Harassment fraud phone identification method, device and equipment and storage medium

Abstract

The application discloses a harassment and fraud phone identification method and device, equipment and storage medium, relates to the technical field of data processing, and is used for improving the identification efficiency and accuracy of harassment and fraud phone. Including: based on the basic information of the target phone identifier, a plurality of basic parameters corresponding to the target phone identifier are determined, the plurality of basic parameters include at least one of the following: caller proportion, caller concentration, called concentration, average call duration and daily average traffic, the caller proportion is used to indicate the ratio of the calling times of the target phone identifier to the total calling times, and the caller concentration is used to indicate the proportion of the first type of number in the calling number of the target phone identifier; according to the plurality of basic parameters and the weight value corresponding to each basic parameter, the target parameter corresponding to the target phone identifier is determined; when it is determined that the target parameter is greater than the target threshold value, the target phone identifier is determined as the identifier of the harassment and fraud phone.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, device, and storage medium for identifying harassing and fraudulent phone calls. Background Technology

[0002] With the rapid development of mobile communication technology, the number of mobile communication service users is constantly increasing, and problems such as nuisance calls and telecommunications fraud are becoming increasingly serious. Among related technologies, the identification of nuisance and fraudulent calls mainly involves detecting these calls (such as multi-dimensional clustering fraud monitoring methods and call detection methods based on intent understanding technology), adding detected nuisance and fraudulent calls to a blacklist, and processing them accordingly, thereby combating nuisance and fraudulent behavior.

[0003] However, due to the complexity of harassing and fraudulent calls and the diverse characteristics of such behavior, the aforementioned methods often result in a large number of ordinary users being falsely identified as harassing or fraudulent users. This negatively impacts the normal user experience and leads to numerous user complaints. Current technologies typically involve secondary verification of these complaints by human customer service personnel. Users confirmed as ordinary users are then added to a whitelist to prevent them from being flagged as harassing or fraudulent calls again. Therefore, the efficiency and accuracy of identifying harassing and fraudulent calls are relatively low. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for identifying harassing and fraudulent calls, which improves the efficiency and accuracy of identifying such calls.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, a method for identifying harassing and fraudulent phone calls is provided. This method includes: determining multiple basic parameters corresponding to the target phone identifier based on its basic information. These basic parameters include at least one of the following: caller ID ratio, caller ID concentration, called party concentration, average call duration, and average daily data usage. The caller ID ratio indicates the ratio of the number of calls made by the target phone identifier to the total number of calls. The caller ID concentration indicates the proportion of first-type numbers among the caller ID numbers of the target phone identifier, where the number of calls made by the target phone identifier is greater than a first preset number. The called party concentration indicates the proportion of second-type numbers among the called party numbers of the target phone identifier, where the number of calls made by the target phone identifier is greater than a second preset number. Based on these multiple basic parameters and the weight value corresponding to each basic parameter, a target parameter corresponding to the target phone identifier is determined. When the determined target parameter is greater than a target threshold, the target phone identifier is identified as a harassing and fraudulent phone call.

[0007] In one design, the target parameters corresponding to the target phone identifier are determined based on multiple basic parameters and the weight value corresponding to each basic parameter. These parameters include: determining a first parameter corresponding to the calling percentage based on the calling percentage and a first threshold; determining a second parameter corresponding to the calling concentration based on the calling concentration and a second threshold; determining a third parameter corresponding to the called concentration based on the called concentration and a third threshold; determining a fourth parameter corresponding to the average call duration based on the average call duration and a fourth threshold; and determining a fifth parameter corresponding to the average daily traffic based on the average daily traffic and a fifth threshold. Finally, the target parameters corresponding to the target phone identifier are determined based on the first parameter and the first weight value corresponding to the calling percentage, the second weight value corresponding to the calling concentration, the third weight value corresponding to the called concentration, the fourth weight value corresponding to the average call duration, and the fifth weight value corresponding to the average daily traffic.

[0008] In one design, before identifying a target phone number as a harassing or fraudulent caller when the target parameter is greater than the target threshold, the method further includes: obtaining the number of target complaint tickets and the total number of complaint tickets in the target time period, and determining the target threshold based on the number of target complaint tickets and the total number of complaint tickets, wherein the number of target complaint tickets is the number of complaint tickets generated when the phone number is identified as a harassing or fraudulent caller.

[0009] In one design, a target threshold is determined based on the target number of complaint work orders and the total number of complaint work orders. This includes: determining a target ratio of the target number of complaint work orders to the total number of complaint work orders; when the target ratio is greater than the historical ratio and the difference between the target ratio and the historical ratio is greater than a sixth threshold, the historical threshold is decreased to obtain the target threshold, where the historical ratio is the ratio of the historical number of target complaint work orders to the historical total number of complaint work orders in the historical time period before the target time period; when the target ratio is less than the historical ratio and the difference between the historical ratio and the target ratio is greater than a sixth threshold, the historical threshold is increased to obtain the target threshold.

[0010] In one design, when the target parameter is determined to be greater than the target threshold, the target phone number is identified as a harassing or fraudulent phone number. Specifically, when the target parameter is determined to be greater than the target threshold and the target phone number is not a phone number in the whitelist, authentication information is sent to the target phone number. The whitelist contains multiple phone numbers used to identify non-harassing or fraudulent phone numbers. When the target phone number is not authenticated, the target phone number is identified as a harassing or fraudulent phone number.

[0011] Secondly, a device for identifying harassing and fraudulent phone calls is provided. The device includes: a determining unit; the determining unit is configured to determine multiple basic parameters corresponding to the target phone identifier based on basic information of the target phone identifier, the multiple basic parameters including at least one of the following: caller share, caller concentration, called party concentration, average call duration, and average daily data traffic; the caller share indicates the ratio of the number of calls made by the target phone identifier to the total number of calls; the caller concentration indicates the proportion of first-type numbers among the caller numbers of the target phone identifier, the first-type numbers being numbers whose caller counts exceed a first preset number; the called party concentration indicates the proportion of second-type numbers among the called party numbers of the target phone identifier, the second-type numbers being numbers whose called party counts exceed a second preset number; the determining unit is configured to determine a target parameter corresponding to the target phone identifier based on the multiple basic parameters and the weight value corresponding to each basic parameter; the determining unit is configured to determine that the target phone identifier is an identifier for harassing and fraudulent phone calls when the determined target parameter is greater than a target threshold.

