A Method and System for Automatic Determination of User Chat Anti-Fraud

Abstract

The present invention provides a method and system for automatically determining user chat anti-fraud. The method includes the following steps: Automatically process the reported data, and based on the anti-fraud database, determine whether the basic data information of the two user parties of the reported data conforms to the recognition rules; Determine the prosecution period, and determine whether the in-depth information of the two user parties of the reported data conforms to the recognition rules; Determine whether the supplementary strategy conforms to the recognition rules, perform an automated process of additional additional logic, and close the order; Set up an automated suspected fraud blacklist, and regularly store it in the cache database redis for storage, so as to facilitate query and user warning. The present invention can provide a fast data sorting and determination method during the tracing process after a user chat is suspected of fraud, greatly reducing the determination process and reducing and avoiding losses caused by anti-fraud.

Description

Technical Field

[0001] The present invention relates to the technical field of computer programming, and in particular, to a method and system for automatically determining user chat anti-fraud. Background Art

[0002] In current network interaction behaviors, there are often fraudulent user behaviors. Only after other users report them does the investigation process start. The investigation process requires a lot of manpower and time to determine. The final result is that it takes too long, and not all the money can be recovered. In serious cases, even all the money is swindled away, causing irreparable losses to other users. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to design an automated determination algorithm to quickly and timely trace and determine the reports of suspected fraud in user chats, so as to reduce or avoid losses in the anti-fraud process.

[0004] The present invention provides a method for automatically determining user chat anti-fraud, including the following steps:

[0005] S1. Automatically process the reported data, including the following steps:

[0006] S11. Based on the anti-fraud database, determine whether the basic data information of the two user parties of the reported data conforms to the recognition rules. If it conforms, enter step S12; if not, transfer it to manual processing;

[0007] The method for establishing the recognition rules includes using a data statistical engine to perform recognition based on the number of suspected relationships within the past 1 to 15 days, the reward income of the beneficiary within 24 hours, the basic consumption of the beneficiary within 24 hours, and / or the reward income of the beneficiary within 48 hours, the basic consumption of the beneficiary within 48 hours, and the reward amount for the suspected relationship, using normal distribution parameter estimation. The normal distribution expression is:

[0008]

[0009] In the formula, μ is the mean, σ is the standard deviation, and σ ² is the variance, where the ratio of x within 1 standard deviation is 68%, the ratio of x within 2 standard deviations is 95%, and the ratio of x within 3 standard deviations is 99%;

[0010] The basic data information includes: amount data, user gender, user level;

[0011] S12. Determine the prosecution period, and determine whether the in-depth information of the two user parties of the reported data conforms to the recognition rules. If it conforms, enter step S13; if not, transfer it to manual processing;

[0012] The in-depth information includes: the duration from the occurrence of the chat to the report, that is, the duration from the initial chat to the reporting moment;

[0013] S13. Determine whether the reported data meets the recognition rules through a supplementary strategy, perform an automated process of additional additional logic, and close the order;

[0014] The supplementary strategy includes: the number of reported hits of the reported user; the additional additional logic includes: punishment, ignoring;

[0015] S2. Set up an automated suspected fraud blacklist, regularly store it in the cache database redis for storage, for querying and user warning;

[0016] Specifically, it is determined by a massive data statistical engine through offline scripting processing according to the recognition rules of the number of suspected relationships and the amount of suspected relationship rewards;

[0017] Preferably, the recognition rules include 3 types: 99 - 199 (coefficient), or ≥200 (coefficient), or ≥400 (coefficient)), and if the recognition conditions are met, the blacklist is set.

[0018] Further, the method of the punishment in the S13 step includes: calculating the amount of the user's earned virtual currency, and rejecting the virtual currency by discounting and deducting the virtual currency.

[0019] Further, the method of the automated process of performing additional additional logic in the S13 step includes: if the recognition rules are met, punishment is performed; if the recognition rules are not met, it is ignored.

