Playing stealing user determination method and device, equipment and storage medium

Abstract

The invention relates to a broadcast stealing user determination method and apparatus, a device and a storage medium. The method comprises the steps of obtaining feature data of each user ID and at least one target feature item group; for each target feature item group, determining a user ID set corresponding to the target feature item group according to the feature data of each user ID and the target feature item group; according to a preset broadcast stealing user blacklist and each user ID set, determining the number of broadcast stealing user IDs in each user ID set; and when the number is greater than a preset numerical value, determining all the user IDs in the corresponding user ID set as the broadcast stealing user IDs. According to the method, the problem that the IDs of the broadcast-stealing users cannot be accurately identified due to the fact that the broadcast-stealing users frequently replace the IDs can be avoided, and the accuracy of identifying the IDs of the broadcast-stealing users is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for determining a pirate broadcasting user. Background Art

[0002] With the development of technology, the problem of video piracy has long plagued long video companies. In order to solve the problem of video piracy, technical personnel often use video watermark technology and interface honeypot technology to provide obvious evidence of piracy after identifying the pirated users, so as to facilitate subsequent legal rights protection.

[0003] In the related art, technicians analyze the characteristic data of each user ID over a period of time to establish a blacklist of pirated users, and then identify the pirated user IDs through the blacklist.

[0004] However, since the pirate broadcasting user may change his ID every once in a while, the pirate broadcasting user blacklist established based on the above method cannot identify all pirate broadcasting user IDs, and the accuracy of identifying pirate broadcasting user IDs is low. Therefore, a pirate broadcasting user identification method is urgently needed. Summary of the invention

[0005] The present application provides a method, device, equipment and storage medium for determining a pirated broadcast user. The method can avoid the problem that the pirated broadcast user ID cannot be accurately identified due to frequent changes of the pirated broadcast user ID, thereby improving the accuracy of identifying the pirated broadcast user ID.

[0006] In a first aspect, the present application provides a method for determining a pirate broadcasting user, the method comprising:

[0007] Obtain feature data of each user ID and at least one target feature item group;

[0008] For each target feature item group, determining a user ID set corresponding to the target feature item group according to feature data of each user ID and the target feature item group;

[0009] According to a preset pirate broadcast user blacklist and each user ID set, determining the number of pirate broadcast user IDs in each user ID set;

[0010] When the number is greater than a preset value, all user IDs in the corresponding user ID set are determined as pirated user IDs.

[0011] Optionally, the step of determining the at least one target feature item group includes:

[0012] Obtain historical feature data of pirated user IDs;

[0013] According to the historical feature data and the trained feature item combination model, a plurality of first feature item groups and a support and a confidence corresponding to each first feature item group are obtained;

[0014] Among the multiple first feature item groups, determining the feature item group whose support is greater than the minimum support and whose confidence is greater than the minimum confidence as the second feature item group;

[0015] The target feature item group is determined according to the second feature item group.

[0016] Optionally, when there are multiple second feature item groups, determining the target feature item group according to the second feature item group includes:

[0017] For each second feature item group, detecting overlapping feature items between the second feature item group and other second feature item groups, and when the overlapping feature items are all feature items of the second feature item group, deleting other second feature item groups containing the overlapping feature items;

[0018] The remaining second feature item group is determined as the target feature item group.

[0019] Optionally, determining the target feature item group according to the second feature item group includes:

[0020] Determine the dimension to which each feature item in the second feature item group belongs;

[0021] Counting a first number of feature items in the second feature item group, and a second number of feature items belonging to a strong dimension in the second feature item group;

[0022] When the first number is greater than a second value and the second number is greater than a third value, the second feature item group is determined as a target feature item group.

[0023] Optionally, determining the target feature item group according to the second feature item group includes:

[0024] Get a preset mutually exclusive feature item group;

[0025] According to a preset mutually exclusive feature item group, detecting whether the mutually exclusive feature item group exists in the second feature item group;

[0026] A second feature item group that does not include the mutually exclusive feature item group is determined as the target feature item group.

[0027] Optionally, determining the user ID set corresponding to the target feature item group according to the feature data of each user ID and the target feature item group includes:

[0028] Determining a target feature item in the target feature item group;

[0029] Compare the feature data of each user ID with the target feature item to obtain the user ID whose feature data includes the target feature item;

[0030] Based on the feature data including the user ID of the target feature item, a user ID set corresponding to the target feature item group is obtained.

