Methods, devices, equipment, and computer storage media for identifying abnormal users

Abstract

This application discloses a method, apparatus, device, and computer storage medium for identifying abnormal users. The method includes: acquiring target information of a user, including basic information and call detail record (CDR) information; calculating a first analysis value corresponding to the basic information based on the basic information; calculating a second analysis value corresponding to the CDR information based on the CDR information, the conventional values ​​corresponding to each item in the CDR information, and the weight coefficients corresponding to each item in the CDR information; calculating an output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, and the weight corresponding to the second analysis value; and determining the user as an abnormal user when the output value is greater than a preset output value. According to the embodiments of this application, the accuracy of identifying abnormal users can be improved.

Description

Technical Field

[0001] This application belongs to the field of data analysis technology, and in particular relates to a method, apparatus, device and computer storage medium for identifying abnormal users. Background Technology

[0002] Current methods for identifying abnormal calls do not make good use of the acquired user data, resulting in low identification accuracy.

[0003] For example, in a currently published method for identifying abnormal phone calls, an abnormal phone call identification model is used to obtain the identification result. In this method, regarding the model itself, if the acquired training dataset contains false or inaccurate information, it will cause biases in the model parameters, ultimately affecting the selection of key features. Furthermore, if identification is based solely on existing basic information features from the training dataset, the identification accuracy will be low, as the basic information may have changed.

[0004] For example, in one currently available method for identifying phone numbers, the method obtains the identification result by acquiring user call behavior data and the attribute information of all phone numbers within that data, based on an abnormal call model and an attribute filtering model. However, regarding the phone number's attribute information, if the acquired attribute information is inaccurate, or if the user's phone number is a re-entry into the network, the previously labeled attribute information will change, causing deviations in the model parameters and ultimately affecting the identification accuracy.

[0005] For example, in a currently disclosed method for identifying abnormal phone calls, an abnormal phone call identification model is used to identify abnormal calls from received phone numbers. In this method, if the algorithm parameters of the abnormal phone call identification model are deviated, it will affect the accuracy of subsequent abnormal phone call identification. Furthermore, directly determining that a phone number is abnormal solely based on the abnormal phone call model may result in false positives, and no appropriate processing is performed on the acquired number. Summary of the Invention

[0006] This application provides a method, apparatus, device, and computer storage medium for identifying abnormal users, which can improve the accuracy of abnormal user identification.

[0007] In a first aspect, embodiments of this application provide a method for identifying abnormal users, the method comprising:

[0008] The system acquires the user's target information, which includes basic information and call detail record (CDR) information. The basic information includes the user's age and the number of mobile communication networks the user has registered with. The CDR information includes a first ratio of the number of calls made to different user numbers to the total number of calls, a second ratio of the number of calls with call forwarding to the number of calls with calling party type, a third ratio of the average call duration to the call duration divided by the number of calls made to different user numbers, and a fourth ratio of the number of different call base stations to the total number of calls.

[0009] Calculate the first analysis value corresponding to the basic information based on age and number of mobile communication networks;

[0010] The second analysis value corresponding to the call detail record information is calculated based on the first ratio, the first normal value corresponding to the first ratio, the first weight coefficient corresponding to the first ratio, the second ratio, the second normal value corresponding to the second ratio, the second weight coefficient corresponding to the second ratio, the third ratio, the third normal value corresponding to the third ratio, the third weight coefficient corresponding to the third ratio, the fourth ratio, the fourth normal value corresponding to the fourth ratio, and the fourth weight coefficient corresponding to the fourth ratio.

[0011] Based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, and the weight corresponding to the second analysis value, calculate the output value corresponding to the target information;

[0012] If the output value is greater than the preset output value, the user is identified as an abnormal user.

[0013] Secondly, embodiments of this application provide an abnormal user identification device, the device comprising:

[0014] The acquisition module is used to acquire the user's target information, which includes basic information and call detail record (CDR) information. The basic information includes the user's age and the number of mobile communication networks the user has registered with. The CDR information includes a first ratio of the number of calls made to different user numbers to the total number of calls, a second ratio of the number of calls with call forwarding to the number of calls with calling party type, a third ratio of the average call duration to the call duration divided by the number of calls made to different user numbers, and a fourth ratio of the number of different call base stations to the total number of calls.

