Number state recognition method, number state recognition device and electronic equipment

Abstract

The invention discloses a number state recognition method, a number state recognition device and electronic equipment, and the method comprises the steps: obtaining the message sending amount and the message receiving amount corresponding to each unit time period of a calling number in a first time period, the message sending amount being the number of messages sent to a called number, and the message receiving amount being the number of messages sent to the called number; the message receiving quantity is the quantity of the received messages from the called number; determining a message sending frequency threshold value in the unit time period corresponding to the calling number based on a quartile method according to the message sending amount and the message receiving amount corresponding to each unit time period; according to the message sending amount and the message receiving amount corresponding to each unit time period, determining a message sending and receiving ratio threshold value in the unit time period corresponding to the calling number based on the quartile method; and performing state identification on the calling number based on the message sending frequency threshold value and the message sending-receiving ratio threshold value.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and specifically relates to a number status recognition method, a number status recognition device and an electronic device. Background Art

[0002] SMS bombing usually refers to a sender sending a large number of text messages to a mobile phone number in a short period of time, causing the receiver to be unable to use the phone or other services normally. At present, the main methods used for security control of SMS bombing include: when the number of messages sent by the sender to the other party within a unit time reaches a certain threshold, it is judged as SMS bombing, and then the messages sent by the sender to the receiver are intercepted.

[0003] However, the usage scenarios and behavior habits of different users vary greatly. For example, some users may send short messages frequently, and this behavior does not represent malicious behavior, but normal communication needs. A fixed threshold may mistakenly mark these normal message behaviors as bombing, thereby performing abnormal processing on the sender's number; or, in some scenarios, such as security verification, account security reminders, etc., a large number of messages may be sent to users in a short period of time. If a fixed threshold is used, it is easy to misjudge these normal messages as bombing behavior, affecting normal business processes. Therefore, judging based on a fixed threshold will result in a high misjudgment rate. Summary of the invention

[0004] The embodiments of the present application provide a number status recognition method, a number status recognition device and an electronic device, which can solve the problem of high misjudgment rate.

[0005] In the first aspect, an embodiment of the present application provides a number status identification method, the method comprising: obtaining the message sending volume and the message receiving volume corresponding to each unit time period of the calling number in a first time period, wherein the message sending volume is the number of messages sent to the called number, and the message receiving volume is the number of messages received from the called number; determining the message sending frequency threshold within the unit time period corresponding to the calling number based on the quartile method according to the message sending volume and the message receiving volume corresponding to each unit time period; determining the message sending-receiving ratio threshold within the unit time period corresponding to the calling number based on the quartile method according to the message sending volume and the message receiving volume corresponding to each unit time period; and identifying the status of the calling number based on the message sending frequency threshold and the message sending-receiving ratio threshold. In the second aspect, an embodiment of the present application provides a number status identification device, which includes: an acquisition module, used to obtain the message sending volume and message receiving volume corresponding to each unit time period of the calling number in a first time period, wherein the message sending volume is the number of messages sent to the called number, and the message receiving volume is the number of messages received from the called number; a first determination module, used to determine the message sending frequency threshold within the unit time period corresponding to the calling number based on the quartile method according to the message sending volume and the message receiving volume corresponding to each unit time period; a second determination module, used to determine the message sending-receiving ratio threshold within the unit time period corresponding to the calling number based on the quartile method according to the message sending volume and the message receiving volume corresponding to each unit time period; an identification module, in which a user identifies the status of the calling number based on the message sending frequency threshold and the message sending-receiving ratio threshold.

[0006] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0008] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0009] In a sixth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes at least one computer program, and when the computer program is loaded and executed by a processor, the method described in the first aspect is implemented.

[0010] In an embodiment of the present application, the amount of message sent and the amount of message received corresponding to each unit time period of the calling number in the first time period are obtained, wherein the amount of message sent is the number of messages sent to the called number, and the amount of message received is the number of messages received from the called number, and then the message sending frequency threshold in the unit time period corresponding to the calling number is determined based on the quartile method according to the amount of message sent and the amount of message received corresponding to each unit time period, and then the message sending-receiving ratio threshold in the unit time period corresponding to the calling number is determined based on the quartile method according to the amount of message sent and the amount of message received corresponding to each unit time period, and finally based on the message sending frequency threshold and the message sending-receiving ratio threshold, and identify the status of the calling number. In this way, the message sending frequency threshold and the message sending-receiving ratio threshold can be dynamically set according to the message sending behavior and message receiving behavior of different users, thereby providing a more accurate and flexible threshold, which can reduce the probability of misjudging normal behavior as message bombing. At the same time, the message sending frequency threshold and the message sending-receiving ratio threshold are determined based on the quartile method, which improves the accuracy of the message sending frequency threshold and the message sending-receiving ratio threshold, and further reduces the misjudgment rate. In addition, the state of the calling number is identified by combining the message sending frequency threshold and the message sending-receiving ratio threshold, which improves the accuracy of the identification and also reduces the misjudgment rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a flowchart of a number status identification method provided in an embodiment of the present application; Figure 2 It is a structural diagram of a number status identification device provided in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0013] In conjunction with the accompanying drawings, a number status identification method, a number status identification device and an electronic device provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0014] Figure 1A method for identifying number status provided by an embodiment of the present application is shown. The method can be executed by an electronic device, and the electronic device may include: a server and / or a terminal device. In other words, the method can be executed by software or hardware installed in the electronic device, and the method includes the following steps: S110: Obtain the message sending volume and message receiving volume corresponding to each unit time period of the calling number in the first time period.

