of indicator data can be sorted according to the mean of the individual group of indicator data, as shown in Table 2:

[0108] Table 2

[0109]

[0110]

[0111] The mean value of each single group of indicator data is used to calculate the total of complete indicator data containing each group of indicator data, that is, the total of complete indicator data = group 1 single group indicator data + group 2 single group indicator data + group 3 single group indicator data + group 4 single group indicator data = 2.1242 + 2.1841 + 2.3401 + 2.0829 = 8.7313, and the mean of complete indicator data is calculated based on the total of complete indicator data, that is, 8.7313 / 28 = 0.3118.

[0112] The sum of the single group indicator data of each group of sub-data, the mean of the single group indicator data of each group of sub-data, the sum of the complete indicator data and the mean of the complete indicator data are taken as the sorted data, as shown in Table 3:

[0113] Table 3

[0114] Group 1 Group 2 Group 3 Group 4 total 2.3401 2.1841 2.1242 2.0829 8.7313 7 7 7 7 28 0.3343 0.312014 0.303457 0.297557 0.3118

[0115] Among them, the first line is the sum of each single group indicator data and the sum of the complete indicator data, the second line is the number of data, and the third line is the mean of the single group indicator data and the mean of the complete indicator data.

[0116] In this embodiment, the variance analysis is performed on the sorted data to obtain the variance analysis result, including:

[0117] Calculate the sum of squares, the within-group sum of squares, the error sum of squares and the within-group variance of the sorted data respectively;

[0118] Calculate the intra-group square sum and degree of freedom based on the number of groups of the single group indicator data, and use the ratio of the intra-group square sum and the intra-group square sum and degree of freedom as the inter-group mean square value of the sorted data;

[0119] Calculate the error square and degrees of freedom based on the total number of data in all single-group indicator data, and calculate the error mean square value of the sorted data by the ratio of the error square and the error square and degrees of freedom;

[0120] Calculate the F critical value based on the within-group square sum of freedom and the error square sum of freedom, and use the ratio of the between-group mean square value to the error mean square value as the F value of the sorted data;

[0121] The variance analysis results are generated based on the sum of squares, the within-group sum of squares, the error sum of squares, the within-group variance, the between-group mean square value, the error mean square value, the F value, and the F critical value.

[0122] Specifically, after obtaining the sorted data, the sum of the squares of the sorted data (denoted as SS Total ), the within-group sum of squares (denoted as SS Treat ), the error sum of squares (denoted as SSError ) and the within-group variance (denoted as S 2 ), and then calculate the within-group square and degrees of freedom (denoted as df Treat ), and the ratio of the within-group sum of squares to the within-group sum of squares and degrees of freedom is taken as the between-group mean square value of the sorted data (denoted as MS Treat ), and, based on the total number of data in all single-group indicator data, calculate the error square and degrees of freedom (denoted as df Error ), and the error mean square value (denoted as MS) of the data after the ratio of the error sum of squares to the error sum of squares degrees of freedom is sorted. E ), and then use the within-group square sum of freedom, the error square sum of freedom and the preset proportionality coefficient (alfa) to calculate the F critical value. At the same time, the ratio of the between-group mean square value to the error mean square value is used as the F value of the sorted data. In this way, the analysis results can be generated based on the total sum of squares, within-group sum of squares, error sum of squares, within-group variance, between-group mean square value, error mean square value, F value and F critical value.

[0123] For example, by performing variance analysis on Table 3, we obtain the analysis results shown in Table 4:

[0124] Table 4

[0125]

[0126] Among them, k is the number of groups of single-group indicator data (4 groups), N is the total number of data in all single-group indicator data (4 groups * 7 = 28), F critical value = F.INV.RT (alfa, df Treat ,df Error )=F.INV.RT(0.05,3,24)=3.01.

[0127] In this embodiment, the detecting whether an inspection is required based on the variance analysis result includes:

[0128] Detecting whether the F value exceeds the F critical value;

[0129] If the F value does not exceed the F critical value, no inspection is required; if the F value exceeds the F critical value, an inspection is required.

[0130] Specifically, it is possible to detect whether the F value exceeds the F critical value. If the F value <= F critical value, then no test is required; if the F value > F critical value, then a test is required. For example, in Table 4, the F value is 29.50, which is greater than the F critical value of 3.01, so a test is required.