[0012] In one design, a determining unit is used to determine a first parameter corresponding to the calling percentage based on the calling percentage and a first threshold; a second parameter corresponding to the calling concentration based on the calling concentration and a second threshold; a third parameter corresponding to the called concentration based on the called concentration and a third threshold; a fourth parameter corresponding to the average call duration based on the average call duration and a fourth threshold; and a fifth parameter corresponding to the average daily traffic based on the average daily traffic and a fifth threshold. The determining unit is also used to determine the target parameter corresponding to the target telephone identifier based on the first parameter and a first weight value corresponding to the calling percentage, the second parameter and a second weight value corresponding to the calling concentration, the third parameter and a third weight value corresponding to the called concentration, the fourth parameter and an average call duration, and the fifth parameter and an average daily traffic.

[0013] In one design, the device further includes: an acquisition unit; the acquisition unit is used to acquire the target number of complaint work orders and the total number of complaint work orders in a target time period; and a determination unit is used to determine a target threshold based on the target number of complaint work orders and the total number of complaint work orders, wherein the target number of complaint work orders is the number of complaint work orders generated when a telephone identifier is identified as a harassing or fraudulent telephone number.

[0014] In one design, the device further includes: a processing unit; a determining unit, configured to determine a target ratio of the number of target complaint work orders to the total number of complaint work orders; a processing unit, configured to decrease the historical threshold to obtain the target threshold when the determined target ratio is greater than the historical ratio and the difference between the target ratio and the historical ratio is greater than a sixth threshold, wherein the historical ratio is the ratio of the number of historical target complaint work orders to the total number of historical complaint work orders in the historical time period before the target time period; and a processing unit, configured to increase the historical threshold to obtain the target threshold when the determined target ratio is less than the historical ratio and the difference between the historical ratio and the target ratio is greater than a sixth threshold.

[0015] In one design, the device further includes: a processing unit; the processing unit is configured to send authentication information to the target phone identifier when the target parameter is determined to be greater than the target threshold and the target phone identifier is not a phone identifier in the whitelist, wherein the whitelist contains multiple phone identifiers for identifying non-harassing fraudulent phone numbers; and a determining unit is configured to determine the target phone identifier as an identifier for harassing fraudulent phone numbers when the target phone identifier has not been authenticated.

[0016] Thirdly, an electronic device is provided, comprising: a processor and a memory; wherein the memory is used to store one or more programs, the one or more programs including computer execution instructions, and when the electronic device is running, the processor executes the computer execution instructions stored in the memory to cause the electronic device to perform a harassment and fraud call identification method as described in the first aspect.

[0017] Fourthly, a computer-readable storage medium is provided for storing one or more programs, the one or more programs including instructions that, when executed by a computer, cause the computer to perform a method for identifying harassing and fraudulent phone calls as described in the first aspect.

[0018] This application provides a method for identifying harassing and fraudulent phone calls, applied to scenarios involving the identification of such calls. First, based on the basic information of the target phone identifier, multiple basic parameters are determined, including at least one of the following: caller ID ratio, caller concentration, called party concentration, average call duration, and daily traffic volume. Further, based on these basic parameters and their corresponding weight values, a target parameter is determined for the target phone identifier. When the target parameter is determined to be greater than a target threshold, the target phone identifier is identified as a harassing or fraudulent call. Through this method, the target parameter corresponding to the phone identifier can be obtained from multiple dimensions based on multiple basic parameters, including caller ID ratio, caller concentration, called party concentration, average call duration, and daily traffic volume. Then, based on the relationship between the target parameter and the target threshold, it can be determined whether the phone identifier is a harassing or fraudulent call, thereby improving the efficiency and accuracy of identifying harassing and fraudulent calls. Attached Figure Description

[0019] Figure 1 A schematic diagram of a harassment and fraud call identification system provided for embodiments of this application. Figure 1 ;

[0020] Figure 2 A flowchart illustrating a method for identifying harassing and fraudulent phone calls provided as an embodiment of this application. Figure 1 ;

[0021] Figure 3 A flowchart illustrating a method for identifying harassing and fraudulent phone calls provided as an embodiment of this application. Figure 2 ;

[0022] Figure 4 A flowchart illustrating a method for identifying harassing and fraudulent phone calls provided as an embodiment of this application. Figure 3 ;

[0023] Figure 5 A flowchart illustrating a method for identifying harassing and fraudulent phone calls provided as an embodiment of this application. Figure 4 ;

[0024] Figure 6 A flowchart illustrating a method for identifying harassing and fraudulent phone calls provided as an embodiment of this application. Figure 5 ;

[0025] Figure 7 A schematic diagram of a harassment and fraud call identification system provided for embodiments of this application. Figure 2 ;

[0026] Figure 8 A flowchart illustrating a method for identifying harassing and fraudulent phone calls provided as an embodiment of this application. Figure 6 ;

[0027] Figure 9 A schematic diagram of a harassment and fraud call identification device provided for an embodiment of this application;

[0028] Figure 10 This is a schematic diagram of an electronic device structure provided for an embodiment of this application. Detailed Implementation

[0029] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0030] In the description of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" and "multiple" refer to two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0031] Currently, due to the increasing severity of information security issues such as nuisance calls and telecommunications fraud, a large number of users are being deceived or harassed by advertising and marketing calls, resulting in significant economic losses. Related technologies primarily address this by setting model dimensions based on the characteristics of nuisance and fraudulent calls, assigning weight values ​​to each dimension, and then using preset thresholds to determine whether a number is a nuisance or fraudulent call. Identified nuisance and fraudulent calls are processed accordingly, and complaints arising from misclassification are subject to secondary manual verification for further processing.

[0032] In the above process, multiple dimensions of parameter information and the weight value of each dimension are mainly used to summarize the information. The judgment is made according to the threshold of the set model. For complaints caused by model misjudgment, only targeted processing is carried out, which can easily lead to a large number of user complaints, secondary complaints and escalation complaints.

