Method and device for determining influence data of video file and electronic equipment

Abstract

The invention discloses a method and a device for determining influence data of a video file and electronic equipment. The method comprises the following steps: acquiring a client group of a video file and a plurality of label data of the client group; based on the multiple pieces of label data, multiple label indexes of the multiple pieces of label data are determined, and the label indexes are used for representing the influence degree of the use frequency of the video file; analyzing the plurality of label indexes to obtain analysis results of the plurality of label indexes, the analysis results being used for representing whether the label indexes are normal label indexes; in response to an analysis result that the tag index is a normal tag index, determining an account ratio of the plurality of tag data based on the account number of the client group and the account number of the plurality of tag data; and determining influence data of the video file based on the plurality of account ratio values and the plurality of tag indexes. The technical problem that the influence data of the video file cannot be effectively determined is solved.

Description

Technical Field

[0001] The present application relates to the field of video files, and in particular, to a method, device and electronic device for determining influencing data of a video file. Background Art

[0002] When watching a video file, the viewing on demand in the user's remote control operation behavior can be analyzed, and then the user's viewing habits and interests can be specifically analyzed. However, this method does not analyze the user's activity, resulting in a technical problem that the impact data of the video file cannot be effectively determined.

[0003] With respect to the above-mentioned technical problem of being unable to effectively determine the influencing data of the video files, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method, device and electronic device for determining influencing data of a video file, so as to at least solve the technical problem that the influencing data of a video file cannot be effectively determined.

[0005] According to one aspect of an embodiment of the present application, a method for determining the influencing data of a video file is provided. The method may include: obtaining a client group of a video file and a plurality of tag data of the client group, wherein the tag data is data that affects the frequency of use of the video file; based on the plurality of tag data, determining a plurality of tag indexes of the plurality of tag data, wherein the tag index is used to characterize the degree of influence of the frequency of use of the video file; analyzing the plurality of tag indexes to obtain analysis results of the plurality of tag indexes, wherein the analysis results are used to characterize whether the tag index is a normal tag index; in response to the analysis result that the tag index is a normal tag index, determining the account ratio values ​​of the plurality of tag data based on the number of accounts of the client group and the number of accounts of the plurality of tag data; determining the influencing data of the video file based on the plurality of account ratio values ​​and the plurality of tag indexes.

[0006] Optionally, based on the multiple label data, determining multiple label indexes of the multiple label data includes: based on the multiple label data, calling a label index function of the label data to obtain multiple label indexes.

[0007] Optionally, multiple label indices are analyzed to obtain analysis results of the multiple label indices, including: based on the target time, calling the density function of the label index to obtain target means and target variances of the multiple label indices; based on the target mean and target variance, determining first target values ​​and second target values ​​of the multiple label indices, wherein the first target value is less than the second target value; based on the first target value and the second target value, analyzing the multiple label indices to obtain analysis results.

[0008] Optionally, based on the first target value and the second target value, multiple label indices are analyzed to obtain analysis results, including: in response to the label index being greater than or equal to the first target value, and less than or equal to the second target value, determining the analysis result as the label index being a normal label index; in response to the label index being less than the first target value, or the label index being greater than the second target value, determining the analysis result as the label index being an abnormal label index.

[0009] Optionally, based on multiple account proportion values ​​and multiple label indexes, the impact data of the video file is determined, including: based on the first baseline value of the label index, multiple account proportion values ​​and multiple label indexes, calling the frequency function of the client group to obtain a target array matrix of the client group; screening the data in the target array matrix to obtain target data of the target array matrix; based on the target data, determining the impact data of the video file.

[0010] Optionally, based on the target data, determining the impact data of the video file includes: determining the impact data based on a target account proportion value corresponding to the target data, a target tag index corresponding to the target data, a first baseline value and a second baseline value of the account proportion value.

[0011] Optionally, the impact data is determined based on the target account proportion value corresponding to the target data, the target tag index corresponding to the target data, the first baseline value and the second baseline value of the account proportion value, including: in response to the target account proportion value being greater than the second baseline value and the target tag index being greater than the first baseline value, the impact data is obtained.

[0012] Optionally, the method further includes: verifying the influencing data to obtain a verification result, wherein the verification result is used to indicate whether the influencing data is accurate.

[0013] According to another aspect of an embodiment of the present application, a device for determining influencing data of a video file is also provided, including: a first acquisition unit, used to acquire a client group of a video file, and multiple label data of the client group, wherein the label data is data that affects the usage frequency of the video file; a first determination unit, used to determine multiple label indexes of the multiple label data based on the multiple label data, wherein the label index is used to characterize the degree of influence of the usage frequency of the video file; an analysis unit, used to analyze the multiple label indexes to obtain analysis results of the multiple label indexes, wherein the analysis results are used to characterize whether the label index is a normal label index; a second determination unit, used to determine an account ratio value of the multiple label data based on the number of accounts of the client group and the number of accounts of the multiple label data in response to the analysis result that the label index is a normal label index; a third determination unit, used to determine the influencing data of the video file based on the multiple account ratio values ​​and the multiple label indexes.

[0014] According to another aspect of an embodiment of the present application, a non-volatile storage medium is also provided, including: the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute any method for determining influencing data of a video file.

[0015] According to another aspect of an embodiment of the present application, there is also provided an electronic device, comprising: a processor; and a memory for storing processor executable instructions; wherein the processor is configured to execute instructions to implement a method for determining influence data of any video file.

