CN110493363B - System and method for distinguishing random MAC address of smart phone - Google Patents
System and method for distinguishing random MAC address of smart phone Download PDFInfo
- Publication number
- CN110493363B CN110493363B CN201810450998.3A CN201810450998A CN110493363B CN 110493363 B CN110493363 B CN 110493363B CN 201810450998 A CN201810450998 A CN 201810450998A CN 110493363 B CN110493363 B CN 110493363B
- Authority
- CN
- China
- Prior art keywords
- mac address
- random
- module
- real
- address information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L2101/00—Indexing scheme associated with group H04L61/00
- H04L2101/60—Types of network addresses
- H04L2101/618—Details of network addresses
- H04L2101/622—Layer-2 addresses, e.g. medium access control [MAC] addresses
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
The invention relates to a system for distinguishing a random MAC address of a smart phone, which comprises a server, wherein the server comprises a random MAC address acquisition module, a random MAC address library, a real MAC address acquisition module, a real MAC address library, a model training module and a random MAC address distinguishing module. The invention also discloses a method for distinguishing the random MAC address of the smart phone, which comprises the processes of random MAC address acquisition, real MAC address acquisition, model training, random MAC address distinguishing and the like. The invention adopts the machine learning training MAC address identification model to identify the authenticity of the mobile phone random MAC address, and has the characteristic of identifying the authenticity of the mobile phone random MAC address.
Description
Technical Field
The invention relates to a system and a method for distinguishing an MAC address, in particular to a system and a method for distinguishing a random MAC address of a smart phone, and belongs to the field of MAC address distinguishing.
Background
With the popularization of smart phones, a scheme for collecting passenger flow based on a WIFI signal of the smart phone appears. The principle is that the MAC address of the mobile phone is globally unique, and the number of people with the passenger flow volume, the staying time in a store, the frequency of arriving at the store and other information can be accurately counted as long as the MAC address of the mobile phone is collected. The random MAC addresses that are currently available make the way in which uniquely identified guests are determined by collecting MAC addresses inaccurate.
Disclosure of Invention
The invention discloses a system and a method for identifying a random MAC address of a smart phone, which disclose a new scheme, and solve the problem that the authenticity of the random MAC address of the smart phone cannot be identified by the existing scheme by adopting a machine learning training MAC address identification model to identify the authenticity of the random MAC address of the smart phone.
The invention discloses a system for distinguishing a random MAC address of a smart phone, which comprises a server, wherein the server comprises a random MAC address acquisition module, a random MAC address base, a real MAC address acquisition module, a real MAC address base, a model training module and a random MAC address distinguishing module, the random MAC address acquisition module is used for acquiring and processing random MAC address information, the random MAC address base is used for storing the random MAC address information, the real MAC address acquisition module is used for acquiring the real MAC address information, the real MAC address base is used for storing the real MAC address information, the model training module is used for training an MAC address distinguishing model, and the random MAC address distinguishing module is used for distinguishing the authenticity of the random MAC address.
Further, the random MAC address acquisition module of the present disclosure includes a random MAC address information preprocessing module and a random MAC address information tag processing module, where the random MAC address information preprocessing module is configured to perform feature selection, feature scaling and dimension reduction on data, and the random MAC address information tag processing module is configured to perform tag processing on data.
Furthermore, the real MAC address acquisition module of the scheme comprises an IEEE MAC acquisition module, a WIFI router verification MAC acquisition module and an artificial MAC acquisition module, wherein the IEEE MAC acquisition module is used for acquiring MAC address information applied by manufacturers provided by IEEE international organization, the WIFI router verification MAC acquisition module is used for acquiring MAC address information of interaction between the mobile phone and the router through WIFI networking communication, and the artificial MAC acquisition module is used for acquiring artificially acquired real MAC address information.