[0020] Further, after the order is closed in the S13 step, if the reported user files an appeal, the following steps are also included:

[0021] Provide a case withdrawal process after the user appeals; the case withdrawal process includes: if the case withdrawal conditions are met, the virtual currency of the reported party is returned after the case is withdrawn.

[0022] Further, the method of the user warning in the S2 step includes:

[0023] Through the suspected fraud blacklist stored by the algorithm, query the user number with the key name fraud:blacklist:uid in redis, and if it is determined that the user is at risk, a risk warning is given at the top of the chat box;

[0024] The method of storing through the algorithm includes: marking the data as blacklist and caching it in redis storage for any one or more of the following data information of chat behaviors that meet the recognition rules; the data information marked as blacklist includes:

[0025] In the past 1 to 15 days: the number of suspected relationships ≥ 3;

[0026] And, the reward amount for suspected relationships: 99 - 199

[0027] The reward income range for the beneficiary within 24 hours is: [42.4, 85]

[0028] The basic consumption of the beneficiary within 24 hours: < 21.3;

[0029] Or,

[0030] The reward amount for suspected relationships: ≥ 200

[0031] The reward income of the beneficiary within 48 hours: ≥ 85

[0032] The basic consumption of the beneficiary within 48 hours: < 42.5;

[0033] Or,

[0034] The reward amount for suspected relationships: ≥ 400

[0035] The reward income of the beneficiary within 48 hours: ≥ 170

[0036] The basic consumption of the beneficiary within 48 hours: < 85;

[0037] Preferably, the user warning is displayed through the client.

[0038] The present invention also provides a user chat anti-fraud automatic determination system, which executes the user chat anti-fraud automatic determination method as described above, including:

[0039] The determination basic data information subsystem: used to determine whether the basic data information of the two users of the reported data conforms to the recognition rules based on the anti-fraud database. If it conforms, it enters the determination prosecution period subsystem. If it does not conform, it is transferred to manual processing;

[0040] The determination prosecution period subsystem: used to determine whether the in-depth information of the two users of the reported data conforms to the recognition rules. If it conforms, it enters the determination supplementary strategy subsystem. If it does not conform, it is transferred to manual processing;

[0041] The suspected fraud blacklist storage subsystem: used to set up an automated suspected fraud blacklist, and regularly store it in the cache database redis for query and user warning.

[0042] The user chat anti-fraud automatic determination system supports automated process flow and manual processing.

[0043] The data part of the user chat anti-fraud automatic determination system of the present invention further includes:

[0044] Nearly real-time chat data processing module: It processes the data generated by the chat between users through the client, including: text chat, picture chat, topic chat, video chat. The client sends the data generated by the above chats to the server through an HTTP request for background data processing;

[0045] Archived data module: It stores and archives data quantitatively. The chat records are segmented by month and saved in MySQL storage to meet the relevant functions of evidence collection for future reference;

[0046] Big data platform offline data processing module: It specifically saves and processes the information data related to users' friend-making and chatting behaviors as needed. It imports the record number, report type, report scenario, report time, source, interval duration from the start of reporting, session duration, total reporting period, recharge amount of the reporting party, reported amount, fine amount, returned amount, basic amount, and reward amount into the massive data statistical engine Sa to facilitate subsequent searching, offline analysis, and offline evaluation of massive data;

[0047] Submitted report data processing module: It imports the corresponding data of the user side, reported party, report type, report scenario, report time, and report content into the archived database MySQL for data verification analysis and automated processing.

