Method and device for determining the number of users of a mobile phone number in the case of a certificate with multiple numbers

Abstract

The application provides a method and device for determining the number of users of a mobile phone number in the case of one certificate and multiple numbers, and relates to the technical field of IT application and personal home service. The method comprises the following steps: determining the feature vector of each mobile phone number according to the label data of all mobile phone numbers corresponding to the user identity information; merging the feature vectors according to the preset label data to determine a first number of feature vectors; and merging the first number of feature vectors according to the cosine algorithm to determine a second number of feature vectors; the second number is the number of users of all mobile phone numbers corresponding to the user identity information; wherein the label data is determined according to the behavior of using the mobile phone number. The method and device for determining the number of users of a mobile phone number in the case of one certificate and multiple numbers can determine the number of users of a mobile phone number in the case of one certificate and multiple numbers, so that the operator can distinguish different users in the marketing process, improve the marketing effect, and improve the user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of IT application and personal home service, and particularly relates to a method and device for determining the number of users of a mobile phone number in a case of one certificate and multiple numbers. BACKGROUND

[0002] In the actual process of marketing a mobile phone number, an operator may encounter a problem that a user with one certificate and multiple numbers may give one of the numbers to another person, such as a parent or a child, for use. The operator does not know the detailed situation, which leads to the problem that the marketing process cannot be differentiated, the multiple numbers are regarded as being used by one person, and the marketing effect is poor, the customer experience is poor, and the customer complaint rate is high. SUMMARY

[0003] The present application provides a method and device for determining the number of users of a mobile phone number in a case of one certificate and multiple numbers, to solve the technical problem of how to determine whether multiple people are using a mobile phone number in a case of one certificate and multiple numbers and the number of users.

[0004] In a first aspect, the present application provides a method for determining the number of users of a mobile phone number in a case of one certificate and multiple numbers, comprising:

[0005] determining a feature vector of each mobile phone number according to label data of all mobile phone numbers corresponding to user identity information;

[0006] merging the feature vectors according to preset label data to determine a first number of feature vectors;

[0007] merging the first number of feature vectors according to a cosine algorithm to determine a second number of feature vectors; the second number is the number of users of all mobile phone numbers corresponding to the user identity information;

[0008] The label data is determined according to the behavior of using a mobile phone number.

[0009] In one embodiment, the merging of the feature vectors according to the preset label data to determine the first number of feature vectors comprises:

[0010] merging feature vectors with the same preset label data to determine the first number of feature vectors.

[0011] In one embodiment, the preset label data comprises:

[0012] an international mobile equipment identity (IMEI).

[0013] In one embodiment, the label data comprises at least one of:

[0014] The preference tag data of the user listening to music using the mobile phone number, the preference tag data of the user watching a movie using the mobile phone number, and the preference tag data of the user exercising using the mobile phone number.

[0015] In one embodiment, the merging of the first number of feature vectors according to the cosine algorithm comprises:

[0016] According to the cosine algorithm, the distance between each two feature vectors in the first number of feature vectors is determined.

[0017] The following steps are repeatedly performed until the preset condition is not met or only one feature vector is left, and the second number of feature vectors is determined:

[0018] The maximum distance is subjected to preset condition judgment, and the two feature vectors corresponding to the maximum distance that meets the preset condition are merged.

[0019] The distance between each two feature vectors in the feature vectors is determined.

[0020] The preset condition is that the maximum distance between the feature vectors is greater than or equal to a preset similarity threshold.

[0021] In one embodiment, the preset similarity threshold has a value range of 0-1.

[0022] In a second aspect, the present application provides a device for determining the number of users of a mobile phone number in a case of one certificate and multiple numbers, comprising:

[0023] A determination module is configured to determine a feature vector of each mobile phone number according to label data of all mobile phone numbers corresponding to user identity information.

[0024] A first merging module is configured to merge the feature vectors according to preset label data to determine a first number of feature vectors.

[0025] A second merging module is configured to merge the first number of feature vectors according to a cosine algorithm to determine a second number of feature vectors; the second number is the number of users of all mobile phone numbers corresponding to the user identity information.

[0026] The label data is determined according to the behavior of using the mobile phone number.

[0027] In one embodiment, the first merging module is specifically configured to:

[0028] Merge the feature vectors with the same preset label data to determine the first number of feature vectors.

[0029] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for determining the number of users of a mobile phone number in the case of one identity with multiple numbers when executing the computer program.

