CN114912503A - Method and system for screening downlink equipment of home gateway - Google Patents

Abstract

The application discloses a method and a system for screening downlink equipment of a home gateway. The method comprises the following steps: acquiring and storing probe data of a user in real time; identifying a type of the downstream device based on the probe data; determining abnormal device detection criteria based on the type of device and the probe data and detecting abnormal devices based on the criteria; and determining a non-home user scenario by performing a factor analysis or clustering algorithm on the probe data. The application also discloses a corresponding system.

Description

Method and system for screening downlink equipment of home gateway

Technical Field

The present application relates to the technical field of gateway downlink device management, and in particular, to a method and a system for managing downlink devices based on home gateway probe data, and more particularly, to a method and a system for screening downlink devices of a home gateway.

Background

A home gateway is a hardware that connects a home or small office network to the Internet. The residential gateway may provide the conversion function and enable the user to share a DSL or cable modem Internet connection with all computers on the internal network. The residential gateway is located between the DSL or cable modem and the internal network. DSL or cable modems can also be integrated into the residential gateway. The home gateway has the functions of modem and routing, and has the function of making the home LAN access to the external WAN.

The actual equipment used by a family user is an important feature for describing the whole family portrait and is also an important dimension for accurate marketing. However, the current home gateway devices in the prior art can only discover devices directly connected thereunder, and the discovery of these devices can only indicate that these devices have connected to the gateway once, but cannot indicate whether they belong to the home user. Therefore, if the data is directly used for marketing, the marketing precision is low, and the problem that the key points are not highlighted is caused.

Therefore, it is very important to accurately screen out the devices under the home gateway that really belong to the home user for characterizing the home portrait.

There is an urgent need in the art for a method and system that can actually screen out the commonly used devices belonging to the home that are linked down by the home gateway.

Disclosure of Invention

In order to solve the problems, an anomaly detection algorithm is introduced to mark suspected non-stationary equipment, and a principal component analysis algorithm and a clustering algorithm (both belong to two main unsupervised learning methods in machine learning and are not described in detail) are introduced on the basis, so that scenes of non-family users are removed, and the purpose of accurately drawing pictures of the family equipment is achieved. Based on this, just can accurately carry out better screening to home gateway's equipment of making contact down to follow-up more accurate attached drawing and the guarantee of removing obstacles of providing.

The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements of all aspects nor delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.

Specifically, according to a first aspect of the present application, there is provided a method for screening a downstream device of a home gateway, the method including the steps of:

acquiring and storing probe data of a user in real time;

identifying a type of the downstream device based on the probe data;

determining abnormal device detection criteria based on the type of device and the probe data and detecting abnormal devices based on the criteria; and

non-home user scenarios are determined by performing a factor analysis or clustering algorithm on the probe data.

According to a preferred embodiment of the present application, identifying the type of the downstream device based on the probe data further comprises: the probe data is processed using a big data processing framework to identify the type of the downstream device.

According to a preferred embodiment of the present application, the abnormal device detection criterion is determined based on the feature vectors of all downstream devices.

According to a preferred embodiment of the present application, detecting the abnormal device based on the criterion further comprises: if the number of active days of the downstream device is less than the abnormal device detection criteria, determining as an abnormal device, and otherwise, determining as a resident device.

According to a preferred embodiment of the present application, determining the non-home user scenario by the factorial analysis and clustering algorithm further comprises: determining a feature vector of the resident equipment; carrying out standardization processing on the feature vector; performing significance checking on the normalized feature vectors; if the result is obvious, performing factor analysis, otherwise, performing cluster analysis; judging whether the result of the factor analysis or the clustering analysis is reasonable; and if the result is reasonable, deleting the abnormal data.

According to a second aspect of the present application, there is provided a system for screening a downstream device of a home gateway, the system including the following modules:

the probe data acquisition module is used for acquiring and storing probe data of a user in real time;

a device identification module to identify a type of the downstream device based on the probe data;

an abnormal apparatus detection module for determining an abnormal apparatus detection criterion based on the type of the apparatus and the probe data and detecting an abnormal apparatus based on the criterion; and

and the non-family scene detection module is used for determining the non-family user scene through factor analysis or clustering algorithm.

To the accomplishment of the foregoing and related ends, the one or more aspects comprise the features hereinafter fully described and particularly pointed out in the claims. The following description and the annexed drawings set forth in detail certain illustrative features of the one or more aspects. These features are indicative, however, of but a few of the various ways in which the principles of various aspects may be employed and the present description is intended to include all such aspects and their equivalents.

