Method, device, computer device and readable storage medium for identifying irregular group accounts

Abstract

The application relates to the technical field of illegal account identification, and provides an illegal group account identification method, device, computer equipment and readable storage medium. The method comprises the following steps: determining a target account set of a current time window according to text content published in the current time window of a non-first time window; obtaining a screened target account set of the current time window according to at least one of account consistency and text content similarity; clustering the text content published in the current time window by the screened target account set according to the similarity of the text content, to obtain a suspected illegal group library of the current time window; and determining an illegal group account according to at least one of the number of times that a same account is classified into suspected illegal group libraries corresponding to multiple time windows and the number of times that a same text content is classified into suspected illegal group libraries corresponding to multiple time windows. The method improves the accuracy of illegal group account identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of illegal account identification, and in particular to an illegal group account identification method and device, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] In order to maintain a healthy community environment and encourage real and original content creation, a content creation platform identifies various group violations, such as a group violation of sending a large number of similar texts for diversion in a short period of time.

[0003] At present, a small number of illegal group accounts can be identified based on the strategy of clustering the same device of multiple accounts, the same device of multiple accounts, and the devices corresponding to the accounts of similar violations at the same time. However, the current illegal group account identification method has the problems of lag and omission in identifying short-term high-frequency group violations, resulting in low accuracy of illegal group account identification. SUMMARY

[0004] Therefore, it is necessary to provide an illegal group account identification method, device, computer equipment, computer readable storage medium and computer program product to solve the above technical problems.

[0005] In a first aspect, the present application provides an illegal group account identification method, comprising:

[0006] If the current time window is not the first time window, the target account set corresponding to the current time window is determined according to the text content published in the current time window; wherein each text content is published by a corresponding account;

[0007] According to at least one of the account consistency and the text content similarity, it is determined whether to include at least part of the target account set and the text content published by the part of the target account set in the suspected illegal group library corresponding to the previous time window, to obtain the screened target account set corresponding to the current time window;

[0008] According to the similarity of the text content, the text content published by the screened target account set in the current time window is clustered to obtain the suspected illegal group library corresponding to the current time window;

[0009] According to at least one of the number of times the same account is included in the suspected illegal group library corresponding to multiple time windows and the number of times the same text content is included in the suspected illegal group library corresponding to multiple time windows, it is determined whether the corresponding account belongs to the account of the illegal group.

[0010] In one of the embodiments, the determining of the target account set corresponding to the current time window according to the text content published in the current time window comprises:

[0011] determining the account publishing the text content in the current time window according to the text content published in the current time window;

[0012] determining the initial account set corresponding to the current time window according to the account publishing the text content in the current time window;

[0013] obtaining the rule violation account and the white list account;

[0014] removing the rule violation account and the white list account from the initial account set to obtain the target account set corresponding to the current time window.

[0015] In one of the embodiments, after obtaining the suspected rule violation group library corresponding to the current time window, the method further comprises:

[0016] obtaining the text content published by the rule violation account in the current time window;

[0017] determining whether to include the rule violation account and the content published by the rule violation account in the suspected rule violation group library corresponding to the current time window according to the similarity between the text content published by the rule violation account in the current time window and the suspected rule violation text content published by the suspected rule violation group account in the current time window.

[0018] In one of the embodiments, the determining of whether to include at least part of the account in the target account set and the text content published by the part of the account in the suspected rule violation group library corresponding to the previous time window according to at least one of the account consistency and the text content similarity to obtain the screened target account set corresponding to the current time window comprises:

[0019] comparing the consistency between each account in the target account set and each suspected rule violation group account in the suspected rule violation group library corresponding to the previous time window in sequence;

[0020] when the account in the target account set is consistent with the suspected rule violation group account in the suspected rule violation group library corresponding to the previous time window, including the account in the target account set and the text content published by the account in the suspected rule violation group library corresponding to the previous time window, and removing the account in the target account set from the target account set to obtain the screened target account set corresponding to the current time window;

[0021] When the account of the target account set is inconsistent with the suspected violation group account of the suspected violation group library corresponding to the previous time window, it is determined according to the text content similarity whether the account of the target account set and the text content published by the account are included in the suspected violation group library corresponding to the previous time window, and the account of the target account set is removed from the target account set to obtain the screened target account set corresponding to the current time window.

[0022] In one of the embodiments, the determination according to the text content similarity whether the account of the target account set and the text content published by the account are included in the suspected violation group library corresponding to the previous time window comprises:

[0023] The account of the target account set is taken as a query account;

[0024] In each suspected violation group in the suspected violation group library corresponding to the previous time window, at least one suspected violation text content published by the suspected violation group account in the previous time window is selected as the representative text content of each suspected violation group;

[0025] According to the similarity between the text content published by the query account in the current time window and each representative text content, the similar representative text content corresponding to the query account is determined;

[0026] The query account and the text content published by the query account are included in the suspected violation group corresponding to the similar representative text content.

[0027] In one of the embodiments, the determination according to the similarity between the text content published by the query account in the current time window and each representative text content, the similar representative text content corresponding to the query account comprises:

[0028] According to the text content published by the query account in the current time window, the hash value of the query account in the current window is obtained;

[0029] The hash value of each representative text content is obtained;

[0030] According to the closeness between two hash values, the account in the same set as the query account is determined among the accounts to which each representative text content belongs, and a target account subset is obtained;

[0031] According to the similarity between the text content published by the query account in the current time window and the representative text content of other accounts in the target account subset, the similar representative text content corresponding to the query account is determined.