[0031] Optionally, the determining the number of pirated broadcast user IDs in each user ID set according to a preset pirated broadcast user blacklist and each user ID set includes:

[0032] Obtain a reference pirated broadcast user ID according to the ID in the preset pirated broadcast user blacklist;

[0033] For each user ID set, comparing the reference pirated broadcast user ID with each user ID in the user ID set to determine the pirated broadcast user ID in the user ID set;

[0034] According to the pirated broadcast user IDs in each user ID set, the number of the pirated broadcast user IDs in each user ID set is determined.

[0035] In a second aspect, the present application provides a device for determining a pirate broadcasting user, the device comprising:

[0036] An acquisition unit, used to acquire feature data of each user ID and at least one target feature item group;

[0037] A first determining unit is used to determine, for each target feature item group, a user ID set corresponding to the target feature item group according to feature data of each user ID and the target feature item group;

[0038] A second determining unit is used to determine the number of pirated broadcast user IDs in each user ID set according to a preset pirated broadcast user blacklist and each user ID set;

[0039] The third determining unit is used to determine all user IDs in the corresponding user ID set as pirated user IDs when the number is greater than a preset value.

[0040] Optionally, the device further includes a fourth determining unit, wherein the fourth determining unit is configured to:

[0041] Obtain historical feature data of pirated user IDs;

[0042] According to the historical feature data and the trained feature item combination model, a plurality of first feature item groups and a support and a confidence corresponding to each first feature item group are obtained;

[0043] Among the multiple first feature item groups, determining the feature item group whose support is greater than the minimum support and whose confidence is greater than the minimum confidence as the second feature item group;

[0044] The target feature item group is determined according to the second feature item group.

[0045] Optionally, the fourth determining unit is configured to:

[0046] For each second feature item group, detecting overlapping feature items between the second feature item group and other second feature item groups, and when the overlapping feature items are all feature items of the second feature item group, deleting other second feature item groups containing the overlapping feature items;

[0047] The remaining second feature item group is determined as the target feature item group.

[0048] Optionally, the fourth determining unit is configured to:

[0049] Determine the dimension to which each feature item in the second feature item group belongs;

[0050] Counting a first number of feature items in the second feature item group, and a second number of feature items belonging to a strong dimension in the second feature item group;

[0051] When the first number is greater than a second value and the second number is greater than a third value, the second feature item group is determined as a target feature item group.

[0052] Optionally, the fourth determining unit is configured to:

[0053] Get a preset mutually exclusive feature item group;

[0054] According to a preset mutually exclusive feature item group, detecting whether the mutually exclusive feature item group exists in the second feature item group;

[0055] A second feature item group that does not include the mutually exclusive feature item group is determined as the target feature item group.

[0056] Optionally, the first determining unit is used to

[0057] Determining a target feature item in the target feature item group;

[0058] Compare the feature data of each user ID with the target feature item to obtain the user ID whose feature data includes the target feature item;

[0059] Based on the feature data including the user ID of the target feature item, a user ID set corresponding to the target feature item group is obtained.

[0060] Optionally, the second determining unit is used to

[0061] Obtain a reference pirated broadcast user ID according to the ID in the preset pirated broadcast user blacklist;

[0062] For each user ID set, comparing the reference pirated broadcast user ID with each user ID in the user ID set to determine the pirated broadcast user ID in the user ID set;

[0063] According to the pirated broadcast user IDs in each user ID set, the number of the pirated broadcast user IDs in each user ID set is determined.

[0064] In a third aspect, the present application provides a pirate broadcast user determination device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; at least one memory connected to the at least one bus, wherein the processor is configured to:

[0065] Obtain feature data of each user ID and at least one target feature item group;

[0066] For each target feature item group, determining a user ID set corresponding to the target feature item group according to feature data of each user ID and the target feature item group;

[0067] According to a preset pirate broadcast user blacklist and each user ID set, determining the number of pirate broadcast user IDs in each user ID set;

[0068] When the number is greater than a preset value, all user IDs in the corresponding user ID set are determined as pirated user IDs.

[0069] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the above-mentioned method for determining pirated users is implemented.