[0016] In an embodiment of the present application, a client group of a video file and multiple tag data of the client group are obtained, wherein the tag data is data that affects the frequency of use of the video file; based on the multiple tag data, multiple tag indexes of the multiple tag data are determined, wherein the tag index is used to characterize the degree of influence of the frequency of use of the video file; the multiple tag indexes are analyzed to obtain analysis results of the multiple tag indexes, wherein the analysis results are used to characterize whether the tag index is a normal tag index; in response to the analysis result that the tag index is a normal tag index, based on the number of accounts of the client group and the number of accounts of the multiple tag data, the account ratio of the multiple tag data is determined; based on the multiple account ratio values ​​and the multiple tag indexes, the impact data of the video file is determined. That is, in this embodiment, the client group of the video file and the multiple tag data of the client group can be obtained first, and then based on the multiple tag data, multiple tag indexes of the multiple tag data can be determined, and then the multiple tag indexes are analyzed to obtain the analysis results of the multiple tag indexes. At this time, if the analysis result does not show that the tag index is a normal tag index, the account ratio values ​​of the multiple tag data can be determined based on the number of accounts of the client group and the number of accounts of the multiple tag data, and finally the impact data of the video file is determined based on the multiple account ratio values ​​and the multiple tag indexes obtained above. Considering that after analyzing the obtained label index and obtaining the analysis results of multiple label indexes, when the analysis result at this time is that the label index is a normal label index, the account proportion values ​​of the multiple label data can be determined according to the number of accounts of the client group and the number of accounts of the multiple label data, so that the impact data of the video file can be determined, so as to solve the technical problem that the impact data of the video file cannot be effectively determined, and achieve the technical effect of effectively determining the impact data of the video file. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1is a flow chart of a method for determining impact data of a video file according to an embodiment of the present application;

[0019] Figure 2 is a flow chart of a method for analyzing factors of low user activity in online videos according to an embodiment of the present application;

[0020] Figure 3 is a flow chart of generating an analysis report according to an embodiment of the present application;

[0021] Figure 4 is a schematic diagram of a device for determining influence data of a video file according to an embodiment of the present application;

[0022] Figure 5 It is a schematic diagram of an exemplary electronic device for implementing an embodiment of the present application according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] In order to facilitate those skilled in the art to better understand the embodiments of the present application, the technical terms or some nouns that may be involved in the present application are now explained:

[0026] The Group and Time Network Video User Activity Model (GT-NVAM) uses labels of different customer groups to perform multi-attribute label index analysis, find out the parts whose label index exceeds the warning baseline and the number of users of the feature attribute also exceeds the warning baseline, and then output the influencing factors of low network video user activity.

[0027] Customer groups: User tags are combined through "and", "or", and "not" to generate customer groups.

[0028] According to an embodiment of the present application, an embodiment of a method for determining impact data of a video file is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] Figure 1 is a flow chart of a method for determining impact data of a video file according to an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0030] Step S102, obtaining a client group of the video file and a plurality of tag data of the client group.

[0031] In the technical solution provided in the above step S102 of the present application, the client group of the video file and a plurality of tag data of the client group can be obtained, wherein the tag data is data that affects the frequency of use of the video file.

[0032] Optionally, the client group can be called a user group or a user customer group, the video file can be called a network video or simply a video, and the tag data can be called user tag data or a user feature attribute tag.

[0033] Optionally, the client group of the video file and multiple tag data of the client group are obtained through the client group analysis system, wherein the analysis system can be called a user experience analysis system. For example, the user group and multiple user tag data of the user group are obtained through the interface of the user experience analysis system.

[0034] Furthermore, user groups can be pre-classified groups, such as low-activity customer groups, high-activity customer groups, customer groups with poor service experience, and high-star user groups. Label data can be used to characterize the reasons for low activity in different customer groups. For example, user characteristic attribute labels such as basic customer information, terminal information, behavioral preferences, and user experience can be listed in categories.

[0035] For example, through the interface of the user experience analysis system, the user group of online videos can be obtained. When the user group of online videos is a low-activity customer group, the label data of the user group can be obtained, such as basic customer information, terminal information, behavioral preferences, and user experience data.

[0036] It should be noted that this is only a preferred implementation method for obtaining the client group of video files and multiple label data of the client group. The process and method for obtaining the client group of video files and multiple label data of the client group are not specifically limited. As long as the process and method for obtaining the client group of video files and multiple label data of the client group are achieved through the user's analysis system, they are within the protection scope of this application and are not listed here.

[0037] Step S104: determining a plurality of tag indexes of the plurality of tag data based on the plurality of tag data.

[0038] In the technical solution provided in the above step S104 of the present application, after obtaining a plurality of tag data, the purpose of determining a plurality of tag indexes of the plurality of tag data can be achieved, wherein the tag index is used to characterize the influence of the frequency of use of the video file.

[0039] Optionally, based on the obtained multiple tag data, a tag index algorithm is used to obtain multiple tag indexes of the multiple tag data. Among them, the tag index (TargetIndex, referred to as TIndex) can be formed by user tags such as customer basic information, terminal information, behavior preference, customer experience, etc., to form a preference for a certain tag in a certain customer group.

[0040] It can be understood that this is only a preferred implementation method for determining multiple label indexes for multiple label data, and does not specifically limit the process and method for determining multiple label indexes for multiple label data. As long as the process and method for determining multiple label indexes for multiple label data are based on multiple label data, they are within the protection scope of this application and will not be repeated here.

