Method, device and readable storage medium for determining users without broadband

By analyzing the user's business data and characteristic values, combining preset prediction models and voting mechanisms, accurately identifying uninstalled home broadband users, solving the accuracy of broadband user identification in the existing technology, and improving the accuracy of broadband services and efficiency.

CN115714708BActive Publication Date: 2024-11-05CHINA UNITED NETWORK COMM GRP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211399133.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-11-09
Publication Date
2024-11-05
Estimated Expiration
2042-11-09

AI Technical Summary

Technical Problem

The existing methods are difficult to accurately determine whether home broadband has been installed in the user's home, especially because the statistical information when installing broadband only includes information about broadband contacts, and it is impossible to effectively distinguish between home users who need to install broadband and do not need broadband, resulting in uninstallation. The target users of home broadband are difficult to identify.

Method used

By obtaining the service data of the user to be identified within the preset time period, including the operation support system O domain data and the service support system B domain data, multiple characteristic values ​​are calculated, such as traffic proportion and average traffic ratio, combined with the preset prediction Model and voting mechanism to determine the broadband-free user from multiple users to be identified.

Benefits of technology

Accurate identification of uninstalled home broadband users is achieved, the accuracy and efficiency of broadband services are improved, and the problem of low accuracy of single-angle prediction is avoided.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115714708B_ABST
    Figure CN115714708B_ABST
Patent Text Reader

Abstract

The present application discloses a method, device and readable storage medium for determining users without broadband, which relates to the field of communication technology and is used to accurately determine users without broadband. The method includes: obtaining business data of multiple users to be identified within a first preset time period; determining multiple characteristic values ​​of each user to be identified based on the business data of each user to be identified, and the multiple characteristic values ​​include a first value, a second value and a third value; for the first characteristic value, determining a first prediction result based on the first characteristic value and the corresponding characteristic threshold, and obtaining multiple first prediction results corresponding to the multiple characteristic values ​​one by one, and the first characteristic value is any one of the multiple characteristic values; determining a second prediction result based on a preset prediction model and the business data of multiple users to be identified; determining users without broadband from multiple users to be identified based on a preset voting mechanism, the first prediction result and the second prediction result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of communication technology, and in particular, to a method, device, and readable storage medium for determining users without broadband. Background Art

[0002] With the continuous maturity of new scenarios such as high-definition video, cloud games, and smart homes, broadband business development still has great potential. How to accurately determine whether home broadband has been installed in the user's home is the main problem restricting the development of broadband business.

[0003] The existing method of determining whether a user's home has installed home broadband is mainly based on statistical information when the broadband is installed. However, the statistical information when the broadband is installed only includes information of broadband contacts. In addition to broadband contacts, it also includes a large number of home users who do not need to install broadband, as well as target users who have not installed home broadband. How to accurately determine target users who have not installed home broadband is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present application provides a method, device and readable storage medium for determining a user without broadband, which are used to accurately determine a target user who has not installed a home broadband.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, a method for determining users without broadband is provided, comprising: obtaining business data of multiple users to be identified within a first preset time period, the business data comprising operation support system O domain data and business support system B domain data; determining multiple characteristic values ​​of each user to be identified based on the business data of each user to be identified, the multiple characteristic values ​​comprising a first numerical value, a second numerical value and a third numerical value; the first numerical value is a ratio of a first target number of days to a first preset time period, the second numerical value is a ratio of a second target number of days to the first preset time period, the third numerical value is a ratio of a third target number of days to the first preset time period, the first target number of days is a number of days on which the ratio of the traffic in the second preset time period of each user to be identified to the traffic throughout the day is greater than or equal to a first threshold, and the second target number of days is a number of days on which the ratio of the traffic in the second preset time period of each user to be identified to the traffic throughout the day is greater than or equal to a first threshold, and the second target number of days is a number of days on which the ratio of the traffic in the second preset time period of each user to be identified to the traffic throughout the day is greater than or equal to a first threshold, and the second target number of days is a number of days on which the ratio of the traffic in the second preset time period of each user to be identified to the traffic in the whole ... a first threshold, and the second target number of days is a number of days on which the ratio of the traffic in the second preset time period of each user to be identified to the traffic in the whole day is greater than a first threshold, and the second target number of days is a number of days on which the ratio of the traffic in the second preset time period of each user to be identified to the traffic in the whole day is greater than a first threshold, and the third target number of days is a number of days on which the ratio of the traffic in the second preset time period of each user to be identified to the number of days when the ratio of the traffic in the first preset time period to the traffic in the third preset time period is greater than or equal to the second threshold, the third target number of days is the number of days when the ratio of the traffic in the second preset time period of each user to be identified to the average of the traffic in the second preset time period of broadband users is greater than or equal to the third threshold; for the first feature value, a first prediction result is determined according to the first feature value and the corresponding feature threshold, and a plurality of first prediction results corresponding to the plurality of feature values ​​are obtained, and the first feature value is any one of the plurality of feature values; the first prediction result is used to characterize the probability score of each user to be identified being a non-broadband user; the second prediction result is determined according to a preset prediction model and the business data of the plurality of users to be identified; the non-broadband users are determined from the plurality of users to be identified according to the preset voting mechanism, the plurality of first prediction results and the second prediction result.

[0007] Based on the technical solution provided by the embodiment of the present application, the determination device can determine multiple characteristic values ​​of each user to be identified through the business data of multiple users to be identified, and the multiple characteristic values ​​include a first value, a second value and a third value. Since the first value and the second value in the multiple characteristic values ​​can reflect the number of days when the usage ratio of the traffic of the user to be identified in the second preset time period in the first preset time period is greater than the preset value, the traffic usage habits of the user to be identified in different time periods can be determined. Considering that the user without broadband can only use mobile traffic for life and entertainment and other activities, the determination device determines the third value in the multiple characteristic values ​​to reflect the size relationship between the traffic of the user to be identified in the second preset time period in the first preset time period and the traffic of the broadband user in the second preset time period in the first preset time period. After obtaining multiple characteristic values ​​of each user to be identified, multiple first prediction results corresponding to the multiple characteristic values ​​can be determined by each characteristic value and the corresponding characteristic threshold. In addition, the determination device can also determine the second prediction result by a preset prediction model. And determine the user without broadband from the multiple users to be identified by the preset voting mechanism, the first prediction result and the second prediction result. In this way, the determination device distinguishes the business data of the multiple users to be identified from multiple angles, and can accurately determine the user without broadband from the multiple users to be identified.

[0008] Optionally, a first prediction result is determined based on the first eigenvalue and the corresponding eigenvalue threshold, including: sorting the first eigenvalues ​​of multiple users to be identified to determine the first eigenvalue ranking of the first user to be identified, the first user to be identified being any one of the multiple users to be identified; when the first eigenvalue ranking of the first user to be identified is greater than or equal to a fourth threshold, determining that the first user to be identified is a non-broadband user.

[0009] In this way, the determination device can determine the first prediction results corresponding to the multiple characteristic values ​​of each user to be identified. Since the one-to-one corresponding first prediction results determine whether the user to be identified is a non-broadband user from different angles, the problem of low accuracy in predicting the non-broadband user from a single angle is avoided, and the non-broadband user among the multiple users to be identified can be accurately determined.