[0033] The method for identifying harassing and fraudulent calls provided in this application embodiment can be applied to harassing and fraudulent call identification systems. Figure 1 A schematic diagram of one structure of this harassment and fraudulent call identification system is shown. Figure 1 As shown, the harassment and fraud call identification system 20 includes: an electronic device 21 and a server 22. The electronic device 21 is connected to the server 22.

[0034] The harassment and fraud call identification system 20 can be used in the Internet of Things. The harassment and fraud call identification system 20 may include hardware such as multiple central processing units (CPUs), multiple memories, and storage devices storing multiple operating systems.

[0035] Electronic device 21 can be used in the Internet of Things to process data. For example, electronic device 21 can interact with server 22 to obtain basic information of the target phone number identifier and determine whether the target phone number identifier is a harassing or fraudulent phone number based on the basic information of the target phone number identifier.

[0036] Server 22 is used to store data. For example, server 22 can be a server that stores basic information of the target telephone identifier, and can provide the electronic device 21 with the basic information required to determine the basic parameters.

[0037] The following describes a method for identifying harassing and fraudulent phone calls provided by an embodiment of this application, with reference to the accompanying drawings.

[0038] like Figure 2 As shown in the figure, an embodiment of this application provides a method for identifying harassing and fraudulent phone calls, including steps S201-S203:

[0039] S201. Based on the basic information of the target telephone identifier, determine multiple basic parameters corresponding to the target telephone identifier.

[0040] The basic parameters include at least one of the following: caller share, caller concentration, called party concentration, average call duration, and average daily traffic. The caller share indicates the ratio of the number of calls made by the target phone number to the total number of calls. The caller concentration indicates the proportion of the first type of numbers among the caller numbers of the target phone number. The first type of numbers are the numbers whose caller counts are greater than a first preset number. The called party concentration indicates the proportion of the second type of numbers among the called numbers of the target phone number. The second type of numbers are the numbers whose called counts are greater than a second preset number.

[0041] Optionally, the basic information of the target phone number identifier can be obtained through the operator's business segmentation system.

[0042] Optionally, the basic information of the target phone identifier may include at least one of the following: total number of calls, number of outgoing calls, number of numbers with more than one preset number of outgoing calls, total number of outgoing numbers, number of incoming calls with more than one preset number of incoming calls, total number of incoming numbers, average call duration, and average daily data usage.

[0043] Optionally, the basic information of the target phone number may also include the account opening date, phone number, average daily number of SMS messages, and whether it has been blacklisted.

[0044] Optionally, the basic parameters can be determined according to specific usage needs. For example, the basic parameters may also include the average number of SMS messages per day.

[0045] Optionally, the first preset number of times can be set according to specific usage needs. For example, the first preset number of times can be 2, in which case the first type of number refers to the number of outgoing calls of the target phone number greater than 2; the second preset number of times can be set according to specific usage needs. For example, the second preset number of times can be 2, in which case the second type of number refers to the number of incoming calls of the target phone number greater than 2.

[0046] It should be noted that both the first preset number of times and the second preset number of times are positive integers. They can be the same positive integer, for example, both the first preset number of times and the second preset number of times are 2. They can also be different positive integers, for example, the first preset number of times is 2 and the second preset number of times is 3.

[0047] Optionally, the basic information of the target telephone identifier can be the basic information of the target telephone identifier within a preset time period, such as the basic information of the target telephone identifier within the first three months of year Q, or the basic information of the target telephone identifier within a week. The preset time period can be determined according to specific usage needs.

[0048] S202. Determine the target parameters corresponding to the target telephone identifier based on multiple basic parameters and the weight value corresponding to each basic parameter.

[0049] Optionally, each basic parameter corresponds to a weight value, and the weight value corresponding to each basic parameter can be set according to specific usage needs.

[0050] For example, the weighting value for the outgoing call percentage is 30%, the weighting value for the outgoing call concentration is 20%, the weighting value for the incoming call concentration is 20%, the weighting value for the average call duration is 15%, and the weighting value for the average daily traffic is 15%.

[0051] Optionally, when the outgoing call percentage is considered an important indicator for identifying harassing and fraudulent calls, the weight value corresponding to the outgoing call percentage can be set to 50%.

[0052] It is understandable that when adjusting the weight value of a certain basic parameter among multiple basic parameters, in order to ensure that the sum of the weight values ​​of all basic parameters is 1, it is necessary to adjust at least one of the weight values ​​of the remaining basic parameters at the same time.

[0053] Optionally, the types of basic parameters can be adjusted. When the types of basic parameters are adjusted, the weight value corresponding to each basic parameter needs to be reset.

[0054] For example, when the basic parameters also include the average number of SMS messages per day, the weighting values ​​can be set as follows: the outgoing call percentage is 20%, the outgoing call concentration is 20%, the incoming call concentration is 20%, the average call duration is 15%, the average daily data traffic is 15%, and the average number of SMS messages per day is 10%.

[0055] S203. When the target parameter is determined to be greater than the target threshold, the target phone number is identified as a harassing or fraudulent phone number.

[0056] Optionally, when the target parameter is greater than the target threshold, it indicates that the target phone number identifier corresponding to the target parameter meets the preset characteristics of the harassment and fraud model, and the target phone number identifier can be determined as the identifier of a harassment and fraud phone number.

[0057] Optionally, when a target phone number is identified as a harassing or fraudulent caller ID, the operator may partially suspend that target phone number.

[0058] Optionally, the target phone number can be partially suspended by the authorities by adding it to a blacklist.

[0059] It should be noted that the partial suspension of service by the authorities can be understood as the user corresponding to the harassing and fraudulent calls being unable to make calls, but still able to receive calls.

[0060] Optionally, identifying a target phone number as a harassing or fraudulent call can be understood as identifying the target phone number as a harassing or fraudulent call.