[0041] Step S106, analyzing the multiple tag indexes to obtain analysis results of the multiple tag indexes.

[0042] In the technical solution provided in the above step S106 of the present application, based on the multiple label indexes obtained in the above steps, the multiple label indexes can be analyzed using a relative density algorithm so as to obtain analysis results of the multiple label indexes. The analysis results are used to characterize whether the label index is a normal label index. The relative density algorithm is implemented using a statistical method.

[0043] Furthermore, when using the relative density algorithm to analyze multiple label indexes, the distribution of label indexes under each customer group can be used to select relevant data whose analysis results are label indexes that are normal label indexes.

[0044] Step S108 , in response to the analysis result that the tag index is a normal tag index, based on the number of accounts of the client group and the number of accounts of the multiple tag data, account ratio values ​​of the multiple tag data are determined.

[0045] In the technical solution provided in the above step S108 of the present application, after obtaining the analysis results of multiple tag indexes, if the analysis result at this time is that the tag index is a normal tag index, the account ratio values ​​of the multiple tag data can be determined according to the number of accounts of the client group and the number of accounts of the multiple tag data. The number of accounts of the client group can be the number of users in the client group, for example, 1000. The number of accounts of the tag data can be the number of users classified under the tag, for example, 160.

[0046] Optionally, the ratio of the number of accounts in the client group to the number of accounts in the tag data is determined as the account ratio of the tag data. For example, when the client group is a low-activity customer group, the number of users in the low-activity customer group is 1000, and the tag data is a preference tag of a movie type that likes educational programs, and the number of users who like educational programs in the movie type preference tag is 160, then the account ratio of the tag data is 160 / 1000. It can be seen that based on the low-activity customer group, the calculation method of other tag data is as shown in the above process, and no example is given here.

[0047] It should be noted that this is only a preferred implementation method for determining the account ratio values ​​of multiple label data, and does not specifically limit the process and method for determining the account ratio values ​​of multiple label data. As long as the analysis result is that the label index is a normal label index, the process and method for determining the account ratio values ​​of multiple label data based on the number of accounts of the client group and the number of accounts of multiple label data are within the scope of protection of this application and will not be repeated here.

[0048] Step S110, determining the impact data of the video file based on multiple account proportion values ​​and multiple tag indexes.

[0049] In the technical solution provided in the above step S110 of the present application, after obtaining multiple account ratio values ​​and multiple tag indexes, the influence data of the video file can be determined. The influence data can be called an influence factor that causes the client group to be less active, a low-activity factor, or a key factor.

[0050] For example, for a client group with poor service experience, based on multiple account proportions and multiple label indexes of this customer group, it can be determined that the influencing data of the online video is that the customer experience rating in the customer experience is poor customer experience, which leads to low user activity of this customer group, and the influencing data of the poor customer experience is the main influencing factor of this customer group.

[0051] In an embodiment of the present application, the client group of the video file and multiple label data of the client group can be obtained first, and then based on the multiple label data, multiple label indexes of the multiple label data can be determined, and then the multiple label indexes are analyzed to obtain analysis results of the multiple label indexes. At this time, if the analysis result shows that the label index is a normal label index, the account ratio of the multiple label data can be determined based on the number of accounts of the client group and the number of accounts of the multiple label data, and finally the impact data of the video file can be determined based on the multiple account ratios and the multiple label indexes obtained above. Considering that after analyzing the obtained label index and obtaining the analysis results of the multiple label indexes, when the analysis result at this time shows that the label index is a normal label index, the account ratio of the multiple label data can be determined based on the number of accounts of the client group and the number of accounts of the multiple label data, so that the impact data of the video file can be determined, so as to solve the technical problem that the impact data of the video file cannot be effectively determined, and achieve the technical effect that the impact data of the video file can be effectively determined.

[0052] In some embodiments of the present application, multiple label indexes of the multiple label data are determined based on the multiple label data, including: based on the multiple label data, calling a label index function of the label data to obtain multiple label indexes.

[0053] In this embodiment, after obtaining a plurality of label data, a label index function of the label data may be called to achieve the purpose of obtaining a plurality of label indexes, wherein the label index function may be a function constructed by a label index algorithm.

[0054] Optionally, the tag index algorithm is executed as follows: if the number of a certain customer group is P, the number of users with multiple tag feature attributes in the customer group is A1...Ai; the number of users watching the video in the whole province is T, and the number of users with the same tag and feature attribute in the whole province is B1...Bi, then the tag index can be expressed by the following formula:

[0055] TIndex=[card(A 1...∩Ai) / card(P)] / [card(B 1...∩Bi) / card(T)]×100.

[0056] Among them, card() is used to represent the preset data processing function. For example, the number of low-activity group users is 1000, and the number of users who like the educational program attribute in the film type preference label is 160; the number of viewing users in the province is 200,000, and the number of users who like the educational program attribute in the film type in the province is 31,000. Then the label index can be calculated by the following formula:

[0057] TIndex=(160 / 1000) / (31000 / 200000)*100=103.25%.

[0058] In some optional embodiments of the present application, multiple label indices are analyzed to obtain analysis results of the multiple label indices, including: based on the target time, calling the density function of the label index to obtain the target mean and target variance of the multiple label indices; based on the target mean and the target variance, determining the first target value and the second target value of the multiple label indices, wherein the first target value is less than the second target value; based on the first target value and the second target value, analyzing the multiple label indices to obtain analysis results.

