Water army behavior identification method and device, medium and computing device

Abstract

The application discloses a water army behavior recognition method and device, a medium and computing equipment, and comprises the following steps: obtaining an event to be recognized; determining each self-media account corresponding to the event to be recognized; for each self-media account in the each self-media account, if the self-media account is in a preset water army network library, obtaining speech data of the self-media account in a preset time period; based on the same corpus existing in the speech data of the each self-media account, generating a target water army account network; and outputting the target water army account network; it can be seen that the application can improve the precision of water army behavior recognition.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a water army behavior identification method and device, medium and computing equipment. BACKGROUND

[0002] At present, water army is usually active in e-commerce websites, forums, microblogs and other social network platforms, and influences normal users by publishing, replying and spreading blog posts by disguising as ordinary netizens or consumers.

[0003] In practice, in order to regulate the behavior of water army, it is necessary to find the blog posts published by water army from each blog post in the social network platform. For this purpose, the traditional water army behavior identification method needs to manually determine the explicit features of water army behavior, such as water army's rhetoric template, and then judge whether the self-media account in the social network platform is a water army based on the manually determined explicit features. However, this water army behavior identification lacks regularity in identifying organized behavior of water army, and has the problem of poor identification accuracy.

[0004] At present, no effective solution has been proposed for the above problems. SUMMARY

[0005] The embodiments of the present application provide a water army behavior identification method, device, medium and computing equipment, which can improve the accuracy of water army behavior identification.

[0006] According to an aspect of the embodiments of the present application, a water army behavior identification method is provided, comprising:

[0007] Obtaining a to-be-identified event;

[0008] Determining each self-media account corresponding to the to-be-identified event;

[0009] For each self-media account in the each self-media account, if the self-media account is in a preset water army network library, obtaining the speech data of the self-media account in a preset time period;

[0010] Generating a target water army account network based on the same corpus existing in the speech data of the each self-media account;

[0011] Outputting the target water army account network.

[0012] As an optional implementation, generating a target water army account network based on the same corpus existing in the speech data of the each self-media account, comprising:

[0013] For the speech data of each self-media account, calculating the simhash value of the small sentence with the number of words exceeding a preset word number threshold in the speech data;

[0014] determine the associated account using the small sentence by inverting index of the simhash value;

[0015] generate the target water army account network based on the respective self-media account and the respective corresponding associated account;

[0016] wherein the number of times the associated account uses the small sentence is proportional to the weight of the node in the target water army network.

[0017] As an optional implementation, the method further comprises:

[0018] record network generation data in the process of generating the target water army account network;

[0019] output the network generation data;

[0020] wherein the network generation data is used to describe the account generation process and the network generation process of the target water army account network.

[0021] As an optional implementation, the method further comprises:

[0022] obtain a sample self-media account set;

[0023] perform small sentence disassembly on the speech data of each sample self-media account in the sample self-media account set to obtain each sample small sentence;

[0024] calculate the simhash value of each sample small sentence;

[0025] inverting index according to the simhash value of each sample small sentence to establish a transient graph network;

[0026] construct the preset water army network library based on the transient graph network.

[0027] As an optional implementation, constructing the preset water army network library based on the transient graph network comprises:

[0028] determine a central suspicious account based on the transient graph network, wherein the associated behavior of the central suspicious account satisfies a preset associated condition;

[0029] construct the preset water army network library based on the central suspicious account and the account whose behavior is directed to the central suspicious account.

[0030] According to another aspect of the embodiment of the present application, a water army behavior recognition device is also provided, comprising:

[0031] an event obtaining unit, configured to obtain a to-be-recognized event;

[0032] An account determining unit is configured to determine each self-media account corresponding to the to-be-identified event;

[0033] A data obtaining unit is configured to, for each self-media account in the self-media accounts, if the self-media account is in a preset army network library, obtain speech data of the self-media account in a preset time period;

[0034] A network generating unit is configured to generate a target army account network based on the same corpus existing in the speech data of the self-media accounts;

[0035] A network output unit is configured to output the target army account network.