[0030] In a fourth aspect, the present application provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method for determining the number of users of a mobile phone number in the case of one identity with multiple numbers.

[0031] The present application provides a method and device for determining the number of users of a mobile phone number in the case of one identity with multiple numbers, which forms a feature vector for each mobile phone number according to label data, performs preliminary screening by a preset label data, and then performs secondary screening by a cosine algorithm, so as to accurately determine the number of users of all mobile phone numbers under the same identity information, so that the operator can treat different users differently in the marketing process, improve the marketing effect, and bring better experience to the user. BRIEF DESCRIPTION OF DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0033] Figure 1 is a flowchart of the method for determining the number of users of a mobile phone number in the case of one identity with multiple numbers provided by the embodiments of the present application;

[0034] Figure 2 is a structural schematic diagram of the determination device for the number of users of a mobile phone number in the case of one identity with multiple numbers provided by the embodiments of the present application;

[0035] Figure 3 is a structural schematic diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0037] Figure 1 is a flowchart of a method for determining the number of users of a mobile phone number in a case of one ID with multiple numbers provided by the present application. Referring to Figure 1 , the method for determining the number of users of a mobile phone number in a case of one ID with multiple numbers provided by the present application can include:

[0038] Step S110, determining a feature vector of each mobile phone number according to label data of all mobile phone numbers corresponding to user identity information;

[0039] Step S120, merging the feature vectors according to preset label data to determine a first number of feature vectors;

[0040] Step S130, merging the first number of feature vectors according to a cosine algorithm to determine a second number of feature vectors; the second number is the number of users of all mobile phone numbers corresponding to the user identity information;

[0041] The label data is determined according to the behavior of using a mobile phone number.

[0042] It should be noted that the execution subject of the method for determining the number of users of a mobile phone number in a case of one ID with multiple numbers provided by the present application can be an electronic device, a component in an electronic device, an integrated circuit, or a chip. The electronic device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc., and the present application is not limited in this regard.

[0043] Specifically, in step S110, a feature vector of each mobile phone number is determined according to label data of all mobile phone numbers corresponding to user identity information.

[0044] The user identity information refers to valid identity information of a user, which can include a valid identity card number of a natural person, including an ID card, an officer's certificate, a passport, a border pass, or a Mainland Travel Permit for Hong Kong and Macau Residents, etc.

[0045] The label is data constructed by the operator for the user's online behavior using the mobile phone number and consumption habit. The label can include the user's basic attribute label, preference label, consumption label, and permanent residence label. For example, the user's basic attribute label can be age, gender, social relationship label, residence, work location, loyalty or credit level, etc. The user's preference label can be music, social chat, reading and learning, financial planning or game, etc. The user's consumption label can be local call fee, basic monthly rent, traffic package fee or value-added service package fee, etc. The permanent residence label can be residence city, work city, residence longitude or residence latitude, etc.

[0046] In the case of multiple mobile phone numbers corresponding to the same valid ID card number, the feature vector of each mobile phone number is constructed according to the label data of each mobile phone number, that is, each mobile phone number corresponds to a feature vector.

[0047] For example, the present application is only for the case of one ID and multiple numbers, so the number of mobile phone numbers (i.e. the number of samples) under one user ID is n, n≥2. The feature vector of each sample (the elements in the feature vector are label data) is composed of m attribute feature values, that is,

[0048] x i =(x 1,i ,x 2,i ,…,x m,i ) T

[0049] Further, the sample set can be represented by matrix X, that is,

[0050]

[0051] The jth column in the matrix represents the jth sample, j=1, 2, …n; the ith row represents the ith attribute, i=1, 2, …m; and the matrix element x i,j represents the ith feature value in the jth sample.

[0052] In step S120, the feature vectors are merged according to the preset label data to determine a first number of feature vectors.

[0053] Specifically, multiple mobile phone numbers corresponding to the same valid ID card number each correspond to a feature vector, for example, the attribute values of the music preference label in two feature vectors are "yes" and "no" respectively, which can be determined that the two mobile phone numbers corresponding to the two feature vectors are used by two users.

[0054] Further, in one embodiment, the feature vectors are merged according to the preset label data to determine a first number of feature vectors, including:

[0055] The feature vectors with the same preset label data are merged to determine the first number of feature vectors.

[0056] All feature vectors are merged according to preset label data, which can be one or multiple, and the mobile phone numbers corresponding to the feature vectors with the preset label data are identified as the same user to determine the first number of feature vectors.