[0015] The message sending amount is the number of messages sent to the called number, and the message receiving amount is the number of messages received from the called number.

[0016] It is understandable that different users have different short message sending requirements and usage frequencies, so it is necessary to dynamically set thresholds based on sending and receiving behaviors for different numbers. In the embodiment of the present application, the sending and receiving behaviors of the calling number are analyzed by obtaining the message sending and message receiving volumes corresponding to each unit time period of the calling number in the first time period.

[0017] In one exemplary embodiment, S110 may include the following steps: S112: Obtain communication history records of the calling number and the called number within the first time period. S114: Based on the communication history record, determine the message sending volume corresponding to each unit time period of the calling number in the first time period, and determine the message receiving volume corresponding to each unit time period of the calling number in the first time period.

[0018] S120: Determine a message sending frequency threshold within the unit time period corresponding to the calling number based on a quartile method according to the message sending amount and the message receiving amount corresponding to each unit time period.

[0019] It is understandable that within a unit time, if the calling number sends a large number of text messages to the called number, it means that the calling number has a high sending frequency. Therefore, the message sending frequency can be determined based on the message sending volume corresponding to each unit time period. Among them, the method for determining the message sending frequency can be based on the quartile method. The quartile method is to identify and eliminate outliers by calculating the interquartile range of the data, which can reduce the impact of outliers on the analysis and calculation results and improve the accuracy of the analysis. Therefore, in an embodiment of the present application, the message sending frequency is determined based on the quartile method, so that the accuracy of the determined message sending frequency is higher.

[0020] S130: Determine a message sending-receiving ratio threshold within the unit time period corresponding to the calling number based on the quartile method according to the message sending amount and the message receiving amount corresponding to each unit time period.

[0021] It can be understood that the message sending and receiving ratio refers to the ratio between the number of messages sent by the calling number to the called number and the number of messages received by the called number within a unit time, that is, the ratio of the number of messages sent to the number of messages received. The larger the message sending and receiving ratio is, the more messages the calling number sends to the called number is greater than the number of messages replied by the other party. Therefore, the message sending and receiving ratio threshold is determined based on the number of messages sent and received corresponding to each unit time period, and based on the message sending and receiving ratio threshold, it can be determined whether the behavior of the calling number is message bombing behavior.

[0022] The message sending / receiving ratio threshold is also determined based on the quartile method, which can make the determined message sending / receiving ratio threshold more accurate.

[0023] S140: Based on the message sending frequency threshold and the message sending-receiving ratio threshold, identify the state of the calling number.

[0024] It is understandable that after the message sending frequency threshold and the message sending-receiving ratio threshold are determined, the state of the calling number can be identified based on the message sending frequency threshold and the message sending-receiving ratio threshold.

[0025] In this step, based on the message sending frequency threshold and the message sending and receiving ratio threshold, the calling number status is identified, and based on the identified status, it can be timely determined whether the message sent by the calling number is a spam bombing message and filtered, which can effectively reduce the interference and interruption to the user. Secondly, it can also prevent the calling number from sending a large amount of spam messages, reduce the probability of user personal information being leaked, and thus enhance user satisfaction and stickiness.

[0026] In an embodiment of the present application, the amount of message sent and the amount of message received corresponding to each unit time period of the calling number in the first time period are obtained, wherein the amount of message sent is the number of messages sent to the called number, and the amount of message received is the number of messages received from the called number, and then the message sending frequency threshold in the unit time period corresponding to the calling number is determined based on the quartile method according to the amount of message sent and the amount of message received corresponding to each unit time period, and then the message sending-receiving ratio threshold in the unit time period corresponding to the calling number is determined based on the quartile method according to the amount of message sent and the amount of message received corresponding to each unit time period, and finally based on the message sending frequency threshold and the message sending-receiving ratio threshold, and identify the status of the calling number. In this way, the message sending frequency threshold and the message sending-receiving ratio threshold can be dynamically set according to the message sending behavior and message receiving behavior of different users, thereby providing a more accurate and flexible threshold, which can reduce the probability of misjudging normal behavior as message bombing. At the same time, the message sending frequency threshold and the message sending-receiving ratio threshold are determined based on the quartile method, which improves the accuracy of the message sending frequency threshold and the message sending-receiving ratio threshold, and further reduces the misjudgment rate. In addition, the state of the calling number is identified by combining the message sending frequency threshold and the message sending-receiving ratio threshold, which improves the accuracy of the identification and also reduces the misjudgment rate.

[0027] The following schematically illustrates how to determine a message sending frequency threshold corresponding to a calling number and how to determine a message sending / receiving ratio threshold corresponding to a calling number.

[0028] (1) In an exemplary embodiment, determining the message sending frequency threshold within the unit time period corresponding to the calling number based on the quartile method according to the message sending amount and the message receiving amount corresponding to each unit time period may include the following steps: S122: Determine a first weighted cumulative distribution value corresponding to each unit time period according to the message sending amount corresponding to each unit time period.