Drawings

So that the manner in which the above recited features of the present application can be understood in detail, a more particular description of the disclosure briefly summarized above may be had by reference to aspects, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only certain typical aspects of this application and are therefore not to be considered limiting of its scope, for the description may admit to other equally effective aspects.

In the drawings:

fig. 1 is a flowchart illustrating a method of screening a home gateway downstream device according to an embodiment of the present application;

fig. 2 is a block diagram illustrating a structure of a system for screening a home gateway downstream device according to an embodiment of the present application;

fig. 3 is a schematic diagram illustrating an abnormal device detection model of the method and system for screening devices commonly used in a home gateway according to an embodiment of the present application;

fig. 4 is a schematic diagram illustrating a non-home scene detection model of a method and system for screening home gateway downstream devices according to an embodiment of the present application; and

fig. 5 is an exemplary sample calculation process illustrating a non-home scene detection model as shown in fig. 4.

Detailed Description

The detailed description set forth below in connection with the appended drawings is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details to provide a thorough understanding of the various concepts. It will be apparent, however, to one skilled in the art that these concepts may be practiced without these specific details. In some instances, well known modules are shown in block diagram form in order to avoid obscuring such concepts.

It is to be understood that other embodiments will be evident based on the present disclosure, and that system, structural, process, or mechanical changes may be made without departing from the scope of the present disclosure.

With reference to fig. 1 and 2, aspects are described with reference to one or more modules and one or more methods that may perform the actions or functions described herein. In an aspect, the term "module" as used herein may be one of the parts that make up a system, may be hardware or software or some combination thereof, and may be divided into other components or modules. While the operations described below in fig. 1 are presented in a particular order and/or as performed by example modules, it should be understood that the order of the actions, as well as the modules performing the actions, may vary depending on the implementation. Further, it should be understood that the following actions or functions may be performed by a specially programmed processor, a processor executing specially programmed software or computer readable media, or by any other combination of hardware modules and/or software modules capable of performing the described actions or functions.

Fig. 1 is a flowchart illustrating a method 100 for screening devices in a home gateway next generation according to an embodiment of the present application.

As shown in fig. 1, the method 100 generally includes the following steps.

Probe data for a user is collected and stored in real time. The probe data includes, but is not limited to, device information of a connection gateway, device connection mode information, and the like.

Identifying the brand, type, model, etc. of the gateway downline equipment based on the collected equipment probe data (step 102)

Then, according to the device probe data collected in a certain period and based on the determined device type, each downstream device is detected to determine a suspected abnormal device and mark the suspected abnormal device (step 103). In particular, a big data processing framework can be used to process the collected probe data, so as to calculate feature vectors of each device connected with the gateway downstream, such as but not limited to device type, device online days and the like, and determine the detection standard of the abnormal device according to the overall feature vector.

By establishing an abnormal equipment detection model (which will be described in detail below), an abnormal detection algorithm is combined with the degree of finding the downstream equipment by the gateway, and the original abnormal detection algorithm is improved in a scene, so that the model can play a role in a special data scene, and the model interpretation is more in line with the habit of the user in actually using the equipment.

Finally, a scenario of gateway usage is pre-determined to identify scenarios of suspected non-home users (step 104). The method mainly utilizes principal component analysis and clustering algorithm to eliminate non-family user scenes, thereby achieving the purpose of accurately portraying family equipment.

Specifically, resident equipment of the gateway can be obtained based on abnormal equipment detection standards determined according to the big data, so that equipment type feature vectors of all the gateways are obtained, and non-home gateway data are removed through principal component analysis and clustering algorithm.

By introducing a non-home scene detection model (which will be described in detail below), the scene used by the gateway downlink device is judged and the suspected scene is marked, so that accurate portrayal can be performed for the home user, and a foundation is laid for providing personalized services.

The structure of a system for screening devices commonly used in a home gateway downlink according to an embodiment of the present application is illustrated in fig. 2.

As shown in fig. 2, a system 200 according to the present application generally includes the following modules: a probe data acquisition module 201; a device identification module 202; an abnormal device detection module 203; and a non-home scenario detection module 204.

The specific functions and implementations of the various modules are described in detail below in conjunction with fig. 2.

Probe data acquisition module 201

The probe data acquisition module is mainly used for acquiring and storing probe data of a user in real time. The probe data such as, but not limited to, device information of the connection gateway, device connection mode information, and the like.

