Method, device, electronic device, and storage medium for identifying harassing numbers

Abstract

The present application provides a method, device, electronic device and storage medium for identifying harassing numbers. The method includes: determining a candidate number that meets a first condition based on the call parameters of each number; for each candidate number, determining the resident area of the called number corresponding to the candidate number, and calculating the number of calls for each of the resident areas; calculating the ratio of the sum of the number of calls for the top predetermined number of resident areas to the sum of the number of calls for all the resident areas according to the number of calls from most to least; if the ratio is greater than a preset second threshold, the candidate number is determined to be a non-harassing number; otherwise, the candidate number is determined to be a harassing number. The solution of the present application improves the accuracy of harassing number identification.

Description

Technical Field

[0001] The present application relates to communications, and in particular to a method, device, electronic device, and storage medium for identifying harassing numbers. Background Art

[0002] With economic development, telephone marketing and telecommunications fraud are emerging in an endless stream. Nuisance calls have seriously affected people's daily lives. Accurate marking of nuisance numbers can effectively avoid the impact of nuisance calls on users.

[0003] Currently, numbers with high calling frequency, low called frequency, short call duration, and low called number repetition rate are marked as spam calls. However, current spam number identification schemes can lead to mislabeling. For example, numbers used for community services, express delivery, food delivery, and other public services may be mistakenly marked as spam calls based on current schemes. Therefore, current spam number identification schemes have low accuracy. Summary of the Invention

[0004] The present application provides a method, device, electronic device, and storage medium for identifying a harassing number, to solve the problem of low accuracy in identifying harassing numbers.

[0005] In the first aspect, the present application provides a method for identifying harassing numbers, including: determining a candidate number that meets a first condition based on the call parameters of each number; wherein the call parameters represent the call frequency of the number, and the first condition is that the call frequency exceeds a preset first threshold; for each candidate number, determining the resident area of the called number corresponding to the candidate number, and calculating the number of calls for each resident area; wherein the number of calls for the resident area is the sum of the number of calls of all called numbers belonging to the resident area among the called numbers corresponding to the candidate number; calculating the ratio of the sum of the number of calls of the top predetermined number of resident areas to the sum of the number of calls of all the resident areas according to the number of calls from most to least; if the ratio is greater than a preset second threshold, the candidate number is determined to be a non-harassing number; otherwise, the candidate number is determined to be a harassing number.

[0006] In one possible implementation, the call parameters include the proportion of callers, the number of calls, and the proportion of local called numbers; determining the candidate numbers that meet the first condition based on the call parameters of each number includes: obtaining the call record data of each number in the first time period; obtaining the proportion of callers, the number of calls, and the proportion of local called numbers for each number based on the call record data; wherein the proportion of local called numbers of the number is the proportion of local numbers in the called numbers corresponding to the number; and taking the numbers whose proportion of callers exceeds the first sub-threshold, the number of calls exceeds the second sub-threshold, and the proportion of local called numbers exceeds the third sub-threshold as the candidate numbers.

[0007] In one possible implementation, obtaining the local called number ratio of each number based on the call bill data includes: determining, for each of the numbers, the calling area of each call made by the number within the first time period; wherein the calling area of the call is the location of the called number in the call; if the calling area with the most calls within the first time period is consistent with the location of the number, then the number is regarded as a local number; and calculating the ratio of local numbers in the called numbers corresponding to the number as the local called number ratio of the number.

[0008] In one possible implementation, determining the permanent area of the called number corresponding to each candidate number includes: determining the permanent work area, permanent residential area and broadband installation area of the called number corresponding to the candidate number; and for each called number corresponding to the candidate number, taking the common area to which the permanent work area, permanent residential area and broadband installation area of the called number belong as the permanent area of the called number.

[0009] In one possible implementation, determining the permanent working area of the called number corresponding to the candidate number includes: determining, for each called number corresponding to the candidate number, the area code and base station identifier of the region used for each call by the called number within the second time period; determining, based on the area code and base station identifier, the base station used for each call by the called number within the second time period; and, based on the base station used for each call by the called number within the second time period, selecting, as the permanent working area of the called number, the area where the base station used most times within the second time period is located.

[0010] In one possible implementation, determining the permanent residential area of the called number corresponding to the candidate number includes: determining, for each called number corresponding to the candidate number, an Internet access address used by the called number for each Internet access within a third time period; and based on the Internet access address used by the called number for each Internet access within the third time period, taking the area where the Internet access address with the longest cumulative access time is located as the permanent residential area of the called number.

[0011] In one possible implementation, determining the broadband installation area of the called number corresponding to the candidate number includes: obtaining the broadband installation address of the called number for each called number corresponding to the candidate number; and using the area where the broadband installation address is located as the broadband installation area of the called number.

[0012] In a second aspect, the present application provides a device for identifying a harassing number, including: a screening module for determining, based on the call parameters of each number, a candidate number that meets a first condition; wherein the call parameters represent the call frequency of the number, and the first condition is that the call frequency exceeds a preset first threshold; a processing module for determining, for each candidate number, the resident area of the called number corresponding to the candidate number; a calculation module for calculating the number of calls received in each of the resident areas; wherein the number of calls received in the resident area is the sum of the number of calls received of all called numbers belonging to the resident area among the called numbers corresponding to the candidate number; the calculation module is further used to calculate, from the most to the least number of calls, the ratio of the sum of the number of calls received of the top predetermined number of resident areas to the sum of the number of calls received of all the resident areas; a determination module for determining, if the ratio is greater than a preset second threshold, that the candidate number is a non-harassing number; otherwise, determining that the candidate number is a harassing number.

[0013] In one possible implementation, the call parameters include the proportion of callers, the number of calls, and the proportion of local called numbers; the screening module includes: a first acquisition unit, used to obtain the call record data of each number in the first time period; a second acquisition unit, used to obtain the proportion of callers, the number of calls, and the proportion of local called numbers for each number based on the call record data; wherein the proportion of local called numbers of the number is the proportion of local numbers in the called numbers corresponding to the number; the screening unit is used to select the numbers whose proportion of callers exceeds the first sub-threshold, the number of calls exceeds the second sub-threshold, and the proportion of local called numbers exceeds the third sub-threshold as the candidate numbers.

[0014] In a possible implementation, the second acquisition unit is specifically configured to: determine, for each of the numbers, a calling area for each call made by the number within the first time period; wherein the calling area of the call is the location of the called number in the call; if the calling area with the most calls within the first time period is consistent with the location of the number, then the number is regarded as a local number; and calculate the proportion of local numbers in the called numbers corresponding to the number as the proportion of local called numbers of the number.

[0015] In one possible implementation, the processing module is specifically used to: determine the permanent work area, permanent residential area and broadband installation area of the called number corresponding to the candidate number; for each called number corresponding to the candidate number, use the common area to which the permanent work area, permanent residential area and broadband installation area of the called number belong as the permanent area of the called number.

[0016] In one possible implementation, the processing module includes: a first determination unit; the first determination unit is used to: determine, for each called number corresponding to the candidate number, the area code and base station identifier of the area used for each call by the called number within the second time period; determine, based on the area code and base station identifier, the base station used for each call by the called number within the second time period; based on the base station used for each call by the called number within the second time period, determine the area where the base station used most times within the second time period is located as the permanent working area of the called number.