[0061] In this embodiment, firstly, based on the basic information of the target phone identifier, multiple basic parameters are determined, including at least one of the following: caller ID ratio, caller concentration, called party concentration, average call duration, and daily traffic. Further, based on the multiple basic parameters and their corresponding weight values, a target parameter is determined for the target phone identifier. When the target parameter is determined to be greater than a target threshold, the target phone identifier is identified as a harassing or fraudulent call. Through this method, the target parameter corresponding to the phone identifier can be obtained from multiple dimensions based on multiple basic parameters, including caller ID ratio, caller concentration, called party concentration, average call duration, and daily traffic. Then, based on the relationship between the target parameter and the target threshold, it can be determined whether the phone identifier is a harassing or fraudulent call, thereby improving the efficiency and accuracy of identifying harassing and fraudulent calls.

[0062] In a design, such as Figure 3 As shown, in the harassment and fraud call identification method provided in this application embodiment, the above-mentioned S202 specifically includes S301-S302:

[0063] S301. Based on the calling percentage and the first threshold, determine the first parameter corresponding to the calling percentage; based on the calling concentration and the second threshold, determine the second parameter corresponding to the calling concentration; based on the called concentration and the third threshold, determine the third parameter corresponding to the called concentration; based on the average call duration and the fourth threshold, determine the fourth parameter corresponding to the average call duration; based on the average daily traffic and the fifth threshold, determine the fifth parameter corresponding to the average daily traffic.

[0064] Optionally, the first threshold, second threshold, third threshold, fourth threshold, and fifth threshold can be determined according to specific usage requirements.

[0065] Optionally, the first parameter corresponding to the calling percentage can be determined based on the ratio of calling percentage to the first threshold, as shown in Formula 1:

[0066]

[0067] Where X1 is the first parameter, a1 is the calling percentage, and b1 is the first threshold.

[0068] For example, the first threshold can be 70%. That is, when a1 is greater than 70%, the first parameter is equal to 100*(a1-70%) / 30%, and when a1 is less than or equal to 70%, the first parameter is equal to 0.

[0069] It is understandable that when the outgoing call percentage is 100%, the first parameter reaches its maximum value.

[0070] Optionally, a second parameter corresponding to the caller concentration can be determined based on the magnitude of the caller concentration and the second threshold, as shown in Formula 2:

[0071]

[0072] Where X2 is the second parameter, a2 is the caller concentration, and b2 is the second threshold.

[0073] For example, the second threshold can be 20%. That is, when a2 is less than 20%, the second parameter is equal to (20% - a2) / 20%, and when a2 is greater than or equal to 20%, the second parameter is equal to 0.

[0074] Optionally, a third parameter corresponding to the called party concentration can be determined based on the magnitude of the called party concentration and the third threshold, as shown in Formula 3:

[0075]

[0076] Where X3 is the third parameter, a3 is the called concentration, and b3 is the third threshold.

[0077] For example, the third threshold can be 20%. That is, when a3 is less than 20%, the third parameter is equal to (20% - a3) / 20%, and when a3 is greater than or equal to 20%, the third parameter is equal to 0.

[0078] Optionally, a fourth parameter corresponding to the average call duration can be determined based on the magnitude of the average call duration and the fourth threshold, as shown in Formula 4:

[0079]

[0080] Where X4 is the fourth parameter, a4 is the average call duration, and b4 is the fourth threshold.

[0081] For example, the fourth threshold can be 60. That is, when a4 is less than 60, the fourth parameter is equal to (60-a4) / 60, and when a4 is greater than or equal to 60, the fourth parameter is equal to 0.

[0082] Optionally, the fifth parameter corresponding to the average daily traffic can be determined based on the magnitude of the average daily traffic and the fifth threshold, as shown in Formula 5:

[0083]

[0084] Where X5 is the fifth parameter, a5 is the average daily flow, and b5 is the fifth threshold.

[0085] For example, the fifth threshold can be 200. That is, when a5 is less than 200, the fifth parameter is equal to (200-a4) / 200, and when a5 is greater than or equal to 200, the fifth parameter is equal to 0.

[0086] S302. Determine the target parameters corresponding to the target telephone identifier based on the first parameter and the first weight value corresponding to the calling percentage, the second parameter and the second weight value corresponding to the calling concentration, the third parameter and the third weight value corresponding to the called concentration, the fourth parameter and the fourth weight value corresponding to the average call duration, and the fifth parameter and the fifth weight value corresponding to the average daily traffic.

[0087] Optionally, the target parameter can be obtained by weighted summation of the first, second, third, fourth, and fifth parameters. Specifically, as shown in Formula Six:

[0088]

[0089] Where y is the target parameter, X i For the i-th parameter, α i Let be the i-th weight value.

[0090] For example, when the basic parameters only include the percentage of outgoing calls, the concentration of outgoing calls, the concentration of incoming calls, the average call duration, and the average daily traffic, and the weight value corresponding to the percentage of outgoing calls is 30%, the weight value corresponding to the concentration of outgoing calls is 20%, the weight value corresponding to the concentration of incoming calls is 20%, the weight value corresponding to the average call duration is 15%, and the weight value corresponding to the average daily traffic is 15%, the value of the target parameter is the sum of the first parameter * 30%, the second parameter * 20%, the third parameter * 20%, the fourth parameter * 15%, and the fifth parameter * 15%.

[0091] In this embodiment, the parameter value corresponding to each basic parameter is determined by each basic parameter and the preset threshold corresponding to the basic parameter. Then, the target parameter is obtained according to the parameter value and the weight value corresponding to each basic parameter. The target parameters corresponding to the target phone identifier are determined by multiple dimensions such as caller ratio, caller concentration, called concentration, average call duration, and average daily traffic, so as to improve the accuracy of identifying harassing and fraudulent calls.

[0092] In a design, such as Figure 4 As shown, in the harassment and fraud call identification method provided in this application embodiment, before S203 above, the method further includes S401:

[0093] S401. Obtain the target number of complaint work orders and the total number of complaint work orders within the target time period, and determine the target threshold based on the target number of complaint work orders and the total number of complaint work orders.

[0094] The target number of complaint tickets is the number of complaint tickets generated when a phone number is identified as a harassing or fraudulent call.

[0095] It should be noted that the target complaint ticket can also be understood as a complaint caused by the network shutdown among all complaint tickets. The complaint caused by the network shutdown refers to the complaint caused by the network operator's partial shutdown of the target telephone number.