[0010] Optionally, the second prediction result includes a first sub-prediction result and / or a second sub-prediction result, the first sub-prediction result is used to characterize the probability score of each user to be identified as a non-broadband user; the second sub-prediction result is used to characterize the probability score of each user to be identified as a broadband user; the second prediction result is determined according to a preset prediction model and business data, including: determining the first sub-prediction result according to the business data of multiple users to be identified and the first prediction model; and / or determining the second sub-prediction result according to the business data of multiple users to be identified and the second prediction model; wherein the positive result corresponding to the first prediction model is a fourth numerical value, and the negative result corresponding to the second prediction model is a fourth numerical value, the positive result is used to indicate that the user to be identified is a non-broadband user, and the negative result is used to indicate that the user to be identified is a broadband user.

[0011] In this way, by setting different positive and negative sample identifiers and selecting differentiated features, different optimal parameters can be trained to obtain the first prediction model and the second prediction model. This can avoid overfitting caused by samples with a large proportion due to sample imbalance, thereby improving the accuracy of determining users without broadband.

[0012] Optionally, when the second prediction result does not include the second sub-prediction result, the non-broadband user is determined from multiple users to be identified according to a preset voting mechanism, multiple first prediction results and the second prediction result, including: for the first user to be identified, if the sum of the scores of the first prediction result and the first sub-prediction result predicting that the first user to be identified is a user without broadband is greater than or equal to a fifth threshold, then the first user to be identified is determined to be a user without broadband.

[0013] In this way, since multiple prediction results determine whether the user to be identified is a user without broadband from different angles, the determination device can use a preset voting mechanism to summarize and analyze multiple prediction results, and finally determine whether the user to be identified is a user without broadband, thereby avoiding the problem of low accuracy in predicting users without broadband from a single angle, and accurately determining users without broadband among multiple users to be identified.

[0014] Optionally, when the second prediction result includes the second sub-prediction result, determining the non-broadband user from multiple users to be identified according to a preset voting mechanism, multiple first prediction results and the second prediction result, including: performing numerical conversion on the second sub-prediction result, and the second sub-prediction result after numerical conversion is used to characterize the probability score of each user to be identified as a non-broadband user; for the first user to be identified, if the sum of the scores of the target prediction result predicting that the first user to be identified is a non-broadband user is greater than or equal to a fifth threshold, then determining that the first user to be identified is a non-broadband user, and the target prediction result includes at least the first prediction result and the second sub-prediction result after numerical conversion.

[0015] In this way, since multiple prediction results determine whether the user to be identified is a non-broadband user from different angles, the determination device can use a preset voting mechanism to summarize and analyze the multiple prediction results to obtain a final prediction result of whether the user to be identified is a non-broadband user, thereby avoiding the problem of low accuracy in predicting non-broadband users from a single angle, and can accurately determine non-broadband users among multiple users to be identified.

[0016] In a second aspect, a device for determining users without broadband is provided, including an acquisition unit and a determination unit; the acquisition unit is used to acquire business data of multiple users to be identified within a first preset time period, the business data including operation support system O domain data and business support system B domain data; the determination unit is used to determine multiple characteristic values ​​of each user to be identified based on the business data of each user to be identified, the multiple characteristic values ​​including a first numerical value, a second numerical value and a third numerical value; the first numerical value is a ratio of a first target day to a first preset time period, the second numerical value is a ratio of a second target day to the first preset time period, the third numerical value is a ratio of a third target day to the first preset time period, the first target day is a day on which the ratio of the traffic in the second preset time period of each user to be identified to the traffic throughout the day is greater than or equal to a first threshold, and the second target day is a day on which the ratio of the traffic in the second preset time period of each user to be identified to the traffic throughout the day is greater than or equal to a first threshold, and the second target day is a day on which the ratio of the traffic in the second preset time period of each user to be identified to the traffic throughout the day is greater than or equal to a first threshold, and the second target day is a day on which the ratio of the traffic in the second preset time period of each user to be identified is greater than or equal to a first threshold The third target number of days is the number of days when the ratio of the traffic in the second preset time period of each user to be identified to the average of the traffic in the second preset time period of broadband users is greater than or equal to the third threshold; the determination unit is further used to determine the first prediction result according to the first characteristic value and the corresponding characteristic threshold for the first characteristic value, and obtain multiple first prediction results corresponding to the multiple characteristic values ​​one by one, and the first characteristic value is any one of the multiple characteristic values; the first prediction result is used to characterize the probability score of each user to be identified being a non-broadband user; the determination unit is further used to determine the second prediction result according to a preset prediction model and the business data of the multiple users to be identified; the determination unit is further used to determine the non-broadband user from the multiple users to be identified according to the preset voting mechanism, the multiple first prediction results and the second prediction result.

[0017] Optionally, the determination unit is specifically used to: sort the first characteristic values ​​of multiple users to be identified to determine the first characteristic value ranking of the first user to be identified, the first user to be identified being any one of the multiple users to be identified; when the first characteristic value ranking of the first user to be identified is greater than or equal to a fourth threshold, determine that the first user to be identified is a non-broadband user.

[0018] Optionally, the second prediction result includes a first sub-prediction result and / or a second sub-prediction result, the first sub-prediction result being used to characterize the probability score of each user to be identified being a non-broadband user; the second sub-prediction result being used to characterize the probability score of each user to be identified being a broadband user; a determination unit being specifically used to: determine the first sub-prediction result based on the business data of multiple users to be identified and a first prediction model; and / or determine the second sub-prediction result based on the business data of multiple users to be identified and a second prediction model; wherein the positive result corresponding to the first prediction model is a fourth numerical value, and the negative result corresponding to the second prediction model is a fourth numerical value, the positive result is used to indicate that the user to be identified is a non-broadband user, and the negative result is used to indicate that the user to be identified is a broadband user.

[0019] Optionally, when the second prediction result does not include the second sub-prediction result, the determination unit is specifically used to: for the first user to be identified, if the sum of the scores of the first prediction result and the first sub-prediction result predicting that the first user to be identified is a user without broadband is greater than or equal to a fifth threshold, then determine that the first user to be identified is a user without broadband.

[0020] Optionally, when the second prediction result includes the second sub-prediction result, the determination unit is specifically used to: perform numerical conversion on the second sub-prediction result, and the second sub-prediction result after numerical conversion is used to characterize the probability score of each user to be identified as a non-broadband user; for the first user to be identified, if the sum of the scores of the target prediction result predicting that the first user to be identified is a non-broadband user is greater than or equal to a fifth threshold, then the first user to be identified is determined to be a non-broadband user, and the target prediction result includes at least the first prediction result and the second sub-prediction result after numerical conversion.

[0021] According to a third aspect, a device for determining a user without broadband is provided. The device for determining a user without broadband can implement the functions performed by the device for determining a user without broadband in the above-mentioned aspects or possible designs. The functions can be implemented by hardware, such as: in one possible design, the device for determining a user without broadband may include: a processor and a communication interface. The processor may be used to support the device for determining a user without broadband to implement the functions involved in the above-mentioned first aspect or any possible design of the first aspect.

[0022] In another possible design, the device for determining no broadband users may further include a memory, the memory being used to store computer-executable instructions and data necessary for the device for determining no broadband users. When the device for determining no broadband users is running, the processor executes the computer-executable instructions stored in the memory, so that the device for determining no broadband users performs the first aspect or any possible method for determining no broadband users of the first aspect.