[0070] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: In the embodiment of the present application, the feature data and at least one target feature item group of each user ID are first obtained. For each target feature item group, the user ID set corresponding to the target feature item group is determined according to the feature data and the target feature item group of each user ID. According to the preset pirated user blacklist and each user ID set, the number of pirated user IDs in each user ID set is determined; when the number is greater than the preset value, all user IDs in the corresponding user ID set are determined as pirated user IDs. Since pirated users use some technical means to achieve batch operations when pirated videos, the data used by pirated users will be the same or similar, which will lead to the aggregation of pirated user IDs on certain feature items. Since pirated user IDs are aggregated on certain feature items, the present application aggregates user IDs with the same feature items and determines whether the aggregated user ID is an aggregated pirated user ID by the number of pirated user IDs in the aggregated user IDs, which avoids the problem that pirated users frequently change their IDs and cannot fully identify pirated user IDs, and improves the accuracy of identifying pirated user IDs. 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] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0073] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0074] Figure 1 A flowchart of a method for determining a pirated broadcast user provided in an embodiment of the present application;

[0075] Figure 2 A flowchart of a method for determining a target feature item group provided in an embodiment of the present application;

[0076] Figure 3 A flowchart of a feature item group filtering method provided in an embodiment of the present application;

[0077] Figure 4A flowchart of another feature item group filtering method provided in an embodiment of the present application;

[0078] Figure 5 A flowchart of another feature item group filtering method provided in an embodiment of the present application;

[0079] Figure 6 A flowchart of a method for determining a user ID set provided in an embodiment of the present application;

[0080] Figure 7 A flowchart of a method for determining the number of pirated broadcasting users provided in an embodiment of the present application;

[0081] Figure 8 A schematic diagram of a process flow of a device for determining a pirated broadcast user provided in an embodiment of the present application;

[0082] Fig. 9 A schematic diagram of a pirate broadcast user identification device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0083] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, 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 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 making creative work are within the scope of protection of this application.

[0084] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0085] With the development of science and technology, the problem of video piracy has long plagued long video companies. In order to solve the problem of video piracy, technicians often use video watermarking technology and interface honeypot technology to provide obvious evidence of piracy after identifying the piracy users, so as to facilitate subsequent legal protection. In related technologies, technicians analyze the characteristic data of each user ID over a period of time to establish a blacklist of piracy users, and then use the blacklist to identify the piracy user ID. However, since the piracy user may change his ID every once in a while, the piracy user blacklist established based on the above method cannot identify all piracy user IDs, and the accuracy of identifying piracy user IDs is low.

[0086] In an embodiment of the present application, feature data and at least one target feature item group of each user ID are first obtained. For each target feature item group, the user ID set corresponding to the target feature item group is determined according to the feature data of each user ID and the target feature item group. According to the preset pirated user blacklist and each user ID set, the number of pirated user IDs in each user ID set is determined; when the number is greater than the preset value, all user IDs in the corresponding user ID set are determined as pirated user IDs. Since pirated users use some technical means to implement batch operations when pirated videos, the data used by pirated users will be the same or similar, which will lead to the aggregation of pirated user IDs on certain feature items. Since pirated user IDs are aggregated on certain feature items, the present application aggregates user IDs with the same feature items and determines whether the aggregated user ID is an aggregated pirated user ID by the number of pirated user IDs in the aggregated user IDs. This avoids the problem that pirated users frequently change their IDs and cannot fully identify pirated user IDs, and improves the accuracy of identifying pirated user IDs.

[0087] In summary, the embodiment of the present application provides a method for identifying a pirate broadcasting user, which can avoid the problem that the pirate broadcasting user frequently changes his ID and thus cannot accurately identify the pirate broadcasting user ID, thereby improving the accuracy of identifying the pirate broadcasting user ID. Figure 1 As shown, the specific steps include:

[0088] Step 101: Acquire feature data of each user ID and at least one target feature item group.

[0089] Wherein, a feature has at least one value, and a value of the feature is used as a feature item. For example, an IP address has many values, such as the IP address 106.23.64.22. In this step, the IP address 106.23.64.22 can be used as a feature item. The feature data includes multiple feature items. The target feature item group includes at least the target feature item.

[0090] In this step, at least one target feature item group is pre-stored in the server. The server can detect all user IDs (Identity Document, ID card identification number) at intervals to determine the pirated users among these user IDs. When the server needs to detect all user IDs, feature data of all user IDs and at least one target feature item group pre-stored can be obtained.

[0091] It should be noted that among all user IDs, some IDs have been determined to be normal IDs. Therefore, in order to reduce the amount of subsequent calculations, the IDs of all user IDs that have been determined to be normal can be removed, and then the remaining user IDs can be tested. For example, a whitelist is set in the server, and the IDs in the whitelist are all IDs of normal users. The server can first remove the IDs of normal users from all user IDs according to the whitelist, and then test the remaining user IDs.