[0057] In step S130, the first number of feature vectors is merged according to the cosine algorithm to determine the second number of feature vectors; the second number is the number of users of all mobile phone numbers corresponding to the user identity information.

[0058] Specifically, the label data contains many types, and feature vector merging by only preset label data is far from enough. Therefore, for the first number of feature vectors after filtering by preset label data, the similarity of two feature vectors can be judged by the cosine algorithm. Cosine similarity, also known as cosine similarity, is to evaluate the similarity of two vectors by calculating the cosine of the included angle. Cosine similarity draws vectors according to coordinate values into vector space, such as the most common two-dimensional space.

[0059] The included angle cosine distance calculation formula between samples x i and x j

[0060]

[0061] According to the characteristics of the operator label, the present application selects the cosine similarity, which is more sensitive to the difference in direction than the traditional Euclidean distance, and is not sensitive to the absolute value, further correcting the problem of non-uniformity of the measurement standard in the feature data. The closer the included angle cosine is to 1, the more similar the samples are, and the closer the included angle cosine is to 0, indicating that the samples are less similar. The similarity between two feature vectors can be obtained by the cosine algorithm, and the two mobile phone numbers corresponding to the two feature vectors with very high similarity can be identified as the same user. According to the cosine algorithm, the first number of feature vectors is screened to obtain the number of users of all mobile phone numbers under the same identity information.

[0062] The present application provides a method for determining the number of users of mobile phone numbers in the case of one certificate and multiple numbers, which forms a feature vector for each mobile phone number according to label data, performs artificial rule primary screening by preset label data, and then performs secondary screening by the cosine algorithm, so as to accurately determine the number of users of all mobile phone numbers under the same identity information, so that the operator can distinguish different users in the marketing process, improve the marketing effect, and bring better experience to the user. ​

[0063] In one embodiment, the preset label data comprises:

[0064] International Mobile Equipment Identity (IMEI).

[0065] Specifically, IMEI is International Mobile Equipment Identity (IMEI), that is, the commonly used mobile phone serial number, mobile phone "serial number", which is used to identify each independent mobile phone and other mobile communication devices in a mobile phone network, and is equivalent to the identity card of a mobile phone. In practice, if multiple mobile phone numbers have the same IMEI, it can be sufficiently determined that multiple mobile phone numbers are used by one person. Because users have privacy needs, and each person has one mobile phone.

[0066] The method for determining the number of users of a mobile phone number in the case of one certificate and multiple numbers provided by the application can ensure a certain recognition accuracy by taking the IMEI number as the preset label data. If multiple mobile phone numbers have the same IMEI, it can be determined that multiple mobile phone numbers are used by one person.

[0067] In one embodiment, the label data comprises at least one of the following:

[0068] The user's preference label data for listening to music using the mobile phone number, the user's preference label data for watching movies using the mobile phone number, and the user's preference label data for exercising using the mobile phone number.

[0069] Specifically, since the samples are all in the case of one certificate and multiple numbers, the basic attribute labels of multiple samples include age, gender, social relationship, etc., which are all registered by the user, and the attribute values can be basically determined to be consistent. Therefore, the user preference label data can be selected, for example, the music preference labels of two samples are "yes" and "no" respectively, and it can be determined that the two samples are used by two users. The user's preference label can be music, social chatting, reading and learning, financial management, or game label, and if multiple preference label data of two samples are the same, it can be indicated that the same user uses the two samples.

[0070] The method for determining the number of users of a mobile phone number in the case of one certificate and multiple numbers provided by the application can intuitively reflect the user behavior and preference by selecting the user preference label data as the feature vector, thereby ensuring the accuracy of the final determination result.

[0071] In one embodiment, the merging of the first number of feature vectors according to the cosine algorithm to determine the second number of feature vectors comprises:

[0072] According to the cosine algorithm, the distance between each two of the first quantity of feature vectors is determined;

[0073] The following steps are repeatedly performed until a preset condition is not met or only one feature vector is left, and a second quantity of feature vectors is determined:

[0074] The maximum distance is subjected to a preset condition judgment, and the two feature vectors corresponding to the maximum distance that meets the preset condition are merged;

[0075] The distance between each two of the feature vectors is determined;

[0076] The preset condition is that the maximum distance between the feature vectors is greater than or equal to a preset similarity threshold.