[0096] Optionally, target complaint tickets can be obtained by classifying all complaint tickets by the reason for the complaint.

[0097] Optionally, the target time period can be a preset time period before the current time, such as obtaining the target number of complaint work orders and the total number of complaint work orders within one month before the current time, the target number of complaint work orders and the total number of complaint work orders within one week before the current time, the target number of complaint work orders and the total number of complaint work orders within one day before the current time, etc.

[0098] It should be noted that the preset time period corresponding to the basic information of the target time period and the target telephone identifier can be a time period of the same length or a time period of different lengths.

[0099] For example, the target time period can be the month preceding the current time, and the preset time period corresponding to the basic information of the target phone number can be the day preceding the current time, the week preceding the current time, the month preceding the current time, etc.

[0100] In this embodiment, the target threshold is determined by the proportion of target complaint tickets generated due to misjudgment by the harassment and fraud identification method, so as to improve the user experience in the process of identifying harassment and fraud calls, thereby improving the efficiency and accuracy of identifying harassment and fraud calls.

[0101] In a design, such as Figure 5 As shown, in the harassment and fraud call identification method provided in this application embodiment, the "determining the target threshold based on the target number of complaint work orders and the total number of complaint work orders" in S401 specifically includes S501-S503:

[0102] S501. Determine the target ratio of the target number of complaint work orders to the total number of complaint work orders.

[0103] Optionally, the target ratio can be understood as the proportion of target complaint orders among all complaint orders within the target time period.

[0104] For example, the target ratio could be the ratio of the number of target complaint tickets to the total number of complaint tickets in February of year Q.

[0105] For example, if there are 50 target complaint tickets in February of year Q, and the total number of complaint tickets in February of year Q is 1000, then the target ratio is 5%.

[0106] S502. When the target ratio is determined to be greater than the historical ratio, and the difference between the target ratio and the historical ratio is greater than the sixth threshold, the historical threshold is reduced to obtain the target threshold.

[0107] The historical ratio is the ratio of the number of historical target complaint work orders to the total number of historical complaint work orders in the historical time period before the target time period.

[0108] S503. When the target ratio is determined to be less than the historical ratio, and the difference between the historical ratio and the target ratio is greater than the sixth threshold, the historical threshold is increased to obtain the target threshold.

[0109] Optional, historical ratio, can be understood as the historical proportion of the target complaint work order in the total number of complaint work orders within a historical period.

[0110] Optionally, the historical threshold can be understood as the historical target threshold that already existed before the target ratio and the historical ratio were determined.

[0111] Optionally, the historical time period and the target time period can have the same length. For example, when the target time period is within one month prior to the current time, the historical time period can also be one month long, such as within a month prior to the target time period.

[0112] For example, the target time period is March of year Q, and the historical time period can be February of year Q, January of year Q, March of the year before year Q, etc.

[0113] In one possible implementation, the historical time period and the target time period can have different durations. For example, when the target time period is within one month prior to the current moment, the duration of the historical time period can also be a week, a day, etc., such as within a week or a day prior to the target time period.

[0114] For example, the target time period is March of year Q, and the historical time period can be the last week of February of year Q, the last day of February of year Q, etc.

[0115] Optionally, when the difference between the target ratio and the historical ratio is greater than the sixth threshold, it can be considered that the proportion of the target complaint work order in all complaint work orders within the target time period is significantly different from the historical proportion of the target complaint work order in all complaint work orders within the historical time period, and the historical threshold needs to be adjusted.

[0116] For example, when the target ratio is determined to be greater than the historical ratio and the difference between the target ratio and the historical ratio is greater than the sixth threshold, it indicates that the proportion of the target complaint work order in all complaint work orders within the target time period is higher than the historical proportion of the target complaint work order in all complaint work orders within the historical time period. In this case, in order to reduce the proportion of the target complaint work order, the previously set historical threshold can be reduced.

[0117] For example, when the target ratio is determined to be less than the historical ratio and the difference between the historical ratio and the target ratio is greater than the sixth threshold, it indicates that the proportion of the target complaint work order in all complaint work orders within the target time period is lower than the historical proportion of the target complaint work order in all complaint work orders within the historical time period. In this case, in order to increase the crackdown on harassing and fraudulent calls, the previously set historical threshold can be increased.

[0118] Optionally, the sixth threshold can be determined according to specific usage needs. For example, when the target threshold needs to have high sensitivity, a smaller sixth threshold can be set; when the target threshold needs to have high stability, a larger sixth threshold can be set.

[0119] In one possible implementation, when the difference between the target ratio and the historical ratio is greater than the sixth threshold, the weight values ​​corresponding to the basic parameters can also be adjusted.

[0120] For example, the weight value corresponding to the calling percentage in the current basic parameters is 50%. When it is determined that the target ratio is greater than the historical ratio and the difference between the target ratio and the historical ratio is greater than the sixth threshold, the weight value corresponding to the calling percentage in the basic parameters can be adjusted to 45%, and the weight values ​​corresponding to other parameters in the basic parameters can be adjusted accordingly. After a certain period of time, the size of the target ratio and the historical ratio is re-determined, and analysis, evaluation and iterative optimization are carried out to continuously optimize the weight value corresponding to each basic parameter.

[0121] Optionally, it is also possible to obtain a reference ratio of the number of target complaint tickets to the total number of complaint tickets for different operators or other different units within the same target time period, and adjust the historical threshold according to the relationship between the reference ratio and the target ratio.

[0122] For example, within the same target time period (such as May of year Q), if the determined reference ratio is greater than the target ratio, and the difference between the reference ratio and the target ratio is greater than the sixth threshold, the previously set historical threshold can be increased.

[0123] In this embodiment, the historical threshold is adjusted by comparing the proportion of the target complaint work order among all complaint work orders within the target time period with the historical proportion of the target complaint work order among all complaint work orders within the historical time period. This improves the user experience during the identification of harassing and fraudulent calls, thereby enhancing the efficiency and accuracy of identifying harassing and fraudulent calls.