The invention also discloses a method for distinguishing the random MAC address of the smart phone, which is based on a distinguishing system, wherein the distinguishing system comprises a server, the server comprises a random MAC address acquisition module, a random MAC address base, a real MAC address acquisition module, a real MAC address base, a model training module and a random MAC address distinguishing module, and the method is characterized by comprising the following steps: the random MAC address acquisition module acquires and processes random MAC address information and stores the random MAC address information into a random MAC address base, the real MAC address acquisition module acquires real MAC address information and stores the real MAC address information into a real MAC address base, the model training module samples the random MAC address base and the real MAC address base to be used for training to obtain an MAC address identification model, and the random MAC address identification module utilizes the MAC address identification model to identify the authenticity of a newly acquired random MAC address.
Further, the random MAC address acquisition module of the method of the present solution includes a random MAC address information preprocessing module and a random MAC address information tag processing module, and the process further includes: the collected random MAC address information is subjected to feature selection, feature scaling and dimension reduction through a random MAC address information preprocessing module, is subjected to labeling processing through a random MAC address information label processing module, and is stored in a random MAC address base.
Further, the real MAC address acquisition module of the method of the present solution includes an IEEE MAC acquisition module, a WIFI router verification MAC acquisition module, and an artificial MAC acquisition module, and the process further includes: the method comprises the steps that an IEEE MAC acquisition module acquires MAC address information applied by a manufacturer and provided by IEEE international organization and stores the MAC address information into a real MAC address base, a WIFI router verifies that the MAC acquisition module acquires the MAC address information of a mobile phone interacting with the router through WIFI networking communication and stores the MAC address information into the real MAC address base, and a manual MAC acquisition module acquires the manually acquired real MAC address information and stores the manually acquired real MAC address information into the real MAC address base.
Further, the process of the method of the scheme also comprises a training process of the model: the model training module samples data from the random MAC address base and the real MAC address base according to a set proportion to generate a sampling data set, the model training module divides the sampling data set into a training data set and a testing data set according to the set proportion, the training data set is used for training the model to be generated by the model training module, the testing data set is used for evaluating the model to generate an MAC address identification model by the model training module, and the authenticity of a newly acquired MAC address is predicted by the model training module by using the MAC address identification model.
Further, the method of the present solution has a ratio of the data amount of the training data set to the data amount of the test data set of 2: 1.
The system and the method for distinguishing the random MAC address of the smart phone adopt the machine learning training MAC address distinguishing model to distinguish the authenticity of the random MAC address of the smart phone, and have the characteristic of distinguishing the authenticity of the random MAC address of the smart phone.
Drawings
Fig. 1 is a schematic diagram of a smartphone random MAC address discrimination system of the present invention.
Fig. 2 is a schematic diagram of a real MAC address bank.
FIG. 3 is a flow chart of model training.
Detailed Description
As shown in fig. 1, the system for identifying a random MAC address of a smart phone according to the present invention includes a server, where the server includes a random MAC address acquisition module, a random MAC address library, a real MAC address acquisition module, a real MAC address library, a model training module, and a random MAC address identification module, the random MAC address acquisition module is configured to acquire and process random MAC address information, the random MAC address library is configured to store random MAC address information, the real MAC address acquisition module is configured to acquire real MAC address information, the real MAC address library is configured to store real MAC address information, the model training module is configured to train a MAC address identification model, and the random MAC address identification module is configured to identify authenticity of a random MAC address. According to the scheme, the machine learning training MAC address identification model is adopted to identify the authenticity of the random MAC address of the mobile phone, so that the intelligent level of the system is improved, and the system has the function of identifying the authenticity of the random MAC address of the mobile phone.