[0077] Specifically, according to the cosine algorithm, the distance between each two of the first quantity of feature vectors is calculated. The maximum distance is found out, and compared with the preset similarity threshold. If the maximum distance is greater than or equal to the preset similarity threshold, it indicates that the similarity of the two feature vectors corresponding to the maximum distance is very close, and it can be determined that they are the same user, i.e., the two feature vectors can be merged into one feature vector.

[0078] The above steps are repeated until the maximum distance between two feature vectors is less than the preset similarity threshold or there is only one feature vector, and a second quantity of feature vectors is determined.

[0079] In an embodiment, the value of λ ranges from 0 to 1. Of course, its specific value can be adjusted according to actual needs, and the present application does not limit this.

[0080] For example, when the first quantity is 4, corresponding to 4 feature vectors, feature vectors x1, x2, x3, and x4, the distance between the vectors is calculated according to the cosine algorithm. If the maximum distance is dist(x1, x2) and is greater than or equal to λ, the feature vectors x1 and x2 are merged into one feature vector x1.

[0081] At this time, there are still 3 feature vectors x1, x3, and x4. If the maximum distance is dist(x3, x4) and is greater than or equal to λ, the feature vectors x3 and x4 are merged into one feature vector x3.

[0082] There are still 2 feature vectors x1 and x3. If dist(x1, x3) is greater than or equal to λ, the feature vectors x1 and x3 are further merged into one feature vector x1, i.e., there is only one feature vector, and the second quantity is 1, i.e., the number of users of all mobile phone numbers under the identity information is 1.

[0083] If dist(x1, x3) is less than λ, then the two feature vectors x1 and x3 are left, the second number is 2, that is, the number of users of all mobile phone numbers under the identity information is 2, and the mobile phone numbers corresponding to the feature vectors x1 and x2 are used by one person, and the mobile phone numbers corresponding to the feature vectors x3 and x4 are used by another person.

[0084] In actual cases, the number of mobile phone numbers (i.e. samples) under the same username is generally not large, and it can be considered that 99.9% of the cases are less than or equal to 10, so the number of samples in clustering is particularly small. Therefore, some traditional algorithms, i.e. bottom-up hierarchical clustering method, can be used. The basic idea of the algorithm is to first mark each sample as a separate cluster, and then merge the clusters according to some conditions until the condition is met and the algorithm is exited. In the actual problem to be solved by the present application, because it is not known how many categories the samples need to be divided into, the termination condition should be set as the similarity threshold between clusters.

[0085] The similarity between samples has been defined previously, so the similarity between clusters (when the number of samples in a cluster is 1, it degenerates to the similarity between samples) needs to be defined now. Common methods for measuring the similarity between clusters include average distance (average linkage algorithm):

[0086]

[0087] For example, the data is preprocessed, and the label data is converted into feature values.

[0088] The input data is: all samples x under a certain identity card i , i = 1, 2, …, n;

[0089] And a similarity threshold λ is preset, and the value range of λ is 0-1.

[0090] Step 10: initialization, each sample is composed of a separate cluster by itself;

[0091] C i = {x i}, i = 1, 2, …, n

[0092] Step 20: primary screening, according to the rules, a certain number of clusters are merged.

[0093] C i = C i ∪ C j , delete(C j ), n = n-1.

[0094] Step 30: secondary screening, find the maximum distance between clusters and the corresponding clusters C i and C j,

[0095] If greater than or equal to a given threshold lambda, merge two clusters, as step 20.

[0096] Step 40: secondary screening, repeat step 30 until less than threshold lambda or merged into only one cluster.

[0097] Output: cluster C i , i = 1, 2, …, n and the number of clusters n.

[0098] n is the number of users of the plurality of mobile phone numbers corresponding to the identity information.

[0099] The method for determining the number of users of mobile phone numbers in the case of one identity and multiple numbers provided by the application determines the number of users of mobile phone numbers in the case of one identity and multiple numbers through a two-level processing mechanism. The first level is artificial rule preliminary screening to ensure accuracy, and the second level is algorithm screening to further improve accuracy. In addition, according to the characteristics of the operator label, the application selects cosine similarity. Compared with the traditional Euclidean distance, the cosine distance is more different in direction and less sensitive to absolute values, further correcting the problem of inconsistent measurement standards that may exist in feature data.

[0100] The device for determining the number of users of mobile phone numbers in the case of one identity and multiple numbers provided by the application is described below. The device for determining the number of users of mobile phone numbers in the case of one identity and multiple numbers described below can be mutually corresponding to the method for determining the number of users of mobile phone numbers in the case of one identity and multiple numbers described above.

