Method, device and related equipment for mining home broadband users

Abstract

The present invention provides a method, device and related equipment for mining home broadband users. The method comprises: obtaining a first data set, the first data set comprising user behavior data corresponding to a plurality of user objects, the user behavior data being used to characterize the behavior characteristics of users in performing communication services; identifying the first data set, removing the user behavior data corresponding to the target user object, and obtaining a second data set; the target user object is used to characterize potential users of non-target home broadband services, and the second data set is used to identify potential users of the target home broadband service. Since the user behavior data corresponding to the potential users of non-target home broadband services in the first data set to be identified are removed, the second data set for identifying potential users of the target home broadband service is obtained, which can avoid the poor accuracy of potential home broadband user prediction caused by the diversity of user usage scenarios.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of communication technology, and in particular to a method and device for mining home broadband users and related equipment. Background Art

[0002] As we all know, for operators, identifying potential home broadband users among mobile phone users is one of the key points of home broadband market operations. Accurately identifying potential home broadband users and then conducting targeted marketing can greatly improve marketing success rate and reduce marketing costs.

[0003] In the prior art, in order to realize the identification of home broadband users, a large amount of user behavior data is usually used to train a model, and the trained identification model is used to perform similarity matching to identify potential home broadband users. At present, due to the diversity of user usage scenarios, when predicting potential home broadband users, it is easy to cause poor prediction accuracy. Summary of the invention

[0004] The embodiments of the present invention provide a method, an apparatus and related equipment for mining home broadband users, so as to solve the problem that the prediction accuracy of potential home broadband users is poor due to the diversity of user usage scenarios.

[0005] To solve the above problems, the present invention is achieved as follows:

[0006] In a first aspect, an embodiment of the present invention provides a method for mining home broadband users, the method comprising:

[0007] Acquire a first data set, the first data set including user behavior data corresponding to a plurality of user objects, the user behavior data being used to characterize behavior characteristics of a user performing a communication service;

[0008] The first data set is identified, and user behavior data corresponding to the target user object is eliminated to obtain a second data set; the target user object is used to characterize potential users of non-target home broadband services, and the second data set is used to identify potential users of the target home broadband service.

[0009] In a second aspect, an embodiment of the present invention provides a device for mining home broadband users, including:

[0010] An acquisition module, configured to acquire a first data set, wherein the first data set includes user behavior data corresponding to a plurality of user objects, wherein the user behavior data is used to characterize behavior characteristics of users in performing communication services;

[0011] The screening module is used to identify the first data set, remove the user behavior data corresponding to the target user object, and obtain a second data set; the target user object is used to characterize potential users of non-target home broadband services, and the second data set is used to identify potential users of the target home broadband service.

[0012] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising: a memory, a processor, and a program stored in the memory and executable on the processor; the processor is used to read the program in the memory to implement the steps in the method described in the first aspect above.

[0013] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium for storing a program, wherein the program, when executed by a processor, implements the steps in the method described in the first aspect.

[0014] The embodiment of the present invention obtains a first data set, wherein the first data set includes user behavior data corresponding to multiple user objects, and the user behavior data is used to characterize the behavior characteristics of users in performing communication services; the first data set is identified, and the user behavior data corresponding to the target user object is removed to obtain a second data set; the target user object is used to characterize potential users of non-target home broadband services, and the second data set is used to identify potential users of the target home broadband service. Since the user behavior data corresponding to the potential users of non-target home broadband services in the first data set to be identified is removed, the second data set for identifying potential users of the target home broadband service is obtained, which can avoid the poor accuracy of potential home broadband user prediction caused by the diversity of user usage scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0016] Figure 1 is a flow chart of a method for mining home broadband users provided by an embodiment of the present invention;

[0017] Figure 2 is a structural diagram of a device for mining home broadband users provided by an embodiment of the present invention;

[0018] Figure 3 It is a schematic diagram of the structure of an electronic device provided by the implementation of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] The terms "first", "second" etc. in the embodiments of the present invention are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. In addition, the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. In addition, "and / or" is used in the present invention to represent at least one of the connected objects, such as A and / or B and / or C, which means including 7 situations including single A, single B, single C, and A and B all exist, B and C all exist, A and C all exist, and A, B and C all exist.