[0059] In this embodiment, the density function of the label index can be called first according to the target time to obtain the target mean and target variance of the multiple label indexes, and then the first target value and the second target value of the multiple label indexes can be determined according to the target mean and the target variance obtained above, and finally the multiple label indexes can be analyzed according to the first target value and the second target value to achieve the purpose of obtaining the analysis results.

[0060] Optionally, the target time may be a preset period of time, such as a time interval n. The target mean may be referred to as the mean and is represented by u. The target variance may be referred to as the standard deviation and is represented by σ. The first target value may be a minimum value, which may be represented by Mi, and Mi=u-3σ. The second target value may be a maximum value, which may be represented by Ma, and Ma=u+3σ.

[0061] Optionally, the density function may be a function established by a relative density algorithm, wherein the relative density algorithm may be to find out abnormal label indexes and normal label indexes according to the distribution of label indexes under each customer group within a time range.

[0062] For example, in time interval n, the label index under the customer group is x i , the density function is called, and the density function is as follows:

[0063]

[0064] And according to the following formula:

[0065]

[0066] The mean u and standard deviation σ of the customer group time sample can be calculated, and then the function is called to traverse the customer group time sample to obtain the minimum value Mi = u-3σ and the maximum value Ma = u+3σ. According to the maximum and minimum values ​​obtained above, multiple label indexes can be analyzed to achieve the purpose of obtaining analysis results.

[0067] In some optional embodiments of the present application, multiple label indices are analyzed based on the first target value and the second target value to obtain analysis results, including: in response to the label index being greater than or equal to the first target value, and less than or equal to the second target value, determining the analysis result as the label index being a normal label index; in response to the label index being less than the first target value, or the label index being greater than the second target value, determining the analysis result as the label index being an abnormal label index.

[0068] In this embodiment, after obtaining the first target value and the second target value, if the label index is greater than or equal to the first target value, and less than or equal to the second target value, it can be determined that the analysis result at this time is that the label index is a normal label index; if the label index is less than the first target value, or the label index is greater than the second target value, it can be determined that the analysis result at this time is that the label index is an abnormal label index.

[0069] For example, after obtaining the label index, and the minimum and maximum values ​​of the label index, a data interval can be formed by the minimum and maximum values, and then it can be determined whether the label index obtained at this time falls within the interval. If it falls within the interval, it means that the label index is a normal label index. If it does not fall within the interval, it is determined that the label index is not abnormal.

[0070] In some embodiments of the present application, the impact data of a video file is determined based on multiple account proportion values ​​and multiple label indexes, including: based on a first baseline value of the label index, multiple account proportion values, and multiple label indexes, calling a frequency function of a client group to obtain a target array matrix of the client group; screening the data in the target array matrix to obtain target data of the target array matrix; and determining the impact data of the video file based on the target data.

[0071] In this embodiment, the frequency function of the client group can be first called according to the first baseline value of the label index, multiple account proportion values ​​and multiple label indexes, and the customer group and time two-dimensional analysis algorithm can be used to obtain the target array matrix of the client group, and then the data in the target array matrix can be screened to obtain the target data of the target array matrix, and finally the purpose of determining the influencing data of the video file can be achieved according to the target data obtained above. Among them, the target array matrix can be called a three-dimensional label array matrix. The frequency function can be called an online video user activity function.

[0072] Table 1 Three-dimensional array matrix table of labels of popular movies and TV shows with high customer activity in April

[0073]

[0074] Optionally, based on the target mean, target variance, first target value and second target value, a first baseline value of the tag index is determined. The first baseline value of the tag index can be called the tag index baseline value, which can be represented by β, that is, for multiple groups of customer time sample data, multiple groups of density data are collected, and the tag index baseline value β=max(Mi / avg(u), Ma / avg(u)) is calculated.

[0075] Optionally, analyze the label index of low-activity customer groups, high-activity customer groups, high-star customer groups, customer groups with poor service experience, etc. within a period of time to find out the low activity factors. According to the label index, introduce the customer group and time two-dimensional analysis algorithm to analyze the customer group and time two-dimensional label index. Time dimension t=1, 2, 3, 4, 5…(t>30), customer group latitude k1, k2, k3…, customer group corresponding label n1, n2, n3…, user number proportion p=p1, p2, p3…, corresponding label index g=g1, g2, g3….

[0076] Furthermore, the three-dimensional array matrix of labels whose absolute error exceeds the label index baseline value β is calculated by the following formula:

[0077]

[0078] Among them, Table 1 is a three-dimensional array matrix table of labels of popular movies and TV shows with high activity in April. As shown in Table 1, the user share value p and label index g for each day in April can be obtained. For example, the label index on April 1 is 106.71%, and the user share value is 12.78%.

[0079] In some optional embodiments of the present application, the impact data of the video file is determined based on the target data, including: determining the impact data based on the target account proportion value corresponding to the target data, the target tag index corresponding to the target data, the first baseline value and the second baseline value of the account proportion value.

[0080] In this embodiment, the influencing data can be determined based on the target account ratio value corresponding to the target data, the target tag index corresponding to the target data, the first baseline value and the second baseline value of the account ratio value.

[0081] Optionally, the second baseline value of the account ratio value may be referred to as the second baseline value of the user ratio value, which may be obtained by a tag index algorithm and may be represented by α, that is, α=min(A i ÷P i )∩A i ≥100.

[0082] Optionally, for the three-dimensional array matrix of labels, if the user proportion value of the same label is lower than the user proportion baseline value α of the total number of days, the label is considered to be a non-critical factor.