[0048] The structure of the algorithm model part of the user chat anti-fraud automatic determination system of the present invention includes:

[0049] User data layer: It includes user basic information, relevant amount data, user gender, and user level for determining basic information;

[0050] Specifically, assuming that the recharge amount of user A is less than 1000.00 yuan in full, the reported user B is female and the level of user B does not reach level 5, system automated determination can be performed;

[0051] Report prosecution period layer: It is used to deeply judge the two users involved in the report, that is, information such as the duration from the chat to the report, and perform corresponding judgments;

[0052] Specifically, for example, if the duration from the first text chat between user A and user B to the reporting moment is 20 days, it is allowed to enter the system automated process;

[0053] Supplementary strategy algorithm layer: It mainly solves additional additional logics for automated processes: punishment, ignoring, entering the manual process, user warning, etc.;

[0054] Specifically, for example, the corresponding number of hits of the reported user is found in the data archive. Assuming it is more than 2 times, it can be determined that the number is suspected to be excessive, and the automated process can be skipped and transferred to the manual environment. Otherwise, it enters the automated punishment process;

[0055] Establish recognition rules through a massive data statistical engine (Sa). For example,

[0056] In the past 1 to 15 days: the number of suspected relationships ≥ 3 (coefficient)

[0057] Reward amount for suspected relationships: 99 - 199 (coefficient)

[0058] The reward income range for the beneficiary within 24 hours is: [42.4 (coefficient), 85 (coefficient)]

[0059] Basic consumption of the beneficiary within 24 hours: < 21.3 (coefficient)

[0060] Reward amount for suspected relationships: ≥ 200 (coefficient)

[0061] Reward income of the beneficiary within 48 hours: ≥ 85 (coefficient)

[0062] Basic consumption of the beneficiary within 48 hours: < 42.5 (coefficient)

[0063] Reward amount for suspected relationships: ≥ 400 (coefficient)

[0064] Reward income of the beneficiary within 48 hours: ≥ 170 (coefficient)

[0065] Basic consumption of the beneficiary within 48 hours: < 85 (coefficient);

[0066] Set up an automated suspected fraud blacklist, and then regularly store it in a cache database (redis) for storage to facilitate high - efficiency query and use for warning purposes.

[0067] The user chat anti - fraud automatic determination system of the present invention supports automated process flow and manual processing, including: quick punishment, quick ignoring, manual confirmation of ignoring, and manual confirmation of punishment;

[0068] Specifically, for example, in the case of punishment, calculate the amount of virtual currency for the user's income, and carry out virtual currency discount rejection and virtual currency deduction.

[0069] The present invention also provides a computer - readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the above - mentioned user chat anti - fraud automatic determination method are implemented.

[0070] The present invention also provides a computer device. The computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the above - mentioned user chat anti - fraud automatic determination method are implemented.

[0071] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0072] In the traceability after a user's chat is reported as suspected fraud, the present invention can provide a fast data sorting and determination method, greatly reducing the determination process and reducing and avoiding the losses caused by anti-fraud. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention.

[0074] In the drawings:

[0075] Figure 1 is a flowchart of an automatic determination method for user chat anti-fraud of the present invention;

[0076] Figure 2 is a schematic diagram of the composition of a computer device according to an embodiment of the present invention;

[0077] Figure 3 is a flowchart of automatically processing reported data according to an embodiment of the present invention;

[0078] Figure 4 is a schematic diagram of the process of an automatic processing link according to an embodiment of the present invention;

[0079] Figure 5 is a schematic diagram of the process of establishing an automatic suspected fraud blacklist according to an embodiment of the present invention;

[0080] Figure 6 is a schematic diagram of the architecture of an automatic determination system for user chat anti-fraud according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0081] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0082] The terms used in the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. The singular forms "a", "the", and "said" used in the present disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0083] It should be understood that although the terms first, second, and third may be used in this disclosure to describe various signals, these signals should not be limited to these terms. These terms are only used to distinguish signals of the same type from each other. For example, without departing from the scope of this disclosure, the first signal may also be referred to as the second signal, and similarly, the second signal may also be referred to as the first signal. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to a determination".