[0131] In this embodiment, the detecting any two groups of sub-data among the at least two groups of sub-data to obtain at least one detection result includes:

[0132] Calculating the error square and degrees of freedom based on the total number of data in each group of sub-data, and calculating the significance level based on the number of groups of sub-data, and calculating the T critical value based on the error square and degrees of freedom and the significance level;

[0133] Calculate the T value between the two groups of sub-data to be detected;

[0134] If the T value exceeds the absolute value of the T critical value, then there is a difference in viewing video preference between the two groups of sub-data to be detected;

[0135] If the T value does not exceed the absolute value of the T critical value, there is no difference in viewing video preference between the two groups of sub-data to be detected.

[0136] Specifically, when testing each group of sub-data, the total number of data in each group of sub-data can be used to calculate the error square and degree of freedom, that is, df Error (Since the number of data in any group of sub-data is the same as the number of data in the corresponding single group of indicator data, the total number of data in each group of sub-data is also the same as the total number of data in all single groups of indicator data), and the significance level is calculated using the preset proportional coefficient (that is, alfa) and the number of groups of sub-data, and the T critical value is calculated using the error square sum of degrees of freedom, the proportional coefficient and the significance level.

[0137] Then, for the two groups of sub-data to be tested, the mean of the single group indicator data corresponding to the two groups of sub-data, the number of data in the two groups of sub-data, and the mean square error (MS E ) calculates the T value between the two groups of sub-data. If the T value exceeds the absolute value of the T critical value, there is a difference in viewing preference for videos between the two groups of sub-data to be detected; if the T value does not exceed the absolute value of the T critical value, there is no difference in viewing preference for videos between the two groups of sub-data to be detected.

[0138] For example, continuing with the previous example, for ease of understanding, the data required for the test are shown in Table 5:

[0139] Table 5

[0140]

[0141] Among them, the first line is the mean value of each single group of indicator data, the second line is the number of data in each group of sub-data, and the third line is the mean square error.

[0142] Specifically, the total number of data in each group of sub-data is used to calculate the error square and the degrees of freedom, that is, df Error =Nk=24; the significance level is calculated using the preset proportionality coefficient (i.e., alfa) and the number of sub-data groups, i.e., significance level = 0.05 / k = 0.05 / 4 = 0.0125; the T critical value is calculated using the error square and degrees of freedom, proportionality coefficient, and significance level, i.e., T critical value = T.INV.2T(alpha,df Error )=TINV(alpha,df Error )=2.70.

[0143] Assuming that Group 1 and Group 2 are tested, the T value is calculated using the mean of the single-group indicator data of Group 1, the number of data, the mean of the single-group indicator data of Group 2, the number of data, and the mean square error value to obtain a T value of 5.31. Since 5.31>2.70, the detection result that there is a difference in video viewing preference between Group 1 and Group 2 is generated.

[0144] Assuming that Group 2 and Group 3 are tested, the T value is calculated using the mean of the single-group indicator data of Group 1, the number of data, the mean of the single-group indicator data of Group 2, the number of data, and the mean square error value to obtain a T value of 2.04. Since -2.70<2.04<2.70, the detection result is that there is no difference in video viewing preference between Group 2 and Group 3.

[0145] And so on, the detection results between each group of sub-data can be obtained.

[0146] In this embodiment, relevant data of the user to be detected is obtained. When classification information is obtained, the relevant data is classified based on the classification information to obtain at least two groups of sub-data. When the inspection index is obtained, any two groups of sub-data in the at least two groups of sub-data are tested based on the inspection index to obtain at least one test result. Any test result represents the difference in viewing preferences between two different user groups. In this way, the users to be detected are divided into at least two groups through classification information, each group corresponds to a group of sub-data, and then each group of sub-data is tested based on the inspection index to obtain at least one test result of whether there is a difference in viewing preferences between the groups, so as to achieve video delivery to each group based on the test results, which not only improves the accuracy of video delivery, but also improves the user's experience of watching videos.

[0147] Figure 2 is a block diagram of a preference difference detection device according to an exemplary embodiment. Figure 2 The device includes an acquisition unit 211, a classification unit 212 and a detection unit 213.

[0148] The acquisition unit 211 is configured to acquire relevant data of the to-be-detected user who is watching the video.

[0149] The classification unit 212 is configured to obtain classification information, and classify the relevant data based on the classification information to obtain at least two groups of sub-data; each group of sub-data has a corresponding user group.

[0150] The detection unit 213 is configured to obtain a detection index, and detect any two groups of sub-data among the at least two groups of sub-data based on the detection index to obtain at least one detection result; any one detection result represents the difference in viewing video preferences between two different user groups.