[0032] In one of the embodiments, the clustering of the text content published by the screened target account set in the current time window according to the similarity of the text content comprises:

[0033] obtaining a hash value of each text content published by the screened target account set in the current time window;

[0034] dividing the text content published by the screened target account set in the current time window according to the closeness between the hash values to obtain a plurality of target text content subsets;

[0035] for any target text content subset, clustering the text content in the target text content subset according to the similarity of the text content in the target text content subset to obtain a plurality of clusters;

[0036] when the number of text contents included in a cluster is greater than or equal to the minimum number of text contents included in a cluster, regarding the text contents included in the cluster as suspected violation text contents to obtain a suspected violation text content set corresponding to the current time window;

[0037] obtaining a suspected violation group account set corresponding to the current time window according to the suspected violation text content set corresponding to the current time window;

[0038] obtaining a suspected violation group library corresponding to the current time window according to the suspected violation text content set and the suspected violation group account set corresponding to the current time window.

[0039] In a second aspect, the present application further provides a violation group account identification device, comprising:

[0040] a target account set obtaining module configured to, if the current time window is not the first time window, determine a target account set corresponding to the current time window according to the text content published in the current time window, wherein each text content is published by a corresponding account;

[0041] a target account set screening module configured to determine whether to include at least part of the accounts of the target account set and the text content published by the part of the accounts into a suspected violation group library corresponding to a previous time window according to at least one of account consistency and text content similarity to obtain a screened target account set corresponding to the current time window;

[0042] a suspected violation group library obtaining module configured to cluster the text content published by the screened target account set in the current time window according to the similarity of the text content to obtain a suspected violation group library corresponding to the current time window;

[0043] The rule-violating group account determining module is configured to determine whether the corresponding account belongs to the account of the rule-violating group according to at least one of the number of times that the same account is included in the suspected rule-violating group library corresponding to multiple time windows and the number of times that the same text content is included in the suspected rule-violating group library corresponding to multiple time windows.

[0044] In a third aspect, the present application further provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor executes the above method.

[0045] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program is executed by a processor to perform the above method.

[0046] In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program, and the computer program is executed by a processor to perform the above method.

[0047] The above rule-violating group account identification method, device, computer device, computer readable storage medium and computer program product, if the current time window is a non-first time window, determine a target account set corresponding to the current time window according to text content published in the current time window, wherein each text content is published by a corresponding account; determine whether to include at least part of the accounts of the target account set and the text content published by the part of the accounts in the suspected rule-violating group library corresponding to the previous time window according to at least one of account consistency and text content similarity, to obtain a screened target account set corresponding to the current time window; cluster the text content published in the current time window by the screened target account set according to the similarity of the text content, to obtain the suspected rule-violating group library corresponding to the current time window; and determine whether the corresponding account belongs to the account of the rule-violating group according to at least one of the number of times that the same account is included in the suspected rule-violating group library corresponding to multiple time windows and the number of times that the same text content is included in the suspected rule-violating group library corresponding to multiple time windows. In the scheme provided by the present application, the length of the time window can be set to be short, at this time, the screened target account set corresponding to the current time window can be clustered according to the similarity of the text content published in the time window with a short length, to obtain the suspected rule-violating group library corresponding to the current time window, the short-term high-frequency group rule-violating behavior can be identified, the lag of group rule-violating behavior identification is alleviated, and the accuracy of rule-violating group account identification is improved; in addition, according to at least one of account consistency and text content similarity, whether to include at least part of the accounts of the target account set in the suspected rule-violating group library corresponding to the previous time window can be determined, which can avoid that part of the accounts actually belonging to the rule-violating group are omitted due to the division of the time window, and further improve the accuracy of rule-violating group account identification. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0049] Figure 1 An application environment diagram of the method for identifying a rule-violating group account in an embodiment;

[0050] Figure 2 A flowchart of the method for identifying a rule-violating group account in an embodiment;

[0051] Figure 3 A flowchart of obtaining a target account set corresponding to a current time window in an embodiment;

[0052] Figure 4 A structural block diagram of a device for identifying a rule-violating group account in an embodiment;

[0053] Figure 5 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0055] The present embodiment provides a method for identifying a rule-violating group account, which can be executed by a computer device, as shown in the following Figure 1 The computer device can obtain text content published in a current time window, and then determine whether the corresponding account belongs to a rule-violating group account. It can be understood that the computer device can be implemented by a server, or by a terminal, or by an interactive system of a terminal and a server. In the present embodiment, the method comprises Figure 2 The steps shown in the following are as follows:

[0056] In step S201, if the current time window is not the first time window, a target account set corresponding to the current time window is determined according to the account of the text content published in the current time window. Each text content is published by a corresponding account.

[0057] The account publishing the text content can include an account modifying the account nickname and an account creating the content; for the account modifying the account nickname, the modified account nickname is the text content, and for the account creating the content, the created content is the text content.

[0058] A short time window length can be set, for example, the time window length is set to 1 min or 5 min.

[0059] The text content published by the specified channel, such as the platform's public screen, private chat, square, room name, room content, etc. can be integrated by channel, and the account publishing the text content within a certain time period can be determined. According to the current time window, the account publishing the text content within the current time window can be determined.

[0060] If the current time window is not the first time window, according to the text content published in the current time window, the account publishing the text content in the current time window is determined, and the account publishing the text content in the current time window is determined as the target account corresponding to the current time window; according to the target account corresponding to the current time window, the target account set corresponding to the current time window is obtained.

[0061] Step S202, according to at least one of the account consistency and the text content similarity, determine whether to include at least part of the account set and the text content published by the part of the account in the suspected violation group library corresponding to the previous time window, to obtain the screened target account set corresponding to the current time window.

[0062] The suspected violation group library includes a suspected violation text content set and a suspected violation group account set, wherein the suspected violation text content corresponds to the suspected violation group account one by one.

[0063] When screening the target account set corresponding to the current time window, at least one of the account consistency and the text content similarity can be used.