In order to realize the acquisition and processing of random MAC address information and real MAC address information, the random MAC address acquisition module of the scheme comprises a random MAC address information preprocessing module and a random MAC address information label processing module, wherein the random MAC address information preprocessing module is used for performing feature selection, feature scaling and dimension reduction processing on data, and the random MAC address information label processing module is used for performing label processing on the data. Meanwhile, the real MAC address acquisition module comprises an IEEE MAC acquisition module, a WIFI router verification MAC acquisition module and an artificial MAC acquisition module, wherein the IEEE MAC acquisition module is used for acquiring MAC address information applied by manufacturers provided by IEEE international organization, the WIFI router verification MAC acquisition module is used for acquiring MAC address information of interaction between the mobile phone and the router through WIFI networking communication, and the artificial MAC acquisition module is used for acquiring artificially acquired real MAC address information. The above scheme provides a large number of data sets required for training.
The invention also discloses a method for distinguishing the random MAC address of the smart phone, which is based on a distinguishing system, wherein the distinguishing system comprises a server, the server comprises a random MAC address acquisition module, a random MAC address base, a real MAC address acquisition module, a real MAC address base, a model training module and a random MAC address distinguishing module, and the method is characterized by comprising the following steps: the random MAC address acquisition module acquires and processes random MAC address information and stores the random MAC address information into a random MAC address base, the real MAC address acquisition module acquires real MAC address information and stores the real MAC address information into a real MAC address base, the model training module samples the random MAC address base and the real MAC address base to be used for training to obtain an MAC address identification model, and the random MAC address identification module utilizes the MAC address identification model to identify the authenticity of a newly acquired random MAC address.
In order to realize the collection and processing of random MAC address information and real MAC address information, the random MAC address collection module of the method of the scheme comprises a random MAC address information preprocessing module and a random MAC address information label processing module, and the process also comprises the following steps: the collected random MAC address information is subjected to feature selection, feature scaling and dimension reduction through a random MAC address information preprocessing module, is subjected to labeling processing through a random MAC address information label processing module, and is stored in a random MAC address base. Meanwhile, the real MAC address acquisition module of the method comprises an IEEE MAC acquisition module, a WIFI router verification MAC acquisition module and an artificial MAC acquisition module, and the process also comprises the following steps: the method comprises the steps that an IEEE MAC acquisition module acquires MAC address information applied by a manufacturer and provided by IEEE international organization and stores the MAC address information into a real MAC address base, a WIFI router verifies that the MAC acquisition module acquires the MAC address information of a mobile phone interacting with the router through WIFI networking communication and stores the MAC address information into the real MAC address base, and a manual MAC acquisition module acquires the manually acquired real MAC address information and stores the manually acquired real MAC address information into the real MAC address base.
In order to realize the training of the model, the scheme also discloses a specific training process, namely the process of the method also comprises the training process of the model: the model training module samples data from the random MAC address base and the real MAC address base according to a set proportion to generate a sampling data set, the model training module divides the sampling data set into a training data set and a testing data set according to the set proportion, the training data set is used for training the model to be generated by the model training module, the testing data set is used for evaluating the model to generate an MAC address identification model by the model training module, and the authenticity of a newly acquired MAC address is predicted by the model training module by using the MAC address identification model. In order to reasonably distribute the training data sets, the ratio of the data amount of the training data sets to the data amount of the testing data sets in the method is 2:1, but the ratio is not fixed and can be adjusted and changed according to the actual training situation.
The scheme discloses a technology for identifying a random MAC address of a mobile phone and a realization method. The scheme is mainly based on the following background: the method comprises the steps of widely using a WIFI technology; popularization of smart phones is achieved; thirdly, carrying out passenger flow statistics based on the WIFI technology; an iPhone mobile phone adopts a random MAC address. According to the scheme, the random MAC address can be identified, and the statistical accuracy of WIFI passenger flow can be improved through the identification of the random MAC address and a real MAC address matching technology. Meanwhile, accurate data and technical support can be provided for other scenes which need random MAC address identification and are associated with the mobile phone real MAC. The method identifies the random MAC address and the real MAC address based on big data analysis, establishes a good classifier model through massive data training, and establishes the MAC address fingerprint library for MAC address identification through the classifier model. Since model training requires a large number of data sets, the present solution is mainly trained by the following two data sets: the method comprises the steps of uploading approximately 2 hundred million data (containing random MAC addresses and true MAC addresses) to a server every day; and secondly, real MAC address data collection. The system of the scheme mainly comprises the following components.