[0029] It is understood that the first weighted cumulative distribution value refers to the result of accumulating each data point after weighting according to the importance or weight of the message sending volume corresponding to each unit time period, and the data point refers to the unit time period. The first weighted cumulative distribution value is used to indicate the importance of each data point. When the importance or frequency of data points is different, weighted accumulation can better reflect the overall trend of the original data or the impact of important data points.

[0030] In an exemplary embodiment, determining the first weighted cumulative distribution value corresponding to each unit time period according to the message sending amount and the message receiving amount corresponding to each unit time period may include the following steps: Step 1: Determine the message sending weight corresponding to each unit time period according to the message sending amount corresponding to each unit time period.

[0031] It is understandable that when performing cumulative calculations, if the importance of each data point is not considered and the data points are directly added together, the first weighted cumulative distribution value may not reflect the essential differences between the data points. After introducing weights, the first weighted cumulative distribution value corresponding to each unit time period can be accurately calculated based on the actual importance of each data point.

[0032] Step 2: Sort the message sending weights corresponding to each of the unit time periods in order from large to small.

[0033] Step 3: Calculate the first weighted cumulative distribution value corresponding to each of the sorted unit time periods.

[0034] Regarding the above steps 2 and 3, it can be understood that the first weighted cumulative distribution value corresponding to each unit time period is the sum of the message sending weights corresponding to all unit time periods before each unit time period. In the process of calculating the first weighted cumulative distribution value, after sorting according to the message sending weights, it can be accumulated directly from the minimum value to the maximum value, which can simplify the accumulation process and reduce errors. If it is not sorted, the message sending weights of some important data may be ignored or mistakenly accumulated to an inappropriate position, resulting in an inaccurate first weighted cumulative distribution value corresponding to a unit time period.

[0035] In an exemplary embodiment, before S112, the method further includes: cleaning the message sending amount, that is, removing abnormal values, which may include a value where the message sending amount is 0, a value where the message sending amount obviously deviates from a normal value, and the like.

[0036] S124: Determine a first upper quartile and a first lower quartile of the first weighted cumulative distribution value based on the quartile method according to the first weighted cumulative distribution value corresponding to each of the unit time periods.

[0037] It can be understood that the first upper quartile is the frequency corresponding to the data point whose first weighted cumulative distribution value reaches 25% of the total weight, and the first lower quartile is the frequency corresponding to the data point whose first weighted cumulative distribution value reaches 75% of the total weight.

[0038] It should be noted that if the position of a quartile is exactly between two data points, that is, the quartile is between the first weighted cumulative distribution values ​​of the two data points, then the quartile takes the weighted average of the first weighted cumulative distribution values ​​of the two data points.

[0039] S126: Determine a minimum threshold and a maximum threshold of the first weighted cumulative distribution value based on the first upper quartile and the first lower quartile.

[0040] In an exemplary embodiment, determining the minimum threshold and the maximum threshold of the first weighted cumulative distribution value based on the first upper quartile and the first lower quartile includes: determining the first interquartile range based on the first upper quartile and the first lower quartile; determining the minimum threshold and the maximum threshold of the first weighted cumulative distribution value based on the first upper quartile, the first lower quartile and the first interquartile range.

[0041] The interquartile range (IQR) can effectively distinguish between extreme values ​​and fluctuations in the normal distribution in the data. The first interquartile range is determined based on the first upper quartile (Q1) and the first lower quartile (Q3). The first interquartile range is the difference between the first lower quartile (Q3) and the first upper quartile (Q1), that is, IQR = Q3 - Q1. In other words, the first interquartile range represents the fluctuation range of the middle 50% of the data and is not affected by extreme values.

[0042] Further, in another exemplary embodiment, determining the minimum threshold and the maximum threshold of the first weighted cumulative distribution value based on the first upper quartile, the first lower quartile and the first interquartile range includes: determining the minimum threshold of the first weighted cumulative distribution value as the difference between the first upper quartile and K times the first interquartile range, where K is a real number greater than 0; determining the maximum threshold of the first weighted cumulative distribution value as the sum of the first lower quartile and K times the first interquartile range.

[0043] That is, the lowest threshold value L1 of the first weighted cumulative distribution value = Q1 - K * IQR, and the highest threshold value H1 of the first weighted cumulative distribution value = Q3 + K * IQR, where K may be 1.5.

[0044] S128: Determine the message sending frequency threshold based on the message sending volume corresponding to the unit time period corresponding to the first weighted cumulative distribution value within the first range, wherein the first range is from the first weighted cumulative distribution value corresponding to the lowest threshold to the first weighted cumulative distribution value corresponding to the highest threshold.

[0045] That is, any value below the minimum threshold or above the maximum threshold is considered an outlier, and these values ​​are not used when determining the frequency threshold. Because the first range usually contains normally distributed data points, excluding outliers can effectively avoid abnormal effects caused by individual extreme values, making the determined frequency threshold more accurate.

[0046] Among them, in an exemplary embodiment, determining the message sending frequency threshold based on the message sending amount corresponding to the unit time period corresponding to the first weighted cumulative distribution value within the first range may include the following steps: Step 1: Based on the message sending amount corresponding to each unit time period corresponding to the first range, determine the average first message sending frequency corresponding to the unit time period.

[0047] That is to say, the average first message sending frequency is the ratio of the sum of the message sending frequencies corresponding to each unit time period to the total number of the message sending frequencies in the unit time period.

[0048] Step 2: Based on the message sending volume corresponding to each unit time period and the first message sending frequency average value, a standard deviation formula is used to determine the second message sending frequency average value.