[0017] In one possible implementation, the processing module includes: a second determination unit; the second determination unit is used to: determine, for each called number corresponding to the candidate number, an Internet access address used by the called number for each Internet access within a third time period; based on the Internet access address used by the called number for each Internet access within the third time period, the area where the Internet access address with the longest cumulative access time is located is located as the permanent residential area of the called number.

[0018] In one possible implementation, the processing module includes: a third determination unit; the third determination unit is used to: obtain the broadband installation address of each called number corresponding to the candidate number; and use the area where the broadband installation address is located as the broadband installation area of the called number.

[0019] In a third aspect, the present application provides an electronic device comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; and the processor executes the computer-executable instructions stored in the memory to implement the method described above.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to implement the method as described above when executed by a processor.

[0021] In the harassment number identification method, device, electronic device and storage medium provided by the present application, the candidate numbers that meet the first condition are determined according to the call parameters of each number; for each candidate number, the resident area of the called number corresponding to the candidate number is determined, and the number of calls in each resident area is calculated; according to the number of calls from most to least, the ratio of the sum of the number of calls in the top predetermined number of resident areas to the sum of the number of calls in all resident areas is calculated; if the ratio is greater than the preset second threshold, the candidate number is determined to be a non-harassment number; otherwise, the candidate number is determined to be a harassment number. The solution of the present application determines whether the called numbers corresponding to the candidate number are concentrated in a predetermined number of resident areas by judging whether the ratio of the sum of the number of calls in the top predetermined number of resident areas to the sum of the number of calls in all resident areas is greater than the second threshold, thereby identifying whether the candidate number is a harassment number and improving the accuracy of harassment number identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0023] Figure 1 Schematic diagram of the scenario for identifying harassing numbers provided for this application;

[0024] Figure 2 A flowchart of the method for identifying harassing numbers provided in Example 1 of this application;

[0025] Figure 3 This is a flowchart of the method for identifying harassing numbers provided in Example 2 of this application;

[0026] Figure 4 This is a schematic diagram of the structure of the harassment number identification device provided in Example 4 of this application;

[0027] Figure 5 This is a structural diagram of an electronic device provided in Example 5 of the present application.

[0028] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0029] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0030] It should be noted that the brief descriptions of terms in this application are only for the purpose of facilitating the understanding of the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and usual meanings.

[0031] In the specification and claims of this application and the drawings, the terms "first," "second," and the like are used to distinguish similar or similar objects or entities and are not necessarily intended to limit a particular order or precedence, unless otherwise indicated. It should be understood that the terms used in this manner are interchangeable where appropriate, for example, the embodiments of this application can be implemented in an order other than that shown or described in the drawings.

[0032] In addition, the terms "including" and "having" and any variations thereof are intended to cover, but not exclude, inclusion. For example, a product or device comprising a list of components is not necessarily limited to those components explicitly listed, but may include other components not explicitly listed or inherent to such products or devices. The term "module" as used in this application refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with the element.

[0033] The technical solutions of the present application and the technical solutions of the present application are described in detail below with reference to specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in certain embodiments. In the description of the present application, unless otherwise clearly specified and limited, each term should be understood in a broad sense within the art. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0034] Figure 1 This is a schematic diagram of the scenario for identifying harassing numbers provided by this application. Figure 1 As shown, the operator 101 identifies the numbers in the to-be-identified number set 100 , stores the numbers identified as spam numbers in the spam number set 102 , and stores the numbers identified as non-spam numbers in the non-spam number set 103 .

[0035] In practice, harassing calls are characterized by high calling frequency, low called frequency, short call duration, and low called number repetition rate. Accurately identifying harassing numbers can prevent them from impacting people's daily lives. Based on the actual scenario, numbers 1 and 3 have high calling frequency, low called frequency, short call duration, and low called number repetition rate. Therefore, the operator identifies numbers 1, 2, and 3 as harassing numbers and stores them in the harassing number collection. Numbers 3, 4, and 5 do not have the characteristics of harassing calls and are therefore identified as non-harassing calls and stored in the non-harassing call collection.

[0036] However, current spam number identification schemes can lead to mislabeling. For example, numbers used for community services, express delivery, food delivery, and other public services may be mislabeled as spam calls. Therefore, current spam number identification schemes have low accuracy.

[0037] In an embodiment of the present application, by judging whether the ratio of the sum of the number of called numbers in the top predetermined number of resident areas to the sum of the number of called numbers in all resident areas is greater than a second threshold, it is determined whether the called numbers corresponding to the candidate number are concentrated in the predetermined number of resident areas, thereby identifying whether the candidate number is a harassment number, thereby improving the accuracy of harassment number identification.

[0038] Example 1

[0039] Figure 2 This is a flow chart of the method for identifying a harassing number provided in the first embodiment of the present application. The implementation subject of this embodiment may be a harassing number identification device, such as Figure 2 As shown, the method includes:

[0040] S201. Determine candidate numbers that meet a first condition based on call parameters of each number.

[0041] S202: For each candidate number, determine the resident zone of the called number corresponding to the candidate number, and calculate the number of called times in each resident zone;

[0042] S203. Calculate the ratio of the sum of the number of called times of the top predetermined number of resident zones to the sum of the number of called times of all resident zones, in descending order of the number of called times;

[0043] S204, determining whether the ratio is greater than a second threshold;

[0044] S205. If the ratio is greater than a preset second threshold, the candidate number is determined to be a non-harassing number;

[0045] S206: If the ratio is not greater than a preset second threshold, the candidate number is determined to be a harassing number.

[0046] In this embodiment, the call parameter represents the call frequency of the number, and the first condition is that the call frequency exceeds a preset first threshold. In actual applications, the call frequency of harassing numbers is relatively high. By determining whether the call frequency exceeds the preset first threshold, candidate numbers that may be harassing numbers can be preliminarily screened.

[0047] In practical applications, the executor of the identification method may be a jitter number identification device. There are many ways to implement the jitter number identification device. For example, it can be implemented through a computer program, such as application software; or it can be implemented as a medium storing the relevant computer program, such as a USB flash drive, a cloud disk, etc.; or it can be implemented through a physical device that integrates or installs the relevant computer program, such as a chip.

[0048] Specifically, in S201, candidate numbers that meet the first condition are determined based on the call parameters of each number. For example, the call frequency of number 1 is 10 times per hour, the call frequency of number 2 is 30 times per hour, and the call frequency of number 3 is 50 times per hour. The preset first threshold is 20 times per hour. The first condition is that the call frequency exceeds 20 times per hour. Numbers 2 and 3 meet the first condition, and numbers 2 and 3 are selected as candidate numbers.

[0049] The number of called numbers in a resident zone is the sum of the number of called numbers in the resident zone for the candidate number. In practice, a called number corresponds to a unique resident zone, and among the called numbers corresponding to a candidate number, there may be called numbers with the same resident zone. In other words, a resident zone may correspond to multiple called numbers. Therefore, the number of called numbers in a resident zone is the sum of the number of called numbers in the resident zone.