[0021] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for mining home broadband users provided by an embodiment of the present invention. Figure 1 As shown, the method for mining home broadband users may include the following steps:

[0022] Step 101, obtaining a first data set, wherein the first data set includes user behavior data corresponding to a plurality of user objects, wherein the user behavior data is used to characterize the behavior characteristics of a user performing a communication service;

[0023] In the embodiments of the present invention, the user object can be understood as user information for uniquely identifying a user, for example, it can be a unique identification code of a certain user, such as the user's ID card number or SIM card number, wherein each user can include one or more SIM card numbers. In the following embodiments, the user object is the user's SIM card number as an example for description. In other words, a certain user can include one or more user objects.

[0024] The above user behavior data can be understood as the behavior data of the user performing communication services through the terminal, which can include B domain and O domain data, where B domain can be understood as the data domain of the business support system, and O domain can be understood as the data domain of the operation support system. Specifically, the first data set may include tariff data, deep packet inspection (DPI) data, call records, family package personnel data, etc.

[0025] It should be understood that, in the embodiment of the present invention, the first data set may be understood as a user data set to be identified, and potential broadband users may be obtained by analyzing the data in the first data set.

[0026] Step 102, identify the first data set, remove the user behavior data corresponding to the target user object, and obtain a second data set; the target user object is used to characterize potential users of non-target home broadband services; the second data set is used to identify potential users of the target home broadband service.

[0027] In the embodiment of the present invention, the target user object can be understood as a broadband user with a special scenario. Optionally, the special scenario can be understood as a scenario where a home broadband service is installed at the permanent location of the user object. The permanent location can be understood as the home address of the user associated with the user object. Specifically, a permanent location can be associated with one or more user objects. Any user object associated with the permanent location that has the permanent location installed can be understood as the home broadband service installed at the permanent location. The home broadband service installed at the permanent location can be the target home broadband service or a third-party home broadband service. At this time, the user object associated with the permanent location does not need to install the target home broadband service, so the user object associated with the permanent location is a potential user of the non-target home broadband service.

[0028] It should be understood that the above-mentioned home broadband service can be understood as a broadband service, and can also be understood as the use of home broadband or home broadband service. For example, after a user installs and activates a certain operator's broadband, he or she can obtain the operator's broadband service.

[0029] Optionally, the above special scenario can also be understood as the area corresponding to the permanent location has no broadband service, for example, a certain cell does not cover the broadband network and cannot provide broadband service. Therefore, the user object associated with the permanent location is a potential user of non-target home broadband service.

[0030] The embodiment of the present invention obtains a first data set, wherein the first data set includes user behavior data corresponding to multiple user objects, and the user behavior data is used to characterize the behavior characteristics of users in performing communication services; the first data set is identified, and the user behavior data corresponding to the target user object is removed to obtain a second data set; the target user object is used to characterize potential users of non-target home broadband services, and the second data set is used to identify potential users of the target home broadband service. Since the user behavior data corresponding to the potential users of non-target home broadband services in the first data set to be identified is removed, the second data set for identifying potential users of the target home broadband service is obtained, which can avoid the poor accuracy of potential home broadband user prediction caused by the diversity of user usage scenarios.

[0031] It should be noted that the method of identifying potential users based on the second data set can be set according to actual needs. For example, in some embodiments, after identifying the first data set and removing the user behavior data corresponding to the target user object to obtain the second data set, the method may further include:

[0032] The second data set is identified using a pre-trained recognition model to obtain potential users of the target home broadband service.

[0033] In the embodiment of the present invention, identifying the second data set using a pre-trained recognition model can be understood as predicting the second data set using user behavior data of user objects that recently installed the target home broadband service to obtain potential users of the target home broadband service.

[0034] Optionally, in some embodiments, the user behavior data can be understood as terminal consumption behavior data, for example, it can include user basic attributes, location information, communication and Internet access behavior, tariff data, etc. The terminal consumption behavior of the user object who recently installed the target home broadband service can be used to filter out users with similar behaviors from the second data set, thereby obtaining potential users of the target home broadband service. That is, the recognition model is trained by using the terminal consumption behavior of the user object who recently installed the target home broadband service, and then the trained recognition model is used for prediction.

[0035] In some embodiments, a weighted random forest algorithm may be used to train the recognition model. This is described in detail below using this as an example.

[0036] Specifically, the model input indicators can be selected based on user basic attributes, location information, communication and Internet access behavior, tariffs and other data, and the identification problem of potential home broadband users can be transformed into a binary classification problem. The labels of users who use home broadband in the sample data are set to 1, and the labels of users who do not use home broadband are set to 0 as predictor variables.