[0064] If the target account set corresponding to the current time window is screened according to the account consistency, the following steps can be specifically performed:

[0065] For the previous time window of the current time window, the suspected violation group library corresponding to the previous time window can be obtained; according to the suspected violation group library corresponding to the previous time window, the suspected violation group account corresponding to the previous time window is obtained.

[0066] Taking account A in the target account set corresponding to the current time window as an example, the following steps can be performed: performing consistency comparison between account A and each suspected rule violation group account of the suspected rule violation group corresponding to the previous time window; if account A is consistent with a suspected rule violation group account corresponding to the previous time window, then account A and the text content published by account A are attributed to the suspected rule violation group to which the suspected rule violation group account belongs in the previous time window, and account A is removed from the target account set corresponding to the current time window. In this way, each account in the target account set corresponding to the current time window is processed, and a screened target account set corresponding to the current time window is obtained.

[0067] If the target account set corresponding to the current time window is screened according to the text content similarity, the following steps can be specifically performed:

[0068] For the previous time window of the current time window, the suspected rule violation group library corresponding to the previous time window can be obtained; according to the suspected rule violation group library corresponding to the previous time window, the suspected rule violation text content corresponding to the previous time window is obtained.

[0069] Taking account B in the target account set corresponding to the current time window as an example, the following steps can be performed: performing similarity comparison between the text content of account B and each suspected rule violation text content of the suspected rule violation group corresponding to the previous time window; if the similarity between the text content of account B and a suspected rule violation text content corresponding to the previous time window satisfies a similarity threshold, then account B and the text content published by account B are attributed to the suspected rule violation group to which the suspected rule violation text content belongs in the previous time window, and account B is removed from the target account set corresponding to the current time window. In this way, each account in the target account set corresponding to the current time window is processed, and a screened target account set corresponding to the current time window is obtained.

[0070] If the target account set corresponding to the current time window is screened according to the account consistency and the text content similarity, the following steps can be specifically performed:

[0071] For the previous time window of the current time window, the suspected rule violation group library corresponding to the previous time window can be obtained; according to the suspected rule violation group library corresponding to the previous time window, the suspected rule violation group account corresponding to the previous time window is obtained, as well as the suspected rule violation text content corresponding to the suspected rule violation group.

[0072] Taking an account C in the target account set corresponding to the current time window as an example, the following steps can be performed: performing consistency comparison between the account C and each suspected rule violation group account of the suspected rule violation group corresponding to the previous time window; if the account C is inconsistent with all suspected rule violation group accounts of the suspected rule violation group corresponding to the previous time window, performing similarity comparison between the text content of the account C and each suspected rule violation text content corresponding to the previous time window; if the similarity between the text content of the account C and a suspected rule violation text content corresponding to the previous time window meets a similarity threshold, the account C and the text content published by the account C are attributed to the suspected rule violation group to which the suspected rule violation text content belongs in the previous time window, and the account C is removed from the target account set corresponding to the current time window. In this way, each account in the target account set corresponding to the current time window is processed, and thus a screened target account set corresponding to the current time window is obtained.

[0073] In step S203, the text contents published by the screened target account set in the current time window are clustered according to the similarity of the text contents, and a suspected rule violation group library corresponding to the current time window is obtained.

[0074] The account plus timestamp can be taken as the unique identifier (id) of the text content, which meets the requirement that the text content has uniqueness when clustering and facilitates the traceability of the text content. Each text content has a corresponding account.

[0075] The initial text content published in the current time window can be obtained, and the initial text content can be standardized to obtain the text content published in the current time window. The specific standardization process is as follows: identifying and removing spaces and invisible characters; converting all letters to lowercase; identifying and converting traditional Chinese characters to simplified Chinese characters; uniformly half-widthing non-half-width characters in the text content; truncating the text content, for example, truncating the text content according to a length of 30 characters.

[0076] The similarity of any two text contents published in the current time window can be calculated, and if the similarity of the two text contents is higher than a similarity threshold, the accounts publishing the two text contents can be classified into the same cluster, and thus multiple clusters can be formed. Each cluster includes a plurality of text contents, and the text contents included in the same cluster can be determined as a suspected rule violation group of the current time window, and thus a suspected rule violation text content set corresponding to the current time window is formed. The suspected rule violation group account set corresponding to the current time window can be obtained according to the suspected rule violation text content set corresponding to the current time window, and the suspected rule violation group library corresponding to the current time window can be obtained according to the suspected rule violation text content set and the suspected rule violation group account set corresponding to the current time window.

[0077] In the embodiment, if the current time window is the first time window, the target account set corresponding to the current time window can be determined according to the text content published in the current time window; at this time, the target account set does not need to be screened, and at this time, the text content published by the target account set in the current time window can be clustered according to the similarity of the text content to obtain the suspected violation group library corresponding to the current time window.

[0078] In the above manner, the suspected violation group library corresponding to the multiple time windows in the set period can be obtained, and step S204 is entered.

[0079] In step S204, whether the corresponding account belongs to the account of the violation group is determined according to at least one of the number of times the same account is included in the suspected violation group library corresponding to the multiple time windows and the number of times the same text content is included in the suspected violation group library corresponding to the multiple time windows.

[0080] The account number threshold and the text number threshold can be determined according to actual conditions.

[0081] If whether the corresponding account belongs to the account of the violation group is determined according to the number of times the same account is included in the suspected violation group library corresponding to the multiple time windows, the following steps can be specifically performed: if the set period includes 10 time windows, the suspected violation group library corresponding to the 10 time windows can be obtained in the above manner. Each account in the suspected violation group library corresponding to the 10 time windows is processed as follows, taking account D as an example: the number of times account D appears in the suspected violation group library corresponding to the 10 time windows is determined, if the number is greater than or equal to the account number threshold, it is determined that account D belongs to the account of the violation group, and if the number is less than the account number threshold, it is determined that account D does not belong to the account of the violation group.