[0101] Figure 2 The structure diagram of the device for determining the number of users of mobile phone numbers in the case of one identity and multiple numbers provided by the application is shown in the figure. Figure 2 As shown in the figure, the device can include:

[0102] The determining module 210 is configured to determine the feature vector of each mobile phone number according to the label data of all mobile phone numbers corresponding to the user identity information.

[0103] The first merging module 220 is configured to merge the feature vectors according to the preset label data to determine a first number of feature vectors.

[0104] The second merging module 230 is configured to merge the first number of feature vectors according to the cosine algorithm to determine a second number of feature vectors. The second number is the number of users of all mobile phone numbers corresponding to the user identity information.

[0105] The label data is determined according to the behavior of using mobile phone numbers.

[0106] The application provides a device for determining the number of users of mobile phone numbers in the case of one identity with multiple numbers, which forms a feature vector for each mobile phone number according to label data, performs primary screening according to preset label data, and then performs secondary screening through a cosine algorithm, so that the number of users of all mobile phone numbers under the same identity information can be accurately determined, so that operators can treat different users differently in the marketing process, improve the marketing effect, and bring better experience to users.

[0107] In one embodiment, the first merging module 220 is specifically used for:

[0108] merging the feature vectors with the same preset label data to determine the first number of feature vectors.

[0109] In one embodiment, the preset label data includes:

[0110] an international mobile equipment identity (IMEI).

[0111] In one embodiment, the label data includes at least one of the following:

[0112] preference label data of a user for listening to music using a mobile phone number, preference label data of a user for watching a movie using a mobile phone number, and preference label data of a user for exercising using a mobile phone number.

[0113] In one embodiment, the second merging module 230 is specifically used for:

[0114] determining the distance between each two feature vectors in the first number of feature vectors according to a cosine algorithm;

[0115] repeating the following steps until a preset condition is not met or only one feature vector is left to determine a second number of feature vectors:

[0116] performing preset condition judgment on the maximum distance, and merging the two feature vectors corresponding to the maximum distance that meets the preset condition;

[0117] determining the distance between each two feature vectors in the first number of feature vectors;

[0118] wherein the preset condition is that the maximum distance between the feature vectors is greater than or equal to a preset similarity threshold.

[0119] In one embodiment, the preset similarity threshold has a value range of 0-1.

[0120] The application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method for determining the number of users of a mobile phone number in a case of one identity and multiple numbers when executing the computer program.

[0121] Figure 3 An example of a schematic diagram of the physical structure of an electronic device is shown in Figure 3 The electronic device can include a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 can communicate with each other through the communication bus 340. The processor 310 can call a computer program in the memory 330 to execute the steps of the method for determining the number of users of a mobile phone number in a case of one identity and multiple numbers provided by the above-mentioned embodiments, for example, including:

[0122] According to the label data of all mobile phone numbers corresponding to the user identity information, a feature vector of each mobile phone number is determined;

[0123] According to the preset label data, the feature vectors are merged to determine a first number of feature vectors;

[0124] According to the cosine algorithm, the first number of feature vectors are merged to determine a second number of feature vectors; the second number is the number of users of all mobile phone numbers corresponding to the user identity information;

[0125] The label data is determined according to the behavior of using a mobile phone number.

[0126] In addition, the logical instructions in the memory 330 described above can be implemented in the form of a software function unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0127] In another aspect, the present application also provides a computer program product, which comprises a computer program stored on a non-transitory computer readable storage medium, and the computer program comprises program instructions, when the program instructions are executed by a computer, the computer can execute the steps of the method for determining the number of users of a mobile phone number in a case of one identity with multiple numbers provided by the above embodiments, for example comprising:

[0128] determining a feature vector of each mobile phone number according to label data of all mobile phone numbers corresponding to the user identity information;

[0129] merging the feature vectors according to preset label data to determine a first number of feature vectors;

[0130] merging the first number of feature vectors according to a cosine algorithm to determine a second number of feature vectors; the second number is the number of users of all mobile phone numbers corresponding to the user identity information;

[0131] The label data is determined according to the behavior of using a mobile phone number.