[0049] Exemplarily, the average value of the second message sending frequency can be expressed by the following standard deviation formula:

[0050] Wherein, S represents the average frequency of sending the second message, N represents the total number of unit time periods within the first range, is the message sending frequency in the i-th unit time period, The average frequency of sending the first message.

[0051] Step 3: Determine the message sending frequency threshold based on the first message sending frequency average value and the second message sending frequency average value.

[0052] In an exemplary embodiment, the message sending frequency threshold can be expressed by the following formula:

[0053] Wherein, X is the message sending frequency threshold, S is the second message sending frequency average value, The average frequency of sending the first message.

[0054] In another exemplary embodiment, the message sending frequency threshold may be expressed by the following formula:

[0055] Wherein, X is the message sending frequency threshold, S is the second message sending frequency average value, The average frequency of sending the first message.

[0056] In the above (1), the method for determining the message sending frequency threshold is based on a combination of quartile analysis and standard deviation, which realizes a fully automated dynamic configuration of the threshold.

[0057] (2) In an exemplary embodiment, determining the message sending-receiving ratio threshold value in the unit time period corresponding to the calling number based on the quartile method according to the message sending amount and the message receiving amount corresponding to each unit time period includes: S132: Determine a message sending-receiving ratio corresponding to each unit time period according to the message sending amount and the message receiving amount corresponding to each unit time period.

[0058] S134: Determine a second weighted cumulative distribution value corresponding to each unit time period based on the message sending / receiving ratio corresponding to each unit time period.

[0059] Among them, in an exemplary embodiment, the second weighted cumulative distribution value corresponding to each unit time period is determined based on the message sending amount and the message receiving amount corresponding to each unit time period, including: determining the message sending and receiving weight corresponding to each unit time period based on the message sending and receiving ratio corresponding to each unit time period; sorting the message sending and receiving weights corresponding to each unit time period in order from large to small; and calculating the second weighted cumulative distribution value corresponding to each unit time period after sorting.

[0060] The message sending / receiving ratio is the ratio of the amount of messages sent to the amount of messages received.

[0061] Among them, for the specific content of S134, please refer to the description in S122 regarding determining the message sending frequency threshold, which will not be repeated here.

[0062] S136: Determine a second upper quartile and a second lower quartile of the second weighted cumulative distribution value based on the quartile method according to the second weighted cumulative distribution value corresponding to each of the unit time periods.

[0063] Among them, for the specific content of S136, please refer to the description in S124 regarding determining the message sending frequency threshold, which will not be repeated here.

[0064] S137: Determine a minimum threshold and a maximum threshold of the second weighted cumulative distribution value based on the second upper quartile and the second lower quartile.

[0065] Wherein, in an exemplary embodiment, determining the minimum threshold and the maximum threshold of the second weighted cumulative distribution value based on the second upper quartile and the second lower quartile includes: determining the second interquartile range based on the second upper quartile and the second lower quartile; determining the minimum threshold and the maximum threshold of the second weighted cumulative distribution value based on the second upper quartile, the second lower quartile and the second interquartile range.

[0066] Further, in another exemplary embodiment, the determining the minimum threshold and maximum threshold of the second weighted cumulative distribution value based on the second upper quartile, the second lower quartile and the second interquartile range includes: determining the minimum threshold of the second weighted cumulative distribution value as the difference between the second upper quartile and M times the second interquartile range, where M is a real number greater than 0; and determining the maximum threshold of the second weighted cumulative distribution value as the sum of the second lower quartile and M times the second interquartile range. Wherein, M may be 1.5.

[0067] Among them, for the specific content of S137, please refer to the description in S126 regarding determining the message sending frequency threshold, which will not be repeated here.

[0068] S138: Determine the message sending-receiving ratio threshold based on the message sending-receiving ratio corresponding to the unit time period corresponding to the second weighted cumulative distribution value within the second range, wherein the second range is from the second weighted cumulative distribution value corresponding to the lowest threshold to the second weighted cumulative distribution value corresponding to the highest threshold.

[0069] Among them, in an exemplary embodiment, the message send-receive ratio threshold is determined based on the message send-receive ratio corresponding to the unit time period corresponding to the second weighted cumulative distribution value within the second range, including: determining the first message send-receive ratio average value corresponding to the unit time period based on the message send-receive ratio corresponding to each unit time period corresponding to the second range; determining the second message send-receive ratio average value by using a standard deviation formula based on the message send-receive ratio corresponding to each unit time period and the first message send-receive ratio average value; determining the message send-receive ratio threshold based on the first message send-receive ratio average value and the second message send-receive ratio average value.

[0070] Among them, for the specific content of S138, please refer to the description in S128 regarding determining the message sending frequency threshold, which will not be repeated here.

[0071] In the above (2), the method for determining the message sending / receiving ratio threshold is based on a combination of quartile analysis and standard deviation, thus achieving fully automated dynamic configuration of the threshold.

[0072] In an exemplary embodiment, the performing status identification on the calling number based on the message sending frequency threshold and the message sending-receiving ratio threshold comprises the following steps: Step 1: Obtain the target message sending volume and the target message receiving volume corresponding to the target unit time period of the calling number in the second time period.

[0073] The target unit time period may be any unit time period.