[0037] First, data preprocessing is performed, such as using data cleaning, data conversion, data reduction and other methods to perform data preprocessing and feature construction;

[0038] Then, the bootstrap sampling method is used to randomly select M training data sets and out-of-bag samples OOB with replacement;

[0039] Finally, the random forest model is trained using M training data sets and out-of-bag samples. Specifically, M decision trees can be constructed based on the M data sets. The Gini value measurement method is used for feature selection and splitting. The Gini value calculation formula is as follows:

[0040]

[0041] Among them, K represents the number of categories, p k It represents the probability that the sample point belongs to the kth class.

[0042] Then, the out-of-bag samples OOB are used as the test set to calculate the weight of each decision tree, which contains a total of N sample values. i Represents the weight of the i-th decision tree, Tree ij Indicates the prediction result of the i-th decision tree for the j-th sample, Tree' j Represents the prediction results of all decision trees for the jth sample. I is the indicative function. Random forest predicts the out-of-bag data and obtains the prediction accuracy RFAcc. The calculation formula is as follows:

[0043]

[0044] Finally, the weighted majority voting method is used to weight the decision tree and make decisions. That is, the category with the most votes in all weighted decision trees is selected as the final classification result.

[0045] Optionally, in some embodiments, the target user object includes at least one type of user among the first type of users, the second type of users and the third type of users;

[0046] Among them, the first type of user is used to represent that the first permanent location corresponding to the first user object has a broadband service installed, and the first user object has not installed the target home broadband service, the second type of user is used to represent that the area where the permanent location corresponding to the second user object is located does not have the target home broadband service, and the third type of user represents that the third user object has installed a third-party home broadband service.

[0047] It should be understood that the above-mentioned third-party home broadband services can be understood as services provided by other broadband service providers.

[0048] In the embodiment of the present invention, for the first type of users, the fact that a broadband service has been installed at the permanent location corresponding to the first user object can be understood as the first user object installing a third-party broadband service at the first permanent location, or other user objects associated with the first permanent location installing a broadband service. For example, user objects who have used services from other broadband service providers at home and user objects who have applied for broadband services using other mobile phone numbers or accounts at home can both be referred to as first type of users.

[0049] The second category of users mentioned above can be understood as users whose home communities do not have relevant broadband services.

[0050] The third category of users mentioned above can be understood as users who already have broadband at home but are not sensitive to traffic and will directly use mobile data at home.

[0051] It should be noted that for the above three types of users, different types of users are identified in different ways. The following is a detailed description of each type of user.

[0052] For example, in some embodiments, identifying the first category of users in the first data set includes:

[0053] determining a first user object in the first data set who has not installed the target home broadband service;

[0054] Determine a first permanent location corresponding to the first user object based on the location information of the first user object;

[0055] determining whether a broadband service has been installed at the first permanent location according to traffic information of the first user object at different time periods at the first permanent location;

[0056] The first user object having broadband service installed at the first permanent location is determined as a first type of user object.

[0057] In an embodiment of the present invention, for the above-mentioned first type of users, the user can be identified based on signaling data, user natural attributes, location information, communication and Internet access behavior, and other information according to the changes in the user's traffic at different time periods every day. For example, based on GPS or base station positioning, when a user has traffic generated in a certain cell for more than a threshold number of days in a month, the cell is located as the user's permanent residence cell. The user's daily traffic is divided into different time periods, such as noon and evening periods, and the average daily traffic in the evening of the permanent cell is compared with the average daily traffic at noon. When the average daily traffic in the evening is much lower than the average daily traffic at noon, it means that the user has broadband coverage in the permanent location. Based on this feature, it can be determined whether the user has installed broadband in the permanent cell.

[0058] It should be understood that the first data set may include corresponding user behavior data of user objects that have installed and not installed the target home broadband service. When the first data set only includes corresponding user behavior data of user objects that have not installed the target home broadband service, all user objects in the first data set may be determined as the first user objects. In other words, when identifying the first type of user, the step of determining the first user object in the first data set that has not installed the target home broadband service may be omitted.

[0059] Optionally, in some embodiments, identifying the second category of users in the first data set includes:

[0060] Determining the second permanent location corresponding to the second user object according to the location information of the second user object in the first data set;

[0061] determining the region to which the second permanent location belongs;

[0062] When the area to which the second permanent location belongs is included in a preset area where no broadband service is provided, the second user object is determined as the second category of user.