Device identification module 202

The equipment identification module is mainly used for identifying the brand, type, model and the like of the gateway downlink equipment based on the acquired equipment probe data.

Abnormal device detection module 203

The abnormal equipment detection module is mainly used for detecting the resident equipment according to the equipment probe data collected in a certain period so as to determine suspected abnormal equipment and mark the suspected abnormal equipment. In particular, the module can process the collected probe data using a big data processing framework to calculate feature vectors of each device connected downstream from the gateway, such as, but not limited to, device type, device on-line days, etc., and determine abnormal device detection criteria from the overall feature vectors. And, the module determines whether the gateway downstream device is an abnormal device based on the abnormal device detection criteria.

Non-home scene detection module 204

The non-family scene detection module is mainly used for prejudging the use scene of the gateway so as to identify the scene of a suspected non-family user. The module mainly utilizes principal component analysis and clustering algorithm to eliminate non-family user scenes, thereby achieving the purpose of accurate family equipment portrait.

Specifically, resident equipment of the gateway is obtained based on abnormal equipment detection standards determined by the abnormal equipment detection module according to the big data, so that equipment feature vectors of all the gateways are obtained, and non-home gateway data are removed through principal component analysis and clustering algorithm.

A schematic diagram of an abnormal device detection model of the method and system for screening devices commonly used in a home gateway according to the embodiment of the present application is illustrated in further detail in fig. 3.

As shown in fig. 3, samples of downstream devices within two weeks of each gateway are taken, for example, according to the abnormal device detection model.

Based on these samples, the upper (qu) and lower (ql) anomaly limits can then be calculated for each gateway activity day. And determining the number nu of the devices with the active days higher than qu, the number nl of the devices with the active days lower than ql and the total number ns according to the abnormal upper limit value qu and the abnormal lower limit value ql of each gateway.

Then, based on these samples, an average (x) of gateway downstream devices in all samples is calculated. Specifically, the classification calculation is performed for all samples, for example, for the handset type, the value is the total number of handsets connected directly to the gateway divided by the total number of users in the whole network.

Combining the number nu of the devices with the number of active days higher than qu, the number nl of the devices with the number of active days lower than ql, the total number ns of the devices, and the average number x of the devices connected in the next row, determining the detection standard rule of the abnormal device according to the following formula:

if abs (ns-nl-x) ≦ abs (nu-x), rule ═ ql;

otherwise rule is qu.

Based on the standard, if the number of active days of the downstream equipment of each gateway is more than or equal to rule, the downstream equipment is the resident equipment of the gateway.

A schematic diagram of a non-home scene detection model of the method and system for screening devices in a home gateway downlink according to the embodiment of the present application is illustrated in further detail in fig. 4.

As shown in fig. 4, according to the non-home scenario detection model, data of each gateway downlinked resident device is extracted and a feature vector of the resident device is determined based on the data (step 401).

For example, the result of the feature vector is as follows:

{ number of unknown-type devices }, { number of OTHER-type devices }, { number of computers }, { number of smart devices }, { number of routers }, { number of mobile phones }, { PAD number }, and { number of network set-top boxes } ]

Next, these resident device feature vectors are normalized (step 402). Such as, but not limited to, this can be achieved by using the min _ max normalization method. Of course, methods of data normalization commonly used in the art are included within the scope of the present application.

Thereafter, a significance test is performed (step 403). For example, KMO testing and the Bartlett test can be used to perform KMO testing on the normalized data. As shown in fig. 5, the value after the verification is 0.6299059749541638, so the bartlett test significance is greater than 0.05. As described below, the results are not suitable for factor analysis, so clustering analysis is performed directly.

At step 404, it is determined whether the result of the significance check is significant.

If the results are significant, at step 405, a factor analysis is performed. The factor analysis mainly comprises principal component analysis and factor rotation.

Factor analysis is a statistical technique that studies the extraction of commonality factors from a variable population. It is also a well-known analytical technique in the field of statistics and therefore will not be described in detail here to avoid affecting the description of the main technical solutions. Principal Component Analysis (PCA) is a technique that simplifies data sets. It is a linear transformation. This transformation transforms the data into a new coordinate system such that the first large variance of any data projection is at the first coordinate (called the first principal component), the second large variance is at the second coordinate (the second principal component), and so on. Principal component analysis is often used to reduce the dimensionality of the data set while maintaining the features of the data set that contribute most to the variance. This is done by keeping the lower order principal components and ignoring the higher order principal components. Such low order components tend to preserve the most important aspects of the data. Since PCA is a commonly used dimension reduction analysis method in the art, further description is not repeated here to avoid affecting the description of the main technical solution.