[0050] Specifically, S202 calculates the number of called calls in each resident area. For example, candidate number 1 corresponds to called number 1, called number 2, called number 3, called number 4, called number 5, and called number 6. The resident areas corresponding to called number 1, called number 2, and called number 3 are all resident area A; the resident areas corresponding to called number 4 and called number 5 are resident area B; and the resident area corresponding to called number 6 is resident area C. Called number 1 has been called 15 times in resident area A, called number 2 has been called 20 times in resident area A, and called number 3 has been called 35 times in resident area A; called number 4 has been called 10 times in resident area B, called number 5 has been called 15 times in resident area B, and called number 6 has been called 20 times in resident area C. Therefore, the sum of the number of times called numbers 1, 2, and 3 were called in resident area A is calculated, and the number of times called numbers in resident area A is 70. The sum of the number of times called numbers 4 and 5 were called in resident area B is calculated, and the number of times called numbers in resident area B is 25. The only called number in resident area C is called number 6. The number of times called number 6 was called in resident area C is counted as the number of times called number 6 was called in resident area C, and the number of times called number 6 was called in resident area C is 20.

[0051] Correspondingly, in S203, the ratio of the sum of the number of calls received by the top predetermined number of resident zones to the sum of the number of calls received by all resident zones is calculated, from the highest to the lowest number of calls received. In the above example, resident zone A has 70 calls received, resident zone B has 25 calls received, and resident zone C has 20 calls received. The sum of the number of calls received by the top two resident zones with the most calls received is 95 times, and the sum of the number of calls received by all resident zones is 115 times. The ratio of the sum of the number of calls received by the top two resident zones with the most calls received to the sum of the number of calls received by all resident zones is 0.83.

[0052] In actual applications, the resident areas of the called numbers of harassment numbers are more dispersed, while the resident areas of the called numbers of people's livelihood service numbers are more concentrated. It can be understood that by judging whether the ratio of the sum of the number of called numbers in the top predetermined number of resident areas to the sum of the number of called numbers in all resident areas is greater than the second threshold, it can be determined whether the called numbers corresponding to the candidate numbers are concentrated in the predetermined number of resident areas, thereby identifying whether the candidate numbers are harassment numbers. For example, the ratio corresponding to candidate number 1 is 0.83, the ratio corresponding to candidate number 2 is 0.35, and the preset second threshold is 0.5. If the ratio corresponding to candidate number 1 is greater than the second threshold, candidate number 1 is determined to be a non-harassment number, and if the ratio corresponding to candidate number 2 is less than the second threshold, candidate number 2 is determined to be a harassment number.

[0053] It should be noted that for each operator, only the communication parameters of each number in this network can be obtained. It can be understood that the called number corresponding to the candidate number is the called number of this network. Optionally, according to the number of called numbers, the ratio of the sum of the number of called numbers in the top predetermined number of resident areas and the total number of calls of the candidate number is calculated; if the ratio is greater than the preset third threshold, the candidate number is determined to be a non-harassment number; otherwise, the candidate number is determined to be a harassment number. The third threshold is the second threshold multiplied by the mobile user market share of this network.

[0054] Optionally, the accuracy of the results of harassing number identification is verified. For example, for candidate number set A, the harassing number identification method of this embodiment and the manual identification method are used to obtain non-harassing number set B and non-harassing number set C, respectively. The ratio of the intersection of non-harassing number set B and non-harassing number set C to non-harassing number set C is calculated. If the ratio is greater than the fourth threshold, it is determined that the accuracy of the harassing number identification result meets the requirements.

[0055] In addition, candidate numbers may be determined based on the caller ratio, call frequency, and local called number ratio of each number. In one possible implementation, the call parameters include the caller ratio, call frequency, and local called number ratio. S201 includes:

[0056] Obtain the call bill data of each number in the first time period;

[0057] Based on the call bill data, obtain the caller ratio, call times, and local called number ratio of each number;

[0058] Numbers whose calling number ratio exceeds the first sub-threshold, the number of calling numbers exceeds the second sub-threshold, and the local called number ratio exceeds the third sub-threshold are selected as candidate numbers.

[0059] The calling ratio of a number is the ratio of calling numbers to the number of calls corresponding to that number; the local called number ratio of a number is the ratio of local numbers to the number of called numbers corresponding to that number.

[0060] In practice, harassing numbers are characterized by a high proportion of outgoing calls, a high number of outgoing calls, and widely dispersed locations of the called users. It's understandable that numbers with an outgoing call percentage exceeding the first sub-threshold, an outgoing call number exceeding the second sub-threshold, and a local called number percentage exceeding the third sub-threshold could be either harassing or non-harassing numbers.

[0061] In this implementation, numbers whose caller ratio exceeds the first sub-threshold, whose call count exceeds the second sub-threshold, and whose local called number ratio exceeds the third sub-threshold are selected as candidate numbers. This effectively determines the number range in which non-harassing numbers may exist, and by identifying candidate numbers, the efficiency of identifying harassing numbers can be improved.

[0062] In addition, regarding the calculation of the proportion of local called numbers, in one possible implementation, obtaining the proportion of local called numbers for each number based on call bill data includes:

[0063] For each of the numbers, determining a calling area for each call made by the number during the first time period;

[0064] If the calling area with the most calls in the first period is the same as the number's location, the number is considered a local number;

[0065] Calculate the percentage of local numbers among the called numbers corresponding to the number, and use this percentage as the local called number percentage for the number.

[0066] The calling area of a call is the location of the called number in the call. In actual applications, during the first time period, the calling area with the most calls is consistent with the location of the number, indicating that during the first time period, the called numbers of the number calls are mainly concentrated in the location of the number, so the number is considered a local number. For example, during the first time period, the location of number 1 is area A, the location of number 2 is area B, the calling area with the most calls for number 1 is area C, and the calling area with the most calls for number 2 is area B. The calling area with the highest call coefficient for number 1 is inconsistent with the location of number 1, so number 1 is considered an out-of-town number, and the calling area with the highest call coefficient for number 2 is consistent with the location of number 2, so number 2 is considered a local number.

[0067] In this implementation, for each number, whether it is a local number is determined by determining whether the calling area with the most calls during the first time period is consistent with the number's location. The percentage of local numbers among the called numbers corresponding to the number is calculated to determine the percentage of local called numbers for the number. Candidate numbers can be identified based on the percentage of outgoing calls, the number of outgoing calls, and the number of local called numbers, improving the efficiency of identifying nuisance numbers.

[0068] In the method for identifying harassing numbers provided in this embodiment, based on the call parameters of each number, a candidate number that meets the first condition is determined; for each candidate number, the resident area of the called number corresponding to the candidate number is determined, and the number of calls in each resident area is calculated; according to the number of calls, the ratio of the sum of the number of calls in the top predetermined number of resident areas to the sum of the number of calls in all resident areas is calculated; if the ratio is greater than a preset second threshold, the candidate number is determined to be a non-harassing number; otherwise, the candidate number is determined to be a harassing number. In this embodiment, by judging whether the ratio of the sum of the number of calls in the top predetermined number of resident areas to the sum of the number of calls in all resident areas is greater than the second threshold, it is determined whether the called numbers corresponding to the candidate number are clustered in a predetermined number of resident areas, thereby identifying whether the candidate number is a harassing number and improving the accuracy of harassing number identification.