[0124] In a design, such as Figure 6 As shown in the embodiment of this application, in a method for identifying harassing and fraudulent phone calls, the above-mentioned S203 includes S601-S602:

[0125] S601. When it is determined that the target parameter is greater than the target threshold and the target phone identifier is not a phone identifier in the whitelist, send authentication information to the target phone identifier.

[0126] The whitelist contains multiple phone number identifiers used to identify non-harassing and fraudulent calls.

[0127] Optionally, the whitelist can be a database set up for specific industries and specific numbers that meet the identification characteristics of harassing and fraudulent calls, such as the express delivery industry and the taxi industry.

[0128] Optionally, for phone numbers that have been verified by a second round of manual verification and are determined to be non-harassing or fraudulent calls, the phone number can be added to the whitelist.

[0129] Optionally, the certification information may be certification information set according to relevant industry requirements and / or relevant regulations.

[0130] For example, the authentication information may be information that requires a target phone number that is not on the whitelist to undergo secondary real-name authentication online or offline within a specified time through a specific notification method (such as SMS or telephone).

[0131] S602. When the target phone number identifier is not authenticated, the target phone number identifier is identified as an identifier for harassing or fraudulent calls.

[0132] Optionally, for target phone numbers that have sent authentication information but have not yet performed the relevant authentication operation within the specified time, the target phone number can be directly identified as a harassing or fraudulent phone number and dealt with accordingly.

[0133] For example, a target phone number identified as a harassing or fraudulent call can be added to a blacklist and its service suspended.

[0134] In one possible implementation, it can also be determined whether the target phone identifier has been blacklisted by using the basic information of the target phone identifier. For target phone identifiers that have been blacklisted, when the target parameter is determined to be greater than the target threshold, the target phone identifier is directly suspended.

[0135] Optional, such as Figure 7 As shown, the electronic device 21 may specifically include a basic parameter determination module 211, a target parameter determination module 212, a target ratio determination module 213, a target threshold adjustment module 214, a numerical comparison module 215, and a telephone identification processing module 216.

[0136] The basic parameter determination module 211 is used to determine multiple basic parameters corresponding to the telephone identifier based on the basic information of the telephone identifier, and send the determined multiple basic parameters corresponding to the telephone identifier to the target parameter determination module 212.

[0137] The target parameter determination module 212 is used to determine the target parameter corresponding to the telephone identifier based on the multiple basic parameters corresponding to the telephone identifier, and send the target parameter corresponding to the telephone identifier to the numerical comparison module 215.

[0138] The target ratio determination module 213 is used to obtain the target number of complaint work orders and the total number of complaint work orders in the target time period, determine the target ratio of the target number of complaint work orders to the total number of complaint work orders, and send the target ratio to the target threshold adjustment module 214.

[0139] The target threshold adjustment module 214 is used to adjust the target threshold according to the relationship between the target ratio and the historical ratio, and send the adjusted target threshold to the numerical comparison module 215.

[0140] The numerical comparison module 215 is used to determine the relationship between the target parameter corresponding to the telephone identifier and the target threshold, and when the target parameter corresponding to the telephone identifier is greater than the target threshold, the telephone identifier is sent to the telephone identifier processing module 216.

[0141] The telephone identification processing module 216 is used to further confirm the telephone identification, thereby determining whether the telephone identification is an identifier for harassing or fraudulent calls.

[0142] Specifically, such as Figure 8 As shown, after receiving a phone identifier, the phone identifier processing module 216 determines whether the phone identifier belongs to the whitelist. If the phone identifier does not belong to the whitelist, authentication information is sent to the phone identifier. If the phone identifier is determined to belong to the whitelist, it is determined that the phone identifier is not a harassing or fraudulent phone identifier and no processing is performed on the phone identifier. Furthermore, after a preset time period, it determines whether the phone identifier has been authenticated. If it is determined that the phone identifier has not been authenticated, it is determined that the phone identifier is a harassing or fraudulent phone identifier and appropriate processing is performed. If it is determined that the phone identifier has been authenticated, it is determined that the phone identifier is not a harassing or fraudulent phone identifier and no processing is performed on the phone identifier.

[0143] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0144] This application embodiment can divide a harassment and fraud call identification device into functional modules based on the above method example. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents a logical functional division; other division methods may be used in actual implementation.

[0145] Figure 9 This is a schematic diagram of a harassment and fraud call identification device provided in an embodiment of this application. Figure 9As shown, the harassment and fraud call identification device 40 is used to improve the efficiency and accuracy of identifying harassment and fraud calls, for example, for performing... Figure 2 The above describes a method for identifying harassing and fraudulent phone calls. The harassing and fraudulent phone call identification device 40 includes: a determining unit 401;

[0146] The determining unit 401 is used to determine multiple basic parameters corresponding to the target telephone identifier based on the basic information of the target telephone identifier. The multiple basic parameters include at least one of the following: calling percentage, calling concentration, called concentration, average call duration and average daily traffic.

[0147] Among them, the calling percentage is used to indicate the ratio of the number of calls made by the target phone identifier to the total number of calls; the calling concentration is used to indicate the proportion of the first type of numbers among the calling numbers of the target phone identifier, which are the numbers whose number of calls made by the target phone identifier is greater than a first preset number; and the called concentration is used to indicate the proportion of the second type of numbers among the called numbers of the target phone identifier, which are the numbers whose number of calls made by the target phone identifier is greater than a second preset number.

[0148] The determining unit 401 is used to determine the target parameters corresponding to the target telephone identifier based on multiple basic parameters and the weight value corresponding to each basic parameter.

[0149] The determining unit 401 is used to determine the target telephone number as a harassing or fraudulent telephone number when the determined target parameter is greater than the target threshold.

[0150] In one design, a determining unit 401 is used to determine a first parameter corresponding to the calling percentage based on the calling percentage and a first threshold, a second parameter corresponding to the calling concentration based on the calling concentration and a second threshold, a third parameter corresponding to the called concentration based on the called concentration and a third threshold, a fourth parameter corresponding to the average call duration based on the average call duration and a fourth threshold, and a fifth parameter corresponding to the average daily traffic based on the average daily traffic and a fifth threshold.