[0015] The calculation module is used to calculate the first analysis value corresponding to the basic information based on age and number of mobile communication networks;

[0016] The calculation module is also used to calculate the second analysis value corresponding to the call detail record information based on the first ratio, the first regular value corresponding to the first ratio, the first weight coefficient corresponding to the first ratio, the second ratio, the second regular value corresponding to the second ratio, the second weight coefficient corresponding to the second ratio, the third ratio, the third regular value corresponding to the third ratio, the third weight coefficient corresponding to the third ratio, the fourth ratio, the fourth regular value corresponding to the fourth ratio, and the fourth weight coefficient corresponding to the fourth ratio.

[0017] The calculation module is also used to calculate the output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, and the weight corresponding to the second analysis value.

[0018] The determination module is used to determine that a user is an abnormal user when the output value is greater than the preset output value.

[0019] Thirdly, embodiments of this application provide an identification device for abnormal users, the device including: a processor and a memory storing computer program instructions;

[0020] The processor executes computer program instructions to implement the method described in the first aspect.

[0021] Fourthly, embodiments of this application provide a computer storage medium on which computer program instructions are stored, which, when executed by a processor, implement the method described in the first aspect.

[0022] Fifthly, embodiments of this application provide a computer program product, characterized in that, when the instructions in the computer program product are executed by the processor of an electronic device, the electronic device performs the method described in the first aspect.

[0023] The abnormal user identification method, apparatus, device, and computer storage medium of this application embodiment acquire target information including basic user information and call detail record (CDR) information. The basic information includes the user's age and the number of mobile communication networks the user has registered with. Based on the age and the number of mobile communication networks, a first analysis value corresponding to the basic information is calculated. The CDR information includes a first ratio of the number of calls made to different user numbers to the total number of calls, a second ratio of the number of calls with call forwarding type to the number of calls with calling type, a third ratio of the average call duration to the call duration divided by the number of calls made to different user numbers, and a ratio of the number of different call base stations to the total number of calls. The fourth ratio is calculated based on the first ratio, the first normal value corresponding to the first ratio, the first weight coefficient corresponding to the first ratio, the second ratio, the second normal value corresponding to the second ratio, the second weight coefficient corresponding to the second ratio, the third ratio, the third normal value corresponding to the third ratio, the third weight coefficient corresponding to the third ratio, the fourth ratio, the fourth normal value corresponding to the fourth ratio, and the fourth weight coefficient corresponding to the fourth ratio. The second analysis value is then calculated based on the first analysis value, its corresponding weight, the second analysis value, and its corresponding weight. When the output value is greater than a preset output value, the user is identified as an abnormal user. Thus, by acquiring target information including the user's basic information and call detail record (CDR) information, calculating the first analysis value corresponding to the basic information and the second analysis value corresponding to the CDR information, and then combining the weights corresponding to the first and second analysis values ​​respectively, the output value corresponding to the target information is calculated. When the output value is greater than a preset output value set based on the target information of normal users, the user is identified as an abnormal user, which improves the accuracy of abnormal user identification. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart illustrating the abnormal user identification method provided in the embodiments of this application.

[0026] Figure 2 This is a schematic diagram of the structure of the abnormal user identification device provided in the embodiments of this application.

[0027] Figure 3 This is a schematic diagram of the structure of the abnormal user identification device provided in the embodiments of this application. Detailed Implementation

[0028] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0029] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0030] Current methods for identifying abnormal calls do not make good use of the acquired user data, resulting in low identification accuracy.

[0031] To address the problems of the prior art, embodiments of this application provide a method, apparatus, device, and computer storage medium for identifying abnormal users. The method for identifying abnormal users provided in this application embodiment will be described first.

[0032] Figure 1 A flowchart illustrating an embodiment of the abnormal user identification method provided in this application is shown. Figure 1 As shown, the abnormal user identification method provided in this application embodiment includes the following steps: S101 to S105.

[0033] S101. Obtain the user's target information, which includes basic information and call detail record (CDR) information. The basic information includes the user's age and the number of mobile communication networks the user has registered with. The CDR information includes a first ratio of the number of calls made to different user numbers to the total number of calls, a second ratio of the number of calls with call forwarding to the number of calls with calling party type, a third ratio of the average call duration to the call duration divided by the number of calls made to different user numbers, and a fourth ratio of the number of different call base stations to the total number of calls.

[0034] The target information can be target information obtained by the identification device for abnormal users based on the current Global System for Mobile Communications (GSM).