[0069] Example 2

[0070] Figure 3 This is a flow chart of the method for identifying harassing numbers provided in Example 2 of this application, as shown in FIG. Figure 3 As shown, S202 specifically includes:

[0071] S301, determining the permanent work area, permanent residential area, and broadband installation area of the called number corresponding to the candidate number;

[0072] S302: For each called number corresponding to the candidate number, the common area of the called number's permanent work area, permanent residential area, and broadband installation area is taken as the permanent area of the called number, and the number of calls in each permanent area is calculated.

[0073] Among them, the permanent work area of the called number is the work area where the called number user has the most calls within a certain period of time. The permanent residential area of the called number is the residential area where the called number user has the longest cumulative Internet access time within a certain period of time. The broadband installation area of the called number is the area where the broadband installation address under the same certificate as the called number is located. For example, the permanent work area of the called number is the community or town where the work address of the called number user is located, where the called number user has the most calls; the permanent residential area of the called number is the community or town where the residential address of the called number user has the longest cumulative Internet access time; the broadband installation area of the called number is the jurisdiction of the operator branch that installs the broadband.

[0074] Specifically, for each called number corresponding to a candidate number, the common area of the called number's permanent work area, permanent residential area, and broadband installation area is used as the called number's permanent area. For example, the permanent work area corresponding to called number 1 is Community A, the permanent residential area corresponding to called number 1 is Community B, and the broadband installation area corresponding to called number 1 is Area C under the jurisdiction of Broadband Branch 1. The common area of Community A, Community B, and Area C is Attribution Area D, and Attribution Area D is used as the permanent area of called number 1.

[0075] It can be understood that the common area of the called number's permanent work area, permanent residential area, and broadband installation area covers the called number's user's activity area and can accurately represent the called number's permanent area. Therefore, using the common area of the called number's permanent work area, permanent residential area, and broadband installation area as the called number's permanent area can accurately determine the called number's permanent area.

[0076] Optionally, the permanent working area of the called number can be determined based on the area where the base station with the most number of calls made by the called number in the second time period is located. In one possible implementation, determining the permanent working area of the called number corresponding to the candidate number in S301 includes:

[0077] For each called number corresponding to the candidate number, determining the area code and base station identifier of each call made by the called number during the second time period;

[0078] determining, based on the area code and the base station identifier, the base station used for each call by the called number during the second time period;

[0079] According to the base stations used for each call by the called number in the second time period, the area where the base station used most times in the second time period is located is used as the permanent working area of the called number.

[0080] Among them, the Location Area Code (LAC) is used to divide and identify the location area, and the Cell Tower ID (CID) represents a mobile base station.

[0081] In practical applications, the area code and base station identifier can be used to uniquely determine the base station address. Therefore, based on the area code and base station identifier of each call made by the called number, the base station used by the called number for each call, as well as the address of the base station used for each call, can be determined. It is understood that the area in which the address of the base station used by the called number for each call is located is consistent with the area in which the called number was located for each call.

[0082] In this embodiment, based on the address of the base station used by the called number for each call in the second time period, the area where the base station used most times in the second time period is located is used as the permanent working area of the called number, thereby obtaining an accurate permanent working area of the called number.

[0083] Optionally, the permanent residential area of the called number may be determined based on the area where the Internet access address with the longest cumulative access time of the called number in the third time period is located. In one possible implementation, determining the permanent residential area of the called number corresponding to the candidate number in S301 includes:

[0084] For each called number corresponding to the candidate number, determining an Internet access address for each Internet access of the called number within the third time period;

[0085] According to the Internet access address of the called number each time during the third period, the area where the Internet access address with the longest cumulative access time is located is used as the permanent residential area of the called number.

[0086] In actual applications, based on home broadband and wireless network information, the Internet access address and access duration of each time the called number accesses the Internet can be determined. It can be understood that the area where the Internet access address with the longest cumulative access duration is located is the area where the called number user has been located the longest.

[0087] In this embodiment, based on the Internet access address of the called number each time during the third period, the area where the Internet access address with the longest cumulative access time during the third period is located is used as the permanent residential area of the called number, thereby obtaining the accurate permanent residential area of the called number.

[0088] In addition, regarding determination of the broadband installation area of the called number, in one possible implementation, determining the broadband installation area of the called number corresponding to the candidate number in S301 includes:

[0089] For each called number corresponding to the candidate number, obtain the broadband installation address of the called number;

[0090] The area where the broadband installation address is located is used as the broadband installation area of the called number.

[0091] It is understood that the broadband installation address is within the jurisdiction of the operator branch that installed the broadband. For example, the jurisdiction of the operator branch that installed the broadband is used as the broadband installation area. Optionally, based on the area divided by the operator, the area where the broadband installation address is located is used as the broadband installation area of the called number.

[0092] In the harassment number identification method provided in this embodiment, the permanent work area, permanent residential area and broadband installation area of the called number corresponding to the candidate number are determined; for each called number corresponding to the candidate number, the common area to which the permanent work area, permanent residential area and broadband installation area of the called number belong is used as the permanent area of the called number. In this embodiment, the common area to which the permanent work area, permanent residential area and broadband installation area of the called number belong is used as the permanent area of the called number, and an accurate permanent area of the called number can be obtained. By judging whether the ratio of the sum of the number of called times of the top predetermined number of resident areas to the sum of the number of called times of all resident areas is greater than the second threshold, it is determined whether the called numbers corresponding to the candidate number are clustered in the predetermined number of resident areas, thereby identifying whether the candidate number is a harassment number, thereby improving the accuracy of harassment number identification.

[0093] Example 3

[0094] To facilitate understanding of the solution, the following example illustrates Example 3 of this application. In this example, candidate numbers are selected for numbers with a call percentage exceeding 70%, a call count exceeding 50, and a local called number percentage exceeding 70% within seven days. The ratio of the sum of the called numbers for the top two resident zones to the sum of the called numbers for all resident zones is calculated, and the ratio is greater than 24%.

[0095] The process of the method for identifying harassing numbers in the third embodiment of the present application includes:

[0096] Step 1: Obtain the call bill data for each number within 7 days.

[0097] For example, the program source code is as follows:

[0098] CREATE TABLE zhuanli_0601AS

[0099] SELECT / *+parallel(d,30)* / d.msisdn,d.call_type,COUNT(*)call_num

[0100] FROM fz_ods_rh_cb_tg_cdr_d d

[0101] WHERE d.acct_month = '202205'

[0102] AND d.day_id IN('25','26','27','28','29','30','31')AND d.net_type_code='50'

[0103] GROUP BY d.msisdn,d.call_type;

[0104] Step 2: Based on the call record data, obtain the middle candidate numbers with a caller ratio of more than 70% and a call count of more than 50 times.