[0036] As an optional implementation, the network generating unit is specifically configured to:

[0037] For the speech data of each self-media account, calculate a simhash value of a small sentence with a word number exceeding a preset word number threshold in the speech data;

[0038] Determine an associated account using the small sentence by performing an inverted index on the simhash value;

[0039] Generate the target army account network based on the self-media accounts and the respective associated accounts;

[0040] The number of times that the associated account uses the small sentence is directly proportional to the weight of a node in the target army network in which the associated account is located.

[0041] As an optional implementation, the network output unit is further configured to:

[0042] Record network generation data in the process of generating the target army account network;

[0043] Output the network generation data;

[0044] The network generation data is used to describe an account generation process and a network generation process of the target army account network.

[0045] According to still another aspect of the embodiments of the present application, a computing device is also provided, which comprises at least one processor, a memory and an input-output unit; the memory is configured to store a computer program, and the processor is configured to invoke the computer program stored in the memory to execute the above-mentioned army behavior identification method.

[0046] According to still another aspect of the embodiments of the present application, a computer readable storage medium is also provided, which comprises instructions, when the instructions are run on a computer, causing the computer to execute the above-mentioned army behavior identification method.

[0047] In the embodiment of the present application, an event to be identified is acquired, each self-media account corresponding to the event to be identified is determined, for each self-media account in the each self-media account, if the self-media account is in a preset water army network library, speech data of the self-media account in a preset time period is acquired, a target water army account network is generated based on the same corpus existing in the speech data of the each self-media account, and the target water army account network is output. It can be seen that the present application can improve the precision of water army behavior identification. BRIEF DESCRIPTION OF DRAWINGS

[0048] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and serve to explain the present application together with the specification: in the drawings:

[0049] Figure 1 is a flowchart of an optional water army behavior identification method according to an embodiment of the present application;

[0050] Figure 2 is a structural schematic diagram of an optional water army behavior identification device according to an embodiment of the present application;

[0051] Figure 3 is a structural schematic diagram of a medium according to an embodiment of the present application;

[0052] Figure 4 is a structural schematic diagram of a computing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative work should belong to the protection scope of the present application.

[0054] It should be noted that the terms "first", "second", and the like in the description and claims of the application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0055] The following refers to Figure 1 , Figure 1 The flowchart of the water army behavior recognition method provided by an embodiment of the application is shown. It should be noted that the embodiments of the application can be applied to any applicable scenario.

[0056] Figure 1 The flowchart of the water army behavior recognition method provided by an embodiment of the application is shown, which includes:

[0057] Step S101, obtaining an event to be recognized.

[0058] In this embodiment, the execution subject can be a terminal device, a server or other electronic device.

[0059] Among them, the event to be recognized can be an event that needs to be recognized whether there is a water army behavior, and the event with a water army behavior can include: a plurality of water army accounts publish corresponding event content on a social platform.

[0060] Step S102, determining each self-media account corresponding to the event to be recognized.

[0061] In this embodiment, the execution subject can further determine a plurality of self-media accounts participating in the event to be recognized, wherein each self-media account corresponding to the event to be recognized can be a self-media account publishing a comment related to the event to be recognized.

[0062] Step S103, for each self-media account in the self-media accounts, if the self-media account is in a preset water army network library, obtaining comment data of the self-media account in a preset time period.

[0063] In the embodiment, after obtaining the self-media accounts, the execution subject can first calculate whether there is a transient graph relationship between the self-media accounts. The transient graph relationship refers to the fact that there are comment or forwarding behaviors between the accounts in a short time. For example, if the self-media accounts have mutual comment or forwarding behaviors within one minute, it is determined that there is a transient graph relationship between the self-media accounts. If it is determined that there is a transient graph relationship between the self-media accounts, it can be determined that the self-media accounts are in the preset water army network library. Then, the execution subject can obtain the speech data of the self-media accounts in the water army network library. The preset time period is preferably within one week. The speech data can be speech data corresponding to other events except the to-be-identified event.

[0064] Before obtaining the to-be-identified event for water army behavior identification, the execution subject can pre-construct a water army network library, which can be generated based on multiple transient graph networks, and the transient graph network is used to reflect the transient graph relationship between the accounts.