[0084] An embodiment of the present invention provides a method for automatically determining user chat anti-fraud, see Figure 1 as shown, including the following steps:

[0085] S1. Automatically process the reported data, see Figure 3 as shown, including the following steps:

[0086] S11. Based on the anti-fraud database, determine whether the basic data information of the two user parties of the reported data conforms to the recognition rules. If it conforms, proceed to step S12; if not, transfer it to manual processing;

[0087] The method for establishing the recognition rules includes using a data statistical engine to perform recognition by normal distribution parameter estimation according to the number of suspected relationships within the past 1 to 15 days, the reward income of the beneficiary within 24 hours, the basic consumption of the beneficiary within 24 hours, and / or the reward income of the beneficiary within 48 hours, the basic consumption of the beneficiary within 48 hours, and the reward amount for the suspected relationship. The normal distribution expression is:

[0088]

[0089] In the formula, μ is the mean, σ is the standard deviation, and σ ² is the variance, where the ratio of x within 1 standard deviation is 68%, the ratio of x within 2 standard deviations is 95%, and the ratio of x within 3 standard deviations is 99%;

[0090] Preferably, the embodiment of the present invention uses the ratio of x within 2 standard deviations;

[0091] The basic data information includes: amount data, user gender, user level;

[0092] S12. Determine the prosecution period, and determine whether the in-depth information of the two user parties of the reported data conforms to the recognition rules. If it conforms, proceed to step S13; if not, transfer it to manual processing;

[0093] The in-depth information includes: the duration from the chat to the report, that is, the duration from the initial chat to the reporting moment;

[0094] S13. Determine whether the reported data meets the recognition rules through a supplementary strategy, perform an automated process with additional logic, and close the case.

[0095] The supplementary strategy includes: the number of reported hits of the reported user; the additional logic includes: punishment, ignoring.

[0096] S2. Set up an automated suspected fraud blacklist, regularly store it in the cache database redis for storage, for querying and user warning.

[0097] Specifically, it is determined by a massive data statistical engine through offline scripting processing according to the recognition rules of the number of suspected relationships and the amount of suspected relationship rewards.

[0098] Preferably, the recognition rules include 3 types: 99 - 199 (coefficient), or ≥200 (coefficient), or ≥400 (coefficient)). If the recognition conditions are met, the blacklist is set up.

[0099] The method of punishment in the S13 step includes: calculating the amount of the user's earned virtual currency, and rejecting the virtual currency discount and deducting the virtual currency.

[0100] The method of performing the automated process with additional logic in the S13 step includes: if it meets the recognition rules, perform punishment; if it does not meet the recognition rules, ignore it.

[0101] After the case is closed in the S13 step, if the reported user lodges an appeal, the following steps are also included:

[0102] Provide a case withdrawal process after the user lodges an appeal; the case withdrawal process includes: if the case withdrawal conditions are met, the virtual currency of the reported party is returned after the case is withdrawn.

[0103] The method of user warning in the S2 step includes:

[0104] Through the suspected fraud blacklist stored by the algorithm, query the user number with the key name fraud:blacklist:uid in redis. If it is determined that the user is at risk, a risk warning is given at the top of the chat box.

[0105] The method of storing through the algorithm includes: marking the data as blacklist according to the recognition rules for any one or more of the following data information of chat behaviors, and caching it in redis for storage; the data information marked as blacklist includes:

[0106] In the past 1 - 15 days: the number of suspected relationships ≥ 3;

[0107] And, the amount of suspected relationship rewards: 99 - 199

[0108] The reward income range for the beneficiary within 24 hours is: [42.4, 85]

[0109] The basic consumption of the beneficiary within 24 hours: < 21.3;

[0110] Or,

[0111] The reward amount for the suspected relationship: ≥ 200

[0112] The reward income of the beneficiary within 48 hours: ≥ 85

[0113] The basic consumption of the beneficiary within 48 hours: < 42.5;

[0114] Or,

[0115] The reward amount for the suspected relationship: ≥ 400

[0116] The reward income of the beneficiary within 48 hours: ≥ 170

[0117] The basic consumption of the beneficiary within 48 hours: < 85;

[0118] Preferably, the user warning is displayed through the client.