[0105] For example, the program source code is as follows:

[0106] CREATE TABLE zhuanli_0601_1AS

[0107] SELECT msisdn,sum(decode(call_type,'01',call_num,0))calling_num,SUM(call_num)total_num FROM zhuanli_0601

[0108] GROUP BY msisdn

[0109] HAVING sum(decode(call_type,'01',call_num,0))>50AND sum(decode(

[0110] call_type,'01',call_num,0)) / SUM(call_num)>0.7;

[0111] Step 3: Screen the intermediate candidate numbers and select those that meet the requirement of more than 70% of local callers as candidate numbers;

[0112] For example, the program source code is as follows:

[0113] Step 31: Screen the intermediate candidate numbers whose location of the called number is consistent with the location of the called number within 7 days;

[0114] CREATE TABLE zhuanli_0602AS

[0115] SELECT / *+parallel(d,30)* / d.msisdn,decode(d.called_home_code,'022',1,2)

[0116] called_code,COUNT(*)call_num FROM fz_ods_rh_cb_tg_cdr_d d

[0117] WHERE d.acct_month = '202205'

[0118] AND d.day_id IN('25','26','27','28','29','30','31')

[0119] AND d.call_type = '01'

[0120] AND d.net_type_code = '50'

[0121] GROUP BY d.msisdn,decode(d.called_home_code,'022',1,2);

[0122] Step 32: Screening the middle candidate numbers whose local call times of the called numbers are greater than 70%;

[0123] CREATE TABLE zhuanli_0602_1AS

[0124] select z.msisdn,sum(decode(z.called_code,1,call_num,0))home_code,

[0125] SUM(z.call_num)total_num

[0126] FROM zhuanli_0602z

[0127] GROUP BY msisdn

[0128] HAVING sum(decode(z.called_code,1,call_num,0)) / SUM(z.call_num)>0.7;

[0129] Step 33: Screen the middle candidate numbers with a local call ratio of more than 70% as candidate numbers;

[0130] CREATE TABLE zhuanli_0603AS

[0131] SELECT msisdn FROM zhuanli_0602_1

[0132] INTERSECT

[0133] SELECT msisdn FROM zhuanli_0601_1;

[0134] Step 4: For each candidate number, determine the permanent zone of the called number corresponding to the candidate number.

[0135] For example, the program source code is as follows:

[0136] Step 41: Determine the permanent workspace of the called number corresponding to the candidate number;

[0137] For each called number corresponding to the candidate number, determine the area code and base station identifier of each call made by the called number within one month;

[0138] CREATE TABLE zhuanli_0604AS

[0139] SELECT / *+parallel(d,30)* / other_party,COUNT(*)call_num

[0140] FROM fz_ods_rh_cb_tg_cdr_d d

[0141] WHERE d.acct_month = '202205'

[0142] AND d.day_id IN('25','26','27','28','29','30','31')

[0143] AND d.call_type = '01'

[0144] AND d.msisdn IN

[0145] (SELECT z.msisdn FROM zhuanli_0603z)

[0146] GROUP BY other_party;

[0147] CREATE TABLE zhuanli_0504_1AS

[0148] SELECT / *+parallel(d,40)* / d.msisdn,d.lac1,d.cell_id1,COUNT(*)call_num

[0149] FROM fz_ods_rh_cb_tg_cdr_d d

[0150] WHERE d.acct_month='202205'AND d.net_type_code='50'

[0151] AND d.msisdn IN

[0152] (SELECT z.other_party FROM zhuanli_0504z)

[0153] GROUP BY d.msisdn,d.lac1,d.cell_id1;

[0154] Based on the area code and base station identifier, determine the area where the base station used by the called number for each call within a month is located;

[0155] CREATE TABLE zhuanli_0505AS

[0156] SELECT / *+parallel(z,40)* / z.*,d.district

[0157] FROM zhuanli_0504_1z,

[0158] (select d.lac,d.cell_id,d.base_station,d.adr_detail,d.district

[0159] from ods.ods_yd_c_laccell_info_m d

[0160] where d.acct_month in(to_char(add_months(sysdate-1,-1),'yyyymm'),

[0161] to_char(add_months(sysdate-1,-2),'yyyymm'))

[0162] union

[0163] select d.lac,d.cell_id,d.net_name,d.station_name,d.district

[0164] from ods.ods_yd_cb_laccell_info_m d

[0165] where d.acct_month in(to_char(add_months(sysdate-1,-1),'yyyymm'),

[0166] to_char(add_months(sysdate-1,-2),'yyyymm'))

[0167] union

[0168] select t.gnodeb_id lac,t.cell_id cell_id,t.station_name,position_infor,t.district

[0169] from ods.ods_yd_5g_laccell_info_m1 t

[0170] where acct_month in(to_char(add_months(sysdate-1,-1),'yyyymm'),

[0171] to_char(add_months(sysdate-1,-2),'yyyymm')))d

[0172] WHERE d.lac=z.lac1 AND d.cell_id=z.cell_id1;

[0173] Based on the base stations used by the called number for each call within a month, the area with the most calls within a month is used as the permanent working area of the called number.

[0174] CREATE TABLE zhuanli_0604AS

[0175] SELECT / *+parallel(d,30)* / other_party,COUNT(*)call_num

[0176] FROM fz_ods_rh_cb_tg_cdr_d d

[0177] WHERE d.acct_month = '202205'

[0178] AND d.day_id IN('25','26','27','28','29','30','31')

[0179] AND d.call_type = '01'

[0180] AND d.msisdn IN

[0181] (SELECT z.msisdn FROM zhuanli_0603z)

[0182] GROUP BY other_party;

[0183] CREATE TABLE zhuanli_0504_1AS

[0184] SELECT / *+parallel(d,40)* / d.msisdn,d.lac1,d.cell_id1,COUNT(*)call_num

[0185] FROM fz_ods_rh_cb_tg_cdr_d d

[0186] WHERE d.acct_month='202205'AND d.net_type_code='50'

[0187] AND d.msisdn IN

[0188] (SELECT z.other_party FROM zhuanli_0504z)

[0189] GROUP BY d.msisdn,d.lac1,d.cell_id1;

[0190] Step 42: Determine the permanent residential area of the called number corresponding to the candidate number;

[0191] create TABLE zhuanli_0620AS

[0192] select mobile_num,area_name from report.rpt_yw_user_imei_m whereacct_month='202204'

[0193] AND visit_cnt_all_tcp>0

[0194] AND mobile_num IN

[0195] (select other_party FROM zhuanli_0604)

[0196] AND area_name IS NOT NULL

[0197] AND area_name<>'other';

[0198] Step 43: Determine the broadband installation area of the called number corresponding to the candidate number;

[0199] For each called number corresponding to the candidate number, obtain the broadband installation address of the called number;

[0200] CREATE TABLE tf_f_0621as

[0201] SELECT*FROM cbkafka.tf_f_user r

[0202] WHERE r.serial_number IN(

[0203] select other_party FROM zhuanli_0604)

[0204] AND r.destroy_time IS NULL;

[0205] CREATE TABLE tf_f_kd_0621AS

[0206] SELECT*FROM cbkafka.tf_f_user r

[0207] WHERE r.cust_id IN

[0208] (SELECT cust_id FROM tf_f_0621)

[0209] AND r.destroy_time IS NULL AND r.net_type_code='40';

[0210] CREATE TABLE tf_f_kd_add_0621AS

[0211] SELECT t.cust_id,m.attr_value FROM tf_f_kd_0621t,cbkafka.tf_f_user_item m

[0212] WHERE t.user_id=m.user_id AND m.Attr_code='DETAIL_INSTALL_ADDRESS';

[0213] The operator branch corresponding to the broadband installation address is extracted, and the jurisdiction of the operator branch corresponding to the broadband installation address is used as the broadband installation area of the called number.