[0065] Step S104, generating a target water army account network based on the same corpus existing in the speech data of the self-media accounts.

[0066] In the embodiment, after obtaining the speech data of the self-media accounts in the preset time period, the execution subject can analyze the speech data to determine whether the self-media accounts have the behavior of publishing the same corpus and determine the frequency data of the self-media accounts publishing the same corpus. Then, the self-media accounts are sorted based on the frequency data to generate a target water army account network.

[0067] The target water army account network includes the self-media accounts and the connection relationship between the self-media accounts. The connection relationship is used to represent the association degree between the self-media accounts. For example, the smaller the connection distance between the self-media accounts, the higher the frequency of the two self-media accounts historically forwarding, commenting or publishing the same corpus, and the greater the association degree.

[0068] Step S105, outputting the target water army account network.

[0069] In the embodiment, after calculating the target water army account network, the execution subject can output the target water army account network to enable the user to directly obtain the water army account information related to the to-be-identified event and the account association information between the water army accounts, thereby improving the accuracy of water army behavior identification.

[0070] As an optional implementation, generating a target water army account network based on the same corpus existing in the speech data of the self-media accounts includes:

[0071] For the speech data of each self-media account, a simhash value of a small sentence with a word number exceeding a preset word number threshold in the speech data is calculated;

[0072] By performing an inverted index on the simhash value, an associated account using the small sentence is determined;

[0073] Based on the respective self-media accounts and the respective associated accounts, the target water army account network is generated;

[0074] The number of times that the associated account uses the small sentence is directly proportional to the weight of a node in the target water army network in which the associated account is located.

[0075] The small sentence refers to a grammatical unit containing a subject and a predicate obtained by separating speech data with a comma.

[0076] In the embodiment, after the execution subject obtains speech data of each self-media account in a preset time period, the execution subject can first determine small sentences with a word number exceeding a preset word number threshold, for example, the word number threshold can be set to 6, and small sentences with more than 6 words can be determined. Then, simhash values of the small sentences are calculated. By performing an inverted index on the simhash values, other authors using the small sentence, that is, the associated accounts, are determined. For the overlapping accounts in the associated accounts and the self-media accounts, the node weight of the overlapping accounts in the target water army network can be increased. In this way, the execution subject can obtain associated accounts using the same corpus (small sentence) and appearing in the to-be-identified event at the same time. The weight of each use of the same-fingerprint small sentence by the associated accounts is increased by 1, and finally, the target water army network is sorted.

[0077] As an optional embodiment, the method further includes:

[0078] In the process of generating the target water army account network, network generation data is recorded;

[0079] The network generation data is outputted;

[0080] The network generation data is used to describe the account generation process and the network generation process of the target water army account network.

[0081] In the embodiment, in the process of generating the target water army account network, the formation process of each account in the target water army account network and information of these network co-occurrences are recorded, which can be displayed and outputted as interpretable evidence.

[0082] As an optional implementation, the method further comprises:

[0083] Obtaining a sample We-media account set;

[0084] Carrying out small sentence disintegration on the speech data of each sample We-media account in the sample We-media account set to obtain each sample small sentence;

[0085] Calculating the simhash value of each sample small sentence;

[0086] Carrying out inverted indexing according to the simhash value of each sample small sentence to establish a transient graph network;

[0087] Based on the transient graph network, constructing the preset water army network library.

[0088] In the embodiment, the execution subject can obtain a large number of We-media accounts as a sample We-media account set for constructing a basic account pool.

[0089] Among them, for each sample We-media account, its speech data in a preset time period can be obtained, for example, all speeches in 1 week. Then, the speech data is disintegrated into a plurality of sample small sentences separated by commas. For each sample small sentence, the simhash value of the sample small sentence can be calculated, wherein the simhash value is an automatic deformation of the small sentence, so as to form an author-to-small sentence inverted index, small sentence simhash->author1, author2, author3, and its hash code:8989473982645619849->author A, author B, author C. At the same time, the execution subject can establish a transient graph network based on all real-time information. Based on the analysis of the transient graph network, the above-mentioned preset water army network library is constructed. Among them, the transient graph network is used to reflect the association between accounts in the transient state. After obtaining the inverted index of the sample small sentence, the execution subject can establish the transient graph network between each sample We-media account based on the author account condition of publishing the same or similar small sentence, and further analyze the transient graph network to obtain the preset water army network library.