[0132] In another aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is used to make a processor execute the steps of the method for determining the number of users of a mobile phone number in a case of one identity with multiple numbers provided by the above embodiments, for example comprising:

[0133] determining a feature vector of each mobile phone number according to label data of all mobile phone numbers corresponding to the user identity information;

[0134] merging the feature vectors according to preset label data to determine a first number of feature vectors;

[0135] merging the first number of feature vectors according to a cosine algorithm to determine a second number of feature vectors; the second number is the number of users of all mobile phone numbers corresponding to the user identity information;

[0136] The label data is determined according to the behavior of using a mobile phone number.

[0137] The processor readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to a magnetic storage (such as a floppy disk, a hard disk, a magnetic tape, a magneto-optical disk (MO) and the like), an optical storage (such as a CD, a DVD, a BD, a HVD and the like), and a semiconductor storage (such as a ROM, an EPROM, an EEPROM, a non-volatile memory (NAND FLASH), a solid state disk (SSD)) and the like.

[0138] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0139] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0140] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for determining the number of users of a mobile phone number in a case of one certificate and multiple numbers, characterized in that, The method comprises the following steps: determining a feature vector of each mobile phone number according to label data of all mobile phone numbers corresponding to user identity information; merging the feature vectors according to preset label data to determine a first number of feature vectors; merging the first number of feature vectors according to a cosine algorithm to determine a second number of feature vectors; the second number is the number of users of all mobile phone numbers corresponding to the user identity information; wherein the label data is determined according to the behavior of using a mobile phone number; the step of merging the first number of feature vectors according to the cosine algorithm to determine the second number of feature vectors comprises: determining the distance between each two feature vectors in the first number of feature vectors according to the cosine algorithm; repeating the following steps until the second number of feature vectors is determined when a preset condition is not met or only one feature vector is left: performing preset condition judgment on the maximum distance, and merging the two feature vectors corresponding to the maximum distance that meets the preset condition; determining the distance between each two feature vectors in the feature vectors; wherein the preset condition is that the maximum distance between the feature vectors is greater than or equal to a preset similarity threshold.

2. The method for determining the number of users of a mobile phone number in the case of one ID card with multiple numbers, as described in claim 1, is characterized in that... the step of merging the feature vectors according to the preset label data to determine the first number of feature vectors comprises: merging the feature vectors with the same preset label data to determine the first number of feature vectors.

3. The method for determining the number of users of a mobile phone number in the case of one ID card with multiple numbers, as described in claim 2, is characterized in that... the preset label data comprises: international mobile equipment identity (IMEI).

4. The method for determining the number of users of a mobile phone number in the case of one ID card with multiple numbers, as described in claim 3, is characterized in that... the label data comprises at least one of the following: preference label data of a user listening to music using a mobile phone number, preference label data of a user watching a movie using a mobile phone number, and preference label data of a user exercising using a mobile phone number.

5. The method for determining the number of users of a mobile phone number in the case of one ID card with multiple numbers, as described in claim 1, is characterized in that... The value range of the preset similarity threshold is 0-1.

6. A device for determining the number of users of a mobile phone number in a case of one certificate and multiple numbers, characterized in that The method comprises the following steps: a determination module for determining a feature vector of each mobile phone number according to label data of all mobile phone numbers corresponding to user identity information; a first merging module for merging the feature vectors according to preset label data to determine a first number of feature vectors; a second merging module for merging the first number of feature vectors according to a cosine algorithm to determine a second number of feature vectors; the second number is the number of users of all mobile phone numbers corresponding to the user identity information; wherein the label data is determined according to the behavior of using a mobile phone number; the step of merging the first number of feature vectors according to the cosine algorithm to determine the second number of feature vectors comprises: determining the distance between each two feature vectors in the first number of feature vectors according to the cosine algorithm; repeating the following steps until the second number of feature vectors is determined when a preset condition is not met or only one feature vector is left: performing preset condition judgment on the maximum distance, and merging the two feature vectors corresponding to the maximum distance that meets the preset condition; determining the distance between each two feature vectors in the feature vectors; wherein the preset condition is that the maximum distance between the feature vectors is greater than or equal to a preset similarity threshold.

7. The apparatus for determining the number of users of a mobile phone number in a case of one certificate and multiple numbers according to claim 6, characterized in that, the first merging module is specifically configured to: merge the feature vectors with the same preset label data to determine the first number of feature vectors.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The computer program is executed by the processor to realize the steps of the method for determining the number of users of a mobile phone number in the case of one certificate and multiple numbers according to any one of claims 1 to 5. 9.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method for determining the number of users of a mobile phone number in the case of one certificate and multiple numbers according to any one of claims 1 to 5.

Images