[0214] CREATE TABLE tf_f_kd_add_r AS

[0215] SELECT f.serial_number,

[0216] replace(substr(replace(t.attr_value,'Binhai New Area',”),1,3),'District','Branch')area_name

[0217] FROM tf_f_0621f,

[0218] tf_f_kd_add_0621t

[0219] WHERE attr_value LIKE'%area%'AND f.cust_id=t.cust_id;

[0220] Step 44: For each called number corresponding to the candidate number, the common area of the called number's permanent work area, permanent residential area, and broadband installation area is used as the permanent area of the called number.

[0221] DROP TABLE zhuanli_0607

[0222] CREATE TABLE zhuanli_0607AS

[0223] SELECT / *+parallel(d,30)* / d.*

[0224] FROM fz_ods_rh_cb_tg_cdr_d d

[0225] WHERE d.acct_month='202205'

[0226] AND d.day_id IN('25','26','27','28','29','30','31')

[0227] AND d.call_type='01'

[0228] AND d.called_code='022'

[0229] AND d.msisdn IN

[0230] (SELECT z.msisdn FROM zhuanli_0603z);

[0231] CREATE TABLE zhuanli_0607_r AS

[0232] SELECT r.*,z.district area_name FROM zhuanli_0607r,zhuanli_0606z

[0233] WHERE r.other_party=z.msisdn

[0234] UNION

[0235] SELECT r.*,z.area_name FROM zhuanli_0607r,zhuanli_0620z

[0236] WHERE r.other_party=z.mobile_num

[0237] UNION

[0238] SELECT r.*,z.area_name FROM zhuanli_0607r,tf_f_kd_add_r z

[0239] WHERE r.other_party=z.serial_number;

[0240] Step 5: Calculate the ratio of the sum of the number of calls to the top two resident areas to the total number of calls to the candidate numbers. Determine the candidate numbers with a ratio greater than 24%* as non-harassing numbers.

[0241] For example, the program source code is as follows:

[0242] DROP TABLE zhuanli_0608

[0243] CREATE TABLE zhuanli_0608AS

[0244] SELECT msisdn,sum(call_num)call_num FROM(

[0245] SELECT msisdn,area_name,call_num,row_number()over(partition by msisdnorder by call_num desc)rn

[0246] FROM

[0247] (SELECT z.msisdn,area_name,count(*)call_num FROM zhuanli_0607_r z

[0248] WHERE area_name IS NOT NULL

[0249] GROUP BY z.msisdn,area_name))

[0250] WHERE rn<=2

[0251] GROUP BY msisdn;

[0252] SELECT COUNT(*)FROM zhuanli_0608;

[0253] create TABLE zhuanli_0608_1AS

[0254] SELECT z.msisdn,count(*)call_num FROM zhuanli_0607z

[0255] GROUP BY msisdn;

[0256] CREATE TABLE zhuanli_0608_r AS

[0257] SELECT z.msisdn,z.call_num CALL_num_main,zh.call_num call_num_total

[0258] FROM zhuanli_0608z,zhuanli_0608_1zh

[0259] WHERE z.msisdn=zh.msisdn AND z.call_num>0.5*0.48*zh.call_num;

[0260] Step 6: Perform accurate verification of the results of harassing number identification.

[0261] CREATE TABLE fz_no_stop AS

[0262] SELECT / *+parallel(d,30)* / d.msisdn,COUNT(*)call_numFROM_fz_ods rh_cb_cdr_d d

[0263] WHERE d.acct_month = '202205'

[0264] AND d.day_id IN('25','26','27','28','29','30','31')

[0265] AND d.net_type_code = '50'

[0266] AND d.call_type = '01'

[0267] AND d.msisdn IN

[0268] (select serial_number FROM no_stop_list t WHERE t.In_Type=100)

[0269] GROUP BY d.msisdn

[0270] HAVING COUNT(*)>50.

[0271] In the method for identifying harassing numbers provided in this embodiment, based on the call parameters of each number, a candidate number that meets the first condition is determined; for each candidate number, the resident area of the called number corresponding to the candidate number is determined, and the number of calls in each resident area is calculated; according to the number of calls, the ratio of the sum of the number of calls in the top predetermined number of resident areas to the sum of the number of calls in all resident areas is calculated; if the ratio is greater than a preset second threshold, the candidate number is determined to be a non-harassing number; otherwise, the candidate number is determined to be a harassing number. In this embodiment, by judging whether the ratio of the sum of the number of calls in the top predetermined number of resident areas to the sum of the number of calls in all resident areas is greater than the second threshold, it is determined whether the called numbers corresponding to the candidate number are clustered in a predetermined number of resident areas, thereby identifying whether the candidate number is a harassing number and improving the accuracy of harassing number identification.

[0272] Example 4

[0273] Figure 4 This is a structural diagram of the harassment number identification device provided in Example 4 of this application, as shown in FIG. Figure 4 As shown, the device includes:

[0274] A screening module 41 is configured to determine candidate numbers that meet a first condition based on call parameters of each number;

[0275] The processing module 42 is used to determine, for each candidate number, the resident zone of the called number corresponding to the candidate number;

[0276] A calculation module 43 is used to calculate the number of called times in each permanent zone;

[0277] The calculation module 43 is further configured to calculate the ratio of the sum of the number of called times of the top predetermined number of resident zones to the sum of the number of called times of all resident zones according to the number of called times from most to least;

[0278] The determination module 44 is configured to determine that the candidate number is a non-disturbance number if the ratio is greater than a preset second threshold; otherwise, determine that the candidate number is a disturbance number.

[0279] In this embodiment, the call parameter represents the call frequency of the number, and the first condition is that the call frequency exceeds a preset first threshold. In actual applications, the call frequency of harassing numbers is relatively high. By determining whether the call frequency exceeds the preset first threshold, candidate numbers that may be harassing numbers can be preliminarily screened.

[0280] The number of called numbers in a resident zone is the sum of the number of called numbers in the resident zone corresponding to the candidate number. In practice, a called number corresponds to a unique resident zone. Among the called numbers corresponding to a candidate number, there may be called numbers with the same resident zone. In other words, a resident zone may correspond to multiple called numbers. Therefore, the number of called numbers in a resident zone is the sum of the number of called numbers in the resident zone.