[0074] Step 2: Based on the target message sending volume and the target message receiving volume, determine the target message sending frequency and the target message sending-receiving ratio of the calling number within the target unit time period.

[0075] Optionally, assuming that the target message sending amount is N1 and the target message receiving amount is N2, if N2 is 0, then N2 is set to 1, and the target message sending-receiving ratio is N1 / N2.

[0076] Step 3: Based on the target message sending frequency, the target message sending-receiving ratio, the message sending frequency threshold and the message sending-receiving ratio threshold, the calling number status is identified. Among them, in an exemplary embodiment, the performing status identification on the calling number based on the target message sending frequency, the target message sending-receiving ratio, the message sending frequency threshold and the message sending-receiving ratio threshold includes one of the following: (1) When the target message sending frequency is less than the message sending frequency threshold and the target message sending / receiving ratio is less than the message sending / receiving ratio threshold, it is determined that the state of the calling number is normal.

[0077] That is to say, when the target message sending frequency and the target message sending / receiving ratio do not reach the corresponding thresholds, it indicates that the state of the calling number is normal.

[0078] (2) When the target message sending frequency is greater than or equal to the message sending frequency threshold, and the target message sending-receiving ratio is less than the message sending-receiving ratio threshold, it is determined that the state of the calling number is suspected to be abnormal.

[0079] That is to say, when the target message sending frequency reaches the corresponding threshold, but the target message sending and receiving ratio does not reach the corresponding threshold, it means that the status of the calling number is suspected to be normal, and further judgment is needed on the number.

[0080] (3) When the target message sending frequency is less than the message sending frequency threshold and the target message sending-receiving ratio is greater than or equal to the message sending-receiving ratio threshold, determine that the state of the calling number is the suspected abnormality.

[0081] That is to say, when the target message sending frequency does not reach the corresponding threshold, but the target message sending and receiving ratio reaches the corresponding threshold, it also means that the status of the calling number is suspected to be normal, and further judgment is needed on the number.

[0082] In another exemplary embodiment, if the target message sending-receiving ratio is larger, it means that the target message sending volume of the bishop number is greater than the target message receiving volume, that is, the target message sending-receiving ratio must be greater than 1. Then, when the target message sending volume of the bishop number is much greater than the target message receiving volume, that is, the difference between the target message sending volume and the target message receiving volume is greater than the preset threshold, it can also be determined that the status of the calling number is suspected abnormal.

[0083] (4) When the target message sending frequency is greater than or equal to the message sending frequency threshold, and the target message sending / receiving ratio is greater than or equal to the message sending / receiving ratio threshold, determining that the state of the calling number is abnormal.

[0084] That is to say, when the target message sending frequency and the target message sending / receiving ratio both reach corresponding thresholds, it indicates that the state of the calling number is abnormal.

[0085] In this embodiment, there is no need to perform manual review or configure keywords to identify spam bombing messages. It is only necessary to identify the state of the calling number through the message sending frequency threshold and the message sending and receiving ratio threshold to determine whether the message sent by the calling number is a spam bombing message.

[0086] In an exemplary embodiment, after the state of the calling number is identified based on the target message sending frequency, the target message sending-receiving ratio, the message sending frequency threshold and the message sending-receiving ratio threshold, the method further includes one of the following: (1) When the status of the calling number is suspected to be abnormal, an in-depth review is performed on the messages sent by the calling number within the target time period.

[0087] It can be understood that the deep review refers to manual review, keyword review, etc. of the message sent by the calling number to determine whether the message sent by the calling number is a spam message. If it is a spam message, the status of the calling number is determined to be abnormal.

[0088] (2) When the state of the calling number is abnormal, intercept a message sent by the calling number to the called number.

[0089] It is understandable that if the sending behavior of the calling number is abnormal and meets the condition of spam message bombing, the message sent by the calling number to the called number is intercepted.

[0090] Figure 2 A schematic diagram of the structure of a number status identification device provided in an embodiment of this specification is shown. Figure 3 As shown, the number status identification device 200 may include: an acquisition module 210 , a first determination module 220 , a second determination module 230 and an identification module 240 .

[0091] In this embodiment, the acquisition module 210 is used to obtain the message sending volume and the message receiving volume corresponding to each unit time period of the calling number in the first time period, wherein the message sending volume is the number of messages sent to the called number, and the message receiving volume is the number of messages received from the called number; the first determination module 220 is used to determine the message sending frequency threshold within the unit time period corresponding to the calling number based on the quartile method according to the message sending volume and the message receiving volume corresponding to each unit time period; the second determination module 230 is used to determine the message sending-receiving ratio threshold within the unit time period corresponding to the calling number based on the quartile method according to the message sending volume and the message receiving volume corresponding to each unit time period; the identification module 240, the user identifies the status of the calling number based on the message sending frequency threshold and the message sending-receiving ratio threshold.

[0092] In an exemplary embodiment, the first determination module 220 is specifically used to: determine the first weighted cumulative distribution value corresponding to each unit time period according to the message sending volume corresponding to each unit time period; determine the first upper quartile and the first lower quartile of the first weighted cumulative distribution value based on the quartile method according to the first weighted cumulative distribution value corresponding to each unit time period; determine the minimum threshold and the maximum threshold of the first weighted cumulative distribution value based on the first upper quartile and the first lower quartile; determine the message sending frequency threshold based on the message sending volume corresponding to the unit time period corresponding to the first weighted cumulative distribution value within a first range, wherein the first range is from the first weighted cumulative distribution value corresponding to the minimum threshold to the first weighted cumulative distribution value corresponding to the maximum threshold.