[0023] In a fourth aspect, a computer-readable storage medium is provided, which may be a readable non-volatile storage medium, and which stores computer instructions or programs. When the computer-readable storage medium is run on a computer, the computer can execute the method for determining users without broadband according to the first aspect or any possible method of determining users without broadband according to the above aspects.

[0024] In a fifth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the method for determining users without broadband according to the first aspect or any possible design of the above aspects.

[0025] In a sixth aspect, a device for determining a user without broadband is provided, the device for determining a user without broadband includes one or more processors and one or more memories. The one or more memories are coupled to the one or more processors, the one or more memories are used to store computer program codes, the computer program codes include computer instructions, and when the one or more processors execute the computer instructions, the device for determining a user without broadband performs the method for determining a user without broadband as described in the first aspect or any possible design of the first aspect.

[0026] In a seventh aspect, a chip system is provided, the chip system including a processor and a communication interface, the chip system can be used to implement the functions performed by the device for determining the lack of broadband users in the first aspect or any possible design of the first aspect, for example, the processor is used to obtain a first request message from a terminal device through a communication interface. In one possible design, the chip system also includes a memory, the memory is used to store program instructions and / or data. The chip system can be composed of a chip, or it can include a chip and other discrete devices, without limitation. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of a target user determination system provided in an embodiment of the present application;

[0028] Figure 2 A schematic diagram of the structure of another device for determining a user without broadband provided in an embodiment of the present application;

[0029] Figure 3 A flowchart of another method for determining a user without broadband provided in an embodiment of the present application;

[0030] Figure 4 A flowchart of another method for determining a user without broadband provided in an embodiment of the present application;

[0031] Figure 5 A flowchart of another method for determining a user without broadband provided in an embodiment of the present application;

[0032] Figure 6 A flowchart of another method for determining a user without broadband provided in an embodiment of the present application;

[0033] Figure 7 A flowchart of another method for determining a user without broadband provided in an embodiment of the present application;

[0034] Figure 8 A schematic diagram of the structure of a device for determining users without broadband provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0037] It should also be understood that the term “comprising” indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or components.

[0038] Before introducing the embodiments of the present application, the terms in the embodiments of the present application are explained.

[0039] Boosting tree (extreme gradient boosting, Xgboost) algorithm model: Xgboost algorithm has the advantages of automatically handling missing values, column sampling to prevent overfitting, etc., and can handle sample sets well. Xgboost algorithm will train multiple trees and calculate the objective function based on the final results of the training trees. For the tth tree, the predicted value of the i-th sample can be determined according to the following formula 1.

[0040]

[0041] in, is the prediction result of sample i after the tth iteration, f t (x i ) is the model prediction result of the tth tree, is the prediction result of the t-1th tree. Then the objective function can be determined according to the following formula 2.

[0042]

[0043] in is the loss function of the model, is the model's predicted value for the i-th sample, y i , is the true value of the i-th sample. is the sum of the complexities of all t trees, serving as the regularization term of the objective function.

[0044] With the continuous maturity of new scenarios such as high-definition video, cloud games, and smart homes, broadband business development still has great potential. How to accurately determine whether home broadband has been installed in the user's home is the main problem restricting the development of broadband business.

[0045] The existing method of determining whether home broadband has been installed in a user's home is mainly based on statistical information when the broadband is installed. However, the statistical information when the broadband is installed only includes information of broadband contacts. In addition to broadband contacts, it also includes a large number of home users who do not need to install broadband, as well as target users who have not installed home broadband. How to accurately determine target users who have not installed home broadband is a technical problem that needs to be solved urgently.

[0046] In view of this, an embodiment of the present application provides a method for determining users without broadband, including: obtaining business data of multiple users to be identified within a first preset time period, the business data including operation support system O domain data and business support system B domain data; determining multiple characteristic values ​​of each user to be identified according to the business data of each user to be identified, the multiple characteristic values ​​including a first numerical value, a second numerical value and a third numerical value; the first numerical value is a ratio of a first target day to a first preset time period, the second numerical value is a ratio of a second target day to the first preset time period, and the third numerical value is a ratio of a third target day to the first preset time period, the first target day is a day on which the ratio of the traffic in the second preset time period of each user to be identified to the traffic throughout the day is greater than or equal to a first threshold, and the second .... The number of days when the ratio of the traffic in the time period to the traffic in the third preset time period is greater than or equal to the second threshold, and the third target number of days is the number of days when the ratio of the traffic in the second preset time period of each user to be identified to the average of the traffic in the second preset time period of broadband users is greater than or equal to the third threshold; for the first characteristic value, a first prediction result is determined according to the first characteristic value and the corresponding characteristic threshold, and a plurality of first prediction results corresponding to the plurality of characteristic values ​​are obtained, and the first characteristic value is any one of the plurality of characteristic values; the first prediction result is used to characterize the probability score of each user to be identified being a non-broadband user; the second prediction result is determined according to a preset prediction model and the business data of the plurality of users to be identified; and the non-broadband users are determined from the plurality of users to be identified according to the preset voting mechanism, the plurality of first prediction results and the second prediction result.

[0047] The method provided in the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0048] It should be noted that the network system described in the embodiment of the present application is to more clearly illustrate the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided in the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of network systems and the emergence of other network systems, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.

[0049] Figure 1 FIG. 1 is a schematic diagram of a target user determination system provided by an embodiment of the present application. Figure 1 As shown, the target user determination system may include a determination device for non-broadband users (hereinafter referred to as determination device) and a server 12. The determination device 11 is connected to the server 12. The determination device 11 and the server 12 may be connected wirelessly.

[0050] The determination device 11 involved in the embodiment of the present application may also be referred to as a computer, a server, etc. In the embodiment of the present application, the specific technology and specific device form adopted by the determination device 11 are not limited.

[0051] Among them, the server 12 involved in the embodiment of the present application can be a core network database, a big data platform, etc. The embodiment of the present application does not limit the specific technology, specific number and specific equipment form adopted by the server 12.

[0052] The server 12 is used to send the service data of multiple users to be identified within the first preset time period to the determining device 11 after receiving the request information from the determining device 11. The determining device 11 is used to receive the service data of multiple users to be identified within the first preset time period sent by the server 12, and determine the target user according to the service data of multiple users to be identified within the first preset time period.

[0053] In different application scenarios, the determination device 11 and the server 12 may be independent devices or integrated into the same device, which is not specifically limited in the embodiment of the present invention.

[0054] It should be noted that Figure 1 This is just an exemplary framework diagram. Figure 1 The names of the individual devices included in the Figure 1 In addition to the functional nodes shown, other nodes may also be included, which is not limited in the embodiments of the present application.

[0055] When implementing it specifically, Figure 1 Each device in the Figure 2 The structure shown, or including Figure 2 Parts shown. Figure 2The present invention provides a schematic diagram of a determination device 200, which may be a server, or a chip or system on chip in the server. Figure 2 As shown, the determination device 200 includes a processor 201 , a communication interface 202 and a communication line 203 .

[0056] Furthermore, the determination device 200 may also include a memory 204. The processor 201, the memory 204 and the communication interface 202 may be connected via a communication line 203.

[0057] The processor 201 is a CPU, a general processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 201 may also be other devices with processing functions, such as circuits, devices, or software modules, without limitation.

[0058] The communication interface 202 is used to communicate with other devices or other communication networks. The communication interface 202 can be a module, a circuit, a communication interface or any device capable of implementing communication.