[0090] As an optional implementation, based on the transient graph network, the preset water army network library is constructed, comprising:

[0091] Based on the transient graph network, determining a central suspicious account whose association behavior satisfies a preset association condition;

[0092] Based on the central suspicious account and the account whose behavior is directed to the central suspicious account, constructing the preset water army network library.

[0093] In the embodiment, the transient graph network includes all account behavior logic existing only within one minute, and has a structure of account->behavior (comment, forward)->account, and is real-time deleted and re-established over one minute. The behavior of one account actively associating with other accounts within one minute is searched, and after a characteristic that one account rapidly associates with more than two accounts is found, the account is recorded as a central suspicious account of a target account for water army operation. Meanwhile, other accounts pointing to the target account (the central suspicious account) appearing at least twice in sixty transient graph (60 minutes) networks are calculated, and these accounts are recorded as other accounts pointing to the target account and associated around the central suspicious account to form a small water army behavior network. When suspicious behaviors of a network are captured in different minutes, the node weight is +1, and a final water army network library is obtained.

[0094] In the embodiment of the application, an event to be identified is acquired, and each self-media account corresponding to the event to be identified is determined. If each self-media account in the self-media accounts is in a preset water army network library, speech data of the self-media account within a preset time period is acquired. A target water army account network is generated based on same corpus existing in the speech data of the self-media accounts, and the target water army account network is output. It can be seen that the application can improve the precision of water army behavior identification.

[0095] After the method of the exemplary embodiment of the application is introduced, next, with reference to the accompanying drawings, the exemplary embodiments of the application are described in detail. Figure 2 A water army behavior identification device of the exemplary embodiment of the application is described, and the device includes:

[0096] An event acquisition unit 201 is configured to acquire an event to be identified.

[0097] An account determination unit 202 is configured to determine each self-media account corresponding to the event to be identified.

[0098] A data acquisition unit 203 is configured to, for each self-media account in the self-media accounts, acquire speech data of the self-media account within a preset time period if the self-media account is in a preset water army network library.

[0099] A network generation unit 204 is configured to generate a target water army account network based on same corpus existing in the speech data of the self-media accounts.

[0100] A network output unit 205 is configured to output the target water army account network.

[0101] As an optional embodiment, the network generation unit 204 is specifically configured to:

[0102] For each self-media account's comment data, a simhash value of a small sentence with a word number exceeding a preset word number threshold in the comment data is calculated.

[0103] By inverting indexing the simhash value, an associated account using the small sentence is determined.

[0104] Based on the respective self-media accounts and the respective corresponding associated accounts, the target water army account network is generated.

[0105] The number of times the associated account uses the small sentence is directly proportional to the weight of the node in the target water army network where the associated account is located.

[0106] As an optional implementation, the network output unit 205 is further configured to:

[0107] In the process of generating the target water army account network, network generation data is recorded.

[0108] The network generation data is outputted.

[0109] The network generation data is used to describe the account generation process and the network generation process of the target water army account network.

[0110] As an optional implementation, the apparatus further comprises:

[0111] A network construction unit is configured to acquire a sample self-media account set; perform small sentence disintegration on the comment data of each sample self-media account in the sample self-media account set to obtain each sample small sentence; calculate a simhash value of each sample small sentence; perform inverting indexing on the simhash values of the respective sample small sentences to establish an instantaneous graph network; and construct the preset water army network library based on the instantaneous graph network.

[0112] As an optional implementation, the network construction unit is specifically configured to:

[0113] Based on the instantaneous graph network, a central suspicious account with an associated behavior satisfying a preset association condition is determined.

[0114] Based on the central suspicious account and an account with a behavior directed to the central suspicious account, the preset water army network library is constructed.

[0115] In the embodiment of the present application, an event to be identified is acquired; each self-media account corresponding to the event to be identified is determined; for each self-media account in the each self-media account, if the self-media account is in a preset water army network library, speech data of the self-media account in a preset time period is acquired; a target water army account network is generated based on the same corpus existing in the speech data of the each self-media account; and the target water army account network is output. It can be seen that the present application can improve the precision of water army behavior identification.