[0063] In the embodiment of the present application, the above-mentioned area can be understood as a cell, and the above-mentioned preset area can be understood as a cell that cannot provide broadband services. Specifically, for the identification of the second type of users, the location of the cell to which the permanent residence belongs can be located based on GPS or base station positioning, and then the cell location is matched with the data of the cell that cannot provide services, and the successfully matched one is defined as the second type of user.

[0064] Optionally, in some embodiments, identifying the third category of users in the first data set includes:

[0065] Filtering the first data set for a third user object that has installed the third-party bandwidth service in the first data set;

[0066] The third user object is determined as the third type of user.

[0067] In an embodiment of the present application, for the above-mentioned third category of users, user objects (such as user mobile phone numbers) that have installed third-party home broadband can be screened out from the user database and determined as the third category of users.

[0068] Since the first, second and third categories of users are clearly defined in the embodiment of the present invention, the user behavior data corresponding to at least one of the first, second and third categories of users can be deleted, thereby avoiding interference of the first, second and third categories of users with the prediction of home broadband users.

[0069] It should be understood that a certain user object may belong to only one of the above three categories of users, or may belong to multiple categories of users among the above three categories of users. For example, a certain user object belongs to both the above first category of users and the third category of users.

[0070] Optionally, in one embodiment, the step of identifying the first data set, removing user behavior data corresponding to the target user object, and obtaining the second data set includes:

[0071] Setting a weight value of each user object in the first data set to an initial value;

[0072] identifying the first user object, the second user object, and the third user object in the first data set;

[0073] reducing a weight value of a first user object associated with at least one of the first category of users, the second category of users, and the third category of users;

[0074] In the first data set after the weight value is adjusted, user behavior data corresponding to user objects whose weight values ​​are greater than or equal to the initial value are obtained to obtain the second data set.

[0075] In an embodiment of the present invention, the above initial value can be 0, and the first type of users, the second type of users, and the third type of users can be identified sequentially or simultaneously in the first data set. During the identification process, if a user object is identified as the first type of user, the second type of user, or the third type of user, the weight value of the first type of user can be reduced or directly set to a certain threshold value, so that the weight value of the user object is less than the initial value after adjustment. After all identifications are completed, all adjusted weight values ​​are less than the initial value. At this time, the user behavior data corresponding to the user objects greater than or equal to the initial value can be extracted from the first data set to obtain the second data set, thereby ensuring that the user behavior data of the first type of users, the user behavior data of the second type of users, and the user behavior data of the third type of users are eliminated from the data set used for identification.

[0076] Optionally, in some embodiments, after the step of reducing the weight value of the first user object associated with at least one of the first category of users, the second category of users, and the third category of users, and before the step of acquiring user behavior data corresponding to user objects having weight values ​​greater than or equal to the initial value, the method further includes:

[0077] identifying a fourth category of users in the first data set;

[0078] Setting the weight value of the fourth user object associated with the fourth type of user to the first preset value, or increasing the weight value of the fourth user object so that the weight value of the fourth user object is greater than or equal to the initial value;

[0079] The fourth type of user is used to indicate that the fourth user object has not installed the home broadband service, and the target home broadband service exists in the area where the permanent location corresponding to the fourth user object is located.

[0080] In the embodiment of the present invention, after identifying the first, second and third types of users and adjusting the weight values, the fourth type of users is identified again and the weight value of the fourth user object is adjusted, so that the weight value of the fourth user object is greater than the initial value, thereby preventing the fourth user object from being mistakenly eliminated. This further improves the accuracy of the prediction of potential home broadband users.

[0081] Optionally, for the identification of the fourth category of users, it can be identified that the user object is in the permanent residence, the corresponding terminal is not turned off, and signaling is generated, but within a certain period of time (for example, one month), the traffic behavior in the permanent residence cell at night exceeds the threshold (for example, n days) for more than a threshold t hours, and it is considered that the home broadband service is not installed. This type of user is defined as the fourth category. In other words, in the embodiment of the present invention, it can be identified that the user object has signaling generated at the permanent residence, and there are K times of traffic behavior generated within a preset time period for a time greater than a preset duration, and the user object is determined as the fourth user object.