[0035] Basic information includes, but is not limited to, the user's age, the number of mobile communication networks (GSM networks) the user has registered with, user identifier, user number, and customer identifier. The user identifier can be the user's phone number; the user number can be the user's code in GSM networks; and the customer identifier can be an individual user's ID card number or a company user's business license number. The number of GSM networks refers to the number of GSM networks the user has registered with under the customer identifier.

[0036] Call detail record (CDR) information can be obtained by an anomaly identification device through statistical calculations based on detailed CDR information. Detailed CDR information can also be obtained by the anomaly identification device based on a user identifier, specifying the detailed CDR information corresponding to that user.

[0037] Detailed call detail records (CDRs) include, but are not limited to, the user's phone number, the user's peer number, call type, call date, call time, call duration, cell ID (CID), number of calls, location area code (LAC), and roaming exchange. The user's phone number is the calling number; the peer number is the called number, the number opposite the calling number. Call types include calling, called, and call forwarding.

[0038] The process involves collecting detailed call detail records (CDRs) showing the number of calls made to different user numbers and the total number of calls, calculating the ratio of these two ratios to obtain a first ratio. It also involves collecting the number of calls with call forwarding as the caller ID and the number of calls with calling as the caller ID, calculating the ratio of these two ratios to obtain a second ratio. Finally, it involves collecting the average call duration and dividing the total call duration by the number of calls made to different user numbers, calculating the ratio of this average call duration to the total call duration divided by the total call duration, and finally collecting the number of different call base stations, and calculating the ratio of this number to the total number of calls to obtain a fourth ratio.

[0039] In one embodiment, the target information may also be the abnormal user identification device obtaining the account opening outlets or target information within the area of ​​existing abnormal users based on the current GSM.

[0040] In one embodiment, the target information may also be the target information of new users who have joined the network at the account opening point within a certain period of time, obtained by the abnormal user identification device based on the current GSM.

[0041] S102. Calculate the first analysis value corresponding to the basic information based on age and number of mobile communication networks.

[0042] From the dimensions of user age and the number of GSM networks registered by the user, based on preset thresholds corresponding to the user's age and the number of GSM networks registered, operators can pre-enter values ​​for the user's age and the number of GSM networks registered. The abnormal user identification device then calculates the first analysis value corresponding to the basic information based on the analysis values ​​corresponding to the user's age and the number of GSM networks registered.

[0043] S103. Calculate the second analysis value corresponding to the call detail record information based on the first ratio, the first regular value corresponding to the first ratio, the first weight coefficient corresponding to the first ratio, the second ratio, the second regular value corresponding to the second ratio, the second weight coefficient corresponding to the second ratio, the third ratio, the third regular value corresponding to the third ratio, the third weight coefficient corresponding to the third ratio, the fourth ratio, the fourth regular value corresponding to the fourth ratio, and the fourth weight coefficient corresponding to the fourth ratio.

[0044] The standard values ​​corresponding to the first, second, third, and fourth ratios can be pre-obtained standard values ​​by the abnormal user identification device based on the known call detail records of normal users. The weight coefficients corresponding to the first, second, third, and fourth ratios can be preset weight coefficients by the abnormal user identification device based on existing abnormal user data. The sum of the weight coefficients corresponding to the first, second, third, and fourth ratios can be set to 1.

[0045] S104. Calculate the output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, and the weight corresponding to the second analysis value.

[0046] The output value is calculated as follows:

[0047]

[0048] Where x represents the output value corresponding to the target information; a1 represents the analysis value corresponding to the user's age; a2 represents the analysis value corresponding to the number of GSM networks registered by the user; b1 represents the first ratio; c1 represents the first regular value corresponding to the first ratio; d1 represents the first weight coefficient corresponding to the first ratio; b2 represents the second ratio; c2 represents the second regular value corresponding to the second ratio; d2 represents the second weight coefficient corresponding to the second ratio; b3 represents the third ratio; c3 represents the third regular value corresponding to the third ratio; d3 represents the third weight coefficient corresponding to the third ratio; b4 represents the fourth ratio; c4 represents the fourth regular value corresponding to the fourth ratio; d4 represents the fourth weight coefficient corresponding to the fourth ratio; s1 represents the weight coefficient corresponding to the first analysis value; and s2 represents the weight coefficient corresponding to the second analysis value.

[0049] The weights s1 corresponding to the first analysis value and s2 corresponding to the second analysis value can be assigned by the abnormal user identification device based on existing characteristic information that distinguishes abnormal users from normal users, combined with relevant conditions.