[0059] The communication line 203 is used to transmit information between the components included in the determination device 200.

[0060] The memory 204 is used to store instructions, where the instructions may be computer programs.

[0061] The memory 204 may be a read-only memory (ROM) or other types of static storage devices that can store static information and / or instructions, or a random access memory (RAM) or other types of dynamic storage devices that can store information and / or instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0062] It should be noted that the memory 204 can exist independently of the processor 201, or can be integrated with the processor 201. The memory 204 can be used to store instructions or program codes or some data, etc. The memory 204 can be located in the determination device 200, or can be located outside the determination device 200, without limitation. The processor 201 is used to execute the instructions stored in the memory 204 to implement the method for determining a non-broadband user provided in the following embodiments of the present application.

[0063] In one example, the processor 201 may include one or more CPUs, for example, Figure 2 CPU0 and CPU1 in.

[0064] As an optional implementation, the determining device 200 includes multiple processors, for example, Figure 2 In addition to the processor 201, a processor 205 may also be included.

[0065] It should be pointed out that Figure 2 The composition shown in the Figure 1 The limitations of each device in Figure 2 In addition to the parts shown, Figure 1 The various devices in the Figure 2 More or fewer components, or combinations of certain components, or different arrangements of components.

[0066] In the embodiment of the present application, the chip system may be composed of a chip, or may include a chip and other discrete devices.

[0067] In addition, the actions, terms, etc. involved in the various embodiments of the present application can refer to each other without limitation. The message name or parameter name in the message exchanged between the various devices in the embodiments of the present application is only an example, and other names can also be used in the specific implementation without limitation.

[0068] In order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish the same or similar items with substantially the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference.

[0069] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0070] In the present application, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0071] Combine the following Figure 1 The target user determination system shown describes the method for determining the non-broadband user provided in the embodiment of the present application.

[0072] Figure 3 A method for determining a user without broadband is provided in an embodiment of the present application, which is applied to a determination device and can also be applied to a server. The determination device can be Figure 1 The determining device 11 in the embodiment may also be a device in the determining device 11, such as a chip. The embodiment of the present application is described by taking the application to the determining device as an example. Figure 3 As shown, the method includes the following S301-S305:

[0073] S301. A determination device obtains service data of a plurality of users to be identified within a first preset time period.

[0074] The business data includes the operation support system O domain data and the business support system B domain data. The number of multiple users to be identified and the first preset time period can be set as needed. For example, the number of multiple users to be identified can be 3, 6, 100, or 10,000. The first preset time period can be one week, 10 days, or one month.

[0075] The O domain data may include information such as traffic value, application type corresponding to the traffic, time, user's geographical location, etc. The B domain data may include information such as user age, gender, package fee, and over-package fee.

[0076] As a possible implementation manner, the operator's server stores service data of multiple users to be identified within a first preset time period, and the determination device can obtain the service data of multiple users to be identified within the first preset time period by connecting to the operator's server.

[0077] The server can be Figure 1 The server 12 may also be a device in the server 12, such as a chip.

[0078] S302: The determining device determines multiple feature values ​​of each user to be identified according to the service data of each user to be identified.

[0079] The multiple characteristic values ​​include a first value, a second value, and a third value; the first value is the ratio of the first target day to the first preset time period, the second value is the ratio of the second target day to the first preset time period, and the third value is the ratio of the third target day to the first preset time period. The first target day is the number of days when the ratio of the flow rate of each user to be identified in the second preset time period to the flow rate of the whole day is greater than or equal to the first threshold, the second target day is the number of days when the ratio of the flow rate of each user to be identified in the second preset time period to the flow rate of the third preset time period is greater than or equal to the second threshold, and the third target day is the number of days when the ratio of the flow rate of each user to be identified in the second preset time period to the average flow rate of broadband users in the second preset time period is greater than or equal to the third threshold.

[0080] It should be noted that the traffic volume of the second preset time period may refer to the traffic volume used by the user to be identified in the preset time period at night, and the traffic volume of the third preset time period may refer to the traffic volume used by the user to be identified in the preset time period during the day. For example, the preset time period at night may refer to the time from 23:00 to 7:00 in the morning, and the preset time period during the day may refer to the time from 7:00 in the morning to 23:00 in the evening.

[0081] The first value, the second value and the third value are described in detail below.

[0082] 1. First value

[0083] In one example, the determining device may determine the first value according to the following formula three.

[0084]

[0085] Wherein, P1 represents the first value, represents the first target number of days, and T represents the number of days in the first preset time period. For example, the determining device can determine I according to the following formula 4 t .

[0086]

[0087] Among them, Flow t,23-7 Indicates the flow of the second preset time period of the user to be identified, Flow t,0-24 represents the all-day traffic of the user, and a represents the first threshold. For example, a can be 0.1, or 0.2, etc., without limitation.

[0088] In an example, as shown in the following Table 1, taking the case where the first preset time period includes 3 days and the flow rate of the second preset time period is from 23:00 to 7:00 as an example, a schematic table of the first target days is specifically shown.

[0089] Table 1 Schematic table of the first target days

[0090]

[0091] It should be noted that the data in Table 1 are only exemplary. In the embodiment of the present application, the first preset time period, the flow data and the first target number of days may also be other data without limitation.

[0092] In this way, the determining device can determine that P1=2 / 3=0.0.667.

[0093] 2. Second numerical value.

[0094] In one example, the determining device may determine the first value according to the following formula five.

[0095]

[0096] Wherein, P2 represents the second value, represents the second target number of days. For example, the determining device can determine Q according to the following formula six t .

[0097]

[0098] Among them, Flow t,23-7 Indicates the flow of the second preset time period of the user to be identified, Flow t,7-23 represents the flow rate of the third preset time period for identifying the user, and b represents the second threshold. For example, a can be 0.4, or 0.5, etc., without limitation.

[0099] In an example, as shown in the following Table 2, taking the first preset time period including 3 days and the flow rate of the second preset time period being 23:00-07:00 as an example, a schematic table of the second target number of days is specifically shown.

[0100] Table 2 Schematic diagram of the second target days

[0101]

[0102]

[0103] It should be noted that the data in Table 2 are only exemplary. In the embodiment of the present application, the first preset time period, the flow data and the second target number of days may also be other data without limitation.

[0104] In this way, the determining device can determine that P2=1 / 3=0.333.

[0105] 3. The third value.

[0106] In one example, the determining device may determine the third value according to the following formula seven.

[0107]

[0108] Wherein, P3 represents the third value, represents the third target number of days. For example, the determining device can determine R according to the following formula eight t .

[0109]

[0110] Among them, Flow t,19-00 Indicates the flow of the user to be identified in the second preset time period (for example, from 19:00 to 0:00), Flow 19-00 represents the average of the traffic of the broadband user in the second preset time period from 19:00 to 0:00, and c represents the third threshold. For example, c can be 1.2, 1.3, etc., without limitation.

[0111] In one example, as shown in Table 3 below, the first preset time period includes 3 days, c is 1.2, and the average evening traffic used by broadband users is Flow 19-00 Taking 78 as an example, a schematic table of the third target number of days is specifically shown.

[0112] Table 3 Schematic diagram of the third target days

[0113]

[0114]

[0115] It should be noted that the data in Table 3 are only exemplary. In the embodiment of the present application, the first preset time period, the flow data and the third target number of days may also be other data without limitation.