[0281] In actual applications, the resident areas of the called numbers of harassing numbers are more dispersed, while the resident areas of the called numbers of public service numbers are more concentrated. It can be understood that by determining whether the ratio of the sum of the number of called numbers in the top predetermined number of resident areas to the sum of the number of called numbers in all resident areas is greater than the second threshold, it can be determined whether the called numbers corresponding to the candidate number are concentrated in the predetermined number of resident areas, thereby identifying whether the candidate number is a harassing number.

[0282] It should be noted that for each operator, only the communication parameters of each number in this network can be obtained. It can be understood that the called number corresponding to the candidate number is the called number of this network. Optionally, according to the number of called numbers, the ratio of the sum of the number of called numbers in the top predetermined number of resident areas and the total number of calls of the candidate number is calculated; if the ratio is greater than the preset third threshold, the candidate number is determined to be a non-harassment number; otherwise, the candidate number is determined to be a harassment number. The third threshold is the second threshold multiplied by the mobile user market share of this network.

[0283] In addition, in a possible implementation, the call parameters include the proportion of calling numbers, the number of calling numbers, and the proportion of local called numbers; the screening module 41 includes:

[0284] A first acquiring unit, configured to acquire call bill data of each number within a first time period;

[0285] The second acquisition unit is used to obtain the caller ratio, call times and local called number ratio of each number according to the call bill data;

[0286] The screening unit is configured to select, as candidate numbers, numbers whose proportion of outgoing calls exceeds a first sub-threshold, whose number of incoming calls exceeds a second sub-threshold, and whose proportion of local called numbers exceeds a third sub-threshold.

[0287] The calling ratio of a number is the ratio of calling numbers to the number of calls corresponding to that number; the local called number ratio of a number is the ratio of local numbers to the number of called numbers corresponding to that number.

[0288] In practice, harassing numbers are characterized by a high proportion of outgoing calls, a high number of outgoing calls, and widely dispersed locations of the called users. It's understandable that numbers with an outgoing call percentage exceeding the first sub-threshold, an outgoing call number exceeding the second sub-threshold, and a local called number percentage exceeding the third sub-threshold could be either harassing or non-harassing numbers.

[0289] In this implementation, numbers whose caller ratio exceeds the first sub-threshold, whose call count exceeds the second sub-threshold, and whose local called number ratio exceeds the third sub-threshold are selected as candidate numbers. This effectively determines the number range in which non-harassing numbers may exist, identifies candidate numbers, and improves the efficiency of identifying harassing numbers.

[0290] In addition, in a possible implementation manner, the second acquiring unit is specifically configured to:

[0291] For each of the numbers, determining a calling area for each call made by the number during the first time period;

[0292] If the calling area with the most calls in the first period is the same as the number's location, the number is considered a local number;

[0293] Calculate the percentage of local numbers among the called numbers corresponding to the number, and use this percentage as the local called number percentage for the number.

[0294] The calling area of a call is the location of the called number. In practice, during the first time period, the calling area with the most calls coincides with the location of the number. This indicates that the called numbers of the number during the first time period were primarily located in the number's location. Therefore, the number is considered a local number.

[0295] In this implementation, for each number, whether it is a local number is determined by determining whether the calling area with the most calls during the first time period is consistent with the number's location. The percentage of local numbers among the called numbers corresponding to the number is calculated to determine the percentage of local called numbers for the number. Candidate numbers can be identified based on the percentage of outgoing calls, the number of outgoing calls, and the number of local called numbers, improving the efficiency of identifying nuisance numbers.

[0296] In a possible implementation, the processing module 42 is specifically configured to:

[0297] Determine the permanent work area, permanent residential area, and broadband installation area of the called number corresponding to the candidate number;

[0298] For each called number corresponding to the candidate number, a common area to which the called number's permanent work area, permanent residential area, and broadband installation area belong is used as the permanent area of the called number.

[0299] The called number's permanent work area is the work area where the called number user made the most calls within a certain time period. The called number's permanent residential area is the residential area where the called number user spent the most time online within a certain time period. The called number's broadband installation area is the area where the broadband installation address, as documented on the same ID as the called number, is located.

[0300] It can be understood that the common area of the called number's permanent work area, permanent residential area, and broadband installation area covers the called number's user's activity area and can accurately represent the called number's permanent area. Therefore, using the common area of the called number's permanent work area, permanent residential area, and broadband installation area as the called number's permanent area can accurately determine the called number's permanent area.

[0301] In this implementation, the common area of the called number's permanent work area, permanent residential area, and broadband installation area is used as the called number's permanent area, allowing accurate identification of the called number's permanent area. By determining whether the ratio of the sum of the number of called calls in the top predetermined number of permanent areas to the sum of the number of called calls in all permanent areas is greater than a second threshold, it is determined whether the called numbers corresponding to the candidate number are clustered within the predetermined number of permanent areas, thereby identifying whether the candidate number is a harassing number and improving the accuracy of harassing number identification.

[0302] In a possible implementation, the processing module 42 includes: a first determining unit; and a first determining unit configured to:

[0303] For each called number corresponding to the candidate number, determining the area code and base station identifier of each call made by the called number during the second time period;

[0304] determining, based on the area code and the base station identifier, the base station used for each call by the called number during the second time period;

[0305] According to the base stations used for each call by the called number in the second time period, the area where the base station used most times in the second time period is located is used as the permanent working area of the called number.

[0306] Among them, the Location Area Code (LAC) is used to divide and identify the location area, and the Cell Tower ID (CID) represents a mobile base station.

[0307] In practical applications, the area code and base station identifier can be used to uniquely determine the base station address. Therefore, based on the area code and base station identifier of each call made by the called number, the base station used by the called number for each call, as well as the address of the base station used for each call, can be determined. It is understood that the area in which the address of the base station used by the called number for each call is located is consistent with the area in which the called number was located for each call.

[0308] In this embodiment, based on the address of the base station used by the called number for each call in the second time period, the area where the base station used most times in the second time period is located is used as the permanent working area of the called number, thereby obtaining an accurate permanent working area of the called number.

[0309] In a possible implementation, the processing module 42 includes: a second determining unit; the second determining unit is configured to:

[0310] For each called number corresponding to the candidate number, determining an Internet access address for each Internet access of the called number within the third time period;

[0311] According to the Internet access address of the called number each time during the third period, the area where the Internet access address with the longest cumulative access time is located is used as the permanent residential area of the called number.

[0312] In actual applications, based on home broadband and wireless network information, the Internet access address and access duration of each time the called number accesses the Internet can be determined. It can be understood that the area where the Internet access address with the longest cumulative access duration is located is the area where the called number user has been located the longest.

[0313] In this embodiment, based on the Internet access address of the called number each time during the third period, the area where the Internet access address with the longest cumulative access time during the third period is located is used as the permanent residential area of the called number, thereby obtaining the accurate permanent residential area of the called number.

[0314] In a possible implementation, the processing module 42 includes: a third determining unit; the third determining unit is configured to:

[0315] For each called number corresponding to the candidate number, obtain the broadband installation address of the called number;

[0316] The area where the broadband installation address is located is used as the broadband installation area of the called number.