[0119] The embodiment of the present invention further provides a user chat anti-fraud automatic determination system, which uses the user chat anti-fraud automatic determination method as described above, including:

[0120] The determination basic data information subsystem: used to determine whether the basic data information of the two parties of the reported data conforms to the recognition rules based on the anti-fraud database. If it conforms, it enters the determination prosecution period subsystem. If it does not conform, it is transferred to manual processing;

[0121] The determination prosecution period subsystem: used to determine whether the in-depth information of the two parties of the reported data conforms to the recognition rules. If it conforms, it enters the determination supplementary strategy subsystem. If it does not conform, it is transferred to manual processing;

[0122] The suspected fraud blacklist storage subsystem: used to set up an automated suspected fraud blacklist, and regularly store it in the cache database redis for query and user warning.

[0123] See Figure 4 As shown, the user chat anti-fraud automatic determination system supports automated process flow and manual processing.

[0124] For the data part of the user chat anti-fraud automatic determination system in the embodiment of the present invention, see Figure 6 As shown, it further includes:

[0125] Quasi-real-time chat data processing module: the chat data generated by the user through the client and other users, including: text chat, picture chat, topic chat, video chat, the client transmits the data generated by the above chat to the server through http request for background data processing;

[0126] Archive data module: quantitative data storage and archiving, chat records are divided into monthly segments and saved in MySQL to meet the relevant forensic function;

[0127] Offline data processing module of the big data platform: Targetedly save and process the data related to user friendship and chat behavior as needed, and import the corresponding data such as record number, report type, report scenario, report time, source, report initiation interval, session duration, total report cycle, reporter recharge amount, report amount, fine amount, return amount, basic amount, and reward amount into the massive data statistics engine Sa, so as to facilitate the subsequent search, offline analysis, and offline evaluation of massive data;

[0128] Submit the reporting data processing module: import the corresponding data of the user, the reported party, the reporting type, the reporting scenario, the reporting time, and the reporting content into the archive database Mysql for data verification analysis and automated processing.

[0129] The structure of the algorithm model part of the user chat anti-fraud automatic determination system of the embodiment of the present invention includes:

[0130] User data layer: includes basic user information, relevant amount data, user gender, and user level, which are used to determine basic information;

[0131] In the embodiment of the present invention, if the recharge amount of user A does not reach RMB 1,000.00, the reported user B is female and the level of user B does not reach level 5, the system can automatically determine;

[0132] Report prosecution period layer: used to conduct in-depth judgment on both parties of the report, i.e. the time from the chat to the report, etc.;

[0133] In the embodiment of the present invention, if the time between the first text chat between user A and user B and the reporting time is 20 days, then the user is allowed to enter the system automation process;

[0134] Supplementary strategy algorithm layer: mainly used to solve additional logic and automate processes: penalties, ignoring, manual intervention, user warnings, etc.

[0135] In the embodiment of the present invention, the number of reported hits of the reported user is found in the data archive corresponding to the number of times. If it is more than 2 times, it can be determined that the number is suspected to be excessive, and the automated process can be skipped and transferred to the manual environment. Otherwise, it enters the automated penalty process;

[0136] See Figure 5 As shown, the recognition rules are established through the massive data statistical engine (Sa).

[0137] In the past 1 to 15 days: the number of suspected relationships ≥ 3 (coefficient)

[0138] Reward amount for suspected relationships: 99 - 199 (coefficient)

[0139] The reward income range of the beneficiary within 24 hours is: [42.4 (coefficient), 85 (coefficient)]

[0140] Basic consumption of the beneficiary within 24 hours: < 21.3 (coefficient)

[0141] Reward amount for suspected relationships: ≥ 200 (coefficient)

[0142] Reward income of the beneficiary within 48 hours: ≥ 85 (coefficient)

[0143] Basic consumption of the beneficiary within 48 hours: < 42.5 (coefficient)

[0144] Reward amount for suspected relationships: ≥ 400 (coefficient)

[0145] Reward income of the beneficiary within 48 hours: ≥ 170 (coefficient)

[0146] Basic consumption of the beneficiary within 48 hours: < 85 (coefficient);

[0147] An automated suspected fraud blacklist is established and then regularly stored in the cache database (redis) for efficient query and used as a warning.