[0116] In this way, the determining device can determine that P3=1 / 3=0.333.

[0117] S303: The determining device determines a first prediction result for the first eigenvalue according to the first eigenvalue and a corresponding eigenvalue threshold, and obtains a plurality of first prediction results corresponding to the plurality of eigenvalues ​​one by one.

[0118] The first eigenvalue is any one of a plurality of eigenvalues; the first prediction result is used to characterize the probability score of each user to be identified as a non-broadband user. For example, the first prediction result can be represented by 0 and 1. 0 can represent that the probability score of the user to be identified as a non-broadband user is 0, and 1 can represent that the probability score of the user to be identified as a non-broadband user is 1.

[0119] The characteristic threshold corresponding to the first characteristic value may be determined according to the number of users to be identified, for example, the 80th percentile of the number of users to be identified.

[0120] As a possible implementation manner, the determining device may determine the first prediction result based on the magnitude relationship between the first characteristic value and the corresponding characteristic threshold.

[0121] It should be noted that the specific description of determining the first prediction result in this possible implementation method will be described in subsequent sections, and this application will not go into details here.

[0122] S304: The determination device determines a second prediction result according to a preset prediction model and business data of a plurality of users to be identified.

[0123] The preset prediction model can be set as needed. For example, it can be an Xgboost algorithm model. The second prediction result is used to characterize the probability score of each user to be identified as a user without broadband or with broadband.

[0124] As a possible implementation manner, the determination device may input the business data of multiple users to be identified into a preset prediction model to obtain a second prediction result.

[0125] It should be noted that the specific description of determining the second prediction result in this possible implementation will be described in subsequent sections, and this application will not go into details here.

[0126] S305: The determining device determines a non-broadband user from a plurality of users to be identified according to a preset voting mechanism, a plurality of first prediction results, and a second prediction result.

[0127] As a possible implementation method, the determination device can vote for each user to be identified based on multiple first prediction results and second prediction results. Each user to be identified can obtain a score based on the obtained votes, and when the score of the first user to be identified is greater than a score threshold, the first user to be identified is determined to be a non-broadband user, and then the non-broadband user is determined from multiple users to be identified.

[0128] The score threshold can be set as required, for example, 50% of the maximum value of the sum of scores.

[0129] It should be noted that the specific description of determining the non-broadband user from multiple users to be identified in this possible implementation will be described in subsequent parts, and this application will not go into details here.

[0130] Based on the technical solution provided by the embodiment of the present application, the determination device can determine multiple characteristic values ​​of each user to be identified through the service data of multiple users to be identified. Since the first value and the second value in the multiple characteristic values ​​can reflect the number of days when the usage ratio of the traffic of the user to be identified in the second preset time period within the first preset time period is greater than the preset value, the traffic usage habits of the user to be identified at night and during the day can be determined. Considering that the user without broadband can only use mobile traffic for life and entertainment activities at night, the determination device determines the third value in the multiple characteristic values ​​to reflect the relationship between the traffic of the user to be identified in the second preset time period within the first preset time period and the traffic of the broadband user in the second preset time period within the first preset time period. After obtaining multiple characteristic values ​​of each user to be identified, multiple first prediction results corresponding to the multiple characteristic values ​​can be determined by each characteristic value and the corresponding characteristic threshold. In addition, the determination device can also determine the second prediction result by a preset prediction model. And determine the user without broadband from the multiple users to be identified by the preset voting mechanism, the first prediction result and the second prediction result. In this way, the determination device distinguishes the service data of the multiple users to be identified from multiple angles, and can accurately determine the user without broadband from the multiple users to be identified.

[0131] A possible embodiment is as follows Figure 4 As shown, in order to determine the first prediction result, the above S303 of the present application may specifically include the following S401-S402.

[0132] S401. A determining device sorts first characteristic values ​​of a plurality of users to be identified to determine a ranking of a first characteristic value of a first user to be identified.

[0133] The first user to be identified is any one of the multiple users to be identified;

[0134] As a possible implementation, a comparator is provided inside the determination device, and the comparator is used to compare the first feature values ​​of multiple users to be identified and sort the first feature values ​​of multiple users to be identified. The determination device can sort the first feature values ​​of multiple users to be identified by the comparator to determine the first feature value ranking of the first user to be identified.

[0135] S402: When the ranking of the first characteristic value of the first user to be identified is greater than or equal to a fourth threshold, the determining device determines that the first user to be identified is a user without broadband.

[0136] The fourth threshold may be set according to the number of users to be identified. For example, when the number of users to be identified is 6, the fourth threshold may be 2.

[0137] In an example, as shown in Table 4, when the number of users to be identified is 6, the first numerical values ​​P1 of the users to be identified are 0.2, 0.4, 0.5, 0.5, 0.7, and 0.8 respectively, and the fourth threshold is 2, the first prediction result D1 corresponding to P1 can be shown in Table 4 below.

[0138] Table 4 Schematic diagram of the first prediction results corresponding to P1

[0139] User 1 User 2 User 3 User 4 User 5 User 6 P1 0.4 0.7 0.55 0.8 0.5 0.2 Ranking 5 2 3 1 4 6 D1 0 1 0 1 0 0

[0140] It should be noted that the data in Table 4 are only exemplary. In the embodiment of the present application, the first prediction result corresponding to P1 may also include other data, which is not limited.

[0141] In an example, as shown in Table 5, when the number of users to be identified is 6, the second values ​​P2 of the users to be identified are 0.6, 0.64, 0.7, 0.71, 0.91, 0.92 respectively, and the fourth threshold is 2, the first prediction result D2 corresponding to P2 can be shown in Table 5 below.

[0142] Table 5 Schematic diagram of the first prediction results corresponding to P2

[0143] User 1 User 2 User 3 User 4 User 5 User 6 P2 0.7 0.71 0.64 0.92 0.91 0.6 Ranking 4 3 5 1 2 6 D2 0 0 0 1 1 0

[0144] It should be noted that the data in Table 5 are only exemplary. In the embodiment of the present application, the first prediction result corresponding to P2 may also include other data, which is not limited.

[0145] In an example, as shown in Table 6, when the number of multiple users to be identified is 6, the third numerical values ​​P3 of the multiple users to be identified are 0.38, 0.57, 0.59, 0.75, 0.83, and 0.84 respectively, and the fourth threshold is 2, the first prediction result D3 corresponding to P3 can be shown in Table 6 below.

[0146] Table 6 Schematic diagram of the first prediction results corresponding to P3

[0147]

[0148]

[0149] It should be noted that the data in Table 6 are only exemplary. In the embodiment of the present application, the first prediction result corresponding to P3 may also include other data, which is not limited.

[0150] In this way, the determination device can determine the first prediction results corresponding to the multiple characteristic values ​​of each user to be identified. Since the one-to-one corresponding first prediction results determine whether the user to be identified is a non-broadband user from different angles, the problem of low accuracy in predicting the non-broadband user from a single angle is avoided, and the non-broadband user among the multiple users to be identified can be accurately determined.

[0151] In a possible embodiment, the second prediction result may include a first sub-prediction result and / or a second sub-prediction result, wherein the first sub-prediction result is used to characterize the probability score of each user to be identified as a non-broadband user; and the second sub-prediction result is used to characterize the probability score of each user to be identified as a broadband user. Figure 5 As shown, in order to determine the second prediction result, the above S304 of the present application may specifically include the following S501.