[0092] Step 102: for each target feature item group, determine the user ID set corresponding to the target feature item group according to the feature data of each user ID and the target feature item group.

[0093] In this step, for each target feature item group, the server searches the feature data of each user ID according to all the target feature items in the target feature item group. When all the target feature items are found in the feature data of a certain user ID, the user ID is used as the user ID corresponding to the target feature item group, and all the user IDs corresponding to the target feature item group constitute the user ID set corresponding to the target feature item group.

[0094] Step 103: Determine the number of pirated broadcast user IDs in each user ID set according to the preset pirated broadcast user blacklist and each user ID set.

[0095] The pirated broadcast user blacklist includes at least one pirated broadcast user ID, where the pirated broadcast user ID is an ID of a confirmed pirated broadcast user, for example, the pirated broadcast user ID is a user ID that has hit a watermark and a honeypot.

[0096] In this step, for each user ID set, the pirated user IDs in the pirated user blacklist are compared with the user IDs in the user ID set to determine whether there are pirated user IDs in the user ID set, and then determine the number of pirated user IDs in the user ID set.

[0097] Step 104: When the number is greater than a preset value, all user IDs in the corresponding user ID set are determined to be pirated user IDs.

[0098] The preset value may be set by a technician based on experience, or may be determined based on the number of IDs in the user ID set corresponding to the number. For example, 50% of the number of IDs in the user ID set may be determined as the preset value.

[0099] In this step, for each user ID set, the server can obtain a preset value in advance. If the preset value is determined based on the number of IDs in the user ID set corresponding to the number, the server also needs to determine the number of IDs in the user ID set, and then determine the preset value based on the number of IDs. When the preset value corresponding to a user ID set is determined, the number of pirated user IDs is compared with the preset value. When the number is greater than the preset value, all user IDs in the user ID set are determined to be pirated user IDs.

[0100] In an embodiment of the present application, feature data and at least one target feature item group of each user ID are first obtained. For each target feature item group, the user ID set corresponding to the target feature item group is determined according to the feature data of each user ID and the target feature item group. According to the preset pirated user blacklist and each user ID set, the number of pirated user IDs in each user ID set is determined; when the number is greater than the preset value, all user IDs in the corresponding user ID set are determined as pirated user IDs. Since pirated users use some technical means to implement batch operations when pirated videos, the data used by pirated users will be the same or similar, which will lead to the aggregation of pirated user IDs on certain feature items. Since pirated user IDs are aggregated on certain feature items, the present application aggregates user IDs with the same feature items and determines whether the aggregated user ID is an aggregated pirated user ID by the number of pirated user IDs in the aggregated user IDs. This avoids the problem that pirated users frequently change their IDs and cannot fully identify pirated user IDs, and improves the accuracy of identifying pirated user IDs.

[0101] In the embodiment of the present application, at least one target feature item group is predetermined by the server. Therefore, the embodiment of the present application provides a method for determining a target feature item group. Figure 2 As shown, including:

[0102] Step 201, obtaining historical feature data of the pirated user ID.

[0103] In this step, the historical characteristic data of the pirated broadcast user ID may be characteristic data of all user IDs at a certain time point, or may be characteristic data of all pirated broadcast user IDs in a certain time period.

[0104] Step 202: Obtain multiple first feature item groups and the support and confidence corresponding to each first feature item group based on the historical feature data and the trained feature item combination model.

[0105] Among them, the support is the frequency of a feature item group appearing in the historical feature data of each pirated user ID. For a feature item group, the support is the ratio of the number of historical feature data containing all feature items of the feature item group to the total number of historical feature data. The higher the support corresponding to a feature item group, the more frequently the feature item group appears. The confidence is the credibility of the feature item group, that is, the probability of feature item B appearing when feature item A appears.

[0106] The feature combination item model involved in this step is a machine learning model, specifically an FPGROWTH model, whose input is a series of feature items, and whose output is multiple feature item groups and the support and confidence corresponding to each feature item group. The training steps of this model are: obtain a sample set, which includes multiple samples, each sample is a feature item set, a benchmark feature item group, and the support and confidence corresponding to each benchmark feature item group. The benchmark feature item group and the support and confidence corresponding to the benchmark feature item group are determined by technicians in the corresponding feature item set based on experience. Based on each sample in the sample set, the feature item combination model is trained to obtain a trained feature item combination model. Its training method is similar to the training method in the prior art, which will not be repeated here.