If the results are not significant, at step 406, a cluster analysis is performed on the results of the significance check. The clustering analysis may employ the k-means algorithm. The k-means clustering algorithm is a common clustering analysis algorithm for iterative solution, and therefore, no further description is given here to avoid affecting the description of the main technical scheme.

As shown in fig. 5, an initial value (number of categories) k is first determined, and the result shown in fig. 5 is obtained by the inflection point method.

Where the horizontal axis x represents the value of the cluster number k (i.e., the number of classes) and the vertical axis y represents the TSSE value (sum of squared deviations within clusters). As can be seen from fig. 5, k is a reasonable result when k is 3.

Whether subjected to factor analysis or cluster analysis, the results are determined at step 407 whether the analysis results are reasonable.

If the analysis results are reasonable, the anomalous data is deleted at step 408.

If the category is not significant, the process ends.

If the result at step 407 is not reasonable, the process also ends.

Through the model, non-household equipment can be eliminated, and therefore the purpose of accurately portraying the household equipment is achieved.

Implementations of systems and methods according to the present application are described in detail below with reference to specific embodiments.

For example, for customer 00E x 1C4, 128 handset MAC addresses can be identified for a month, and the specific on-line times are shown in the table below.

Days of line	MAC number of mobile phone equipment
		1	125
6	1
		9	1
31	1

Referring to fig. 5, by means of the abnormal device detection module 203, the resident mobile phone of the client can be determined to be 3 (i.e., the number of devices with the number of online days greater than 1) based on the abnormal device detection criteria. Thereafter, device feature vectors are established for the customer's resident devices: { UNKNOWN:10, OTHER:0, PC:0, SMTDEV:0, ROUTER:1, PHONE:3, PAD:0, STB:0 }. According to the calculation of more than 160 ten thousand samples, the client can be determined to belong to a normal user through a k-means clustering algorithm.

Further, for the customer 6CD a07, the resident device of the customer is determined by the abnormal device detection criteria by the abnormal device detection module 203. Then, for these resident devices, its device feature vector is determined to be: { UNKNOWN:3397, OTHER:0, PC:6, SMTDEV:27, ROUTER:3, PHONE:5, PAD:0, STB:0 }. Calculated according to over 160 million samples, the client is obtained to belong to an abnormal user (namely, determined to be a non-family scene) through k-means clustering. According to the actual service, the commercial occupation ratio of the home gateway is not high, so the result is in line with the expectation.

Compared with the prior art, the method and the system for screening the equipment commonly used for the lower connection of the home gateway have the following advantages.

Firstly, an abnormal equipment detection model is established, an abnormal equipment detection algorithm is combined with the degree of finding the downstream equipment by the gateway, and the original abnormal equipment detection algorithm is improved in a scene mode. Therefore, the model can play a role in a specific data scene, and the model interpretation is more in line with the habit of the user for actually using the equipment.

Secondly, a non-family scene detection model is introduced, so that suspected marking is carried out on the use scene of the equipment, and a foundation is provided for subsequent personalized services.

Aspects, elements, or any portion of elements, or any combination of elements according to the present disclosure may be implemented with a "processing system" that includes one or more processors. Examples of processors include: microprocessors, microcontrollers, Digital Signal Processors (DSPs), Field Programmable Gate Arrays (FPGAs), Programmable Logic Devices (PLDs), state machines, gated logic, discrete hardware circuits, and other suitable hardware configured to perform the various functionalities described throughout this disclosure. One or more processors in the processing system may execute software. Software should be construed broadly to mean instructions, instruction sets, code segments, program code, programs, subprograms, software modules, applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, etc., whether referred to in software, firmware, middleware, microcode, hardware description language, or other terminology. The software may reside on a computer readable medium. The computer readable medium may be a non-transitory computer readable medium. By way of example, a non-transitory computer-readable medium comprises: magnetic storage devices (e.g., hard disk, floppy disk, magnetic strips), optical disks (e.g., Compact Disk (CD), Digital Versatile Disk (DVD)), smart cards, flash memory devices (e.g., memory card, memory stick, key drive), Random Access Memory (RAM), Read Only Memory (ROM), programmable ROM (prom), erasable prom (eprom), electrically erasable prom (eeprom), registers, removable disk, and any other suitable medium for storing software and/or instructions that may be accessed and read by a computer. By way of example, computer-readable media may also include carrier waves, transmission lines, and any other suitable media for conveying software and/or instructions that are accessible and readable by a computer. The computer readable media may reside in a processing system, external to the processing system, or distributed across multiple entities including the processing system. The computer readable medium may be embodied in a computer program product. By way of example, a computer program product may include a computer-readable medium in packaging material. Those skilled in the art will recognize how best to implement the described functionality presented throughout this disclosure, depending on the particular application and the overall design constraints imposed on the overall system.