[0152] S501. The determination device determines a first sub-prediction result according to the business data of multiple users to be identified and a first prediction model; and / or determines a second sub-prediction result according to the business data of multiple users to be identified and a second prediction model.

[0153] Among them, the positive result corresponding to the first prediction model is the fourth value, and the negative result corresponding to the second prediction model is the fourth value. The positive result is used to indicate that the user to be identified is a non-broadband user, and the negative result is used to indicate that the user to be identified is a broadband user.

[0154] For example, when it is determined that the user to be identified is a non-broadband user, the first prediction model may output a positive result of 1. When it is determined that the user to be identified is a broadband user, the first prediction model may output a result of 0.

[0155] When it is determined that the user to be identified is a broadband user, the second prediction model may output a positive result of 1. When it is determined that the user to be identified is a non-broadband user, the first prediction model may output a result of 0.

[0156] As a possible implementation method, after acquiring the business data of multiple users to be identified, the determination device can input the business data of multiple users to be identified into a first prediction model to obtain a first sub-prediction result, and / or input the business data of multiple users to be identified into a second prediction model to obtain a second sub-prediction result.

[0157] It should be noted that the first prediction model and the second prediction model may be pre-trained models. Taking the first prediction model and the second prediction model as Xgboost algorithm models as an example, the training process of the first prediction model and the second prediction model is described as follows:

[0158] 1. The first prediction model.

[0159] S1. Obtain a user sample set from an operator database. The user sample set includes service data of multiple users and data on whether the users have broadband.

[0160] In one example, taking the user's service data including user age, gender, package fee, package traffic, network time, and total daytime traffic as an example, the format of the obtained user sample set can be as shown in Table 7 below:

[0161] Table 7 User sample diagram

[0162]

[0163] It should be noted that the data in Table 7 are only exemplary. In the embodiment of the present application, the user sample set may also include other data, which is not limited.

[0164] S2. The identifier of no broadband user in the user sample set is determined as 1, which is a positive sample, and the identifier of the broadband user is determined as 0, which is a negative sample.

[0165] S3. The user sample set is imported into the XGboost algorithm model for training, and the parameters in the XGboost algorithm model are adjusted until the output result is the same as the corresponding identifier, thereby obtaining a trained XGboost algorithm model (ie, the first prediction model).

[0166] Furthermore, the determination device may input the business data of the user to be identified into the trained first prediction model, and output the result through calculation by the XGboost algorithm model as the first sub-prediction result of the user (which may also be expressed as D4).

[0167] 2. The second prediction model.

[0168] S1. The process of obtaining the user sample set can refer to the description of the first prediction model above and will not be elaborated herein.

[0169] S2. The identifier of the broadband user in the user sample set is determined as 1, which is a positive sample, and the identifier of the non-broadband user is determined as 0, which is a negative sample.

[0170] S3. The user sample set is imported into the XGboost algorithm model for training, and the parameters in the XGboost algorithm model are adjusted until the output result is the same as the corresponding identifier, thereby obtaining a trained XGboost algorithm model (ie, the second prediction model).

[0171] Furthermore, the determination device may input the business data of the user to be identified into the trained second prediction model, and output the result through calculation by the XGboost algorithm model as the second sub-prediction result of the user (which may also be expressed as D5).

[0172] In this way, by setting different positive and negative sample identifiers and selecting differentiated features, different optimal parameters can be trained to obtain the first prediction model and the second prediction model. This can avoid overfitting caused by samples with a large proportion due to sample imbalance, thereby improving the accuracy of determining users without broadband.

[0173] In a possible embodiment, when the second prediction result does not include the second sub-prediction result, such as Figure 6 As shown, in order to determine the non-broadband user from multiple users to be identified, the above S305 of the present application may specifically include the following S601.

[0174] S601: The determination device determines, for a first user to be identified, that the first user to be identified is a user without broadband if the sum of the scores of the first prediction result and the first sub-prediction result predicting that the first user to be identified is a user without broadband is greater than or equal to a fifth threshold.

[0175] The fifth threshold value may be set as required, for example, 50% of the maximum value of the sum of scores.

[0176] In an example, as shown in Table 8 below, a schematic diagram of prediction results is shown in which multiple users to be identified include user 1, user 2, and user 3, the first prediction result includes D1, D2, and D3, and the second preset result includes D4.

[0177] Table 8 Schematic diagram of prediction results

[0178] user D1 D2 D3 D4 Sum of scores 1 1 0 1 1 3 2 0 0 1 1 2 3 1 1 0 0 2

[0179] For example, when the fifth threshold is 2 and the first prediction results and the second prediction results of multiple users to be identified are as shown in Table 8, the determination device can determine that user 1, user 2 and user 3 among the multiple users to be identified are non-broadband users.

[0180] It should be noted that the data in Table 8 are only exemplary. In the embodiments of the present application, D1, D2, D3, and D4 may also be other data without limitation.

[0181] In this way, since multiple prediction results determine whether the user to be identified is a user without broadband from different angles, the determination device can use a preset voting mechanism to summarize and analyze the multiple prediction results, and finally determine whether the user to be identified is a user without broadband, thereby avoiding the problem of low accuracy in predicting users without broadband from a single angle, and accurately determining users without broadband among multiple users to be identified.

[0182] In a possible embodiment, when the second prediction result includes the second sub-prediction result, as Figure 7As shown, in order to determine the non-broadband user from multiple users to be identified, the above S305 of the present application may specifically include the following S701-702.

[0183] S701. The determination device performs numerical conversion on the second sub-prediction result.

[0184] The second sub-prediction result after numerical conversion is used to characterize the probability score of each user to be identified as a non-broadband user.

[0185] In one example, when the second sub-prediction result D5=0, it can be indicated that the user to be identified is a broadband user, that is, the probability score of the user to be identified is a broadband user is 0. When the second sub-prediction result D5=1, it can be indicated that the user to be identified is a non-broadband user, that is, the probability score of the user to be identified is 1.

[0186] In one example, when D5=0, the determination device performs a numerical conversion on the second sub-prediction result, and D5 after the numerical conversion is 1. The numerical conversion of D5=1 can indicate that the probability score of the user to be identified as a non-broadband user is 1. When D5=1, the determination device performs a numerical conversion on the second sub-prediction result, and D5 after the numerical conversion is 0. The numerical conversion of D5=0 can indicate that the probability score of the user to be identified as a non-broadband user is 0.

[0187] S702: The determining device determines, for a first user to be identified, that the first user to be identified is a user without broadband if the sum of the scores of the target prediction result predicting that the first user to be identified is a user without broadband is greater than or equal to a fifth threshold.

[0188] The target prediction result includes at least a first prediction result and a second sub-prediction result after numerical conversion.

[0189] The following is an explanation of the different possible results that the target prediction results may include.

[0190] 1. The target prediction result includes the first prediction result and the second sub-prediction result after numerical conversion.

[0191] In an example, as shown in Table 9 below, a schematic diagram of prediction results is shown in which multiple users to be identified include user 1, user 2, and user 3, the first prediction result includes D1, D2, and D3, and the second preset result includes D5.

[0192] Table 9 Schematic diagram of prediction results

[0193] user D1 D2 D3 D5 Sum of scores 1 1 0 1 0 2 2 0 0 1 1 2 3 1 1 0 1 3

[0194] For example, when the fifth threshold is 2 and the first prediction results and the second prediction results of multiple users to be identified are as shown in Table 9, the determination device can determine that user 1, user 2 and user 3 among the multiple users to be identified are non-broadband users.