[0050] Optionally, in one embodiment, s1+s2=1, which makes it easier to obtain the comparison results between abnormal users and normal users, making the obtained output value x more accurate.

[0051] S105. When the output value is greater than the preset output value, the user is determined to be an abnormal user.

[0052] The preset output value can be the output value of a known normal user obtained by the abnormal user identification device, and can be preset to a normal value. Because the absolute value of the numerator of the abnormal user parameter is relatively large, if the calculated output value is greater than the preset output value, the user can be identified as an abnormal user. In this case, the user's user number information can be output.

[0053] The above is a specific implementation of the abnormal user identification method provided in this application embodiment. It obtains target information including basic user information and call detail record (CDR) information. The basic information includes the user's age and the number of mobile communication networks the user has registered with. Based on the age and the number of mobile communication networks, a first analysis value corresponding to the basic information is calculated. The CDR information includes a first ratio of the number of calls made to different user numbers to the total number of calls; a second ratio of the number of calls with call forwarding type to the number of calls with calling type; a third ratio of the average call duration to the call duration divided by the number of calls made to different user numbers; and a fourth ratio of the number of different call base stations to the total number of calls. Based on the first ratio and the first... The second analysis value corresponding to the call detail record (CDR) information is calculated using the first normal value corresponding to the first ratio, the first weight coefficient corresponding to the first ratio, the second ratio, the second normal value corresponding to the second ratio, the second weight coefficient corresponding to the second ratio, the third ratio, the third normal value corresponding to the third ratio, the third weight coefficient corresponding to the third ratio, the fourth ratio, the fourth normal value corresponding to the fourth ratio, and the fourth weight coefficient corresponding to the fourth ratio. Based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, and the weight corresponding to the second analysis value, the output value corresponding to the target information is calculated. When the output value is greater than the preset output value, the user is determined to be an abnormal user.

[0054] In this way, by acquiring target information including the user's basic information and call detail record (CDR) information, calculating the first analysis value corresponding to the basic information and the second analysis value corresponding to the CDR information, and then combining the weights corresponding to the first and second analysis values ​​respectively, the output value corresponding to the target information is calculated. When the output value is greater than the preset output value set according to the target information of normal users, the user is determined to be an abnormal user. This can improve the accuracy of judging abnormal users, thereby reducing the identification time and improving the identification efficiency, thus reducing user complaints and improving user satisfaction.

[0055] In some embodiments of this application, the first analysis value includes a first sub-analysis value corresponding to age and a second sub-analysis value corresponding to the number of mobile communication networks. S102 may also include the following step: S1021.

[0056] S1021: Calculate the sum of the first sub-analysis value and the second analysis value to obtain the first analysis value;

[0057] Among them, when the age is greater than the first preset age threshold or less than the second preset age threshold, the first sub-analysis value is the first target value, and the first target value is a value greater than zero;

[0058] When the age is less than the first preset age threshold and greater than the second preset age threshold, the first sub-analysis value is equal to zero.

[0059] When the number of mobile communication networks exceeds a preset threshold, the second sub-analysis value is the second target value, which is a value greater than zero.

[0060] When the number of mobile communication networks is not greater than a preset threshold, the second sub-analysis value is equal to zero.

[0061] The first preset age threshold, the second preset age threshold, and the preset quantity threshold can be conventional values ​​preset by the abnormal user identification device based on the values ​​of known normal users.

[0062] For example, the first preset age threshold is set to 60, and the second preset age threshold is set to 18.

[0063] If the user's age is greater than 60 or less than 18, the first sub-analysis value, i.e., the analysis value a1 corresponding to the user's age, is assigned the first target value, which is a value greater than zero, i.e., a1>0; if the user's age is greater than 18 and less than 60, the first sub-analysis value, i.e., the analysis value a1 corresponding to the user's age, is assigned the value equal to zero, i.e., a1=0.

[0064] For example, set the preset quantity threshold to 2.

[0065] If the number of GSM networks registered by the user is greater than 2, then the second sub-analysis value, i.e., the analysis value a2 corresponding to the number of GSM networks registered by the user, is assigned the second target value, which is a value greater than zero, i.e., a2>0; if the number of GSM networks registered by the user is not greater than 2, then the second sub-analysis value, i.e., the analysis value a2 corresponding to the number of GSM networks registered by the user, is assigned the value equal to zero, i.e., a2=0.