[0083] In some optional embodiments of the present application, the impact data is determined based on the target account proportion value corresponding to the target data, the target tag index corresponding to the target data, the first baseline value and the second baseline value of the account proportion value, including: in response to the target account proportion value being greater than the second baseline value and the target tag index being greater than the first baseline value, the impact data is obtained.

[0084] In this embodiment, after obtaining the target account ratio value corresponding to the target data, the target tag index corresponding to the target data, the first baseline value and the second baseline value of the account ratio value, if the target account ratio value is greater than the second baseline value and the target tag index is greater than the first baseline value, the influencing data can be obtained. The influencing data can also be called influencing factors.

[0085] For example, when the user proportion value of the filtered label data is greater than the baseline α, and its corresponding label index is greater than the warning baseline β, it can be determined that the label data at this time is the final influencing factor, that is, the label that meets the above conditions at the same time is the influencing factor.

[0086] For another example, Table 2 is a table of influencing factors of user groups. As shown in Table 2, the user share and label index of the influencing factors obtained by different customer groups on April 1 can be obtained. The label data for the low-activity customer group is the poor customer experience label, then the label index of the poor customer experience label is 132.71%, and the user share is 12.78%; the label data for the high-activity customer group is the hot drama lover label, then the label index of the hot drama lover label is 112.32%, and the user share is 11.56%; the label data for the poor service experience customer group is the live broadcast freeze label, then the label index of the live broadcast freeze label is 113.43%, and the user share is 64.68%; the label data for the high-star user group is the hot drama lover label, then the label index of the hot drama lover label is 111.12%, and the user share is 10.12%.

[0087] Table 2 Influencing factors of user groups

[0088]

[0089] In some optional embodiments of the present application, the method further includes: verifying the influencing data to obtain a verification result, wherein the verification result is used to characterize whether the influencing data is accurate.

[0090] In this embodiment, after the influence data of the video file is obtained, the influence data may be verified to obtain a verification result for indicating whether the influence data is accurate.

[0091] For example, 100 users were randomly selected on April 1st and 2nd for telephone follow-up verification, and the actual influencing factors were found from customer service experience, hot film updates, video freezes, etc. The actual influencing factors were compared with the impact data obtained by this solution. If they are consistent, it means that the impact data obtained is accurate; if not, it means that the impact data obtained is inaccurate.

[0092] Further, Table 3 is a comparison result table of actual influencing factors and influencing data. As shown in Table 3, for the label data: poor customer service experience, it can be obtained that the number of failed return visits is 4 times, the number of low activity factors that meet is 55, and the number of low activity factors that do not meet is 4; for the label data: hot film update is not timely, it can be obtained that the number of failed return visits is 3 times, the number of low activity factors that meet is 79, and the number of low activity factors that do not meet is 4; for the label data: video freeze, it can be obtained that the number of failed return visits is 3 times, the number of low activity factors that meet is 46, and the number of low activity factors that do not meet is 2.

[0093] Table 3 Comparison results between actual impact factors and impact data

[0094]

[0095] In an embodiment of the present application, the client group of the video file and multiple label data of the client group can be obtained first, and then based on the multiple label data, multiple label indexes of the multiple label data can be determined, and then the multiple label indexes are analyzed to obtain analysis results of the multiple label indexes. At this time, if the analysis result shows that the label index is a normal label index, the account ratio of the multiple label data can be determined based on the number of accounts of the client group and the number of accounts of the multiple label data, and finally the impact data of the video file can be determined based on the multiple account ratios and the multiple label indexes obtained above. Considering that after analyzing the obtained label index and obtaining the analysis results of the multiple label indexes, when the analysis result at this time shows that the label index is a normal label index, the account ratio of the multiple label data can be determined based on the number of accounts of the client group and the number of accounts of the multiple label data, so that the impact data of the video file can be determined, so as to solve the technical problem that the impact data of the video file cannot be effectively determined, and achieve the technical effect that the impact data of the video file can be effectively determined.

[0096] Currently, when watching video files, the viewing on demand in the user's remote control operation behavior can be analyzed, and then the user's viewing habits and interests can be specifically analyzed. However, this method does not analyze the user's activity, resulting in a technical problem that the impact data of the video file cannot be effectively determined.

[0097] In order to solve the above problems, the present application proposes a method for analyzing the factors of low user activity of online videos. The method uses the customer group time two-dimensional analysis network video user activity model GT-NVAM, can customize different time periods (such as holidays, hot event periods, etc.), and conduct combined analysis in combination with different customer groups to find out the differences in the factors of low activity among different customer groups. Based on this time-related factor, the effects of disturbances such as holidays and hot events are eliminated, and the key factors of low activity are found to solve the technical problem of being unable to effectively determine the impact data of video files, and achieve the technical effect of being able to effectively determine the impact data of video files.

[0098] In an embodiment of the present application, time and multiple customer groups can be selected, and based on the label data, a low-activity multi-label index analysis model can be constructed to output labels with greater low-activity impact and their corresponding characteristic attributes, as well as an analysis report, to improve user stickiness and product value, so as to solve the technical problem of being unable to effectively determine the impact data of video files and achieve the technical effect of being able to effectively determine the impact data of video files.

[0099] In order to facilitate those skilled in the art to better understand the technical solution of the present application, a specific embodiment is now described.