[0093] In an exemplary embodiment, the first determination module 220 is specifically used to: determine the message sending weight corresponding to each unit time period based on the message sending volume corresponding to each unit time period; sort the message sending weights corresponding to each unit time period in order from large to small; and calculate the first weighted cumulative distribution value corresponding to each unit time period after sorting.

[0094] In an exemplary embodiment, the first determination module 220 is specifically used to: determine a first interquartile range based on the first upper quartile and the first lower quartile; determine a minimum threshold and a maximum threshold of the first weighted cumulative distribution value based on the first upper quartile, the first lower quartile and the first interquartile range.

[0095] In an exemplary embodiment, the first determination module 220 is specifically used to: determine the lowest threshold of the first weighted cumulative distribution value as the difference between the first upper quartile and K times the first interquartile range, K is a real number greater than 0; determine the highest threshold of the first weighted cumulative distribution value as the sum of the first lower quartile and K times the first interquartile range.

[0096] In an exemplary embodiment, the first determination module 220 is specifically used to: determine the average value of the first message sending frequency corresponding to the unit time period based on the message sending volume corresponding to each unit time period corresponding to the first range; determine the average value of the second message sending frequency using the standard deviation formula based on the message sending volume corresponding to each unit time period and the first message sending frequency average value; determine the message sending frequency threshold based on the first message sending frequency average value and the second message sending frequency average value.

[0097] In an exemplary embodiment, the second determination module 230 is specifically used to: determine the message sending / receiving ratio corresponding to each unit time period according to the message sending amount and the message receiving amount corresponding to each unit time period; determine the second weighted cumulative distribution value corresponding to each unit time period based on the message sending / receiving ratio corresponding to each unit time period; determine the second upper quartile and the second lower quartile of the second weighted cumulative distribution value based on the quartile method according to the second weighted cumulative distribution value corresponding to each unit time period; determine the minimum threshold and the maximum threshold of the second weighted cumulative distribution value based on the second upper quartile and the second lower quartile; determine the message sending / receiving ratio threshold based on the message sending / receiving ratio corresponding to the unit time period corresponding to the second weighted cumulative distribution value within a second range, wherein the second range is from the second weighted cumulative distribution value corresponding to the minimum threshold to the second weighted cumulative distribution value corresponding to the maximum threshold.

[0098] In an exemplary embodiment, the second determination module 230 is specifically used to: determine the message sending and receiving weight corresponding to each unit time period based on the message sending and receiving ratio corresponding to each unit time period; sort the message sending and receiving weights corresponding to each unit time period in order from large to small; and calculate the second weighted cumulative distribution value corresponding to each unit time period after sorting.

[0099] In an exemplary embodiment, the second determination module 230 is specifically used to: determine the second interquartile range based on the second upper quartile and the second lower quartile; determine the minimum threshold and the maximum threshold of the second weighted cumulative distribution value based on the second upper quartile, the second lower quartile and the second interquartile range.

[0100] In an exemplary embodiment, the second determination module 230 is specifically used to: determine the lowest threshold of the second weighted cumulative distribution value as the difference between the second upper quartile and M times the second interquartile range, where M is a real number greater than 0; determine the highest threshold of the second weighted cumulative distribution value as the sum of the second lower quartile and M times the second interquartile range.

[0101] In an exemplary embodiment, the second determination module 230 is specifically used to: determine the first message send-receive ratio average value corresponding to the unit time period based on the message send-receive ratio value corresponding to each unit time period corresponding to the second range; determine the second message send-receive ratio average value using a standard deviation formula based on the message send-receive ratio value corresponding to each unit time period and the first message send-receive ratio average value; determine the message send-receive ratio threshold value based on the first message send-receive ratio average value and the second message send-receive ratio average value.

[0102] In an exemplary embodiment, the identification module 240 is specifically used to: obtain the target message sending volume and the target message receiving volume corresponding to the target unit time period of the calling number in the second time period; determine the target message sending frequency and the target message sending-receiving ratio of the calling number in the target unit time period based on the target message sending volume and the target message receiving volume; and perform status identification on the calling number based on the target message sending frequency, the target message sending-receiving ratio, the message sending frequency threshold and the message sending-receiving ratio threshold. In an exemplary embodiment, the identification module 240 is specifically used for one of the following: when the target message sending frequency is less than the message sending frequency threshold, and the target message sending-receiving ratio is less than the message sending-receiving ratio threshold, determining that the state of the calling number is normal; when the target message sending frequency is greater than or equal to the message sending frequency threshold, and the target message sending-receiving ratio is less than the message sending-receiving ratio threshold, determining that the state of the calling number is suspected abnormal; when the target message sending frequency is less than the message sending frequency threshold, and the target message sending-receiving ratio is greater than or equal to the message sending-receiving ratio threshold, determining that the state of the calling number is the suspected abnormal; when the target message sending frequency is greater than or equal to the message sending frequency threshold, and the target message sending-receiving ratio is greater than or equal to the message sending-receiving ratio threshold, determining that the state of the calling number is the abnormal.