[0082] If 5 of the 10 time window corresponding suspected violation group libraries include account B, the number of times account B appears in the 10 time window corresponding suspected violation group library can be determined as 5.

[0083] If the number of times that the same text content is included in the suspected violation group libraries corresponding to multiple time windows is used to determine whether the corresponding account belongs to the account of a violation group, the following steps can be specifically performed: if the setting period includes 10 time windows, the suspected violation group libraries corresponding to the 10 time windows can be obtained in the above manner. For each suspected violation text content in the suspected violation group libraries corresponding to the 10 time windows, the following processing is performed, taking suspected violation text content M as an example: the number of times that the suspected violation text content M appears in the suspected violation group libraries corresponding to the 10 time windows is determined, if the number of times is greater than or equal to the text number threshold, it is determined that the suspected violation group account that publishes the suspected violation text content M belongs to the account of a violation group, and if the number of times is less than the text number threshold, it is determined that the suspected violation group account that publishes the suspected violation text content M does not belong to the account of a violation group.

[0084] In which, the number of times that the same word group is included in the suspected violation group libraries corresponding to multiple time windows can also be used to determine whether the corresponding account belongs to the account of a violation group, and the following steps can be specifically performed: if the setting period includes 10 time windows, the suspected violation group libraries corresponding to the 10 time windows can be obtained in the above manner. The word group whose appearance number in the suspected violation group libraries corresponding to the 10 time windows is greater than or equal to the text number threshold is determined, taking word group N as an example: the word group N is determined in the suspected violation text content corresponding to the 10 time windows, and the suspected violation group account that publishes the above suspected violation text content is determined as the account of a violation group.

[0085] If the number of times that the same account is included in the suspected violation group libraries corresponding to multiple time windows and the number of times that the same text content is included in the suspected violation group libraries corresponding to multiple time windows are used to determine whether the corresponding account belongs to the account of a violation group, the number of times that the same account is included in the suspected violation group libraries corresponding to multiple time windows can be used to determine whether the corresponding account belongs to the account of a violation group first, and then the number of times that the same text content is included in the suspected violation group libraries corresponding to multiple time windows is used to determine whether the corresponding account belongs to the account of a violation group; or the number of times that the same text content is included in the suspected violation group libraries corresponding to multiple time windows can be used to determine whether the corresponding account belongs to the account of a violation group first, and then the number of times that the same account is included in the suspected violation group libraries corresponding to multiple time windows is used to determine whether the corresponding account belongs to the account of a violation group.

[0086] In the above method for identifying a group account in violation, the length of the time window can be set to be short. In this case, the similarity of the text content published in the time window with a short length can be used to cluster the target account set corresponding to the current time window to obtain a suspected group library corresponding to the current time window, so as to reduce the magnitude of the clustered data, improve the calculation efficiency, identify short-term and high-frequency group violation behaviors, alleviate the lag of group violation behavior identification, and improve the accuracy of the group account in violation.

[0087] In one of the embodiments, the target account set corresponding to the current time window is determined according to the accounts publishing text content in the current time window, and the specific steps are as shown in Figure 3 According to the text content published in the current time window, the accounts publishing text content in the current time window are determined. According to the accounts publishing text content in the current time window, the initial account set corresponding to the current time window is determined. The violation accounts and the whitelist accounts are obtained. The violation accounts and the whitelist accounts are removed from the initial account set to obtain the target account set corresponding to the current time window.

[0088] According to the text content published in the current time window, the accounts publishing text content in the current time window are determined. According to the accounts publishing text content in the current time window, the initial account set corresponding to the current time window is determined. The violation accounts and the whitelist accounts are obtained. The violation accounts and the whitelist accounts are removed from the initial account set to obtain the target account set corresponding to the current time window.

[0089] The violation account refers to an account that has violated recently or has been active. The whitelist account refers to an account with a low probability of group violation behavior, such as an account with a high level.

[0090] The violation accounts and the whitelist accounts can be obtained, and the violation accounts and the whitelist accounts can be removed from the initial account set to obtain the target account set corresponding to the current time window. The method for removing the violation accounts and the whitelist accounts can be referred to as a strategy funnel filtering method.

[0091] In the embodiment, the violation accounts and the whitelist accounts are removed from the initial account set to obtain the target account set corresponding to the current time window, which can reduce the invalid calculation in the process of identifying the group account in violation and reduce the calculation burden.

[0092] In one of the embodiments, after obtaining the suspected violation group library corresponding to the current time window, the method provided by the application further comprises: obtaining the text content published by the violation account in the current time window; and determining whether to attribute the violation account and the content published by the violation account to the suspected violation group library corresponding to the current time window according to the similarity between the text content published by the violation account in the current time window and the suspected violation text content published by the suspected violation group account in the current time window.

[0093] The text content published by the violation account in the current time window can be obtained. The violation account refers to an account that has violated recently and is active, but the account does not necessarily belong to the violation group account and needs to be further identified.

[0094] At least one text content published by a suspected violation group account in the previous time window can be selected as the representative text content of each suspected violation group in the suspected violation group library corresponding to the previous time window. For example, one suspected violation text content published by a suspected violation group account in the previous time window is randomly selected as the representative text content of the suspected violation group in the N suspected violation groups in the suspected violation group library corresponding to the previous time window, and N representative text contents are obtained.

[0095] The similar representative text content corresponding to the violation account can be determined according to the similarity between the text content published by the violation account in the current time window and each representative text content, and the violation account is attributed to the suspected violation group corresponding to the similar representative text content.