[0066] The final result of the first analysis value is the sum of the first sub-analytical value and the second analysis value, i.e., a1 + a2.

[0067] By adding age and number of mobile communication networks as judgment criteria, the analysis process for determining whether a user is abnormal can more accurately assign analysis values ​​corresponding to the user's age and the number of GSM networks the user has registered with, calculate the first analysis value corresponding to the basic information, and adjust the output value, thereby further improving the accuracy of abnormal user identification.

[0068] In some embodiments of this application, S104 may further include the following step: S1041.

[0069] S1041: Calculate the output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, the weight corresponding to the second analysis value, and the preset feedback value.

[0070] The preset feedback value can be the weight of the user feedback information at the other end of the call. If the identification device for an abnormal user does not receive user feedback, the preset feedback value can be set to a fixed value; if the identification device for an abnormal user receives user feedback, the weight of the preset feedback value can be increased based on the user feedback.

[0071] At this point, the output value is calculated as follows:

[0072]

[0073] Where x represents the output value corresponding to the target information; a1 represents the analysis value corresponding to the user's age; a2 represents the analysis value corresponding to the number of GSM networks registered by the user; b1 represents the first ratio; c1 represents the first regular value corresponding to the first ratio; d1 represents the first weight coefficient corresponding to the first ratio; b2 represents the second ratio; c2 represents the second regular value corresponding to the second ratio; d2 represents the second weight coefficient corresponding to the second ratio; b3 represents the third ratio; c3 represents the third regular value corresponding to the third ratio; d3 represents the third weight coefficient corresponding to the third ratio; b4 represents the fourth ratio; c4 represents the fourth regular value corresponding to the fourth ratio; d4 represents the fourth weight coefficient corresponding to the fourth ratio; s1 represents the weight coefficient corresponding to the first analysis value; s2 represents the weight coefficient corresponding to the second analysis value; and e represents the preset feedback value.

[0074] By adding a preset feedback value based on user feedback, the weight of the user feedback information from the other end of the call is added to the analysis process to determine whether a user is abnormal. This adjusts the output value, and then a comparative analysis is performed to identify abnormal users, further improving the accuracy of abnormal user identification.

[0075] In some embodiments of this application, the method may further include the following step: S106.

[0076] S106: When an abnormal user's device sends a call request to the called device, a preset message is sent to the called device for display on the called device to remind the user of the called device that the abnormal user is an abnormal user.

[0077] If the current user is determined to be an abnormal user, when the abnormal user's device sends a call request to the called device, a warning message, i.e. a preset message, is triggered. The abnormal user identification device will send the preset message to the called device to remind the user of the called device that the abnormal user is an abnormal user.

[0078] By sending a warning message to the called device when an abnormal user's device sends a call request, the called device can determine whether the calling device is an abnormal user's device, thus improving the user experience.

[0079] In some embodiments of this application, the method may further include the following step: S107.

[0080] S107: After the call ends, collect the feedback information received by the user's peer device from the abnormal user based on preset information.

[0081] S104 may also include the following step: S1042.

[0082] S1042: Calculate the output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, the weight corresponding to the second analysis value, and the preset feedback value corresponding to the feedback information.

[0083] After the call between the abnormal user and the peer user ends, the abnormal user's identification device will initiate feedback collection and send preset information to the peer user's device. The peer user's device will then receive the feedback information entered by the user based on the preset information.

[0084] When the device for identifying abnormal users receives feedback from the user, that is, when the device for identifying abnormal users receives feedback information, it can increase the weight of the preset feedback value based on the user's feedback.

[0085] In one embodiment, the feedback information may be a feedback value entered by the user based on preset information and received by the peer user device of the abnormal user. Each number corresponds to a preset feedback value e.

[0086] To avoid misjudgment, the preset feedback value can be set to a negative value, i.e., e < 0, as a supplementary value for calculating the output value x.

[0087] At this point, if the identification device for the abnormal user does not receive feedback from the user, the preset feedback value can be set to a fixed value, i.e., a fixed value of 0.

[0088] By increasing the more accurate preset feedback value corresponding to the user's feedback information, the specific weight of the user's feedback information from the other end of the call is added to the analysis process to determine whether the user is abnormal. The output value is then adjusted and compared to determine the abnormal user, thus further improving the accuracy of abnormal user identification.

[0089] In some embodiments of this application, the call detail record information also includes target user type identification information. Before S101, the method may also include the following steps: S108 to S109.