[0148] The user chat anti-fraud automatic determination system in the embodiment of the present invention supports the transfer of automated processes and manual processing, including: quick penalty, quick ignore, manual confirmation of ignore, and manual confirmation of penalty;

[0149] In the embodiment of the present invention, the method of punishment is to calculate the amount of virtual currency of the user's income and perform virtual currency discount rejection and virtual currency deduction.

[0150] In the embodiment of the present invention, in the traceability after the user chat is suspected of fraud reporting, it can provide a fast data sorting and determination method, greatly reducing the determination process and reducing and avoiding the losses caused by anti-fraud.

[0151] The embodiment of the present invention also provides a computer device.Figure 2 It is a schematic structural diagram of a computer device provided by an embodiment of the present invention; refer to the attached drawings Figure 2 As shown, the computer device includes: an input device 23, an output device 24, a memory 22, and a processor 21; the memory 22 is used to store one or more programs; when the one or more programs are executed by the one or more processors 21, the one or more processors 21 implement the user chat anti-fraud automatic determination method provided in the above embodiment; wherein the input device 23, the output device 24, the memory 22, and the processor 21 can be connected through a bus or other means, Figure 2 Taking connection through a bus as an example.

[0152] As a readable and writable storage medium of a computing device, the memory 22 can be used to store software programs and computer-executable programs, such as program instructions corresponding to the user chat anti-fraud automatic determination method described in the embodiment of the present invention; the memory 22 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the device, etc.; in addition, the memory 22 can include high-speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices; in some instances, the memory 22 can further include a memory remotely set relative to the processor 21, and these remote memories can be connected to the device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0153] The input device 23 can be used to receive input digital or character information, and generate key signal inputs related to the user settings and function control of the device; the output device 24 can include a display device such as a display screen.

[0154] The processor 21 executes various functional applications and data processing of the device by running software programs, instructions, and modules stored in the memory 22, that is, implements the above user chat anti-fraud automatic determination method.

[0155] The above-provided computer device can be used to execute the user chat anti-fraud automatic determination method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0156] An embodiment of the present invention also provides a storage medium containing computer-executable instructions. The computer-executable instructions are used to execute the user chat anti-fraud automatic determination method provided in the above embodiment when executed by a computer processor. The storage medium is any of various types of memory devices or storage devices, including: installation media such as CD-ROMs, floppy disks or magnetic tape devices; computer system memories or random access memories such as DRAM, DDRRAM, SRAM, EDORAM, Rambus RAM, etc.; non-volatile memories such as flash memories, magnetic media (such as hard disks or optical storage); registers or other similar types of memory elements, etc.; the storage medium may also include other types of memories or combinations thereof; additionally, the storage medium may be located in a first computer system in which the program is executed, or may be located in a different second computer system, and the second computer system is connected to the first computer system through a network (such as the Internet); the second computer system may provide program instructions to the first computer for execution. The storage medium includes two or more storage media that may reside in different locations (such as in different computer systems connected through a network). The storage medium can store program instructions (such as specifically implemented as a computer program) executable by one or more processors.

[0157] Of course, the computer-executable instructions of a storage medium containing computer-executable instructions provided in an embodiment of the present invention are not limited to the user chat anti-fraud automatic determination method described in the above embodiment, and can also execute related operations in the user chat anti-fraud automatic determination method provided in any embodiment of the present invention.