[0103] In an exemplary embodiment, the identification module 240 is specifically used for one of the following: when the status of the calling number is the suspected abnormality, performing an in-depth review of the messages sent by the calling number within the target time period; when the status of the calling number is the abnormality, intercepting the messages sent by the calling number to the called number.

[0104] The number status identification device provided in the embodiment of the present application can realize Figure 1 To avoid repetition, the various processes implemented in the illustrated method embodiment will not be described again here.

[0105] A number status identification device in the embodiment of the present application may be a device, or a component, an integrated circuit, or a chip in an electronic device. The embodiment of the present application is not specifically limited.

[0106] A number status identification device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0107] Optional, such as Figure 3 As shown, an embodiment of the present application also provides an electronic device 300, including a processor 310, a memory 320, and a program or instruction stored in the memory 320 and executable on the processor 310. When the program or instruction is executed by the processor 310, each process of the above-mentioned number status identification method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0108] An embodiment of the present application also provides a computer-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned number status identification method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0109] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0110] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned number status identification method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0111] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0112] The embodiment of the present application also provides a computer program product, which includes at least one computer program. When the computer program is loaded and executed by a processor, it implements the various processes of the above-mentioned number status identification method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0113] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0115] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for identifying number status, characterized in that: include: Obtaining the number of messages sent and received corresponding to each unit time period of the calling number in the first time period, wherein the number of messages sent is the number of messages sent to the called number, and the number of messages received is the number of messages received from the called number; Determine, based on the quartile method, a message sending frequency threshold within the unit time period corresponding to the calling number according to the message sending amount and the message receiving amount corresponding to each unit time period; According to the message sending amount and the message receiving amount corresponding to each of the unit time periods, determining a message sending-receiving ratio threshold value within the unit time period corresponding to the calling number based on the quartile method; Based on the message sending frequency threshold and the message sending-receiving ratio threshold, the calling number is identified in status.

2. The method according to claim 1, characterized in that The determining, based on the quartile method according to the message sending amount and the message receiving amount corresponding to each of the unit time periods, the message sending frequency threshold within the unit time period corresponding to the calling number comprises: Determine a first weighted cumulative distribution value corresponding to each unit time period according to the message sending amount corresponding to each unit time period; According to the first weighted cumulative distribution value corresponding to each of the unit time periods, determine the first upper quartile and the first lower quartile of the first weighted cumulative distribution value based on the quartile method; Determine a minimum threshold and a maximum threshold of the first weighted cumulative distribution value based on the first upper quartile and the first lower quartile; The message sending frequency threshold is determined based on the message sending volume corresponding to the unit time period corresponding to the first weighted cumulative distribution value within a first range, wherein the first range is from the first weighted cumulative distribution value corresponding to the lowest threshold to the first weighted cumulative distribution value corresponding to the highest threshold.

3. The method according to claim 2, characterized in that The determining, according to the message sending amount and the message receiving amount corresponding to each unit time period, a first weighted cumulative distribution value corresponding to each unit time period includes: Determine a message sending weight corresponding to each unit time period according to the message sending amount corresponding to each unit time period; Sort the message sending weights corresponding to each of the unit time periods in descending order; The first weighted cumulative distribution value corresponding to each of the sorted unit time periods is calculated.

4. The method according to claim 2, characterized in that: The determining the lowest threshold and the highest threshold of the first weighted cumulative distribution value based on the first upper quartile and the first lower quartile comprises: determining a first interquartile range based on the first upper quartile and the first lower quartile; Based on the first upper quartile, the first lower quartile, and the first interquartile range, a minimum threshold and a maximum threshold of the first weighted cumulative distribution value are determined.

5. The method according to claim 4, characterized in that The determining, based on the first upper quartile, the first lower quartile and the first interquartile range, a minimum threshold and a maximum threshold of the first weighted cumulative distribution value comprises: Determine the lowest threshold of the first weighted cumulative distribution value as the difference between the first upper quartile and K times the first interquartile range, where K is a real number greater than 0; The highest threshold of the first weighted cumulative distribution value is determined to be the sum of the first lower quartile and K times the first interquartile range.

6. The method according to claim 2, characterized in that The determining the message sending frequency threshold based on the message sending amount corresponding to the unit time period corresponding to the first weighted cumulative distribution value within the first range includes: Determine an average value of the first message sending frequency corresponding to the unit time period based on the message sending amount corresponding to each unit time period corresponding to the first range; Based on the message sending amount corresponding to each of the unit time periods and the first message sending frequency average value, determine the second message sending frequency average value by using a standard deviation formula; The message sending frequency threshold is determined based on the first message sending frequency average value and the second message sending frequency average value.

7. The method according to claim 1, characterized in that The determining, based on the quartile method and according to the message sending amount and the message receiving amount corresponding to each of the unit time periods, a message sending-receiving ratio threshold value within the unit time period corresponding to the calling number, comprises: Determine a message sending-receiving ratio corresponding to each unit time period according to the message sending amount and the message receiving amount corresponding to each unit time period; Determine a second weighted cumulative distribution value corresponding to each unit time period based on the message sending / receiving ratio corresponding to each unit time period; According to the second weighted cumulative distribution value corresponding to each of the unit time periods, determining the second upper quartile and the second lower quartile of the second weighted cumulative distribution value based on the quartile method; Determine a minimum threshold and a maximum threshold of the second weighted cumulative distribution value based on the second upper quartile and the second lower quartile; The message sending-receiving ratio threshold is determined based on the message sending-receiving ratio corresponding to the unit time period corresponding to the second weighted cumulative distribution value within a second range, wherein the second range is from the second weighted cumulative distribution value corresponding to the lowest threshold to the second weighted cumulative distribution value corresponding to the highest threshold.