[0090] S108: Obtain the user's initial data, which includes the user's basic information and call detail records.

[0091] S109: Select data including target user type identification information from the initial data as target information.

[0092] The device for identifying anomalous users acquires initial user data based on GSM. This initial data includes both target user type identification information and non-target user type identification information. The non-target user type identification information consists of data from legitimate users in industries such as delivery drivers and / or food delivery workers.

[0093] The device for identifying abnormal users can obtain data identifying non-target user types by collecting third-party marking information after a user joins the network. This third-party marking information includes registration information for group members.

[0094] In the initial data, all data except for the target user type identification information can be the target user type identification information.

[0095] By selecting data containing target user type identification information from the initial data as the target information, and removing data of normal users in industries such as couriers and / or food delivery workers from the initial data, data cleaning of the initial data is achieved, further improving the accuracy of abnormal user identification.

[0096] Based on the abnormal user identification method provided in the above embodiments, this application also provides specific implementations of an abnormal user identification device. Please refer to the following embodiments.

[0097] First see Figure 2 The abnormal user identification device provided in this application embodiment includes the following modules:

[0098] The acquisition module 201 is used to acquire the user's target information, which includes basic information and call detail record (CDR) information. The basic information includes the user's age and the number of mobile communication networks the user has registered with. The CDR information includes a first ratio of the number of calls made to different user numbers to the total number of calls, a second ratio of the number of calls with call forwarding to the number of calls with calling party type, a third ratio of the average call duration to the call duration divided by the number of calls made to different user numbers, and a fourth ratio of the number of different call base stations to the total number of calls.

[0099] Calculation module 202 is used to calculate the first analysis value corresponding to the basic information based on age and number of mobile communication networks;

[0100] The calculation module 202 is also used to calculate the second analysis value corresponding to the call detail record information based on the first ratio, the first regular value corresponding to the first ratio, the first weight coefficient corresponding to the first ratio, the second ratio, the second regular value corresponding to the second ratio, the second weight coefficient corresponding to the second ratio, the third ratio, the third regular value corresponding to the third ratio, the third weight coefficient corresponding to the third ratio, the fourth ratio, the fourth regular value corresponding to the fourth ratio, and the fourth weight coefficient corresponding to the fourth ratio.

[0101] The calculation module 202 is also used to calculate the output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, and the weight corresponding to the second analysis value;

[0102] The determination module 203 is used to determine that a user is an abnormal user when the output value is greater than the preset output value.

[0103] The acquisition module 201 acquires target information including the user's basic information and call detail record (CDR) information; the calculation module 202 calculates the first analysis value corresponding to the basic information based on the user's age and the number of mobile communication networks the user has registered with; the CDR information includes a first ratio of the number of calls made to different user numbers to the total number of calls, a second ratio of the number of calls with call forwarding to the number of calls with calling party type, a third ratio of the average call duration to the call duration divided by the number of calls made to different user numbers, and a fourth ratio of the number of different call base stations to the total number of calls; the calculation module 202 calculates the target information based on the first ratio, the first analysis value, the second analysis value, the third analysis value, the fourth analysis value, the fifth analysis value, the sixth analysis value, the seventh analysis value, the eighth analysis value, the ninth analysis value, the tenth ... The first ratio corresponds to a first normal value, the first ratio corresponds to a first weight coefficient, the second ratio, the second ratio corresponds to a second normal value, the second ratio corresponds to a second weight coefficient, the third ratio, the third ratio corresponds to a third normal value, the third ratio corresponds to a third weight coefficient, the fourth ratio, the fourth ratio corresponds to a fourth normal value, and the fourth ratio corresponds to a fourth weight coefficient. The calculation module 202 calculates the output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, and the weight corresponding to the second analysis value. When the output value is greater than a preset output value, the determination module 203 determines the user as an abnormal user. Thus, by acquiring target information including the user's basic information and call detail record information, calculating the first analysis value corresponding to the basic information and the second analysis value corresponding to the call detail record information, and then combining the weights corresponding to the first and second analysis values ​​respectively, the output value corresponding to the target information is calculated. When the output value is greater than a preset output value set based on the target information of normal users, the user is determined to be an abnormal user. This improves the accuracy of abnormal user judgment, thereby reducing identification time and improving identification efficiency, ultimately reducing user complaints and increasing user satisfaction.

[0104] In some embodiments of this application, the above-mentioned calculation module 202 may further include: a calculation unit.