[0151] The determining unit 401 is used to determine the target parameters corresponding to the target telephone identifier based on the first parameter and the first weight value corresponding to the calling percentage, the second parameter and the second weight value corresponding to the calling concentration, the third parameter and the third weight value corresponding to the called concentration, the fourth parameter and the fourth weight value corresponding to the average call duration, and the fifth parameter and the fifth weight value corresponding to the average daily traffic.

[0152] In one design, the harassment and fraud call identification device 40 further includes: an acquisition unit 402; the acquisition unit 402 is used to acquire the number of target complaint work orders and the total number of complaint work orders in a target time period.

[0153] The determination unit 401 is used to determine the target threshold based on the target number of complaint work orders and the total number of complaint work orders.

[0154] The target number of complaint tickets is the number of complaint tickets generated when a phone number is identified as a harassing or fraudulent call.

[0155] In one design, the harassment and fraud call identification device 40 further includes: a processing unit 403; and a determining unit 401, used to determine a target ratio of the number of target complaint work orders to the total number of complaint work orders.

[0156] The processing unit 403 is used to reduce the historical threshold to obtain the target threshold when the target ratio is determined to be greater than the historical ratio and the difference between the target ratio and the historical ratio is greater than the sixth threshold.

[0157] The historical ratio is the ratio of the number of historical target complaint work orders to the total number of historical complaint work orders in the historical time period before the target time period.

[0158] The processing unit 403 is used to increase the historical threshold to obtain the target threshold when the target ratio is determined to be less than the historical ratio and the difference between the historical ratio and the target ratio is greater than the sixth threshold.

[0159] In one design, the harassment and fraud call identification device 40 further includes: a processing unit 403; the processing unit 403 is used to send authentication information to the target call identifier when it is determined that the target parameter is greater than the target threshold and the target call identifier does not belong to the call identifier in the whitelist.

[0160] The whitelist contains multiple phone number identifiers used to identify non-harassing and fraudulent calls.

[0161] The determining unit 401 is used to determine that the target phone number identifier is an identifier for harassing or fraudulent calls when the target phone number identifier has not been authenticated.

[0162] In the case of implementing the functions of the integrated modules described above in hardware, this application provides another possible structural diagram of the electronic device involved in the above embodiments. For example... Figure 10 As shown, an electronic device 70 is used to improve the efficiency and accuracy of identifying harassing and fraudulent calls, for example, for performing... Figure 2 The diagram illustrates a method for identifying harassing and fraudulent phone calls. The electronic device 70 includes a processor 701, a memory 702, and a bus 703. The processor 701 and the memory 702 are connected via the bus 703.

[0163] Processor 701 is the control center of the communication device. It can be a single processor or a collective term for multiple processing elements. For example, processor 701 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0164] As one embodiment, processor 701 may include one or more CPUs, for example Figure 10 CPU 0 and CPU 1 are shown in the diagram.

[0165] The memory 702 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0166] As one possible implementation, the memory 702 can exist independently of the processor 701. The memory 702 can be connected to the processor 701 via a bus 703 and is used to store instructions or program code. When the processor 701 calls and executes the instructions or program code stored in the memory 702, it can implement the harassment and fraud call identification method provided in this application embodiment.

[0167] In another possible implementation, the memory 702 can also be integrated with the processor 701.

[0168] Bus 703 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0169] It should be pointed out that, Figure 10 The structure shown does not constitute a limitation on the electronic device 70. Except... Figure 10 In addition to the components shown, the electronic device 70 may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0170] As an example, combined Figure 9 The functions implemented by the determining unit 401, the acquiring unit 402, and the processing unit 403 in the harassment and fraud call identification device 40 are the same as those in the previous device. Figure 10 The processor 701 in it has the same function.

[0171] Optional, such as Figure 10 As shown, the electronic device 70 provided in this application embodiment may further include a communication interface 704.

[0172] Communication interface 704 is used to connect with other devices via a communication network. This communication network can be Ethernet, a wireless access network, a wireless local area network (WLAN), etc. Communication interface 704 may include a receiving unit for receiving data and a transmitting unit for transmitting data.

[0173] In one design, the communication interface in the electronic device provided in this application embodiment can also be integrated into the processor.

[0174] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional units is used as an example. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the device can be divided into different functional units to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0175] This application also provides a computer-readable storage medium storing instructions. When a computer executes these instructions, the computer performs each step of the method flow shown in the above-described method embodiments.

[0176] Embodiments of this application provide a computer program product containing instructions that, when executed on a computer, cause the computer to perform a method for identifying harassing and fraudulent phone calls as described in the above method embodiments.

[0177] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), registers, hard disks, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof, or any other form of computer-readable storage medium in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in an application-specific integrated circuit (ASIC). In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0178] Since the electronic devices, computer-readable storage media, and computer program products in the embodiments of this application can be applied to the above methods, the technical effects they can achieve can also be referred to the above method embodiments. The embodiments of this application will not be repeated here.

[0179] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A method for identifying harassing and fraudulent phone calls, characterized in that, The method includes: Based on the basic information of the target phone identifier, several basic parameters corresponding to the target phone identifier are determined. The several basic parameters include at least one of the following: caller ratio, caller concentration, called party concentration, average call duration, and average daily traffic. The caller ratio is used to indicate the ratio of the number of calls made by the target phone identifier to the total number of calls. The caller concentration is used to indicate the proportion of the first type of numbers among the caller numbers of the target phone identifier. The first type of numbers are the numbers of the target phone identifier whose number of calls is greater than a first preset number. The called party concentration is used to indicate the proportion of the second type of numbers among the called numbers of the target phone identifier. The second type of numbers are the numbers of the target phone identifier whose number of calls is greater than a second preset number. Based on the multiple basic parameters and the weight value corresponding to each basic parameter, the target parameter corresponding to the target telephone identifier is determined; Obtain the number of target complaint tickets and the total number of complaint tickets within the target time period. The number of target complaint tickets is the number of complaint tickets generated when the telephone number is identified as a harassing or fraudulent telephone number. Determine the target ratio of the target number of complaint work orders to the total number of complaint work orders; When it is determined that the target ratio is greater than the historical ratio, and the difference between the target ratio and the historical ratio is greater than the sixth threshold, the historical threshold is reduced to obtain the target threshold. The historical ratio is the ratio of the number of historical target complaint work orders to the total number of historical complaint work orders in the historical time period before the target time period. When it is determined that the target ratio is less than the historical ratio, and the difference between the historical ratio and the target ratio is greater than the sixth threshold, the historical threshold is increased to obtain the target threshold; When the target parameter is determined to be greater than the target threshold, the target phone number is identified as a harassing or fraudulent phone number.