[0082] Optionally, in some embodiments, in addition to using a pre-trained recognition model to identify the second data set to obtain potential users of the target home broadband service, user objects for specific scenarios may be supplemented to improve the use of a pre-trained recognition model to identify the second data set to obtain potential users of the target home broadband service. In other words, in the embodiment of the present application, after identifying the first data set, excluding the user behavior data corresponding to the target user object, and obtaining the second data set, the method further includes:

[0083] Using a pre-trained recognition model to identify the second data set to obtain potential users of the target home broadband service;

[0084] In the first data set, a fifth user object is selected that matches the target data of the fifth category of user objects;

[0085] Determine the potential user and the fifth user object as target users to be mined;

[0086] The fifth category of users is a sixth user object transferred from a third-party broadband service to a target home broadband service within a preset time period, and the target data is user behavior data corresponding to the sixth user object before being transferred to the target home broadband service.

[0087] In the embodiment of the present invention, the specific implementation of using the pre-trained recognition model to identify the second data set to obtain potential target home broadband users can refer to the above embodiment and will not be repeated here.

[0088] It should be understood that in the first data set, the method of screening the fifth user object that matches the target data of the fifth category of user objects can be similar to the method of identifying potential users. In other words, the random forest algorithm can be used to identify the willingness of home broadband users in different networks to switch networks. At this time, the target data of the fifth category of user objects can be used to train a model for identifying the willingness of home broadband users in different networks to switch networks, and then screen out users with similar behaviors. In this way, since the users who switch networks are identified and added to the potential users to obtain the target users that are finally mined, the embodiment of the present invention can further improve the mining of potential users.

[0089] See also Figure 2 , Figure 2 is a structural diagram of a device for mining home broadband users provided by an embodiment of the present invention. Figure 2 As shown, the mining device 200 for home broadband users includes:

[0090] An acquisition module 201 is used to acquire a first data set, where the first data set includes user behavior data corresponding to a plurality of user objects, where the user behavior data is used to characterize the behavior characteristics of a user in performing a communication service;

[0091] The screening module 202 is used to identify the first data set, remove the user behavior data corresponding to the target user object, and obtain a second data set; the target user object is used to characterize potential users of non-target home broadband services, and the second data set is used to identify potential users of the target home broadband service.

[0092] Optionally, the target user objects include at least one type of user among a first type of user, a second type of user and a third type of user;

[0093] Among them, the first type of user is used to represent that the first permanent location corresponding to the first user object has installed broadband service, and the first user object has not installed the target home broadband service, the second type of user is used to represent that the area where the second permanent location corresponding to the second user object is located does not have the target home broadband service, and the third type of user represents that the third user object has installed a third-party home broadband service.

[0094] Optionally, the screening module 202 includes:

[0095] A first determination unit is used to determine a first user object in the first data set in which the target home broadband service is not installed; determine a first permanent location corresponding to the first user object based on location information of the first user object; determine whether the first permanent location has installed the broadband service based on traffic information of the first user object in different time periods at the first permanent location; and determine the first user object in which the broadband service is installed at the first permanent location as a first-category user object.

[0096] Optionally, the screening module 202 includes:

[0097] A second determination unit is used to determine the second permanent location corresponding to the second user object based on the location information of the second user object in the first data set; determine the area to which the second permanent location belongs; when the area to which the second permanent location belongs is included in a preset area where broadband service is not provided, determine the second user object as the second type of user.

[0098] Optionally, the screening module 202 includes:

[0099] a screening unit, configured to screen the first data set for third user objects in the first data set that have installed the third-party bandwidth service;

[0100] The third determining unit is configured to determine the third user object as the third type of user.

[0101] Optionally, the screening module 202 includes:

[0102] A setting unit, configured to set a weight value of each user object in the first data set to an initial value;

[0103] an identification unit, configured to identify the first user object, the second user object and the third user object in the first data set;

[0104] an adjusting unit, configured to reduce a weight value of a first user object associated with at least one of the first category of users, the second category of users, and the third category of users;

[0105] The acquisition unit is used to acquire user behavior data corresponding to user objects whose weight values ​​are greater than or equal to the initial value in the first data set after the weight values ​​are adjusted, so as to obtain the second data set.

[0106] Optionally, the screening module 202 is further configured to: identify a fourth category of users in the first data set; set a weight value of a fourth user object associated with the fourth category of users to a first preset value, or increase the weight value of the fourth user object so that the weight value of the fourth user object is greater than or equal to the initial value;

[0107] The fourth type of user is used to indicate that the fourth user object has not installed the home broadband service, and the target home broadband service exists in the area where the permanent location corresponding to the fourth user object is located.