[0107] The feature item set used in the above process is determined based on the feature data of all users at a certain point in time, or it can be determined based on the feature data of all users in a certain time period. However, whether it is the feature data of normal users or the feature data of pirated users, there may be a situation where the value of a certain feature is missing. In order to enable the feature combination item model to aggregate the feature data of pirated users, the value of a missing feature can be set to a fixed value, such as 1. In order not to aggregate the feature data of normal users, the value of a missing feature can be set to a random non-repeating value.

[0108] In this step, for each pirated user ID, the server obtains at least one feature item from the historical feature data of the pirated user ID, inputs these feature items into the trained feature item combination model, and outputs multiple first feature item groups and the support and confidence corresponding to each first feature item group.

[0109] Step 203: among the multiple first feature item groups, determine the feature item group whose support is greater than the minimum support and whose confidence is greater than the minimum confidence as the second feature item group.

[0110] The minimum support and the minimum confidence can be set by technicians based on experience.

[0111] In this step, since only feature item groups that appear sufficiently many times in the feature data of pirated users and are sufficiently credible can accurately cluster pirated users, it is necessary to screen the first feature item groups based on support and confidence to screen out feature item groups that appear sufficiently many times in the feature data of pirated users and are sufficiently credible. In this step, when the support of a feature item group is greater than the minimum support, it is determined that the feature item group appears sufficiently many times in the feature data of pirated users, and when the confidence of a feature item group is greater than the minimum confidence, it is determined that the feature item group is sufficiently credible. Therefore, this step only requires screening out feature item groups whose support is greater than the minimum support and whose confidence is greater than the minimum confidence from multiple first feature item groups, and determining the screened out first feature item groups as the second feature item groups.

[0112] Step 204: determine a target feature item group according to the second feature item group.

[0113] In this step, the server can directly determine the second feature item group as the target feature item group, or filter the second feature item group to filter out irregular or unnecessary combinations, improve the quality of the feature item group, and reduce the amount of calculation in subsequent steps.

[0114] In the second feature item group determined in the above embodiment, there may be some feature item groups with overlapping feature items. For such feature item groups, it is necessary to detect whether the overlapping part is a separate feature item group. If so, the feature item group including the overlapping part but not equal to the overlapping part can be deleted. Therefore, the embodiment of the present application provides a method for filtering feature item groups. The method is as follows: Figure 3 As shown, the specific steps include:

[0115] Step 301: for each second feature item group, detect overlapping feature items between the second feature item group and other second feature item groups.

[0116] In this step, for each second feature item group, the server compares each feature item in the second feature item group with each feature item in any other second feature item group, and when there are feature items that match the comparison, the feature items that match the comparison are determined as overlapping feature items between the second feature item group and the other second feature item groups, and step 302 is executed. When there are no feature items that match the comparison, it means that there are no overlapping feature items between the second feature item group and the other second feature item groups, and the second feature item group continues to be compared with the remaining other second feature item groups until the second feature item group is compared with all other second feature item groups.

[0117] Step 302: When the overlapping feature items are all the feature items of the second feature item group, other second feature item groups containing the overlapping feature items are deleted.

[0118] In this step, when the overlapping features are all feature items of the second feature item group, it means that the second feature item group substantially covers other second feature item groups including the overlapping feature items. Therefore, the other second feature item groups including the overlapping feature items can be deleted.

[0119] For example, feature item group A is IP address 106.23.64.22 + used the same mobile phone model iPhone 12 + registration time is 14:00 on September 1, 2023. Feature item group B is IP address 106.23.64.22 + used the same mobile phone model iPhone 12 + registration time is 14:00 on September 1, 2023 + accounts are bound to overseas mobile phone numbers. It can be seen that feature item group A actually covers feature item group B, so feature item group B can be deleted.

[0120] Step 303: determine the remaining second feature item group as the target feature item group.

[0121] In this step, after deleting a portion of the second feature item groups, the server may determine the remaining second feature item groups as target feature item groups.

[0122] In the embodiment of the present application, some feature items appear more frequently in the feature data of pirated users, while some feature items do not. Therefore, according to this characteristic, the embodiment of the present application divides the feature items into two dimensions, namely, a strong dimension and a weak dimension, and divides the feature items that appear more frequently in the feature data of pirated users into the strong dimension, and divides the other feature items into the weak dimension. On the basis of the above, the second feature item group can be filtered based on the feature items of the strong dimension to obtain the target feature item group. Therefore, the embodiment of the present application provides another feature item group filtering method, such as Figure 4 As shown, the specific steps include:

[0123] Step 401: determine the dimension to which each feature item in the second feature item group belongs.