[0096] The specific steps of determining the similar representative text content corresponding to the violation account are as follows: the hash value of the violation account in the current window can be obtained according to the text content published by the violation account in the current time window; the hash value of each representative text content can be obtained; the hash value can be a minimum hash value (MinHash); the accounts in the same set as the violation account can be determined among the accounts to which each representative text content belongs according to the closeness between two hash values, and a target account third subset is obtained; the similar representative text content corresponding to the violation account is determined according to the similarity between the text content published by the violation account in the current time window and the representative text content of the other accounts in the target account third subset.

[0097] In the embodiment, the similarity between the text content published by the violation account in the current time window and the suspected violation text content published by the suspected violation group account in the current time window is determined to determine whether to attribute the violation account to the suspected violation group library corresponding to the current time window, which can avoid missing the violation account that actually belongs to the violation group and further improve the identification accuracy of the violation group account.

[0098] In one of the embodiments, whether to include at least part of the accounts of the target account set and the text content published by the part of the accounts into the suspected violation group library corresponding to the previous time window is determined according to at least one of the account consistency and the text content similarity, to obtain the screened target account set corresponding to the current time window, and the specific steps are as follows: the consistency of each account of the target account set and each suspected violation group account of the suspected violation group library corresponding to the previous time window is compared in sequence; when the account of the target account set is consistent with the suspected violation group account of the suspected violation group library corresponding to the previous time window, the account of the target account set and the text content published by the account are included into the suspected violation group library corresponding to the previous time window, and the account of the target account set is removed from the target account set to obtain the screened target account set corresponding to the current time window; when the account of the target account set is inconsistent with the suspected violation group account of the suspected violation group library corresponding to the previous time window, whether to include the account of the target account set and the text content published by the account into the suspected violation group library corresponding to the previous time window is determined according to the text content similarity, and the account of the target account set is removed from the target account set to obtain the screened target account set corresponding to the current time window.

[0099] For the previous time window of the current time window, the suspected violation group library corresponding to the previous time window can be obtained; the suspected violation group account corresponding to the previous time window is obtained according to the suspected violation group library corresponding to the previous time window, and the suspected violation text content of the suspected violation group account in the previous time window.

[0100] The consistency of each account of the target account set and each suspected violation group account of the suspected violation group library corresponding to the previous time window can be compared in sequence; when the account of the target account set is consistent with the suspected violation group account of the suspected violation group library corresponding to the previous time window, it is indicated that the account of the target account set meets the inclusion standard, and at this time the account of the target account set and the text content published by the account can be included into the suspected violation group library corresponding to the previous time window, and the account of the target account set is removed from the target account set to obtain the screened target account set corresponding to the current time window.

[0101] When the account of the target account set is inconsistent with the suspected violation group account of the suspected violation group library corresponding to the previous time window, it is indicated that the account of the target account set does not meet the inclusion standard, and at this time whether the account of the target account set meets the inclusion standard is further determined according to the text content similarity.

[0102] When it is determined that the account of the target account set meets the storage standard, the account of the target account set and the text content published by the account are stored in the suspected violation group library corresponding to the previous time window, and the account of the target account set is removed from the target account set, to obtain the screened target account set corresponding to the current time window.

[0103] Taking the account C in the target account set corresponding to the current time window as an example, the account C can be compared with each suspected violation group account of the suspected violation group corresponding to the previous time window for consistency; if the account C is inconsistent with all suspected violation group accounts of the suspected violation group corresponding to the previous time window, the text content of the account C is compared with each suspected violation text content of the suspected violation group corresponding to the previous time window for similarity; if the similarity between the text content of the account C and a suspected violation text content corresponding to the previous time window meets a similarity threshold, the account C and the text content published by the account C are stored in the suspected violation group to which the account C belongs in the previous time window, and the account C is removed from the target account set corresponding to the current time window. In this way, each account in the target account set corresponding to the current time window is processed, to obtain the screened target account set corresponding to the current time window.

[0104] In the embodiment, whether to store at least part of the accounts of the target account set in the suspected violation group library corresponding to the previous time window is determined according to the account consistency; when the accounts of the target account set are inconsistent with the accounts of the suspected violation group library corresponding to the previous time window, whether to store at least the accounts of the target account set in the suspected violation group library corresponding to the previous time window is determined according to the text content similarity, to obtain the screened target account set corresponding to the current time window, which can reduce invalid calculation in the violation group account identification process and reduce the calculation burden; in addition, it can avoid that part of the accounts actually belonging to the violation group are omitted due to the division of the time window, and further improve the violation group account identification accuracy.

[0105] In one of the embodiments, whether to store the account of the target account set and the text content published by the account in the suspected violation group library corresponding to the previous time window is determined according to the text content similarity, and the specific steps are as follows: the account of the target account set is taken as a query account; in each suspected violation group in the suspected violation group library corresponding to the previous time window, at least one suspected violation text content published by a suspected violation group account in the previous time window is selected as the representative text content of each suspected violation group; the similarity between the text content published by the query account in the current time window and each representative text content is determined to obtain the similar representative text content corresponding to the query account; the query account and the text content published by the query account are stored in the suspected violation group corresponding to the similar representative text content.

[0106] When the account of the target account set is inconsistent with the suspected violation group account of the suspected violation group library corresponding to the previous time window, the account of the target account set is taken as the account to be queried.

[0107] In each suspected violation group in the suspected violation group library corresponding to the previous time window, a suspected violation text content published by at least one suspected violation group account in the suspected violation group in the previous time window is randomly selected as the representative text content of the suspected violation group. For example, a suspected violation text content published by a suspected violation group account in the previous time window is randomly selected as the representative text content of the suspected violation group in turn in N suspected violation groups in the suspected violation group library corresponding to the previous time window, and N representative text contents are obtained.