[0108] Optionally, the device 200 for mining home broadband users further includes a determination module and an identification module:

[0109] The identification module is used to identify the second data set using a pre-trained identification model to obtain potential users of the target home broadband service;

[0110] The screening module 202 is further used to: screen the first data set for a fifth user object that matches the target data of the fifth category of user objects;

[0111] The determination module is used to determine the potential user and the fifth user object as target users to be mined;

[0112] The fifth category of users is a sixth user object transferred from a third-party broadband service to a target home broadband service within a preset time period, and the target data is user behavior data corresponding to the sixth user object before being transferred to the target home broadband service.

[0113] The mining device 200 for home broadband users can realize the mining of home broadband users in the embodiment of the present invention. Figure 1 The various processes of the method embodiment and the same beneficial effects are achieved, and will not be described again here to avoid repetition.

[0114] The embodiment of the present invention also provides an electronic device. Figure 3 , the electronic device may include a processor 301, a memory 302, and a program 3021 stored in the memory 302 and executable on the processor 301.

[0115] When the program 3021 is executed by the processor 301, it can achieve Figure 1 Any steps in the corresponding method embodiments and achieving the same beneficial effects will not be repeated here.

[0116] A person skilled in the art can understand that all or part of the steps of implementing the above-mentioned embodiment method can be completed by hardware related to program instructions, and the program can be stored in a readable medium. The embodiment of the present invention also provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned Figure 1 Any steps in the corresponding method embodiments can achieve the same technical effect and will not be repeated here to avoid repetition.

[0117] The storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0118] The above is a preferred implementation of the embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for mining home broadband users, characterized in that: The method comprises: Acquire a first data set, the first data set including user behavior data corresponding to a plurality of user objects, the user behavior data being used to characterize behavior characteristics of a user performing a communication service; Identify the first data set, remove user behavior data corresponding to the target user object, and obtain a second data set; the target user object is used to characterize potential users of non-target home broadband services, and the second data set is used to identify potential users of the target home broadband service; The target user objects include at least one type of user among the first type of users, the second type of users and the third type of users; Among them, the first type of user is used to represent that the first permanent location corresponding to the first user object has installed broadband service, and the first user object has not installed the target home broadband service, the second type of user is used to represent that the area where the second permanent location corresponding to the second user object is located does not have the target home broadband service, and the third type of user represents that the third user object has installed a third-party home broadband service.

2. The method according to claim 1, characterized in that The identifying of the first category of users in the first data set includes: determining a first user object in the first data set who has not installed the target home broadband service; Determine a first permanent location corresponding to the first user object based on the location information of the first user object; determining whether a broadband service has been installed at the first permanent location according to traffic information of the first user object at different time periods at the first permanent location; The first user object having broadband service installed at the first permanent location is determined as a first type of user object.

3. The method according to claim 1, characterized in that The identifying of the second category of users in the first data set includes: Determining the second permanent location corresponding to the second user object according to the location information of the second user object in the first data set; determining the region to which the second permanent location belongs; When the area to which the second permanent location belongs is included in a preset area where no broadband service is provided, the second user object is determined as the second category of user.

4. The method according to claim 1, characterized in that: The identification of the third category of users in the first data set includes: Filtering the first data set for a third user object that has installed the third-party bandwidth service in the first data set; The third user object is determined as the third type of user.

5. The method according to claim 1, characterized in that The step of identifying the first data set, removing the user behavior data corresponding to the target user object, and obtaining the second data set includes: Setting a weight value of each user object in the first data set to an initial value; identifying the first user object, the second user object, and the third user object in the first data set; reducing a weight value of a first user object associated with at least one of the first category of users, the second category of users, and the third category of users; In the first data set after the weight value is adjusted, user behavior data corresponding to user objects whose weight values ​​are greater than or equal to the initial value are obtained to obtain the second data set.

6. The method according to claim 5, characterized in that After the step of reducing the weight value of the first user object associated with at least one of the first type of users, the second type of users, and the third type of users, and before the step of acquiring user behavior data corresponding to the user object whose weight value is greater than or equal to the initial value, the method further includes: identifying a fourth category of users in the first data set; Setting the weight value of the fourth user object associated with the fourth type of user to the first preset value, or increasing the weight value of the fourth user object so that the weight value of the fourth user object is greater than or equal to the initial value; The fourth type of user is used to indicate that the fourth user object has not installed the home broadband service, and the target home broadband service exists in the area where the permanent location corresponding to the fourth user object is located.