The MAC acquisition module: the load preprocesses the data uploaded by the collector, and the data are subjected to labeling processing and then are stored in a warehouse.
True MAC acquisition module: in order to provide a good test set during model training, the method and the device establish a real MAC address base by collecting real MAC addresses. There are mainly the following ways: acquiring a MAC address applied by a manufacturer provided by an IEEE (institute of electrical and electronic engineers); collecting the MAC address of the mobile phone from an electrical store periodically; and thirdly, acquiring a real MAC address through public WIFI internet access service (the real MAC address is interacted with the router during internet access communication). The composition of the real MAC fingerprint library is shown in fig. 2.
A model training module: and providing the functions of establishing, training, optimizing and the like of the true and false MAC identification model, and finally forming a stable identification model.
A service module: and providing authentication services of MAC truth and falseness for other services through the API.
The model training process of the present solution is shown in fig. 3, and may specifically include the following processes.
Preparation of a sample data set: the model training is to prepare a data set first, and the data preparation is mainly carried out in the following way. A portion of the sampled data set data is from set a, which is a data set with only true MAC addresses, and a portion from set B, which is a set with both true MAC addresses and random MAC addresses. The specific proportions are shown in the following table:
the assignment of the training data and the test data sets is set in accordance with 2/3 where the training set data is the acquisition data set and 1/3 where the test set data is the acquisition data set. The preprocessing of the scheme is to perform feature selection, feature scaling and dimension reduction on data. The main characteristics adopted are as follows: dwell time, whether multiple sites occur, frequency of occurrence, and the like. The post-processing of the scheme mainly comprises model selection and performance index evaluation.
The system and method for identifying a random MAC address of a smartphone according to the present disclosure are not limited to the contents disclosed in the specific embodiments, and the technical solutions presented in the embodiments may be extended based on the understanding of those skilled in the art, and a simple alternative made by those skilled in the art according to the present disclosure in combination with common general knowledge also belongs to the scope of the present disclosure.
Claims (7)
1. A method for distinguishing a random MAC address of a smart phone is based on a distinguishing system, the distinguishing system comprises a server, the server comprises a random MAC address acquisition module, a random MAC address base, a real MAC address acquisition module, a real MAC address base, a model training module and a random MAC address distinguishing module, and the method is characterized by comprising the following steps:
the random MAC address acquisition module acquires and processes random MAC address information and stores the random MAC address information into a random MAC address base, the real MAC address acquisition module acquires real MAC address information and stores the real MAC address information into a real MAC address base, the model training module samples the random MAC address base and the real MAC address base to train and obtain an MAC address identification model, the random MAC address identification module identifies the authenticity of a newly acquired random MAC address by using the MAC address identification model,
the process also includes a training process of the model: the model training module samples data from the random MAC address base and the real MAC address base according to a set proportion to generate a sampling data set, the model training module divides the sampling data set into a training data set and a testing data set according to the set proportion, the training data set is used for training the model to be generated by the model training module, the testing data set is used for evaluating the model to generate an MAC address identification model by the model training module, and the authenticity of a newly acquired MAC address is predicted by the model training module by using the MAC address identification model.
2. The method for identifying the random MAC address of the smart phone according to claim 1, wherein the random MAC address acquisition module comprises a random MAC address information preprocessing module and a random MAC address information tag processing module, and the process further comprises: the collected random MAC address information is subjected to feature selection, feature scaling and dimension reduction through a random MAC address information preprocessing module, is subjected to labeling processing through a random MAC address information label processing module, and is stored in a random MAC address base.