It is to be understood that the specific order or hierarchy of steps in the methods disclosed is an illustration of exemplary processes. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the methods or methodologies described herein may be rearranged. The accompanying method claims present elements of the various steps in a sample order, and are not meant to be limited to the specific order or hierarchy presented unless specifically recited herein.

The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Thus, the claims are not intended to be limited to the aspects shown herein, but is to be accorded the full scope consistent with the language claims, wherein reference to an element in the singular is not intended to mean "one and only one" (unless specifically so stated) but rather "one or more". The term "some" means one or more unless specifically stated otherwise. A phrase referring to "at least one of a list of items refers to any combination of those items, including a single member. By way of example, "at least one of a, b, or c" is intended to encompass: at least one a; at least one b; at least one c; at least one a and at least one b; at least one a and at least one c; at least one b and at least one c; and at least one a, at least one b, and at least one c. All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Moreover, nothing disclosed herein is intended to be dedicated to the public regardless of whether such disclosure is explicitly recited in the claims.

Claims (10)

1. A method for screening downstream devices of a home gateway, the method comprising the steps of:

acquiring and storing probe data of a user in real time;

identifying a type of the downstream device based on the probe data;

determining abnormal device detection criteria based on the type of device and the probe data and detecting abnormal devices based on the criteria; and

determining a non-home user scenario by performing a factor analysis or clustering algorithm on the probe data.

2. The method of claim 1, wherein identifying the type of the downstream device based on the probe data further comprises:

processing the probe data using a big data processing framework to identify a type of the downstream device.

3. The method of claim 1, wherein the abnormal device detection criteria is determined based on feature vectors of all downstream devices.

4. The method of claim 1, wherein detecting an anomalous device based on the criteria further comprises:

if the number of active days of the downstream device is less than the abnormal device detection criteria, determining that the downstream device is an abnormal device, an

Otherwise, determining as the resident equipment.

5. The method of claim 4, wherein determining non-home user scenarios through a factorial analysis and clustering algorithm further comprises:

determining a feature vector of the resident equipment;

carrying out standardization processing on the feature vector;

performing significance checking on the normalized feature vectors;

if the result is remarkable, factor analysis is carried out,

otherwise, performing clustering analysis;

judging whether the result of the factor analysis or the clustering analysis is reasonable; and

and if the result is reasonable, deleting the abnormal data.

6. A system for screening the downstream equipment of a home gateway is characterized by comprising the following modules:

the probe data acquisition module is used for acquiring and storing the probe data of the user in real time;

a device identification module to identify a type of the downstream device based on the probe data;

an abnormal device detection module for determining abnormal device detection criteria based on the type of the device and the probe data and detecting abnormal devices based on the criteria; and

and the non-family scene detection module is used for determining the non-family user scene through factor analysis or clustering algorithm.

7. The system of claim 6, wherein identifying the type of the downstream device based on the probe data further comprises:

processing the probe data using a big data processing framework to identify a type of the downstream device.

8. The system of claim 6, wherein the abnormal device detection criteria is determined based on feature vectors of all downstream devices.

9. The system of claim 6, wherein detecting an anomalous device based on the criteria further comprises:

if the number of active days of the downstream device is less than the abnormal device detection criteria, determining that the downstream device is an abnormal device, an

Otherwise, determining as the resident equipment.

10. The system of claim 9, wherein determining non-home user scenarios through a factorial analysis and clustering algorithm further comprises:

determining a feature vector of the resident equipment;

carrying out standardization processing on the feature vector;

performing significance checking on the normalized feature vectors;

if the result is remarkable, factor analysis is carried out,

otherwise, performing clustering analysis;

judging whether the result of the factor analysis or the clustering analysis is reasonable; and

and if the result is reasonable, deleting the abnormal data.

Images