[0124] In this step, the server stores the correspondence between each feature item and its corresponding dimension, so that the dimension to which each feature item in the second feature item group belongs can be determined based on the correspondence and each feature item in the second feature item group.

[0125] Step 402: Count a first number of feature items in the second feature item group and a second number of feature items belonging to a strong dimension in the second feature item group.

[0126] In this step, the server may count the number of feature items in the second feature item group and determine it as the first number, and count the number of feature items belonging to the strong dimension in the second feature item group and determine it as the second number.

[0127] Step 403: when the first number is greater than the second value and the second number is greater than the third value, the second feature item group is determined as the target feature item group.

[0128] The second value and the third value are set by technicians based on experience. Specifically, the second value is set to 3, and the third value is set to 1.

[0129] In this step, for a feature item group, if there is no feature item belonging to a strong dimension in the feature item group, it means that the feature item group rarely or even never appears in the feature data of the pirated broadcasting user, and even if such a feature item group is used, the pirated broadcasting user cannot be identified, so such a feature item group needs to be filtered out. Therefore, the server can detect whether the first number is greater than the second value and whether the second number is greater than the third value. When it is detected that the first number is greater than the second value and the second number is greater than the third value, the second feature item group is determined as the target feature item group.

[0130] In the embodiment of the present application, some feature items are mutually exclusive and cannot be in the same group. Therefore, the feature item group including mutually exclusive feature items is wrong and needs to be deleted. Therefore, the embodiment of the present application provides another method for filtering feature item groups. Figure 5 As shown, the specific steps include:

[0131] Step 501: Obtain a preset mutually exclusive feature item group.

[0132] The mutually exclusive feature item group includes multiple feature items, and these feature items cannot exist in the same feature item group at the same time. For example, the feature item IMEI (International Mobile Equipment Identity) of an Android device and the feature item Mac address cannot exist in the same feature item group at the same time, so these two feature items can be combined into a mutually exclusive feature item group.

[0133] In this step, the technician can set mutually exclusive feature items based on experience and store them in the server. When the server needs to filter based on the mutually exclusive feature items, the server can obtain the preset mutually exclusive feature items.

[0134] Step 502: According to the preset mutually exclusive feature item groups, it is detected whether there is a mutually exclusive feature item group in the second feature item group.

[0135] In this step, for each second feature item group, the server may compare the mutually exclusive feature item group with the second feature item group to determine whether there is a mutually exclusive feature item group in the second feature item group.

[0136] Step 503: determine the second feature item group that does not have a mutually exclusive feature item group as the target feature item group.

[0137] In this step, when it is detected that there is a mutually exclusive feature item group in the second feature item group, the second feature item group is deleted, and the remaining second feature item group is determined as the target feature item group.

[0138] In an embodiment of the present application, for each second feature item group, the number of feature items included in the second feature item group can also be determined, and it can be detected whether the number is greater than a preset number. When it is detected that the number is less than the preset value, it is deleted; when it is detected that the number is greater than or equal to the preset value, it is determined as the target feature item group.

[0139] It should be noted that in the implementation Figure 2 After the method is described, the server can sequentially execute the method described in the embodiment of the present application, Figure 3 The method, Figure 4 The method and Figure 5 The execution order of the method is not limited. Of course, only one or more of the above methods can be executed, and this application does not limit this.

[0140] The present application embodiment also provides a method for determining a user ID set, which is a further limitation of step 102. Specifically, Figure 6 As shown, including:

[0141] Step 601: determine the target feature items included in the target feature item group.

[0142] In this step, after obtaining the target feature item, the server determines all target feature items included in the target feature item group.

[0143] Step 602: Compare the feature data of each user ID with the target feature item to obtain the user ID whose feature data includes the target feature item.

[0144] In this step, for each user ID, the server obtains feature data of the user ID, obtains feature items in the feature data, and compares them with target feature items to obtain a user ID whose feature data includes all target feature items.

[0145] Step 603: Based on the feature data including the user ID of the target feature item, a user ID set corresponding to the target feature item group is obtained.

[0146] In this step, the server composes a user ID set corresponding to the target feature item group based on the feature data including the user IDs of all target feature items.

[0147] The embodiment of the present application also provides a method for determining the number of pirated broadcasting users, which is a further limitation of step 103. Specifically, Figure 7 As shown, including:

[0148] Step 701, obtaining a reference pirated broadcast user ID according to an ID in a preset pirated broadcast user blacklist.