[0108] According to the similarity between the text content published by the account to be queried in the current time window and each representative text content, a similar representative text content corresponding to the account to be queried is determined, and the account to be queried and the text content published by the account to be queried are classified into the suspected violation group corresponding to the similar representative text content.

[0109] In the embodiment, according to the similarity between the text content published by the account to be queried in the current time window and each representative text content, a similar representative text content corresponding to the account to be queried is determined, and the account to be queried and the text content published by the account to be queried are classified into the suspected violation group corresponding to the similar representative text content, which can avoid the omission of some accounts actually belonging to the violation group due to the division of the time window, and further improve the accuracy of the violation group account identification.

[0110] In one of the embodiments, according to the similarity between the text content published by the account to be queried in the current time window and each representative text content, a similar representative text content corresponding to the account to be queried is determined, and the specific steps are as follows: according to the text content published by the account to be queried in the current time window, the hash value of the account to be queried in the current window is obtained; the hash value of each representative text content is obtained; according to the closeness between two hash values, the accounts belonging to the same set as the account to be queried are determined among the accounts to which each representative text content belongs, and a target account subset is obtained; according to the similarity between the text content published by the account to be queried in the current time window and the representative text content of other accounts in the target account subset, a similar representative text content corresponding to the account to be queried is determined.

[0111] The hash value of the account to be queried in the current window can be obtained according to the text content published by the account to be queried in the current time window, and the hash value can be a minimum hash value (MinHash).

[0112] The hash value of each representative text content can be obtained, and the hash value can be a minimum hash value (MinHash).

[0113] According to the closeness between the hash values, the accounts in each representative text content belonging account are determined to be in the same set as the to-be-queried account, and a target account subset is obtained. A Locality Sensitive Hashing (LSH) index can be set for each account in the target account subset.

[0114] According to the similarity between the text content published by the to-be-queried account in the current time window and the representative text content of other accounts in the target account subset, similar representative text content corresponding to the to-be-queried account is determined. Specifically, when there is a representative text content whose similarity with the text content published by the to-be-queried account in the current time window is higher than a similarity threshold, the representative text content is determined as the similar representative text content corresponding to the to-be-queried account; when there are multiple representative text contents whose similarity with the text content published by the to-be-queried account in the current time window is higher than the similarity threshold, the magnitudes of the suspected violation groups corresponding to the multiple representative text contents are determined, and the representative text content corresponding to the largest magnitude of the suspected violation group is determined as the similar representative text content corresponding to the to-be-queried account.

[0115] In this embodiment, according to the closeness between the hash value of the to-be-queried account in the current window and the hash value of each representative text content, the accounts in each representative text content belonging account are determined to be in the same set as the to-be-queried account, and a target account subset is obtained; according to the similarity between the text content published by the to-be-queried account in the current time window and the representative text content of other accounts in the target account subset, similar representative text content corresponding to the to-be-queried account is determined, and the calculation efficiency is effectively improved without reducing the calculation accuracy.

[0116] In one of the embodiments, the text contents published by the screened target account set in the current time window are clustered according to the similarity of the text contents, to obtain a suspected violation group library corresponding to the current time window, and the specific steps are as follows: obtaining a hash value of each text content published by the screened target account set in the current time window; dividing the text contents corresponding to the current time window of the screened target account set according to the closeness between two hash values, to obtain a plurality of target text content subsets; for any target text content subset, clustering the text contents in the target text content subset according to the similarity of the text contents in the target text content subset, to obtain a plurality of clusters; when the number of text contents included in a cluster is greater than or equal to the number of text contents included in a minimum cluster, the text contents included in the cluster are regarded as suspected violation text contents, to obtain a suspected violation text content set corresponding to the current time window; obtaining a suspected violation group account set corresponding to the current time window according to the suspected violation text content set corresponding to the current time window; obtaining a suspected violation group library corresponding to the current time window according to the suspected violation text content set and the suspected violation group account set corresponding to the current time window.

[0117] The hash value of each text content published by the screened target account set in the current time window is obtained, wherein the hash value can be a minimum hash value (MinHash).

[0118] The text contents corresponding to the current time window of the screened target account set can be divided according to the closeness between two hash values, to obtain a plurality of target text content subsets, wherein a local sensitive hash index can be set for each text content in the target text content subset.

[0119] For any target text content subset, the text contents in the target text content subset are clustered according to the similarity of the text contents in the target text content subset, to obtain a plurality of clusters; when the number of text contents included in a cluster is greater than or equal to the number of text contents included in a minimum cluster, the text contents included in the cluster are regarded as suspected violation text contents, to obtain a suspected violation text content set corresponding to the current time window; obtaining a suspected violation group account set corresponding to the current time window according to the suspected violation text content set corresponding to the current time window; obtaining a suspected violation group library corresponding to the current time window according to the suspected violation text content set and the suspected violation group account set corresponding to the current time window. Wherein, the number of text contents included in the minimum cluster can be set according to the actual situation, for example, the number of text contents included in the minimum cluster can be set to 5.

[0120] After obtaining the suspected violation group library corresponding to the plurality of time windows, some suspected violation group accounts can be marked according to a strategy configuration scheme, and subsequent different degrees of punishment can be performed. The specific strategy configuration scheme is as follows: a clustering process in which the number of text contents included in the minimum cluster is greater than or equal to 5 is determined as a target clustering process, a cluster in which the score is greater than or equal to a score threshold in the target clustering process is taken as a target cluster, and a suspected violation group account corresponding to a suspected violation text located in a set order in the target cluster is marked, and subsequent different degrees of punishment can be performed. The score threshold can be set according to actual conditions, for example, the score threshold can be set to 0.8; the set order can be set according to actual conditions, for example, the order can be set to 15%.