[0116] After the method and device of the exemplary embodiments of the present application are introduced, next, with reference to Figure 3 The computer readable storage medium of the exemplary embodiments of the present application is described, please refer to Figure 3 The computer readable storage medium shown is an optical disc 30, and a computer program (i.e. program product) is stored on the optical disc 30. When the computer program is run by a processor, each step recorded in the above method embodiments can be implemented, for example, an event to be identified is acquired; each self-media account corresponding to the event to be identified is determined; for each self-media account in the each self-media account, if the self-media account is in a preset water army network library, speech data of the self-media account in a preset time period is acquired; a target water army account network is generated based on the same corpus existing in the speech data of the each self-media account; and the target water army account network is output. The specific implementation of each step is not repeated here.

[0117] It should be noted that examples of the computer readable storage medium can also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical, magnetic storage medium, which will not be repeated here.

[0118] After the method, medium and device of the exemplary embodiments of the present application are introduced, next, with reference to Figure 4 The computing device for water army behavior identification of the exemplary embodiments of the present application.

[0119] Figure 4 A block diagram of an exemplary computing device 40 suitable for implementing embodiments of the present application is shown, which can be a computer system or a server. Figure 4 The computing device 40 shown is only an example, and should not bring any limitation to the function and use range of the embodiments of the present application.

[0120] As Figure 4As shown, the components of the computing device 40 can include, but are not limited to, one or more processors or processing units 401, a system memory 402, and a bus 403 that couples various system components including the system memory 402 to the processing unit 401.

[0121] The computing device 40 typically includes a variety of computer system readable media. Such media can be any available media that is located either internally or externally to the computing device 40 such as volatile and non-volatile media, removable and non-removable media.

[0122] The system memory 402 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 4021 and / or cache memory 4022. The computing device 40 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, ROM 4023 can be used to read-only memory, such as a magnetic floppy disk, a magnetic hard disk, or a magnetic tape (e.g., any of which can be considered a magnetic disk drive). Figure 4 As shown, the computing device 40 can also include a removable / non-removable, volatile / non-volatile computer system storage medium such as a magnetic floppy disk drive with a floppy disk 4024, and / or hard disk drive with a hard disk 4025, which can be used for data storage and / or computer program storage. Figure 4 Although the exemplary computing device 40 is shown as having components such as the system memory 402, the processing unit 401, and the bus 403, it is understood that any of the components of the exemplary computing device 40 can be used in combination, or independently, of the other components to perform one or more of the methods described herein.

[0123] The program / utility 4025, having a set of programs / modules 4024, can be stored in, for example, system memory 402 and / or the storage device 4026 of the computing device 40. It is to be appreciated that the

[0124] The computing device 40 can also communicate with one or more external devices 404 such as a keyboard, a pointing device, a display, etc. via an input / output (I / O) interface 405. Further, the computing device 40 can communicate with one or more networks such as a local area network (LAN), a wide area network (WAN), and / or the Internet through a network adapter 406. As Figure 4 illustrated, the network adapter 406 communicates with the other components of the computing device 40 via the bus 403. It should be understood that although not shown, other hardware and / or software components could be used in conjunction with the exemplary computing device 40. Such components can include, but are not limited to, MICR, a modem, a printer, a scanner, and the like.​ Other hardware and / or software modules can be used in conjunction with the computing device 40, as shown.

[0125] The processing unit 401 performs various function applications and data processing by running programs stored in the system memory 402, such as obtaining an event to be identified, determining each self-media account corresponding to the event to be identified, for each of the self-media accounts, if the self-media account is in a preset water army network library, obtaining speech data of the self-media account in a preset time period, generating a target water army account network based on the same corpus existing in the speech data of the self-media accounts, and outputting the target water army account network. The specific implementation of each step is not repeated here. It should be noted that although several units / modules or sub-units / sub-modules of the water army behavior identification device are mentioned in the foregoing detailed description, such division is only exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules.