[0149] In this step, after obtaining the pirated broadcast user blacklist, the server may determine the ID in the pirated broadcast user blacklist as the reference pirated broadcast user ID.

[0150] Step 702: For each user ID set, compare the reference pirated user ID with each user ID in the user ID set to determine the pirated user ID in the user ID set.

[0151] In this step, for each user ID set, all user IDs in the user ID set are compared with the reference pirated user IDs to determine the pirated user IDs in the user ID set.

[0152] Step 703: Determine the number of pirated broadcasting user IDs in each user ID set according to the pirated broadcasting user IDs in each user ID set.

[0153] In this step, after determining the pirated broadcast user IDs in each user ID set, the server counts and determines the number of pirated broadcast user IDs in each user ID set.

[0154] In the embodiment of the present application, a device for determining a pirated broadcasting user is also provided. The device corresponds to the method embodiment, and is specifically as follows: Figure 8 As shown, including:

[0155] An acquisition unit 801 is used to acquire feature data of each user ID and at least one target feature item group;

[0156] A first determining unit 802 is configured to determine, for each target feature item group, a user ID set corresponding to the target feature item group according to feature data of each user ID and the target feature item group;

[0157] The second determining unit 803 is used to determine the number of pirated broadcast user IDs in each user ID set according to a preset pirated broadcast user blacklist and each user ID set;

[0158] The third determining unit 804 is configured to determine all user IDs in the corresponding user ID set as pirated user IDs when the number is greater than a preset value.

[0159] Optionally, the apparatus further includes a fourth determining unit 805, wherein the fourth determining unit 805 is configured to:

[0160] Obtain historical feature data of pirated user IDs;

[0161] According to the historical feature data and the trained feature item combination model, a plurality of first feature item groups and a support and a confidence corresponding to each first feature item group are obtained;

[0162] Among the multiple first feature item groups, determining the feature item group whose support is greater than the minimum support and whose confidence is greater than the minimum confidence as the second feature item group;

[0163] The target feature item group is determined according to the second feature item group.

[0164] Optionally, the fourth determining unit 805 is configured to:

[0165] For each second feature item group, detecting overlapping feature items between the second feature item group and other second feature item groups, and when the overlapping feature items are all feature items of the second feature item group, deleting other second feature item groups containing the overlapping feature items;

[0166] The remaining second feature item group is determined as the target feature item group.

[0167] Optionally, the fourth determining unit 805 is configured to:

[0168] Determine the dimension to which each feature item in the second feature item group belongs;

[0169] Counting a first number of feature items in the second feature item group, and a second number of feature items belonging to a strong dimension in the second feature item group;

[0170] When the first number is greater than a second value and the second number is greater than a third value, the second feature item group is determined as a target feature item group.

[0171] Optionally, the fourth determining unit 805 is configured to:

[0172] Get a preset mutually exclusive feature item group;

[0173] According to a preset mutually exclusive feature item group, detecting whether the mutually exclusive feature item group exists in the second feature item group;

[0174] A second feature item group that does not include the mutually exclusive feature item group is determined as the target feature item group.

[0175] Optionally, the first determining unit 802 is used to

[0176] Determining a target feature item in the target feature item group;

[0177] Compare the feature data of each user ID with the target feature item to obtain the user ID whose feature data includes the target feature item;

[0178] Based on the feature data including the user ID of the target feature item, a user ID set corresponding to the target feature item group is obtained.

[0179] Optionally, the second determining unit 803 is used to

[0180] Obtain a reference pirated broadcast user ID according to the ID in the preset pirated broadcast user blacklist;

[0181] For each user ID set, comparing the reference pirated broadcast user ID with each user ID in the user ID set to determine the pirated broadcast user ID in the user ID set;

[0182] According to the pirated broadcast user IDs in each user ID set, the number of the pirated broadcast user IDs in each user ID set is determined.

[0183] like Fig. 9 As shown, the embodiment of the present application provides a pirate broadcast user determination device, including a processor 901, a communication interface 902, a memory 903 and a communication bus 904, wherein the processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904.

[0184] Memory 903, used for storing computer programs;

[0185] In one embodiment of the present application, the processor 901 is configured to execute the program stored in the memory 903 to implement the method for determining a pirated broadcast user provided by any one of the aforementioned method embodiments, including:

[0186] Obtain feature data of each user ID and at least one target feature item group;

[0187] For each target feature item group, determining a user ID set corresponding to the target feature item group according to feature data of each user ID and the target feature item group;

[0188] According to a preset pirate broadcast user blacklist and each user ID set, determining the number of pirate broadcast user IDs in each user ID set;

[0189] When the number is greater than a preset value, all user IDs in the corresponding user ID set are determined as pirated user IDs.