[0195] It should be noted that the data in Table 9 are only exemplary. In the embodiments of the present application, D1, D2, D3, and D5 may also be other data without limitation.

[0196] 2. The target prediction result includes the first prediction result, the first sub-prediction result and the second sub-prediction result.

[0197] In an example, as shown in Table 10 below, a schematic diagram of prediction results is shown in which multiple users to be identified include user 1, user 2 and user 3, the first prediction results include D1, D2, D3, and the second preset results include D4 and D5.

[0198] Table 10 Schematic diagram of prediction results

[0199] user D1 D2 D3 D4 D5 Sum of scores 1 1 0 1 1 0 3 2 0 0 1 1 1 3 3 1 1 0 0 1 3

[0200] For example, when the fifth threshold is 2.5 and the first prediction results and the second prediction results of multiple users to be identified are as shown in Table 10, the determination device can determine that user 1, user 2 and user 3 among the multiple users to be identified are non-broadband users.

[0201] It should be noted that the data in Table 10 are only exemplary. In the embodiments of the present application, D1, D2, D3, D4, and D5 may also be other data without limitation.

[0202] In this way, since multiple prediction results determine whether the user to be identified is a user without broadband from different angles, the determination device can use a preset voting mechanism to summarize and analyze the multiple prediction results, and finally determine whether the user to be identified is a user without broadband, thereby avoiding the problem of low accuracy in predicting users without broadband from a single angle, and accurately determining users without broadband among multiple users to be identified.

[0203] The various solutions in the above embodiments of the present application can be combined without contradiction.

[0204] The embodiment of the present application can divide the determination device into functional modules or functional units according to the above method example. For example, each functional module or functional unit can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules or functional units. Among them, the division of modules or units in the embodiment of the present application is schematic, which is only a logical function division, and there may be other division methods in actual implementation.

[0205] In the case of dividing each functional module into corresponding functional modules, Figure 8 A schematic diagram of the structure of a determination device is shown. The determination device may be a server or a chip used in a server. The determination device may be used to execute the functions on the server involved in the above embodiments. Figure 8 The determination device shown may include: an acquisition unit 801 and a determination unit 802. The acquisition unit 801 is used to acquire business data of multiple users to be identified within a first preset time period, and the business data includes operation support system O domain data and business support system B domain data; the determination unit 802 is used to determine multiple characteristic values ​​of each user to be identified according to the business data of each user to be identified, and the multiple characteristic values ​​include a first numerical value, a second numerical value and a third numerical value; the first numerical value is the ratio of the first target day to the first preset time period, the second numerical value is the ratio of the second target day to the first preset time period, and the third numerical value is the ratio of the third target day to the first preset time period. The first target day is the day when the ratio of the flow rate of the second preset time period of each user to be identified to the flow rate of the whole day is greater than or equal to the first threshold, and the second target day is the day when the ratio of the flow rate of the second preset time period of each user to be identified to the flow rate of the third preset time period is greater than or equal to the first threshold. The third target number of days is the number of days when the ratio of the traffic in the second preset time period of each user to be identified to the average traffic in the second preset time period of broadband users is greater than or equal to the third threshold; the determination unit 802 is also used to determine the first prediction result according to the first characteristic value and the corresponding characteristic threshold for the first characteristic value, and obtain multiple first prediction results corresponding to the multiple characteristic values ​​one by one, and the first characteristic value is any one of the multiple characteristic values; the first prediction result is used to characterize the probability score of each user to be identified being a non-broadband user; the determination unit 802 is also used to determine the second prediction result according to a preset prediction model and the business data of multiple users to be identified; the determination unit 802 is also used to determine the non-broadband user from multiple users to be identified according to the preset voting mechanism, the multiple first prediction results and the second prediction result.

[0206] In one possible design, the determination unit 802 is specifically used to: sort the first characteristic values ​​of multiple users to be identified to determine the first characteristic value ranking of the first user to be identified, where the first user to be identified is any one of the multiple users to be identified; when the first characteristic value ranking of the first user to be identified is greater than or equal to a fourth threshold, determine that the first user to be identified is a non-broadband user.

[0207] In one possible design, the second prediction result includes a first sub-prediction result and / or a second sub-prediction result, the first sub-prediction result is used to characterize the probability score of each user to be identified as a non-broadband user; the second sub-prediction result is used to characterize the probability score of each user to be identified as a broadband user; the determination unit 802 is specifically used to: determine the first sub-prediction result based on the business data of multiple users to be identified and the first prediction model; and / or determine the second sub-prediction result based on the business data of multiple users to be identified and the second prediction model; wherein the positive result corresponding to the first prediction model is the fourth numerical value, and the negative result corresponding to the second prediction model is the fourth numerical value, the positive result is used to indicate that the user to be identified is a non-broadband user, and the negative result is used to indicate that the user to be identified is a broadband user.

[0208] In one possible design, when the second prediction result does not include the second sub-prediction result, the determination unit 802 is specifically used to: for the first user to be identified, if the sum of the scores of the first prediction result and the first sub-prediction result predicting that the first user to be identified is a user without broadband is greater than or equal to a fifth threshold, then determine that the first user to be identified is a user without broadband.

[0209] In one possible design, when the second prediction result includes the second sub-prediction result, the determination unit 802 is specifically used to: perform numerical conversion on the second sub-prediction result, and the second sub-prediction result after numerical conversion is used to characterize the probability score of each user to be identified as a non-broadband user; for the first user to be identified, if the sum of the scores of the target prediction result predicting that the first user to be identified is a non-broadband user is greater than or equal to the fifth threshold, then the first user to be identified is determined to be a non-broadband user, and the target prediction result includes at least the first prediction result and the second sub-prediction result after numerical conversion.

[0210] The embodiment of the present application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be completed by a computer program to instruct the relevant hardware, and the program can be stored in the above computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be an internal storage unit of the determination device (including the data sending end and / or the data receiving end) of any of the above embodiments, such as a hard disk or memory of the determination device. The above computer-readable storage medium can also be an external storage device of the above terminal device, such as a plug-in hard disk equipped on the above terminal device, a smart memory card (smart media card, SMC), a secure digital (secure digital, SD) card, a flash card (flash card), etc. Further, the above computer-readable storage medium can also include both the internal storage unit of the above determination device and an external storage device. The above computer-readable storage medium is used to store the above computer program and other programs and data required by the above determination device. The above computer-readable storage medium can also be used to temporarily store data that has been output or is to be output.