[0151] Optionally, the preset classification information includes: location information, identity information, and preference information;

[0152] The classification unit includes:

[0153] A first acquisition subunit is configured to acquire at least one target classification information determined from the preset classification information;

[0154] The classification subunit is configured to classify the relevant data based on the target classification information to obtain at least two groups of sub-data.

[0155] Optionally, the detection unit includes:

[0156] A data sorting subunit is configured to sort each group of sub-data based on the inspection index to obtain sorted data;

[0157] A variance analysis subunit is configured to perform variance analysis on the sorted data to obtain a variance analysis result;

[0158] A judgment subunit, configured to detect whether an inspection is required based on the variance analysis result;

[0159] The inspection subunit is configured to inspect any two groups of sub-data among the at least two groups of sub-data to obtain at least one inspection result if inspection is required.

[0160] Optionally, the data sorting subunit is specifically configured as follows:

[0161] Obtaining a single group of indicator data corresponding to the inspection indicator in each group of sub-data;

[0162] Calculate the sum of the single group indicator data of each single group indicator data, and calculate the single group indicator data mean of each single group indicator data based on the sum of the single group indicator data;

[0163] Calculate the sum of the complete indicator data including each group of indicator data based on the mean value of each single group of indicator data, and calculate the mean value of the complete indicator data based on the sum of the complete indicator data;

[0164] The sum of the single-group indicator data of each group of sub-data, the mean of the single-group indicator data of each group of sub-data, the sum of the complete indicator data and the mean of the complete indicator data are taken as the sorted data.

[0165] Optionally, the variance analysis subunit is specifically configured as follows:

[0166] Calculate the sum of squares, the within-group sum of squares, the error sum of squares and the within-group variance of the sorted data respectively;

[0167] Calculate the intra-group square sum and degree of freedom based on the number of groups of the single group indicator data, and use the ratio of the intra-group square sum and the intra-group square sum and degree of freedom as the inter-group mean square value of the sorted data;

[0168] Calculate the error square and degrees of freedom based on the total number of data in all single-group indicator data, and calculate the error mean square value of the sorted data by the ratio of the error square and the error square and degrees of freedom;

[0169] Calculate the F critical value based on the within-group square sum of freedom and the error square sum of freedom, and use the ratio of the between-group mean square value to the error mean square value as the F value of the sorted data;

[0170] The variance analysis results are generated based on the sum of squares, the within-group sum of squares, the error sum of squares, the within-group variance, the between-group mean square value, the error mean square value, the F value, and the F critical value.

[0171] Optionally, the inspection subunit is specifically configured as follows:

[0172] Calculating the error square and degrees of freedom based on the total number of data in each group of sub-data, and calculating the significance level based on the number of groups of sub-data, and calculating the T critical value based on the error square and degrees of freedom and the significance level;

[0173] Calculate the T value between the two groups of sub-data to be detected;

[0174] If the T value exceeds the absolute value of the T critical value, then there is a difference in viewing video preference between the two groups of sub-data to be detected;

[0175] If the T value does not exceed the absolute value of the T critical value, there is no difference in viewing video preference between the two groups of sub-data to be detected.

[0176] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0177] Figure 3 is a block diagram of an apparatus 300 for detecting preference differences according to an exemplary embodiment. For example, the apparatus 300 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0178] Reference Figure 3 , the device 300 may include one or more of the following components: a processing component 302 , a memory 304 , a power component 306 , a multimedia component 308 , an audio component 310 , an input / output (I / O) interface 312 , a sensor component 314 , and a communication component 316 .

[0179] The processing component 302 generally controls the overall operation of the device 300, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 302 may include one or more processors 320 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 302 may include one or more modules to facilitate the interaction between the processing component 302 and other components. For example, the processing component 302 may include a multimedia module to facilitate the interaction between the multimedia component 308 and the processing component 302.

[0180] The memory 304 is configured to store various types of data to support operations on the device 300. Examples of such data include instructions for any application or method operating on the device 300, contact data, phone book data, messages, pictures, videos, etc. The memory 304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0181] The power supply component 306 provides power to the various components of the device 300. The power supply component 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 300.

[0182] The multimedia component 308 includes a screen that provides an output interface between the device 300 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 308 includes a front camera and / or a rear camera. When the device 300 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0183] The audio component 310 is configured to output and / or input audio signals. For example, the audio component 310 includes a microphone (MIC), and when the device 300 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 304 or sent via the communication component 316. In some embodiments, the audio component 310 also includes a speaker for outputting audio signals.