[0100] In the embodiments of the present application, Figure 2 : is a flowchart of a method for analyzing factors of low user activity in online videos according to an embodiment of the present application, the method comprising the following steps:

[0101] Step S201, obtaining user tag data and user customer groups.

[0102] In this embodiment, user tag data can be obtained, such as basic customer information, terminal information, behavior preferences, and user characteristic attribute tags such as user experience. User customer groups can be obtained, such as low-activity customer groups, high-activity customer groups, customer groups with poor service experience, and high-star user customer groups.

[0103] Step S202, obtaining the user percentage value and tag index of the tag data.

[0104] In this embodiment, based on the obtained multiple tag data, a tag index algorithm is used to obtain multiple tag indexes of the multiple tag data, and then based on the tag indexes, the user proportion value of the tag data can be determined.

[0105] Optionally, the tag index algorithm is executed as follows: if the number of a certain customer group is P, the number of users with multiple tag feature attributes in the customer group is A1...Ai; the number of users watching the video in the whole province is T, and the number of users with the same tag and feature attribute in the whole province is B1...Bi, then the tag index can be expressed by the following formula:

[0106] TIndex=[card(A 1...∩Ai) / card(P)] / [card(B 1...∩Bi) / card(T)]×100.

[0107] Among them, card() is used to represent the preset data processing function. For example, the number of low-activity group users is 1000, and the number of users who like the educational program attribute in the film type preference label is 160; the number of viewing users in the province is 200,000, and the number of users who like the educational program attribute in the film type in the province is 31,000. Then the label index can be calculated by the following formula:

[0108] TIndex=(160 / 1000) / (31000 / 200000)*100=103.25%.

[0109] Optionally, based on the above formula, a tag index can be obtained, thereby achieving the purpose of determining the user ratio value of the tag data.

[0110] Step S203, determining whether the tag index is a normal tag index.

[0111] In this embodiment, a relative density algorithm is used to analyze multiple label indexes so that it can be determined whether the label index is a normal label index. If the label index at this time is a normal label index, step S204 is executed; if the label index at this time is an abnormal label index, it is necessary to re-acquire the label index, that is, execute step S202.

[0112] Optionally, the relative density algorithm may be used to find out abnormal label indexes and normal label indexes according to the distribution of label indexes for each customer group within a time range.

[0113] For example, in time interval n, the label index under the customer group is x i , the density function is called, and the density function is as follows:

[0114]

[0115] And according to the following formula:

[0116]

[0117] The mean u and standard deviation σ of the customer group time sample can be calculated, and then the function is called to traverse the customer group time sample to obtain the minimum value Mi = u-3σ and the maximum value Ma = u+3σ. It is determined whether the label index obtained at this time falls into the interval [Mi, Ma]. If not, it is judged as an abnormal label index; if so, it is judged as a normal label index.

[0118] Optionally, multiple sets of density data are collected to calculate the baseline value of the tag index β = max(Mi / avg(u), Ma / avg(u)). For tag numbers within a reasonable range, the user share baseline value α = min(A i ÷P i )∩A i ≥100.

[0119] Step S204, determining the influencing factors of the video.

[0120] In this embodiment, after obtaining a normal label index, the influencing factors of the network video can be determined.

[0121] Optionally, analyze the label index of low-activity customer groups, high-activity customer groups, high-star customer groups, customer groups with poor service experience, etc. within a period of time to find out the low activity factors. According to the label index, introduce the customer group and time two-dimensional analysis algorithm to analyze the customer group and time two-dimensional label index. Time dimension t=1, 2, 3, 4, 5…(t>30), customer group latitude k1, k2, k3…, customer group corresponding label n1, n2, n3…, user number proportion p=p1, p2, p3…, corresponding label index g=g1, g2, g3….

[0122] Furthermore, the three-dimensional array matrix of labels whose absolute error exceeds the label index baseline value β is calculated by the following formula:

[0123]

[0124] Optionally, according to the above formula, the user proportion value and label index of a certain customer group can be obtained, as shown in Table 1, which will not be repeated here.

[0125] Optionally, for the three-dimensional array matrix of labels, if the user proportion value of the same label is lower than the user proportion baseline value α of the total number of days, the label is considered to be a non-critical factor.

[0126] Optionally, for example, when the user proportion value of the filtered label data is greater than the baseline α, and its corresponding label index is greater than the warning baseline β, it can be determined that the label data at this time is the final influencing factor, that is, the labels that meet the above conditions at the same time are influencing factors, and the influencing factors of different customer groups are shown in Table 2 and are not listed here.

[0127] Step S205, verifying the influencing factors.

[0128] In this embodiment, after the influencing factors are obtained, the influencing factors can be tested. For example, 100 users are randomly selected from April 1st to April 2nd for telephone return verification, and the actual influencing factors are found from customer service experience, hot film updates, video freezes, etc. The actual influencing factors are compared with the influencing data obtained by this solution. If they are consistent, it means that the obtained influencing data is accurate; if they are inconsistent, it means that the obtained influencing data is inaccurate. It should be noted that Table 3 is the comparison result of the actual influencing factors and the influencing data, which will not be repeated here.

[0129] In the embodiments of the present application, Figure 3 This is a flow chart of generating an analysis report according to an embodiment of the present application, and the flow mainly includes the following steps:

[0130] Step S301, data collection.

[0131] Step S302, obtaining user groups and multiple tag data.

[0132] Step S303, calculating the tag index.

[0133] Step S304, determining a two-dimensional analysis algorithm for time customer groups.

[0134] Step S305: Generate an analysis report.