[0105] A calculation unit is used to calculate the sum of the first sub-analysis value and the second analysis value to obtain the first analysis value;

[0106] Among them, when the age is greater than the first preset age threshold or less than the second preset age threshold, the first sub-analysis value is the first target value, and the first target value is a value greater than zero;

[0107] When the age is less than the first preset age threshold and greater than the second preset age threshold, the first sub-analysis value is equal to zero.

[0108] When the number of mobile communication networks exceeds a preset threshold, the second sub-analysis value is the second target value, which is a value greater than zero.

[0109] When the number of mobile communication networks is not greater than a preset threshold, the second sub-analysis value is equal to zero.

[0110] By adding age and number of mobile communication networks as judgment criteria, the analysis process for determining whether a user is abnormal can more accurately assign analysis values ​​corresponding to the user's age and the number of GSM networks the user has registered with, calculate the first analysis value corresponding to the basic information, and adjust the output value, thereby further improving the accuracy of abnormal user identification.

[0111] In some embodiments of this application, the above-mentioned calculation unit can also be used to calculate the output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, the weight corresponding to the second analysis value, and the preset feedback value.

[0112] By adding a preset feedback value based on user feedback, the weight of the user feedback information from the other end of the call is added to the analysis process to determine whether a user is abnormal. This adjusts the output value, and then a comparative analysis is performed to identify abnormal users, further improving the accuracy of abnormal user identification.

[0113] In some embodiments of this application, the apparatus may further include a transmitting module 204.

[0114] The sending module 204 is used to send preset information to the called device when the device of an abnormal user sends a call request to the called device, so as to display the preset information on the called device to remind the user of the called device that the abnormal user is an abnormal user.

[0115] By sending a warning message to the called device when an abnormal user's device sends a call request, the called device can determine whether the calling device is an abnormal user's device, thus improving the user experience.

[0116] In some embodiments of this application, the device may further include a data acquisition module 205.

[0117] The data collection module 205 is used to collect feedback information received by the peer user device of the abnormal user based on preset information after the call ends.

[0118] The aforementioned calculation unit can also be used to calculate the output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, the weight corresponding to the second analysis value, and the preset feedback value corresponding to the feedback information.

[0119] By increasing the more accurate preset feedback value corresponding to the user's feedback information, the specific weight of the user's feedback information from the other end of the call is added to the analysis process to determine whether the user is abnormal. The output value is then adjusted and compared to determine the abnormal user, thus further improving the accuracy of abnormal user identification.

[0120] In some embodiments of this application, the call detail record information also includes target user type identification information, and the device may further include: selection module 206.

[0121] The aforementioned acquisition module 201 is also used to acquire the user's initial data, which includes the user's basic information and call detail record information.

[0122] Selection module 206 is used to select data including target user type identification information from the initial data as target information.

[0123] By selecting data containing target user type identification information from the initial data as the target information, and removing data of normal users in industries such as couriers and / or food delivery workers from the initial data, data cleaning of the initial data is achieved, further improving the accuracy of abnormal user identification.

[0124] Figure 2 The abnormal user identification device shown can achieve Figure 1 The steps of the abnormal user identification method shown are simplified and will not be elaborated here.

[0125] Figure 3 A schematic diagram of the hardware structure of the abnormal user identification device provided in an embodiment of this application is shown.

[0126] The device for identifying abnormal users may include a processor 301 and a memory 302 storing computer program instructions.

[0127] Specifically, the processor 301 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0128] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 302 is non-volatile solid-state memory.

[0129] In certain embodiments, memory 302 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, memory 302 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method of the first aspect.

[0130] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any of the abnormal user identification methods in the above embodiments.

[0131] In one example, the device for identifying abnormal users may further include a communication interface 303 and a bus 310. For example, Figure 3 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.

[0132] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0133] Bus 310 includes hardware, software, or both, that couples components of an identification device for an abnormal user together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0134] Furthermore, in conjunction with the abnormal user identification methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the abnormal user identification methods in the above embodiments.