[0190] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for determining a pirated broadcast user provided in any one of the aforementioned method embodiments are implemented.

[0191] The device embodiments described above are merely illustrative, wherein 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 network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0192] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0193] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0194] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for identifying pirated broadcast users, characterized in that: The method comprises: Obtain feature data of each user ID and at least one target feature item group; For each target feature item group, determining a user ID set corresponding to the target feature item group according to feature data of each user ID and the target feature item group; According to a preset pirate broadcast user blacklist and each user ID set, determining the number of pirate broadcast user IDs in each user ID set; When the number is greater than a preset value, all user IDs in the corresponding user ID set are determined as pirated user IDs.

2. The method according to claim 1, characterized in that: The step of determining at least one target feature item group comprises: Obtain historical feature data of pirated user IDs; According to the historical feature data and the trained feature item combination model, a plurality of first feature item groups and a support and a confidence corresponding to each first feature item group are obtained; Among the multiple first feature item groups, determining the feature item group whose support is greater than the minimum support and whose confidence is greater than the minimum confidence as the second feature item group; The target feature item group is determined according to the second feature item group.

3. The method according to claim 2, characterized in that: When there are multiple second feature item groups, determining the target feature item group according to the second feature item group includes: For each second feature item group, detecting overlapping feature items between the second feature item group and other second feature item groups, and when the overlapping feature items are all feature items of the second feature item group, deleting other second feature item groups containing the overlapping feature items; The remaining second feature item group is determined as the target feature item group.

4. The method according to claim 2, characterized in that: The step of determining the target feature item group according to the second feature item group includes: Determine the dimension to which each feature item in the second feature item group belongs; Counting a first number of feature items in the second feature item group, and a second number of feature items belonging to a strong dimension in the second feature item group; When the first number is greater than a second value and the second number is greater than a third value, the second feature item group is determined as a target feature item group.

5. The method according to claim 2, characterized in that: The step of determining the target feature item group according to the second feature item group includes: Get a preset mutually exclusive feature item group; According to a preset mutually exclusive feature item group, detecting whether the mutually exclusive feature item group exists in the second feature item group; A second feature item group that does not include the mutually exclusive feature item group is determined as the target feature item group.

6. The method according to claim 1, characterized in that: The step of determining the user ID set corresponding to the target feature item group according to the feature data of each user ID and the target feature item group includes: Determining a target feature item in the target feature item group; Compare the feature data of each user ID with the target feature item to obtain the user ID whose feature data includes the target feature item; Based on the feature data including the user ID of the target feature item, a user ID set corresponding to the target feature item group is obtained.

7. The method according to claim 1, characterized in that: The step of determining the number of pirated broadcast user IDs in each user ID set according to the preset pirated broadcast user blacklist and each user ID set comprises: Obtain a reference pirated broadcast user ID according to the ID in the preset pirated broadcast user blacklist; For each user ID set, comparing the reference pirated broadcast user ID with each user ID in the user ID set to determine the pirated broadcast user ID in the user ID set; According to the pirated broadcast user IDs in each user ID set, the number of the pirated broadcast user IDs in each user ID set is determined.

8. A device for identifying pirated broadcast users, characterized in that: The device comprises: An acquisition unit, used to acquire feature data of each user ID and at least one target feature item group; A first determining unit is used to determine, for each target feature item group, a user ID set corresponding to the target feature item group according to feature data of each user ID and the target feature item group; A second determining unit is used to determine the number of pirated broadcast user IDs in each user ID set according to a preset pirated broadcast user blacklist and each user ID set; The third determining unit is used to determine all user IDs in the corresponding user ID set as pirated user IDs when the number is greater than a preset value.

9. A device for determining a pirate broadcasting user, characterized in that: include: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; at least one memory connected to the at least one bus, wherein the processor is configured to: Obtain feature data of each user ID and at least one target feature item group; For each target feature item group, determining a user ID set corresponding to the target feature item group according to feature data of each user ID and the target feature item group; According to a preset pirate broadcast user blacklist and each user ID set, determining the number of pirate broadcast user IDs in each user ID set; When the number is greater than a preset value, all user IDs in the corresponding user ID set are determined as pirated user IDs.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining a pirated user according to any one of claims 1 to 7 is implemented.

Images