2. The method for identifying harassing and fraudulent phone calls according to claim 1, characterized in that, The step of determining the target parameter corresponding to the target phone identifier based on the plurality of basic parameters and the weight value corresponding to each basic parameter includes: Based on the calling percentage and the first threshold, a first parameter corresponding to the calling percentage is determined; based on the calling concentration and the second threshold, a second parameter corresponding to the calling concentration is determined; based on the called concentration and the third threshold, a third parameter corresponding to the called concentration is determined; based on the average call duration and the fourth threshold, a fourth parameter corresponding to the average call duration is determined; and based on the average daily traffic and the fifth threshold, a fifth parameter corresponding to the average daily traffic is determined. The target parameters corresponding to the target phone identifier are determined based on the first parameter and the first weight value corresponding to the calling percentage, the second parameter and the second weight value corresponding to the calling concentration, the third parameter and the third weight value corresponding to the called concentration, the fourth weight value corresponding to the fourth parameter and the average call duration, and the fifth weight value corresponding to the fifth parameter and the average daily traffic.

3. The method for identifying harassing and fraudulent phone calls according to claim 1 or 2, characterized in that, The step of identifying the target phone number as a harassing or fraudulent caller when the target parameter is determined to be greater than the target threshold specifically includes: When it is determined that the target parameter is greater than the target threshold and the target phone identifier is not a phone identifier in the whitelist, authentication information is sent to the target phone identifier. The whitelist contains multiple phone identifiers used to identify non-harassing and fraudulent phone numbers. When the target phone number identifier is not authenticated, it is determined that the target phone number identifier is an identifier for harassing or fraudulent calls.

4. A device for identifying harassing and fraudulent phone calls, characterized in that, The device includes: a determining unit, an acquiring unit, and a processing unit; The determining unit is used to determine multiple basic parameters corresponding to the target phone identifier based on the basic information of the target phone identifier. The multiple basic parameters include at least one of the following: caller ratio, caller concentration, called party concentration, average call duration, and average daily traffic. The caller ratio is used to indicate the ratio of the number of calls made by the target phone identifier to the total number of calls. The caller concentration is used to indicate the proportion of the first type of numbers among the caller numbers of the target phone identifier. The first type of numbers are the numbers whose caller count of the target phone identifier is greater than a first preset number. The called party concentration is used to indicate the proportion of the second type of numbers among the called party numbers of the target phone identifier. The second type of numbers are the numbers whose called party count of the target phone identifier is greater than a second preset number. The determining unit is used to determine the target parameter corresponding to the target telephone identifier based on the plurality of basic parameters and the weight value corresponding to each basic parameter; The acquisition unit is used to acquire the number of target complaint work orders and the total number of complaint work orders in the target time period. The determining unit is used to determine a target threshold based on the target number of complaint work orders and the total number of complaint work orders, wherein the target number of complaint work orders is the number of complaint work orders generated when the telephone identifier is identified as a harassing or fraudulent telephone number; The determining unit is used to determine a target ratio between the target number of complaint work orders and the total number of complaint work orders; The processing unit is configured to reduce the historical threshold to obtain the target threshold when it is determined that the target ratio is greater than the historical ratio and the difference between the target ratio and the historical ratio is greater than the sixth threshold. The historical ratio is the ratio of the number of historical target complaint work orders to the total number of historical complaint work orders in the historical time period before the target time period. The processing unit is configured to increase the historical threshold to obtain the target threshold when it is determined that the target ratio is less than the historical ratio and the difference between the historical ratio and the target ratio is greater than the sixth threshold. The determining unit is used to determine that the target phone number is an identifier for a harassing or fraudulent phone number when the target parameter is determined to be greater than the target threshold.

5. The harassment and fraud call identification device according to claim 4, characterized in that, The determining unit is configured to determine a first parameter corresponding to the calling percentage based on the calling percentage and a first threshold, determine a second parameter corresponding to the calling concentration based on the calling concentration and a second threshold, determine a third parameter corresponding to the called concentration based on the called concentration and a third threshold, determine a fourth parameter corresponding to the average call duration based on the average call duration and a fourth threshold, and determine a fifth parameter corresponding to the average daily traffic based on the average daily traffic and a fifth threshold. The determining unit is configured to determine the target parameters corresponding to the target phone identifier based on the first parameter and the first weight value corresponding to the calling percentage, the second parameter and the second weight value corresponding to the calling concentration, the third parameter and the third weight value corresponding to the called concentration, the fourth weight value corresponding to the fourth parameter and the average call duration, and the fifth weight value corresponding to the fifth parameter and the average daily traffic.

6. The harassment and fraud call identification device according to claim 4 or 5, characterized in that, The device further includes: a processing unit; The processing unit is configured to send authentication information to the target phone identifier when it is determined that the target parameter is greater than the target threshold and the target phone identifier does not belong to the phone identifier in the whitelist. The whitelist contains multiple phone identifiers used to identify non-harassing and fraudulent phone numbers. The determining unit is used to determine that the target phone identifier is an identifier for harassing or fraudulent calls when the target phone identifier has not been authenticated.

7. An electronic device, characterized in that, include: A processor and a memory; wherein the memory is used to store one or more programs, the one or more programs including computer execution instructions, and when the electronic device is running, the processor executes the computer execution instructions stored in the memory to cause the electronic device to perform a method for identifying harassing and fraudulent phone calls according to any one of claims 1-3.

8. A computer-readable storage medium for storing one or more programs, characterized in that, The one or more programs include instructions that, when executed by a computer, cause the computer to perform a method for identifying harassing and fraudulent phone calls according to any one of claims 1-3.

Images