[0211] It should be noted that the terms "first" and "second" in the specification, claims and drawings of the present application are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0212] It should be understood that in the present application, "at least one (item)" means one or more, "more than one" means two or more, "at least two (items)" means two or three and more than three, and "and / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0213] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0214] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0215] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0216] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0217] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0218] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for determining a user without broadband, characterized in that: The method comprises: Acquire business data of multiple users to be identified within a first preset time period; Determine multiple characteristic values ​​of each user to be identified according to the service data of each user to be identified, the multiple characteristic values ​​include a first value, a second value and a third value; the first value is the ratio of the first target day to the first preset time period, the second value is the ratio of the second target day to the first preset time period, the third value is the ratio of the third target day to the first preset time period, the first target day is the number of days when the ratio of the flow rate of the second preset time period of each user to be identified to the all-day flow rate is greater than or equal to the first threshold, the second target day is the number of days when the ratio of the flow rate of the second preset time period of each user to be identified to the daytime flow rate is greater than or equal to the second threshold, and the third target day is the number of days when the ratio of the flow rate of the second preset time period of each user to be identified to the average flow rate of the second preset time period of broadband users is greater than or equal to the third threshold; For the first eigenvalue, determining a first prediction result according to the first eigenvalue and a corresponding eigenvalue threshold, obtaining a plurality of first prediction results corresponding to the plurality of eigenvalues ​​one by one, wherein the first eigenvalue is any one of the plurality of eigenvalues; the first prediction result is used to characterize a probability score of each user to be identified being the non-broadband user; Determining a second prediction result according to a preset prediction model and the business data of the plurality of users to be identified; Determine the non-broadband user from the multiple users to be identified according to a preset voting mechanism, the multiple first prediction results, and the second prediction result; The determining a first prediction result according to the first feature value and the corresponding feature threshold comprises: sorting the first feature values ​​of the plurality of users to be identified to determine a ranking of the first feature value of a first user to be identified, where the first user to be identified is any one of the plurality of users to be identified; When the ranking of the first characteristic value of the first to-be-identified user is greater than or equal to a fourth threshold, determining that the first to-be-identified user is the non-broadband user; The second prediction result includes a first sub-prediction result and / or a second sub-prediction result, wherein the first sub-prediction result is used to characterize the probability score of each user to be identified as a non-broadband user; the second sub-prediction result is used to characterize the probability score of each user to be identified as a broadband user; and the second prediction result is determined according to the preset prediction model and the service data, including: Determine the first sub-prediction result according to the business data of the multiple users to be identified and the first prediction model; and / or, determining the second sub-prediction result according to the business data of the plurality of users to be identified and the second prediction model; Among them, the positive result corresponding to the first prediction model is the fourth value, the negative result corresponding to the second prediction model is the fourth value, the positive result is used to indicate that the user to be identified is the non-broadband user, and the negative result is used to indicate that the user to be identified is the broadband user.

2. The method according to claim 1, characterized in that In a case where the second prediction result does not include the second sub-prediction result, determining the non-broadband user from the multiple users to be identified according to a preset voting mechanism, the multiple first prediction results, and the second prediction result includes: For the first user to be identified, if the sum of the scores of the first prediction result and the first sub-prediction result predicting that the first user to be identified is the user without broadband is greater than or equal to a fifth threshold, it is determined that the first user to be identified is the user without broadband.

3. The method according to claim 2, characterized in that In a case where the second prediction result includes the second sub-prediction result, determining the non-broadband user from the multiple users to be identified according to a preset voting mechanism, the multiple first prediction results, and the second prediction result includes: Performing numerical conversion on the second sub-prediction result, where the second sub-prediction result after numerical conversion is used to characterize the probability score of each to-be-identified user being a non-broadband user; For the first user to be identified, if the sum of the scores of the target prediction result predicting that the first user to be identified is the user without broadband is greater than or equal to the fifth threshold, then the first user to be identified is determined to be the user without broadband, and the target prediction result includes at least the first prediction result and the second sub-prediction result after numerical conversion.

4. A device for determining a user without broadband, characterized in that: The device comprises an acquisition unit and a determination unit; The acquisition unit is used to acquire the service data of multiple users to be identified within a first preset time period; The determination unit is used to determine multiple characteristic values ​​of each user to be identified according to the business data of each user to be identified, and the multiple characteristic values ​​include a first value, a second value and a third value; the first value is a ratio of a first target day to the first preset time period, the second value is a ratio of a second target day to the first preset time period, and the third value is a ratio of a third target day to the first preset time period. The first target day is the number of days on which the ratio of the flow rate of the second preset time period of each user to be identified to the flow rate of the whole day is greater than or equal to a first threshold, the second target day is the number of days on which the ratio of the flow rate of the second preset time period of each user to be identified to the flow rate of the third preset time period is greater than or equal to a second threshold, and the third target day is the number of days on which the ratio of the flow rate of the second preset time period of each user to be identified to the flow rate of the second preset time period of broadband users is greater than or equal to a third threshold; The determination unit is further configured to determine a first prediction result according to the first characteristic value and a corresponding characteristic threshold value for the first characteristic value, to obtain a plurality of first prediction results corresponding to the plurality of characteristic values ​​one by one, wherein the first characteristic value is any one of the plurality of characteristic values; the first prediction result is used to characterize a probability score of each user to be identified as the non-broadband user; The determining unit is further configured to determine a second prediction result according to a preset prediction model and the service data of the plurality of users to be identified; The determining unit is further configured to determine the non-broadband user from the multiple users to be identified according to a preset voting mechanism, the multiple first prediction results and the second prediction result; The determining unit is specifically configured to: sorting the first feature values ​​of the plurality of users to be identified to determine a ranking of the first feature value of a first user to be identified, where the first user to be identified is any one of the plurality of users to be identified; When the ranking of the first characteristic value of the first to-be-identified user is greater than or equal to a fourth threshold, determining that the first to-be-identified user is the non-broadband user; The second prediction result includes a first sub-prediction result and / or a second sub-prediction result, wherein the first sub-prediction result is used to characterize the probability score of each user to be identified as the non-broadband user; the second sub-prediction result is used to characterize the probability score of each user to be identified as a broadband user; the determination unit is specifically used to: Determine the first sub-prediction result according to the business data of the multiple users to be identified and the first prediction model; and / or, determining the second sub-prediction result according to the business data of the plurality of users to be identified and the second prediction model; Among them, the positive result corresponding to the first prediction model is the fourth value, the negative result corresponding to the second prediction model is the fourth value, the positive result is used to indicate that the user to be identified is the non-broadband user, and the negative result is used to indicate that the user to be identified is the broadband user.

5. The device according to claim 4, characterized in that In a case where the second prediction result does not include the second sub-prediction result, the determining unit is specifically configured to: For the first user to be identified, if the sum of the scores of the first prediction result and the first sub-prediction result predicting that the first user to be identified is the user without broadband is greater than or equal to a fifth threshold, it is determined that the first user to be identified is the user without broadband.

6. The device according to claim 5, characterized in that In a case where the second prediction result includes the second sub-prediction result, the determining unit is specifically configured to: Performing numerical conversion on the second sub-prediction result, where the second sub-prediction result after numerical conversion is used to characterize the probability score of each to-be-identified user being a non-broadband user; For the first user to be identified, if the sum of the scores of the target prediction result predicting that the first user to be identified is the user without broadband is greater than or equal to the fifth threshold, then the first user to be identified is determined to be the user without broadband, and the target prediction result includes at least the first prediction result and the second sub-prediction result after numerical conversion.

7. A computer-readable storage medium, characterized in that: The readable storage medium stores instructions, and when the instructions are executed by a computer, the method according to any one of claims 1 to 3 is implemented.

8. A device for determining a user without broadband, characterized in that: include: A processor, a memory and a communication interface; wherein the communication interface is used for the determination device of the non-broadband user to communicate; The memory is used to store one or more programs, which include computer-executable instructions. When the device for determining users without broadband is running, the processor executes the computer-executable instructions stored in the memory to enable the device for determining users without broadband to perform the method described in any one of claims 1-3.