[0158] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make different changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

[0159] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and variations. Any modification, different substitution, or improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An automatic determination method for user chat anti-fraud, characterized in that, It includes the following steps: S1. Automatically process the reported data, including the following steps: S11. Based on the anti-fraud database, determine whether the basic data information of the two user sides of the reported data conforms to the recognition rules. If it conforms, enter step S12; if not, transfer it to manual processing; The method for establishing the recognition rules includes using a data statistics engine to perform recognition by normal distribution parameter estimation based on the number of suspected relationships within the past 1 to 15 days, the reward income of the beneficiary within 24 hours, the basic consumption of the beneficiary within 24 hours, and / or the reward income of the beneficiary within 48 hours, the basic consumption of the beneficiary within 48 hours, and the reward amount for suspected relationships. The normal distribution expression is: ； where μ is the mean, σ is the standard deviation, and σ ² is the variance, and the ratio of x within 1 standard deviation is 68%, within 2 standard deviations is 95%, and within 3 standard deviations is 99%; The basic data information includes: amount data, user gender, user level; S12. Determine the statute of limitations, and determine whether the in-depth information of the two user sides of the reported data conforms to the recognition rules. If it conforms, enter step S13; if not, transfer it to manual processing; The in-depth information includes: the duration from the chat occurrence to the report; S13. Determine whether the reported data conforms to the recognition rules through a supplementary strategy, perform an automated process of additional additional logic, and close the case; The supplementary strategy includes: the number of times the reported user is reported and hit; the additional additional logic includes: punishment, ignoring; S2. Set up an automated suspected fraud blacklist, and regularly store it in the cache database redis for storage for querying and user warning.

2. The automatic determination method for user chat anti-fraud according to claim 1, wherein, The method of the punishment in step S13 includes: calculating the amount of the user's earned virtual currency, and performing virtual currency discount rejection and virtual currency deduction.

3. The user chat anti-fraud automatic determination method according to claim 1, characterized in that The method of the automated process of the additional additional logic in step S13 includes: if it conforms to the recognition rules, perform punishment; if it does not conform to the recognition rules, perform ignoring.

4. The method for automatically determining user chat anti-fraud according to claim 1, wherein After the case is closed in step S13, if the reported user files an appeal, it further includes the following steps: Provide a case withdrawal process after the user appeals; the case withdrawal process includes: if the case withdrawal conditions are met, return the virtual currency of the reported party after the case is withdrawn.

5. The user chat anti-fraud automatic determination method according to claim 1, characterized in that The method of the user warning in step S2 includes: Through the suspected fraud blacklist stored by the algorithm, query the user number with the key name fraud:blacklist:uid in redis. If it is determined that the user is at risk, give a risk warning at the top of the chat box; The method of storing through the algorithm includes: using a data statistics engine to mark the data information that meets any one or more of the following chat behaviors as a blacklist and cache it in redis for storage; the data information marked as a blacklist includes: Within the past 1 to 15 days: the number of suspected relationships ≥ 3; And, the reward amount for suspected relationships: 99 - 199, The reward income range of the beneficiary within 24 hours is: [42.4, 85], The basic consumption of the beneficiary within 24 hours: <21.3; Or, The reward amount for suspected relationships: ≥200, The reward income of the beneficiary within 48 hours: ≥85, The basic consumption of the beneficiary within 48 hours: <42.5; Or, The reward amount for suspected relationships: ≥400, The reward income of the beneficiary within 48 hours: ≥170, Beneficiary's basic consumption within 48 hours: <85.

6. A user chat anti-fraud automatic determination system, characterized in that Implement the automatic determination method for user chat anti-fraud according to any one of claims 1-5, including: Determination of basic data information subsystem: used to determine whether the basic data information of the two parties of the reported data conforms to the recognition rules based on the anti-fraud database. If it conforms, it enters the determination of the prosecution period subsystem. If it does not conform, it is transferred to manual processing; Determination of the prosecution period subsystem: used to determine whether the in-depth information of the two parties of the reported data conforms to the recognition rules. If it conforms, it enters the determination of supplementary strategy subsystem. If it does not conform, it is transferred to manual processing; Subsystem for storing suspected fraud blacklist: used to set up an automated suspected fraud blacklist, which is regularly stored in the cache database redis for query and user warning.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the automatic determination method for user chat anti-fraud according to any one of claims 1-5.

8. A computer device, the computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the automatic determination method for user chat anti-fraud according to any one of claims 1-5.

Images