[0135] In an embodiment of the present application, the group information, parameter information and process information of the task can be obtained first, and then the dispatch mode of the task can be determined based on the group information, parameter information and process information obtained above, and then the target database of the task can be used according to the dispatch mode to achieve the purpose of determining the target execution status of the task. Furthermore, the target execution status of the task can be displayed in the task management system to solve the technical problem of being unable to uniformly manage tasks and achieve the technical effect of being able to uniformly manage tasks.

[0136] Figure 4 is a schematic diagram of a device for determining impact data of a video file according to an embodiment of the present application, such as Figure 4 As shown, the apparatus 400 for determining the impact data of a video file includes: a first obtaining unit 401 , a first determining unit 402 , an analyzing unit 403 , a second determining unit 404 and a third determining unit 405 .

[0137] The first acquisition unit 401 is used to acquire a client group of a video file and a plurality of tag data of the client group, wherein the tag data is data that affects the frequency of use of the video file.

[0138] The first determining unit 402 is configured to determine a plurality of tag indexes of the plurality of tag data based on the plurality of tag data, wherein the tag index is used to characterize the influence degree of the usage frequency of the video file.

[0139] The analyzing unit 403 is used to analyze the multiple label indexes to obtain analysis results of the multiple label indexes, wherein the analysis results are used to indicate whether the label index is a normal label index.

[0140] The second determining unit 404 is configured to determine account ratio values ​​of the plurality of tag data based on the number of accounts of the client group and the number of accounts of the plurality of tag data in response to the analysis result that the tag index is a normal tag index.

[0141] The third determination unit 405 is used to determine the impact data of the video file based on multiple account proportion values ​​and multiple tag indexes.

[0142] Optionally, the first determining unit 402 may include: a first obtaining module, configured to call a label index function of the label data based on the plurality of label data to obtain a plurality of label indexes.

[0143] Optionally, the analysis unit 403 may include: a calling module, used to call the density function of the label index based on the target time to obtain the target mean and target variance of multiple label indexes; a first determination module, used to determine the first target value and the second target value of multiple label indexes based on the target mean and the target variance, wherein the first target value is less than the second target value; and an analysis module, used to analyze multiple label indexes based on the first target value and the second target value to obtain an analysis result.

[0144] Optionally, the analysis module may include: a first determination submodule, used to determine that the analysis result is that the label index is a normal label index in response to the label index being greater than or equal to a first target value and less than or equal to a second target value; a second determination submodule, used to determine that the analysis result is that the label index is an abnormal label index in response to the label index being less than the first target value, or the label index being greater than the second target value.

[0145] Optionally, the third determination unit 405 may include: a second acquisition module, used to call the frequency function of the client group based on the first baseline value of the label index, multiple account proportion values ​​and multiple label indices to obtain a target array matrix of the client group; a third acquisition module, used to filter the data in the target array matrix to obtain target data of the target array matrix; a second determination module, used to determine the impact data of the video file based on the target data.

[0146] Optionally, the second determination module may include: a third determination submodule, used to determine the impact data based on the target account proportion value corresponding to the target data, the target tag index corresponding to the target data, the first baseline value and the second baseline value of the account proportion value.

[0147] Optionally, the third determination submodule is further used to obtain influence data in response to the target account ratio value being greater than the second baseline value and the target tag index being greater than the first baseline value.

[0148] Optionally, the device further includes: a verification unit, configured to verify the influencing data to obtain a verification result, wherein the verification result is used to indicate whether the influencing data is accurate.

[0149] In the device, a client group of a video file and a plurality of tag data of the client group are acquired through a first acquisition unit 401, wherein the tag data is data that affects the frequency of use of the video file; a plurality of tag indexes of the plurality of tag data are determined based on the plurality of tag data through a first determination unit 402, wherein the tag index is used to characterize the degree of influence of the frequency of use of the video file; the plurality of tag indexes are analyzed through an analysis unit 403 to obtain analysis results of the plurality of tag indexes, wherein the analysis results are used to characterize whether the tag index is a normal tag index; in response to the analysis result that the tag index is a normal tag index, an account ratio value of the plurality of tag data is determined based on the number of accounts of the client group and the number of accounts of the plurality of tag data through a second determination unit 404; and the influencing data of the video file is determined based on the plurality of account ratio values ​​and the plurality of tag indexes through a third determination unit 405, so as to solve the technical problem that the influencing data of the video file cannot be effectively determined, and achieve the technical effect that the influencing data of the video file can be effectively determined.

[0150] According to another aspect of an embodiment of the present application, a non-volatile storage medium is further provided, the non-volatile storage medium including a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute any method for determining influencing data of a video file.

[0151] Specifically, the above storage medium is used to store program instructions for the following functions to implement the following functions:

[0152] Obtain a client group of a video file and multiple tag data of the client group, wherein the tag data is data that affects the usage frequency of the video file; determine multiple tag indexes of the multiple tag data based on the multiple tag data, wherein the tag index is used to characterize the degree of influence of the usage frequency of the video file; analyze the multiple tag indexes to obtain analysis results of the multiple tag indexes, wherein the analysis results are used to characterize whether the tag index is a normal tag index; in response to the analysis result that the tag index is a normal tag index, determine account ratio values ​​of the multiple tag data based on the number of accounts of the client group and the number of accounts of the multiple tag data; determine the influencing data of the video file based on the multiple account ratio values ​​and the multiple tag indexes.