[0121] In this embodiment, the text contents corresponding to the filtered target account set in the current time window are divided according to the closeness between the hash values of the text contents published by the filtered target account set in the current time window, to obtain a plurality of target text content subsets; for any target text content subset, the text contents in the target text content subset are clustered according to the similarity of the text contents in the target text content subset, to obtain a suspected violation text content set corresponding to the current time window, and then a suspected violation group library corresponding to the current time window is obtained, so that the clustering efficiency can be effectively improved without reducing the clustering accuracy.

[0122] It should be understood that, although each step in the flowchart involved in each of the above-described embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each of the above-described embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0123] Based on the same inventive concept, the embodiments of the present application also provide a violation group account identification device for implementing the above-mentioned violation group account identification method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more violation group account identification device embodiments provided below can refer to the limitations of the violation group account identification method in the above text, which will not be repeated here.

[0124] In one exemplary embodiment, as Figure 4As shown, there is provided a device for identifying a rule-breaking group account, wherein:

[0125] The target account set acquisition module 401 is configured to, if the current time window is not the first time window, determine a target account set corresponding to the current time window according to text content published in the current time window; wherein each text content is published by a corresponding account.

[0126] The target account set screening module 402 is configured to determine whether to include at least part of the accounts in the target account set and text content published by the part of the accounts into a suspected rule-breaking group library corresponding to a previous time window according to at least one of account consistency and text content similarity, so as to obtain a screened target account set corresponding to the current time window.

[0127] The suspected rule-breaking group library acquisition module 403 is configured to cluster text content published by the screened target account set in the current time window according to the similarity of the text content, so as to obtain a suspected rule-breaking group library corresponding to the current time window.

[0128] The rule-breaking group account determination module 404 is configured to determine whether a corresponding account belongs to a rule-breaking group account according to at least one of the number of times the same account is included in suspected rule-breaking group libraries corresponding to multiple time windows and the number of times the same text content is included in suspected rule-breaking group libraries corresponding to multiple time windows.

[0129] In one of the embodiments, the target account set acquisition module 401 is further configured to determine accounts publishing text content in the current time window according to the text content published in the current time window, determine an initial account set corresponding to the current time window according to the accounts publishing text content in the current time window, acquire rule-breaking accounts and white-listed accounts, and remove the rule-breaking accounts and the white-listed accounts from the initial account set to obtain the target account set corresponding to the current time window.

[0130] In one of the embodiments, the device further comprises a rule-breaking account storage module configured to acquire text content published by a rule-breaking account in a current time window, and determine whether to include the rule-breaking account and content published by the rule-breaking account into a suspected rule-breaking group library corresponding to the current time window according to the similarity between the text content published by the rule-breaking account in the current time window and suspected rule-breaking text content published by a suspected rule-breaking group account in the current time window.

[0131] In one of the embodiments, the target account set screening module 402 is further configured to: compare each account in the target account set with each suspected rule violation group account in the suspected rule violation group library corresponding to the previous time window in sequence; when the account in the target account set is consistent with the suspected rule violation group account in the suspected rule violation group library corresponding to the previous time window, attribute the account in the target account set and the text content published by the account to the suspected rule violation group library corresponding to the previous time window, and remove the account in the target account set from the target account set to obtain the screened target account set corresponding to the current time window; and when the account in the target account set is inconsistent with the suspected rule violation group account in the suspected rule violation group library corresponding to the previous time window, determine whether to attribute the account in the target account set and the text content published by the account to the suspected rule violation group library corresponding to the previous time window according to the text content similarity, and remove the account in the target account set from the target account set to obtain the screened target account set corresponding to the current time window.

[0132] In one of the embodiments, the target account set screening module 402 is further configured to: take the account in the target account set as a query account; select suspected rule violation text content published by at least one suspected rule violation group account in each suspected rule violation group in the suspected rule violation group library corresponding to the previous time window as representative text content of each suspected rule violation group; determine similar representative text content corresponding to the query account according to the similarity between the text content published by the query account in the current time window and each representative text content; and attribute the query account and the text content published by the query account to the suspected rule violation group corresponding to the similar representative text content.

[0133] In one of the embodiments, the target account set screening module 402 is further configured to: obtain the hash value of the query account in the current time window according to the text content published by the query account in the current time window; obtain the hash value of each representative text content; determine the account in the same set as the query account according to the closeness between two hash values, and obtain a target account subset according to the similarity between the text content published by the query account in the current time window and the representative text content of other accounts in the target account subset; and determine similar representative text content corresponding to the query account according to the similarity between the text content published by the query account in the current time window and the representative text content of other accounts in the target account subset.

[0134] In one embodiment, the suspected violation group database acquisition module 403 is further configured to: acquire the hash value of each text content published by the filtered target account set within the current time window; divide the text content corresponding to the filtered target account set in the current time window according to the closeness between pairwise hash values ​​to obtain several target text content subsets; for any target text content subset, cluster the text content in the target text content subset according to the similarity of the text content in the target text content subset to obtain multiple clusters; when the number of text content included in a cluster is greater than or equal to the number of text content included in the smallest cluster, regard the text content included in the cluster as suspected violation text content to obtain the suspected violation text content set corresponding to the current time window; obtain the suspected violation group account set corresponding to the current time window according to the suspected violation text content set corresponding to the current time window; and obtain the suspected violation group database corresponding to the current time window according to the suspected violation text content set and the suspected violation group account set corresponding to the current time window.

[0135] Each module in the aforementioned device for identifying illegal group accounts can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or separate from the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0136] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The database stores data for embodiments of the method for identifying illegal group accounts. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for identifying illegal group accounts.