[0184] I / O interface 312 provides an interface between processing component 302 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0185] The sensor assembly 314 includes one or more sensors for providing various aspects of status assessment for the device 300. For example, the sensor assembly 314 can detect the open / closed state of the device 300, the relative positioning of components, such as the display and keypad of the device 300, the sensor assembly 314 can also detect the position change of the device 300 or a component of the device 300, the presence or absence of user contact with the device 300, the orientation or acceleration / deceleration of the device 300, and the temperature change of the device 300. The sensor assembly 314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 314 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 314 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0186] The communication component 316 is configured to facilitate wired or wireless communication between the device 300 and other devices. The device 300 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 5G), or a combination thereof. In an exemplary embodiment, the communication component 316 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 316 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0187] In an exemplary embodiment, the apparatus 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0188] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 304 including instructions, and the instructions can be executed by the processor 320 of the device 300 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0189] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0190] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for detecting preference differences, characterized in that: include: Obtain relevant data of the user to be detected who is watching the video; Acquiring classification information, and classifying the relevant data based on the classification information to obtain at least two groups of sub-data; Each group of sub-data has a corresponding user group; Acquire a test indicator, and test any two groups of sub-data among the at least two groups of sub-data based on the test indicator to obtain at least one test result; the test result represents a difference in viewing video preferences between two different user groups; The step of testing any two groups of sub-data among the at least two groups of sub-data based on the test index to obtain at least one test result includes: Arrange each group of sub-data based on the inspection index to obtain arranged data; Performing variance analysis on the sorted data to obtain variance analysis results; Detecting whether an inspection is needed based on the variance analysis result; If inspection is required, any two groups of sub-data among the at least two groups of sub-data are inspected to obtain at least one inspection result; The detecting any two groups of sub-data among the at least two groups of sub-data to obtain at least one detection result includes: Obtaining the single group indicator data corresponding to the inspection indicator in the two groups of sub-data; calculating the sum of the single group indicator data of each single group indicator data, and calculating the single group indicator data mean of each single group indicator data based on the sum of the single group indicator data; The error square sum of degrees of freedom is calculated based on the total number of data in the single group of indicator data, and the error mean square value is obtained by arranging the ratio of the error square sum of degrees of freedom to the error square sum of degrees of freedom; Calculating the error square and degrees of freedom based on the total number of data in each group of sub-data, and calculating the significance level based on the number of groups of sub-data, and calculating the T critical value based on the error square and degrees of freedom and the significance level; Calculate the T value between the two groups of sub-data to be detected; the T value between the two groups of sub-data to be detected is calculated based on the mean of the single group of indicator data corresponding to the two groups of sub-data, the number of data in the two groups of sub-data, and the mean square error; the mean of the single group of indicator data If the T value exceeds the absolute value of the T critical value, then there is a difference in viewing video preference between the two groups of sub-data to be detected; If the T value does not exceed the absolute value of the T critical value, there is no difference in viewing video preference between the two groups of sub-data to be detected.

2. The preference difference detection method according to claim 1, characterized in that: The obtaining of classification information and classifying the relevant data based on the classification information to obtain at least two groups of sub-data includes: Acquire at least one target classification information determined from preset classification information; the preset classification information includes: location information, identity information, and preference information; The relevant data is classified based on the target classification information to obtain at least two groups of sub-data.

3. The preference difference detection method according to claim 1, characterized in that: The step of sorting each group of sub-data based on the inspection index to obtain sorted data includes: Obtaining a single group of indicator data corresponding to the inspection indicator in each group of sub-data; Calculate the sum of the single group indicator data of each single group indicator data, and calculate the single group indicator data mean of each single group indicator data based on the sum of the single group indicator data; Calculate the sum of the complete indicator data including each group of indicator data based on the mean value of each single group of indicator data, and calculate the mean value of the complete indicator data based on the sum of the complete indicator data; The sum of the single-group indicator data of each group of sub-data, the mean of the single-group indicator data of each group of sub-data, the sum of the complete indicator data and the mean of the complete indicator data are taken as the sorted data.

4. The preference difference detection method according to claim 1, characterized in that: The performing variance analysis on the sorted data to obtain variance analysis results includes: Calculate the sum of squares, the within-group sum of squares, the error sum of squares and the within-group variance of the sorted data respectively; Calculate the intra-group square sum and degree of freedom based on the number of groups of the single group indicator data, and use the ratio of the intra-group square sum and the intra-group square sum and degree of freedom as the inter-group mean square value of the sorted data; Calculate the error square and degrees of freedom based on the total number of data in all single-group indicator data, and calculate the error mean square value of the sorted data by the ratio of the error square and the error square and degrees of freedom; Calculate the F critical value based on the within-group square sum of freedom and the error square sum of freedom, and use the ratio of the between-group mean square value to the error mean square value as the F value of the sorted data; The variance analysis results are generated based on the sum of squares, the within-group sum of squares, the error sum of squares, the within-group variance, the between-group mean square value, the error mean square value, the F value, and the F critical value.