7. The method according to claim 1, characterized in that After identifying the first data set and removing the user behavior data corresponding to the target user object to obtain the second data set, the method further includes: Using a pre-trained recognition model to identify the second data set to obtain potential users of the target home broadband service; In the first data set, a fifth user object is selected that matches the target data of the fifth category of user objects; Determine the potential user and the fifth user object as target users to be mined; The fifth category of users is a sixth user object transferred from a third-party broadband service to a target home broadband service within a preset time period, and the target data is user behavior data corresponding to the sixth user object before being transferred to the target home broadband service.

8. A device for mining home broadband users, characterized in that: The device comprises: An acquisition module, configured to acquire a first data set, wherein the first data set includes user behavior data corresponding to a plurality of user objects, wherein the user behavior data is used to characterize behavior characteristics of users in performing communication services; A screening module, configured to identify the first data set, remove user behavior data corresponding to a target user object, and obtain a second data set; the target user object is used to characterize potential users of non-target home broadband services, and the second data set is used to identify potential users of the target home broadband service; The target user objects include at least one type of user among the first type of users, the second type of users and the third type of users; Among them, the first type of user is used to represent that the first permanent location corresponding to the first user object has installed broadband service, and the first user object has not installed the target home broadband service, the second type of user is used to represent that the area where the second permanent location corresponding to the second user object is located does not have the target home broadband service, and the third type of user represents that the third user object has installed a third-party home broadband service.

9. The device according to claim 8, characterized in that The screening module comprises: A first determination unit is used to determine a first user object in the first data set in which the target home broadband service is not installed; determine a first permanent location corresponding to the first user object based on location information of the first user object; determine whether the first permanent location has installed the broadband service based on traffic information of the first user object in different time periods at the first permanent location; and determine the first user object in which the broadband service is installed at the first permanent location as a first-category user object.

10. The device according to claim 8, characterized in that The screening module comprises: A second determination unit is used to determine the second permanent location corresponding to the second user object based on the location information of the second user object in the first data set; determine the area to which the second permanent location belongs; when the area to which the second permanent location belongs is included in a preset area where broadband service is not provided, determine the second user object as the second type of user.

11. The device according to claim 8, characterized in that The screening module comprises: a screening unit, configured to screen the first data set for third user objects in the first data set that have installed the third-party bandwidth service; The third determining unit is configured to determine the third user object as the third type of user.

12. The device according to claim 8, characterized in that The screening module comprises: A setting unit, configured to set a weight value of each user object in the first data set to an initial value; an identification unit, configured to identify the first user object, the second user object and the third user object in the first data set; an adjusting unit, configured to reduce a weight value of a first user object associated with at least one of the first category of users, the second category of users, and the third category of users; The acquisition unit is used to acquire user behavior data corresponding to user objects whose weight values ​​are greater than or equal to the initial value in the first data set after the weight values ​​are adjusted, so as to obtain the second data set.

13. The device according to claim 12, characterized in that The screening module is further used to: identify a fourth category of users in the first data set; set a weight value of a fourth user object associated with the fourth category of users to a first preset value, or increase the weight value of the fourth user object so that the weight value of the fourth user object is greater than or equal to the initial value; The fourth type of user is used to indicate that the fourth user object has not installed the home broadband service, and the target home broadband service exists in the area where the permanent location corresponding to the fourth user object is located.

14. The device according to claim 8, characterized in that The device for mining home broadband users also includes a determination module and an identification module: The identification module is used to identify the second data set using a pre-trained identification model to obtain potential users of the target home broadband service; The screening module is further used to: screen the first data set for a fifth user object that matches the target data of the fifth category of user objects; The determination module is used to determine the potential user and the fifth user object as target users to be mined; The fifth category of users is a sixth user object transferred from a third-party broadband service to a target home broadband service within a preset time period, and the target data is user behavior data corresponding to the sixth user object before being transferred to the target home broadband service.

15. An electronic device, comprising: A memory, a processor, and a program stored in the memory and executable on the processor; wherein the processor is used to read the program in the memory to implement the steps in the method for mining home broadband users as described in any one of claims 1 to 6.

16. A readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the steps of the method for mining home broadband users according to any one of claims 1 to 6 are implemented.

Images