[0137] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0138] In an embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0139] In an embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0140] In an embodiment, a computer program product is provided, including a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0142] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0143] The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combinations of the technical features do not exist contradictory, they should be considered as the scope of the present application.

[0144] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method for identifying a rogue group account, the method comprising: The method comprises: If the current time window is not the first time window, determining a target account set corresponding to the current time window according to text content published in the current time window; each text content is published by a corresponding account; sequentially comparing each account in the target account set with each suspected rule violation group account in a suspected rule violation group library corresponding to a previous time window; when the accounts in the target account set are consistent with the suspected rule violation group accounts in the suspected rule violation group library corresponding to the previous time window, the accounts in the target account set and the text content published by the accounts are classified into the suspected rule violation group library corresponding to the previous time window, and the accounts in the target account set are removed from the target account set to obtain a screened target account set corresponding to the current time window; when the accounts in the target account set are inconsistent with the suspected rule violation group accounts in the suspected rule violation group library corresponding to the previous time window, determining whether the accounts in the target account set and the text content published by the accounts are classified into the suspected rule violation group library corresponding to the previous time window according to a text content similarity, and removing the accounts in the target account set from the target account set to obtain a screened target account set corresponding to the current time window; performing clustering on the text content published by the screened target account set in the current time window according to the text content similarity to obtain a suspected rule violation group library corresponding to the current time window; determining whether a corresponding account belongs to a rule violation group according to at least one of a number of times that a same account is classified into suspected rule violation group libraries corresponding to multiple time windows and a number of times that a same text content is classified into suspected rule violation group libraries corresponding to multiple time windows.

2. The method of claim 1, wherein, The method comprises: determining an account publishing text content in the current time window according to the text content published in the current time window; determining an initial account set corresponding to the current time window according to the account publishing text content in the current time window; obtaining rule violation accounts and whitelist accounts; removing the rule violation accounts and the whitelist accounts from the initial account set to obtain a target account set corresponding to the current time window.

3. The method of claim 2, wherein, After obtaining the suspected rule violation group library corresponding to the current time window, the method further comprises: obtaining text content published by a rule violation account in the current time window; determining whether the rule violation account and the content published by the rule violation account are classified into the suspected rule violation group library corresponding to the current time window according to a similarity between the text content published by the rule violation account in the current time window and suspected rule violation text content published by a suspected rule violation group account in the current time window.

4. The method of claim 1, wherein, The method comprises: taking the accounts in the target account set as to-be-queried accounts; selecting, in each suspected rule-violating group in the suspected rule-violating group library corresponding to the previous time window, at least one suspected rule-violating text content published by a suspected rule-violating group account in the suspected rule-violating group in the previous time window as representative text content of the suspected rule-violating group; determining, according to similarity between the text content published by the account to be queried in the current time window and each representative text content, similar representative text content corresponding to the account to be queried; classifying the account to be queried and the text content published by the account to be queried into the suspected rule-violating group corresponding to the similar representative text content.

5. The method of claim 4, wherein, The method further includes: obtaining a hash value of the account to be queried in the current window according to the text content published by the account to be queried in the current time window; obtaining hash values of the representative text contents; determining, according to closeness between two hash values, accounts in the account set to which the account to be queried belongs, to obtain a target account subset; determining, according to similarity between the text content published by the account to be queried in the current time window and representative text content of another account in the target account subset, similar representative text content corresponding to the account to be queried.

6. The method of claim 1, wherein, The method further includes: obtaining a hash value of each text content published by the target account set in the current time window; dividing, according to closeness between two hash values, the text content of the target account set in the current time window, to obtain a plurality of target text content subsets; for any target text content subset, clustering, according to similarity between text contents in the target text content subset, the text contents in the target text content subset, to obtain a plurality of clusters; when the number of text contents included in a cluster is greater than or equal to the number of text contents included in a minimum cluster, regarding the text contents included in the cluster as suspected rule-violating text contents, to obtain a suspected rule-violating text content set corresponding to the current time window; obtaining a suspected rule-violating group account set corresponding to the current time window according to the suspected rule-violating text content set corresponding to the current time window; obtaining a suspected rule-violating group library corresponding to the current time window according to the suspected rule-violating text content set and the suspected rule-violating group account set corresponding to the current time window.

7. A device for identifying a rule-violating group account, characterized by comprising: The apparatus includes: a target account set obtaining module, configured to, if the current time window is not the first time window, determine a target account set corresponding to the current time window according to text contents published in the current time window, wherein each text content is published by a corresponding account. The target account set screening module is configured to compare each account in the target account set with each suspected rule violation group account in the suspected rule violation group library corresponding to the previous time window in sequence; when the account in the target account set is consistent with the suspected rule violation group account in the suspected rule violation group library corresponding to the previous time window, the account in the target account set and the text content published by the account are classified into the suspected rule violation group library corresponding to the previous time window, and the account in the target account set is removed from the target account set, to obtain the screened target account set corresponding to the current time window; when the account in the target account set is inconsistent with the suspected rule violation group account in the suspected rule violation group library corresponding to the previous time window, whether the account in the target account set and the text content published by the account are classified into the suspected rule violation group library corresponding to the previous time window is determined according to the similarity of the text content, and the account in the target account set is removed from the target account set, to obtain the screened target account set corresponding to the current time window; The suspected rule violation group library acquisition module is configured to cluster the text content published by the screened target account set in the current time window according to the similarity of the text content, to obtain the suspected rule violation group library corresponding to the current time window. The rule violation group account determination module is configured to determine whether a corresponding account belongs to a rule violation group account according to at least one of the number of times that the same account is classified into suspected rule violation group libraries corresponding to multiple time windows and the number of times that the same text content is classified into suspected rule violation group libraries corresponding to multiple time windows.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

Images