5. A preference difference detection device, characterized in that: include: An acquisition unit, configured to acquire relevant data of a user to be detected who is watching a video; a classification unit, configured to obtain classification information, and classify the relevant data based on the classification information to obtain at least two groups of sub-data; Each group of sub-data has a corresponding user group; a detection unit configured to obtain a detection index, and detect any two groups of sub-data among the at least two groups of sub-data based on the detection index to obtain at least one detection result; The detection result represents the difference in viewing video preferences between two different user groups; The detection unit comprises: A data sorting subunit is configured to sort each group of sub-data based on the inspection index to obtain sorted data; A variance analysis subunit is configured to perform variance analysis on the sorted data to obtain a variance analysis result; A judgment subunit, configured to detect whether an inspection is required based on the variance analysis result; a testing subunit, configured to test any two groups of sub-data among the at least two groups of sub-data to obtain at least one test result if a test is required; The inspection subunit is specifically configured as follows: Obtaining the single group indicator data corresponding to the inspection indicator in the two groups of sub-data; calculating the sum of the single group indicator data of each single group indicator data, and calculating the single group indicator data mean of each single group indicator data based on the sum of the single group indicator data; The error square sum of degrees of freedom is calculated based on the total number of data in the single group of indicator data, and the error mean square value is obtained by arranging the ratio of the error square sum of degrees of freedom to the error square sum of degrees of freedom; Calculating the error square and degrees of freedom based on the total number of data in each group of sub-data, and calculating the significance level based on the number of groups of sub-data, and calculating the T critical value based on the error square and degrees of freedom and the significance level; Calculating a T value between two groups of sub-data to be detected; the T value between the two groups of sub-data to be detected is calculated based on the mean of the single group indicator data corresponding to the two groups of sub-data, the number of data in the two groups of sub-data, and the mean square error value; If the T value exceeds the absolute value of the T critical value, then there is a difference in viewing video preference between the two groups of sub-data to be detected; If the T value does not exceed the absolute value of the T critical value, there is no difference in viewing video preference between the two groups of sub-data to be detected.

6. The preference difference detection device according to claim 5, characterized in that: The preset classification information includes: location information, identity information, and preference information; The classification unit includes: A first acquisition subunit is configured to acquire at least one target classification information determined from the preset classification information; The classification subunit is configured to classify the relevant data based on the target classification information to obtain at least two groups of sub-data.

7. The preference difference detection device according to claim 5, characterized in that: The data sorting subunit is specifically configured as follows: Obtaining a single group of indicator data corresponding to the inspection indicator in each group of sub-data; Calculate the sum of the single group indicator data of each single group indicator data, and calculate the single group indicator data mean of each single group indicator data based on the sum of the single group indicator data; Calculate the sum of the complete indicator data including each group of indicator data based on the mean value of each single group of indicator data, and calculate the mean value of the complete indicator data based on the sum of the complete indicator data; The sum of the single-group indicator data of each group of sub-data, the mean of the single-group indicator data of each group of sub-data, the sum of the complete indicator data and the mean of the complete indicator data are taken as the sorted data.

8. The preference difference detection device according to claim 5, characterized in that: The variance analysis subunit is specifically configured as follows: Calculate the sum of squares, the within-group sum of squares, the error sum of squares and the within-group variance of the sorted data respectively; Calculate the intra-group square sum and degree of freedom based on the number of groups of the single group indicator data, and use the ratio of the intra-group square sum and the intra-group square sum and degree of freedom as the inter-group mean square value of the sorted data; Calculate the error square and degrees of freedom based on the total number of data in all single-group indicator data, and calculate the error mean square value of the sorted data by the ratio of the error square and the error square and degrees of freedom; Calculate the F critical value based on the within-group square sum of freedom and the error square sum of freedom, and use the ratio of the between-group mean square value to the error mean square value as the F value of the sorted data; The variance analysis results are generated based on the sum of squares, the within-group sum of squares, the error sum of squares, the within-group variance, the between-group mean square value, the error mean square value, the F value, and the F critical value.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the preference difference detection method according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the preference difference detection method according to any one of claims 1 to 4 is implemented.

11. A computer program product comprising a computer program or computer instructions, characterized in that When the computer program or computer instruction is executed by a processor, the preference difference detection method as described in any one of claims 1 to 4 is implemented.