[0135] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0136] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0137] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0138] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0139] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for identifying abnormal users, characterized in that, The method includes: The system acquires user target information, which includes basic information and call detail record (CDR) information. The basic information includes the user's age and the number of mobile communication networks the user has registered with. The CDR information includes a first ratio of the number of calls made to different user numbers to the total number of calls, a second ratio of the number of calls with call forwarding to the number of calls with calling party type, a third ratio of the average call duration to the call duration divided by the number of calls made to different user numbers, and a fourth ratio of the number of different call base stations to the total number of calls. Calculate the first analysis value corresponding to the basic information based on the age and the number of mobile communication networks; The second analysis value corresponding to the call detail record information is calculated based on the first ratio, the first normal value corresponding to the first ratio, the first weight coefficient corresponding to the first ratio, the second ratio, the second normal value corresponding to the second ratio, the second weight coefficient corresponding to the second ratio, the third ratio, the third normal value corresponding to the third ratio, the third weight coefficient corresponding to the third ratio, the fourth ratio, the fourth normal value corresponding to the fourth ratio, and the fourth weight coefficient corresponding to the fourth ratio. Based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, and the weight corresponding to the second analysis value, calculate the output value corresponding to the target information; If the output value is greater than the preset output value, the user is determined to be an abnormal user.

2. The method according to claim 1, characterized in that, The first analysis value includes a first sub-analysis value corresponding to the age and a second sub-analysis value corresponding to the number of mobile communication networks; The step of calculating the first analysis value corresponding to the basic information based on the age and the number of mobile communication networks includes: The sum of the first sub-analysis value and the second analysis value is calculated to obtain the first analysis value; Wherein, when the age is greater than a first preset age threshold or less than a second preset age threshold, the first sub-analysis value is a first target value, and the first target value is a value greater than zero; When the age is less than a first preset age threshold and greater than a second preset age threshold, the first sub-analysis value is equal to zero. When the number of mobile communication networks exceeds a preset threshold, the second sub-analysis value is the second target value, and the second target value is a value greater than zero. When the number of mobile communication networks is not greater than a preset threshold, the second sub-analysis value is equal to zero.

3. The method according to claim 1, characterized in that, The step of calculating the output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, and the weight corresponding to the second analysis value includes: The output value corresponding to the target information is calculated based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, the weight corresponding to the second analysis value, and the preset feedback value.

4. The method according to any one of claims 1 to 3, characterized in that, After determining that the user is an abnormal user when the output value is greater than a preset output value, the method further includes: When the device of the abnormal user sends a call request to the called device, a preset message is sent to the called device for display on the called device to remind the user of the called device that the abnormal user is an abnormal user.

5. The method according to claim 4, characterized in that, The method further includes: After the call ends, the feedback information received by the abnormal user's peer device based on the preset information is collected; The step of calculating the output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, and the weight corresponding to the second analysis value further includes: The output value corresponding to the target information is calculated based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, the weight corresponding to the second analysis value, and the preset feedback value corresponding to the feedback information.

6. The method according to claim 1, characterized in that, The call detail record (CDR) information also includes target user type identification information; Before acquiring the target information, the method further includes: Obtain the user's initial data, which includes the user's basic information and call detail records (CDRs). Select data including the target user type identification information from the initial data as the target information.

7. A device for identifying abnormal users, characterized in that, The device includes: The acquisition module is used to acquire the user's target information, which includes basic information and call detail record (CDR) information. The basic information includes the user's age and the number of mobile communication networks the user has registered with. The CDR information includes a first ratio of the number of calls made to different user numbers to the total number of calls, a second ratio of the number of calls with call forwarding to the number of calls with calling party status, a third ratio of the average call duration to the call duration divided by the number of calls made to different user numbers, and a fourth ratio of the number of different call base stations to the total number of calls. The calculation module is used to calculate a first analysis value corresponding to the basic information based on the age and the number of mobile communication networks; The calculation module is further configured to calculate the second analysis value corresponding to the call detail record information based on the first ratio, the first regular value corresponding to the first ratio, the first weight coefficient corresponding to the first ratio, the second ratio, the second regular value corresponding to the second ratio, the second weight coefficient corresponding to the second ratio, the third ratio, the third regular value corresponding to the third ratio, the third weight coefficient corresponding to the third ratio, the fourth ratio, the fourth regular value corresponding to the fourth ratio, and the fourth weight coefficient corresponding to the fourth ratio. The calculation module is also used to calculate the output value corresponding to the target information based on the first analysis value, the weight corresponding to the first analysis value, the second analysis value, and the weight corresponding to the second analysis value; The determination module is used to determine that the user is an abnormal user when the output value is greater than a preset output value.

8. A device for identifying abnormal users, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device causes the electronic device to perform the method as described in any one of claims 1-6.

Images