3. The method of claim 1, wherein the real MAC address collection module comprises an IEEE MAC collection module, a WIFI router verification MAC collection module, and an artificial MAC collection module, and the process further comprises: the method comprises the steps that an IEEE MAC acquisition module acquires MAC address information applied by a manufacturer and provided by IEEE international organization and stores the MAC address information into a real MAC address base, a WIFI router verifies that the MAC acquisition module acquires the MAC address information of a mobile phone interacting with the router through WIFI networking communication and stores the MAC address information into the real MAC address base, and a manual MAC acquisition module acquires the manually acquired real MAC address information and stores the manually acquired real MAC address information into the real MAC address base.
4. The method of claim 1, wherein the ratio of the data size of the training data set to the test data set is 2: 1.
5. A smart phone random MAC address discrimination system according to the smart phone random MAC address discrimination method of claim 1, comprising a server, wherein the server includes a random MAC address acquisition module, a random MAC address library, a real MAC address acquisition module, a real MAC address library, a model training module, and a random MAC address discrimination module, the random MAC address acquisition module is configured to acquire and process random MAC address information, the random MAC address library is configured to store random MAC address information, the real MAC address acquisition module is configured to acquire real MAC address information, the real MAC address library is configured to store real MAC address information, the model training module is configured to train a MAC address discrimination model, and the random MAC address discrimination module is configured to discriminate authenticity of a random MAC address.
6. The system for identifying the random MAC address of the smart phone according to claim 5, wherein the random MAC address acquisition module comprises a random MAC address information preprocessing module and a random MAC address information tag processing module, the random MAC address information preprocessing module is configured to perform feature selection, feature scaling and dimension reduction on data, and the random MAC address information tag processing module is configured to perform tag processing on data.
7. The system for distinguishing the random MAC address of the smart phone according to claim 5, wherein the real MAC address acquisition module comprises an IEEE MAC acquisition module, a WIFI router verification MAC acquisition module and an artificial MAC acquisition module, the IEEE MAC acquisition module is used for acquiring MAC address information applied by manufacturers provided by IEEE international organization, the WIFI router verification MAC acquisition module is used for acquiring MAC address information of interaction between the smart phone and the router through WIFI networking communication, and the artificial MAC acquisition module is used for acquiring manually acquired real MAC address information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810450998.3A CN110493363B (en) | 2018-05-11 | 2018-05-11 | System and method for distinguishing random MAC address of smart phone |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810450998.3A CN110493363B (en) | 2018-05-11 | 2018-05-11 | System and method for distinguishing random MAC address of smart phone |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110493363A CN110493363A (en) | 2019-11-22 |
| CN110493363B true CN110493363B (en) | 2022-05-17 |
Family
ID=68543590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810450998.3A Active CN110493363B (en) | 2018-05-11 | 2018-05-11 | System and method for distinguishing random MAC address of smart phone |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110493363B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111050397B (en) * | 2020-03-12 | 2020-06-26 | 深圳中科爱讯科技有限公司 | Method for positioning mobile terminal using pseudo MAC strategy |
| CN111914244B (en) * | 2020-07-31 | 2024-06-07 | 深圳力维智联技术有限公司 | Data processing method, device and computer readable storage medium |
| CN112235825B (en) * | 2020-12-09 | 2021-03-16 | 南京华苏科技有限公司 | Method for analyzing random MAC (media access control) by WIFI (wireless fidelity) probe equipment based on Internet of things |