[0317] It is understood that the broadband installation address is within the jurisdiction of the operator branch that installed the broadband. For example, the jurisdiction of the operator branch that installed the broadband is used as the broadband installation area. Optionally, based on the area divided by the operator, the area where the broadband installation address is located is used as the broadband installation area of the called number.

[0318] In the harassment number identification device provided in this embodiment, the screening module determines the candidate numbers that meet the first condition based on the call parameters of each number; the processing module determines the resident area of the called number corresponding to each candidate number; the calculation module calculates the number of calls in each resident area, and calculates the ratio of the sum of the number of calls in the top predetermined number of resident areas to the sum of the number of calls in all resident areas according to the number of calls from most to least; if the ratio is greater than a preset second threshold, the determination module determines that the candidate number is a non-harassment number; otherwise, the candidate number is determined to be a harassment number. In this embodiment, by judging whether the ratio of the sum of the number of calls in the top predetermined number of resident areas to the sum of the number of calls in all resident areas is greater than the second threshold, it is determined whether the called numbers corresponding to the candidate number are concentrated in the predetermined number of resident areas, thereby identifying whether the candidate number is a harassment number, thereby improving the accuracy of harassment number identification.

[0319] Example 5

[0320] Figure 5 This is a structural diagram of an electronic device provided in Example 5 of the present application, such as Figure 5 As shown, the electronic device includes:

[0321] The electronic device includes a processor 51 and a memory 52; a communication interface 53, and a bus 54. The processor 51, memory 52, and communication interface 53 can communicate with each other via bus 54. Communication interface 53 can be used for information transmission. The processor 51 can invoke logic instructions in memory 52 to execute the methods of the above embodiments.

[0322] In addition, the logic instructions in the memory 52 can be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as an independent product.

[0323] The memory 52 is a computer-readable storage medium that can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present application. The processor 51 executes the software programs, instructions, and modules stored in the memory 52 to perform functional applications and data processing, thereby implementing the methods in the above-mentioned method embodiments.

[0324] The memory 52 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data generated based on the use of the terminal device. Furthermore, the memory 52 may include high-speed random access memory and non-volatile memory.

[0325] An embodiment of the present application provides a non-transitory computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method of the aforementioned embodiment.

[0326] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0327] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for identifying harassing numbers, characterized in that: include: Determining candidate numbers that meet a first condition based on call parameters of each number; wherein the call parameters represent the call frequency of the number, and the first condition is that the call frequency exceeds a preset first threshold; For each candidate number, determine the resident zone of the called number corresponding to the candidate number, and calculate the number of calls in each resident zone; wherein the number of calls in the resident zone is the sum of the number of calls of all called numbers belonging to the resident zone among the called numbers corresponding to the candidate number; Calculate the ratio of the sum of the number of called times of the top predetermined number of resident areas to the sum of the number of called times of all the resident areas according to the number of called times from the highest to the lowest; If the ratio is greater than a preset second threshold, the candidate number is determined to be a non-harassing number; otherwise, the candidate number is determined to be a harassing number; The call parameters include the proportion of calling numbers, the number of calling numbers, and the proportion of local called numbers; and determining the candidate numbers that meet the first condition based on the call parameters of each number includes: Obtaining call record data for each number within the first time period; According to the call bill data, the calling percentage, calling times and local called number percentage of each number are obtained; wherein the local called number percentage of the number is the percentage of local numbers in the called numbers corresponding to the number; The numbers whose calling ratio exceeds the first sub-threshold, the number of calling times exceeds the second sub-threshold, and the local called number ratio exceeds the third sub-threshold are used as the candidate numbers; The step of determining, for each candidate number, a permanent zone of a called number corresponding to the candidate number, includes: Determining a permanent work area, a permanent residential area, and a broadband installation area of the called number corresponding to the candidate number; For each called number corresponding to the candidate number, a common area to which the permanent work area, permanent residential area, and broadband installation area of the called number belong is used as the permanent area of the called number.

2. The method according to claim 1, characterized in that The step of obtaining the local called number ratio of each number based on the call bill data includes: For each of the numbers, determining a calling area for each call made by the number during the first time period; wherein the calling area of the call is the location of the called number in the call; If the calling area with the most calls during the first time period is the same as the location of the number, the number is considered a local number; The proportion of local numbers in the called numbers corresponding to the number is calculated as the local called number proportion of the number.

3. The method according to claim 1, characterized in that The step of determining the resident work area of the called number corresponding to the candidate number includes: For each called number corresponding to the candidate number, determining the area code and base station identifier of each call made by the called number within the second time period; determining, based on the area code and the base station identifier, a base station used by the called number for each call during the second time period; According to the base stations used by the called number for each call during the second time period, the area where the base station used most times during the second time period is located is used as the permanent working area of the called number.

4. The method according to claim 1, wherein Determining the permanent residential area of the called number corresponding to the candidate number includes: For each called number corresponding to the candidate number, determining an Internet access address for each Internet access of the called number within a third time period; According to the Internet access address of the called number each time during the third period, the area where the Internet access address with the longest cumulative access time is located is used as the permanent residential area of the called number.

5. The method according to claim 1, wherein Determining the broadband installation area of the called number corresponding to the candidate number includes: For each called number corresponding to the candidate number, obtaining the broadband installation address of the called number; The area where the broadband installation address is located is used as the broadband installation area of the called number.

6. A device for identifying harassing numbers, characterized in that: include: a screening module, configured to determine candidate numbers that meet a first condition based on call parameters of each number; wherein the call parameters represent the call frequency of the number, and the first condition is that the call frequency exceeds a preset first threshold; A processing module, configured to determine, for each candidate number, a permanent zone of a called number corresponding to the candidate number; A calculation module, configured to calculate the number of called numbers in each of the resident areas; wherein the number of called numbers in the resident area is the sum of the number of called numbers of all called numbers belonging to the resident area among the called numbers corresponding to the candidate number; The calculation module is further configured to calculate the ratio of the sum of the number of called times of the top predetermined number of resident zones to the sum of the number of called times of all the resident zones according to the number of called times from most to least; a determination module, configured to determine that the candidate number is a non-harassing number if the ratio is greater than a preset second threshold; otherwise, determine that the candidate number is a harassing number; The call parameters include the proportion of calling numbers, the number of calling numbers, and the proportion of local called numbers; the candidate numbers that meet the first condition are determined based on the call parameters of each number, and the screening module is used to: Obtaining call record data for each number within the first time period; According to the call bill data, the calling percentage, calling times and local called number percentage of each number are obtained; wherein the local called number percentage of the number is the percentage of local numbers in the called numbers corresponding to the number; The numbers whose calling ratio exceeds the first sub-threshold, the number of calling times exceeds the second sub-threshold, and the local called number ratio exceeds the third sub-threshold are used as the candidate numbers; For each candidate number, determining the resident zone of the called number corresponding to the candidate number, the processing module is used to: Determining a permanent work area, a permanent residential area, and a broadband installation area of the called number corresponding to the candidate number; For each called number corresponding to the candidate number, a common area to which the permanent work area, permanent residential area, and broadband installation area of the called number belong is used as the permanent area of the called number.

7. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 5 when executed by a processor.

Images