[0153] Optionally, in this embodiment, the above-mentioned storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above-mentioned contents. More specific examples of the above-mentioned storage medium may include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above-mentioned contents.

[0154] In an exemplary embodiment of the present application, a computer program product is further provided, including a computer program, and when the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for determining influence data of a video file.

[0155] Optionally, the computer program may implement the following steps when executed by a processor:

[0156] Obtain a client group of a video file and multiple tag data of the client group, wherein the tag data is data that affects the usage frequency of the video file; determine multiple tag indexes of the multiple tag data based on the multiple tag data, wherein the tag index is used to characterize the degree of influence of the usage frequency of the video file; analyze the multiple tag indexes to obtain analysis results of the multiple tag indexes, wherein the analysis results are used to characterize whether the tag index is a normal tag index; in response to the analysis result that the tag index is a normal tag index, determine account ratio values ​​of the multiple tag data based on the number of accounts of the client group and the number of accounts of the multiple tag data; determine the influencing data of the video file based on the multiple account ratio values ​​and the multiple tag indexes.

[0157] According to an embodiment of the present application, an electronic device is provided, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any of the above-mentioned methods for determining the impact data of a video file.

[0158] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0159] Figure 5It is a schematic diagram of an example electronic device for implementing an embodiment of the present application according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0160] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0161] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0162] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as a method for processing call chain data. For example, in some embodiments, the method for processing call chain data may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the method for processing call chain data described above may be executed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the method for processing call chain data in any other appropriate manner (eg, by means of firmware).

[0163] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0164] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0165] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0166] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0167] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0168] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0169] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0170] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0171] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0172] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0173] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0174] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0175] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining impact data of a video file, characterized in that: include: Acquire a client group of a video file and a plurality of tag data of the client group, wherein the tag data is data that affects the usage frequency of the video file; Based on the plurality of tag data, determining a plurality of tag indexes of the plurality of tag data, wherein the tag index is used to characterize the influence degree of the usage frequency of the video file; Analyze the plurality of label indexes to obtain analysis results of the plurality of label indexes, wherein the analysis results are used to indicate whether the label index is a normal label index; In response to the analysis result that the tag index is the normal tag index, based on the number of accounts of the client group and the number of accounts of the multiple tag data, determining account ratio values ​​of the multiple tag data; Based on the multiple account proportion values ​​and the multiple tag indexes, influence data of the video file is determined.

2. The method according to claim 1, characterized in that: Determining a plurality of tag indexes of the plurality of tag data based on the plurality of tag data includes: Based on the plurality of label data, a label index function of the label data is called to obtain a plurality of label indexes.

3. The method according to claim 1, characterized in that Analyzing the plurality of tag indices to obtain analysis results of the plurality of tag indices includes: Based on the target time, calling the density function of the label index to obtain a target mean and a target variance of a plurality of the label indexes; Determining a first target value and a second target value of a plurality of the tag indexes based on the target mean and the target variance, wherein the first target value is less than the second target value; Based on the first target value and the second target value, a plurality of the tag indexes are analyzed to obtain the analysis result.

4. The method according to claim 3, characterized in that Based on the first target value and the second target value, a plurality of the tag indexes are analyzed to obtain the analysis result, including: In response to the label index being greater than or equal to the first target value and less than or equal to the second target value, determining that the analysis result is that the label index is the normal label index; In response to the label index being less than the first target value, or the label index being greater than the second target value, the analysis result is determined as the label index being an abnormal label index.

5. The method according to claim 1, characterized in that Determining the influence data of the video file based on the plurality of account proportion values ​​and the plurality of tag indexes includes: Based on the first baseline value of the tag index, the plurality of account proportion values ​​and the plurality of tag indices, calling the frequency function of the client group to obtain a target array matrix of the client group; Screening the data in the target array matrix to obtain target data of the target array matrix; Based on the target data, influence data of the video file is determined.

6. The method according to claim 5, characterized in that Determining, based on the target data, impact data of the video file, including: The impact data is determined based on the target account ratio value corresponding to the target data, the target tag index corresponding to the target data, the first baseline value and the second baseline value of the account ratio value.

7. The method according to claim 6, characterized in that Determining the impact data based on a target account ratio value corresponding to the target data, a target tag index corresponding to the target data, the first baseline value, and a second baseline value of the account ratio value includes: In response to the target account ratio being greater than the second baseline value, and the target tag index being greater than the first baseline value, the impact data is obtained.

8. The method according to claim 1, characterized in that The method further comprises: The influencing data is verified to obtain a verification result, wherein the verification result is used to indicate whether the influencing data is accurate.

9. A device for determining influence data of a video file, characterized in that: include: A first acquisition unit is used to acquire a client group of a video file and a plurality of tag data of the client group, wherein the tag data is data that affects the usage frequency of the video file; A first determining unit is used to determine a plurality of label indexes of the plurality of label data based on the plurality of label data, wherein the label index is used to characterize the influence degree of the use frequency of the video file; An analysis unit, used for analyzing the plurality of label indexes to obtain analysis results of the plurality of label indexes, wherein the analysis results are used to indicate whether the label index is a normal label index; A second determining unit is configured to determine, in response to the analysis result that the tag index is the normal tag index, account ratio values ​​of the plurality of tag data based on the number of accounts of the client group and the number of accounts of the plurality of tag data; The third determination unit is used to determine the impact data of the video file based on the multiple account proportion values ​​and the multiple tag indexes.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for determining influence data of a video file as described in any one of claims 1 to 8.

Images