| CN114158031B (en) * | 2021-12-02 | 2023-08-22 | 深圳市共进电子股份有限公司 | Method, device, router and storage medium for counting terminals |
| GB2614572B (en) * | 2022-01-10 | 2024-09-11 | British Telecomm | Telecommunications network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3127298A1 (en) * | 2014-03-31 | 2017-02-08 | Google, Inc. | Specifying a mac address based on location |
| CN106412809A (en) * | 2016-11-22 | 2017-02-15 | 任子行网络技术股份有限公司 | MAC address acquisition method and system based on Bluetooth and WIFI |
| CN106658586A (en) * | 2016-12-05 | 2017-05-10 | 任子行网络技术股份有限公司 | Method used for acquiring MAC address of iOS device |
| CN107623754A (en) * | 2017-09-28 | 2018-01-23 | 武汉虹旭信息技术有限责任公司 | WiFi acquisition systems and its method based on true and false MAC identifications |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9930009B2 (en) * | 2015-03-13 | 2018-03-27 | Intel IP Corporation | Systems and methods to enable network coordinated MAC randomization for wi-fi privacy |
| CN107094293A (en) * | 2017-06-27 | 2017-08-25 | 南京赢纳信息科技有限公司 | A kind of device and method for obtaining WiFi terminal real MAC address |
-
2018
- 2018-05-11 CN CN201810450998.3A patent/CN110493363B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3127298A1 (en) * | 2014-03-31 | 2017-02-08 | Google, Inc. | Specifying a mac address based on location |
| CN106412809A (en) * | 2016-11-22 | 2017-02-15 | 任子行网络技术股份有限公司 | MAC address acquisition method and system based on Bluetooth and WIFI |
| CN106658586A (en) * | 2016-12-05 | 2017-05-10 | 任子行网络技术股份有限公司 | Method used for acquiring MAC address of iOS device |
| CN107623754A (en) * | 2017-09-28 | 2018-01-23 | 武汉虹旭信息技术有限责任公司 | WiFi acquisition systems and its method based on true and false MAC identifications |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110493363A (en) | 2019-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110493363B (en) | System and method for distinguishing random MAC address of smart phone | |
| CN110719605B (en) | Network speed detection system based on 5G technology | |
| CN111385297B (en) | Wireless device fingerprint identification method, system, device and readable storage medium | |
| CN111159254B (en) | Vehicle and personnel association method based on big data processing | |
| CN105677728A (en) | Object image recognition and classification managing method | |
| CN106028279B (en) | Network registration method and device | |
| CN105306495B (en) | user identification method and device | |
| CN112040432A (en) | Method and device for identifying mobile terminal user type | |
| CN111078818B (en) | Address analysis method and device, electronic equipment and storage medium | |
| CN104657389A (en) | Positioning method, system and mobile terminal | |
| WO2020134299A1 (en) | Indoor and outdoor label distinguishing method, training method and device of classifier and medium | |
| CN109379698B (en) | Cell measurement report positioning method and system based on channel model feature extraction | |
| CN107172209A (en) | Information-pushing method and device | |
| CN103731851A (en) | Network performance evaluation method and device | |
| CN106255082A (en) | The recognition methods of a kind of refuse messages and system | |
| CN110022182A (en) | Interference source prediction model method for building up, method for interference source identification, device and terminal device | |
| CN108650145A (en) | Phone number characteristic automatic extraction method under a kind of home broadband WiFi | |
| CN108063811B (en) | Intelligent equipment network access tracking method and component | |
| CN105959911A (en) | Method and device for identifying user | |
| CN112581337B (en) | Method and terminal for judging whether real population is bounced or not | |
| CN101330707B (en) | Method and apparatus for dialing and measuring wireless network information | |
| CN110944290B (en) | Companion relationship analysis method and apparatus | |
| CN110611600B (en) | Network state information acquisition method and system | |
| CN105611556B (en) | A kind of wireless access point device performance superiority and inferiority judgment method and device | |
| CN106330592A (en) | Method, system and device for testing network performance of communication module |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230707 Address after: 201111 floor 2, building 2, No. 1508, Kunyang Road, Minhang District, Shanghai Patentee after: Shanghai Ouxin Technology Co.,Ltd. Address before: No. 665, Zhangjiang Road, China (Shanghai) Free Trade Pilot Area, Pudong New Area, Shanghai, 2003 Patentee before: SHANGHAI NEW SEAGULL SOFTWARE CO.,LTD. |
|
| TR01 | Transfer of patent right |