8. The method according to claim 7, characterized in that The determining, according to the message sending amount and the message receiving amount corresponding to each unit time period, a second weighted cumulative distribution value corresponding to each unit time period includes: Determine the message sending and receiving weight corresponding to each unit time period based on the message sending and receiving ratio corresponding to each unit time period; Sort the message sending and receiving weights corresponding to each of the unit time periods in descending order; The second weighted cumulative distribution value corresponding to each of the sorted unit time periods is calculated.

9. The method according to claim 7, characterized in that: The step of determining a minimum threshold and a maximum threshold of the second weighted cumulative distribution value based on the second upper quartile and the second lower quartile comprises: determining a second interquartile range based on the second upper quartile and the second lower quartile; Based on the second upper quartile, the second lower quartile, and the second interquartile range, a lowest threshold and a highest threshold of the second weighted cumulative distribution value are determined.

10. The method according to claim 9, characterized in that The step of determining a minimum threshold and a maximum threshold of the second weighted cumulative distribution value based on the second upper quartile, the second lower quartile, and the second interquartile range comprises: Determine the lowest threshold of the second weighted cumulative distribution value as the difference between the second upper quartile and M times the second interquartile range, where M is a real number greater than 0; The highest threshold of the second weighted cumulative distribution value is determined to be the sum of the second lower quartile and M times the second interquartile range.

11. The method according to claim 7, characterized in that The determining the message sending-receiving ratio threshold value based on the message sending-receiving ratio value corresponding to the unit time period corresponding to the second weighted cumulative distribution value within the second range includes: Determine an average value of the first message sending / receiving ratio corresponding to the unit time period based on the message sending / receiving ratio corresponding to each unit time period corresponding to the second range; Determine a second message sending-receiving ratio average value by using a standard deviation formula based on the message sending-receiving ratio values ​​corresponding to each of the unit time periods and the first message sending-receiving ratio average value; The message sending-receiving ratio threshold is determined based on the first message sending-receiving ratio average value and the second message sending-receiving ratio average value.

12. The method according to claim 1, characterized in that The performing status identification on the calling number based on the message sending frequency threshold and the message sending-receiving ratio threshold includes: Obtaining a target message sending volume and a target message receiving volume corresponding to a target unit time period of the calling number in a second time period; Determine the target message sending frequency and the target message sending-receiving ratio of the calling number within the target unit time period based on the target message sending volume and the target message receiving volume; The calling number is identified in status based on the target message sending frequency, the target message sending / receiving ratio, the message sending frequency threshold, and the message sending / receiving ratio threshold.

13. The method according to claim 12, characterized in that The performing status identification on the calling number based on the target message sending frequency, the target message sending-receiving ratio, the message sending frequency threshold and the message sending-receiving ratio threshold comprises one of the following: When the target message sending frequency is less than the message sending frequency threshold, and the target message sending-receiving ratio is less than the message sending-receiving ratio threshold, determining that the state of the calling number is normal; When the target message sending frequency is greater than or equal to the message sending frequency threshold, and the target message sending-receiving ratio is less than the message sending-receiving ratio threshold, determining that the state of the calling number is suspected abnormal; When the target message sending frequency is less than the message sending frequency threshold, and the target message sending-receiving ratio is greater than or equal to the message sending-receiving ratio threshold, determining that the state of the calling number is the suspected abnormality; When the target message sending frequency is greater than or equal to the message sending frequency threshold, and the target message sending-receiving ratio is greater than or equal to the message sending-receiving ratio threshold, it is determined that the state of the calling number is abnormal.

14. The method according to claim 13, characterized in that After the state of the calling number is identified based on the target message sending frequency, the target message sending-receiving ratio, the message sending frequency threshold and the message sending-receiving ratio threshold, the method further includes one of the following: When the status of the calling number is the suspected abnormality, an in-depth review is performed on the messages sent by the calling number within the target time period; When the state of the calling number is the abnormality, a message sent by the calling number to the called number is intercepted.

15. A number status identification device, characterized in that: include: An acquisition module, used to acquire the message sending amount and message receiving amount corresponding to each unit time period of the calling number in the first time period, wherein the message sending amount is the number of messages sent to the called number, and the message receiving amount is the number of messages received from the called number; A first determination module is used to determine the message sending frequency threshold within the unit time period corresponding to the calling number based on the quartile method according to the message sending amount and the message receiving amount corresponding to each unit time period; A second determination module is used to determine a message sending-receiving ratio threshold value within the unit time period corresponding to the calling number based on the quartile method according to the message sending amount and the message receiving amount corresponding to each unit time period; The identification module is used for identifying the status of the calling number based on the message sending frequency threshold and the message sending-receiving ratio threshold.

16. An electronic device, characterized in that: It comprises a processor, a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the number status identification method as described in any one of claims 1 to 14.

17. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the number status identification method according to any one of claims 1 to 14 are implemented.

18. A computer program product, characterized in that The computer program product includes program instructions, and when the program instructions are executed by a computer, the computer implements the steps of the number status identification method according to any one of claims 1 to 14.

Images