[0126] In the description of the present application, it should be noted that the terms "first", "second", "third" are only for the purpose of description and cannot be understood or implied as indicating or implying relative importance.

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0128] In the several embodiments of the present application, it should be understood that the disclosed system, device and method can be implemented by other ways. The above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and there can be another division way in actual implementation, and for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0129] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0130] Additionally, each functional unit in various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0131] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a nonvolatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0132] Finally, it should be noted that: the above-described embodiments are merely specific embodiments of the present application, used to illustrate the technical solutions of the present application, and not to limit the same. The protection scope of the present application is not limited thereto, although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily think of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed by the present application, or make equivalent replacements to some of the technical features; and these modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0133] In addition, although the operations of the method of the present application are described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in that specific order, or that all of the shown operations must be performed to achieve the desired result. Additionally or alternatively, some steps can be omitted, a plurality of steps can be combined into one step, and / or one step can be divided into a plurality of steps.

Claims

1. A method for identifying water army behavior, characterized in that: include: Get the event to be identified; Determine each self-media account corresponding to the event to be identified; For each of the self-media accounts, if the self-media account is in a preset water army network database, obtaining speech data of the self-media account within a preset time period; Generate a target water army account network based on the common corpus in the speech data of each of the self-media accounts; Output the target water army account network; Based on the common corpus in the speech data of each self-media account, a target water army account network is generated, including: For each social media account's speech data, calculate the simhash value of the sentences in the speech data whose word count exceeds the preset word count threshold; Determine the associated account using the sentence by performing an inverted index on the simhash value; Based on the various self-media accounts and their corresponding associated accounts, the target water army account network is generated; The number of times the associated account uses the sentence is proportional to the weight of the node where the associated account is located in the target water army account network.

2. The method for identifying water army behavior according to claim 1, characterized in that: The method further comprises: During the process of generating the target water army account network, recording network generation data; outputting the network generated data; Among them, the network generation data is used to describe the account generation process and network generation process of the target water army account network.

3. The method for identifying water army behavior according to claim 1, characterized in that: The method further comprises: Get a collection of sample self-media accounts; Decomposing the speech data of each sample self-media account in the sample self-media account set into small sentences to obtain each sample small sentence; Calculate the simhash value of each sample sentence; Perform inverted indexing based on the simhash value of each sample sentence and build a transient graph network; Based on the instantaneous graph network, the preset water army network library is constructed.

4. The method for identifying water army behavior according to claim 3, characterized in that: Based on the instantaneous graph network, the preset water army network library is constructed, including: Based on the instantaneous graph network, determining a central suspect account whose associated behavior meets a preset association condition; The preset water army network library is constructed based on the central suspected account and accounts whose behaviors point to the central suspected account.

5. A device for identifying water army behavior, characterized in that: include: An event acquisition unit, used for acquiring an event to be identified; An account determination unit, configured to determine each self-media account corresponding to the event to be identified; a data acquisition unit configured to acquire, for each of the self-media accounts, speech data of the self-media account within a preset time period if the self-media account is in a preset water army network database; A network generation unit, configured to generate a target water army account network based on the same corpus present in the speech data of each of the self-media accounts; A network output unit, configured to output the target water army account network; Based on the common corpus in the speech data of each self-media account, a target water army account network is generated, including: For each social media account's speech data, calculate the simhash value of the sentences in the speech data whose word count exceeds the preset word count threshold; Determine the associated account using the sentence by performing an inverted index on the simhash value; Based on the various self-media accounts and their corresponding associated accounts, the target water army account network is generated; The number of times the associated account uses the sentence is proportional to the weight of the node where the associated account is located in the target water army account network.

6. The device for identifying water army behavior according to claim 5, characterized in that: The network output unit is further used for: During the process of generating the target water army account network, recording network generation data; outputting the network generated data; Among them, the network generation data is used to describe the account generation process and network generation process of the target water army account network.

7. A computing device, comprising: at least one processor, memory, and input-output unit; The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the method according to any one of claims 1 to 4. 8 . A computer-readable storage medium comprising instructions, which, when executed on a computer, causes the computer to execute the method according to claim 1 .

Images