WO2017114167A1 - 终端真伪验证方法、装置及*** - Google Patents

终端真伪验证方法、装置及*** Download PDF

Info

Publication number
WO2017114167A1
WO2017114167A1 PCT/CN2016/110066 CN2016110066W WO2017114167A1 WO 2017114167 A1 WO2017114167 A1 WO 2017114167A1 CN 2016110066 W CN2016110066 W CN 2016110066W WO 2017114167 A1 WO2017114167 A1 WO 2017114167A1
Authority
WO
WIPO (PCT)
Prior art keywords
terminal
feature information
tested
verification result
verification
Prior art date
Application number
PCT/CN2016/110066
Other languages
English (en)
French (fr)
Inventor
侯冬梅
朱佳来
邓志坚
童道远
唐振乙
罗运广
Original Assignee
阿里巴巴集团控股有限公司
侯冬梅
朱佳来
邓志坚
童道远
唐振乙
罗运广
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 阿里巴巴集团控股有限公司, 侯冬梅, 朱佳来, 邓志坚, 童道远, 唐振乙, 罗运广 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2017114167A1 publication Critical patent/WO2017114167A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/06—Authentication

Definitions

  • the present application relates to the field of Internet technologies, and in particular, to a terminal authenticity verification method, apparatus, and system.
  • the IMEI International Mobile Equipment Identity
  • the terminal is proved to be Genuine terminal, otherwise the terminal is a pirate terminal.
  • the IMEI that can be successfully registered can be forged on the pirated terminal, which results in the accuracy of verifying the authenticity of the terminal through the IMEI alone.
  • the inventor of the present application found in the research process that the authenticity of the terminal can be automatically and accurately verified on the server.
  • the specific execution process on the server is as follows:
  • the server may pre-acquire hardware parameter information of each model of the plurality of terminals, wherein the hardware parameter information may include hardware parameters of the plurality of hardware items.
  • the server can determine the proportion of each hardware parameter for each hardware item.
  • the hardware project 1 of an X-type terminal is taken as an example to describe the process of determining the proportion of each hardware parameter by the server.
  • the server collects the hardware parameters of the hardware items 1 of the 100 X-type terminals, assuming that the hardware parameters of the 80 terminals for the hardware item 1 are a, the hardware parameters of the 10 terminals for the hardware item 1 are b, and the 10 terminals are for The hardware parameter of hardware item 1 is c. Then, the ratio of each hardware parameter of the hardware item 1 is: hardware parameter a accounts for 80%, hardware parameter b accounts for 10%, and hardware parameter c accounts for 10%.
  • the server takes the hardware parameter that accounts for the largest proportion of hardware items as a genuine hardware parameter. For example, for the hardware item 1 of the X-type terminal, the server uses the hardware parameter a as the genuine hardware parameter information of the hardware item 1.
  • the server may scan the hardware parameter information of the plurality of hardware items of the terminal, and then compare the hardware parameter information to be tested with the genuine hardware parameter information of the same model on the server, if If the agreement is consistent, the terminal to be tested is a genuine terminal. If the terminal is inconsistent, the terminal to be tested is a pirated terminal. In this manner, since the server can judge the authenticity of the terminal based on various hardware parameters of the terminal, compared with the prior art, only the IMEI can be used, and the authenticity and accuracy of the verification terminal can be greatly improved.
  • the server determines the genuine hardware parameter information by selecting the hardware parameter information with the largest proportion as the genuine hardware parameter information. For example, the hardware parameter a with the proportion of 80% is selected as the genuine hardware parameter information, and the hardware parameter b and the hardware parameter c are the pirated hardware parameter information.
  • the inventor of the present application found in the research process that the above method can verify the authenticity of the terminal to a certain extent, but still has the problem of low accuracy. Because, there is currently a mainstream design with a large production volume for the same model on the market, and there are some small batch designs with small production volume.
  • the terminal belonging to the small batch design is also a genuine terminal, but due to its small production volume, the market has less circulation. If the server determines the genuine hardware parameters in the above manner, it is likely that the genuine terminal of the small batch design is misidentified as a pirated terminal, that is, the manner in which the above verification terminal is authentic is not accurate.
  • the present invention provides a terminal authenticity verification method, apparatus and system, so that the terminal can be accurately verified for different batches of terminals.
  • a terminal authenticity verification method is applied to a server, including:
  • the preset feature information model is based on feature information and category results of several terminals
  • the training sample set of the training is used to distinguish the classifiers of the genuine terminal and the pirated terminal according to the feature information;
  • the first verification result and the category result are all one of a genuine terminal or a pirated terminal.
  • the method further includes:
  • the second verification result is a genuine terminal, adding the feature information of the terminal to be tested and the second verification result to the training sample set;
  • the feature information includes software feature information and hardware feature information.
  • the software feature information includes an operating system software version, a network frequency, a data service, a body memory, and a running memory;
  • the hardware feature information includes: a CPU ID, a CPU model, a CPU frequency, a CPU core number, a screen resolution, and a sensor type.
  • a terminal authenticity verification method is applied to a client, and the method includes:
  • the first verification result is determined by the server performing authenticity verification on the feature information of the terminal to be tested according to the preset feature information model; the preset feature information model is based on feature information of a plurality of terminals.
  • the training sample set consisting of the category results is trained to distinguish the genuine terminal and the pirated terminal classifier according to the feature information; wherein the first verification result and the category result are one of a genuine terminal or a pirated terminal .
  • the acquiring the feature information of the terminal to be tested includes:
  • the feature information includes software feature information and hardware feature information.
  • the software feature information includes a system software version, a network frequency, a data service, a body memory, and a running memory;
  • the hardware feature information includes: a CPU ID, a CPU model, a CPU frequency, a CPU core number, a screen resolution, and a sensor type.
  • the method further includes:
  • the first verification result of the terminal to be tested is displayed by using a human-machine display interface.
  • a terminal authenticity verification device integrated in a server comprising:
  • a first receiving unit configured to receive, by the client, a verification request that includes feature information of the terminal to be tested
  • a verification unit configured to perform authenticity verification on the feature information of the terminal to be tested according to the preset feature information model, and determine a first verification result of the terminal to be tested;
  • the preset feature information model is based on a plurality of terminals
  • the training sample set consisting of the feature information and the category result is obtained by the classifier for distinguishing the genuine terminal from the pirated terminal according to the feature information; wherein the first verification result and the category result are both genuine terminals or pirated terminals one of the;
  • a first feedback unit configured to feed back the first verification result to the client.
  • the method further includes:
  • a second receiving unit configured to receive a second verification result of the terminal to be tested, where the second verification result is determined by using a manual analysis manner
  • a training unit configured to retrain the preset feature information model according to the training sample set.
  • the feature information includes software feature information and hardware feature information.
  • the software feature information includes a system software version, a network frequency, a data service, a body memory, and a running memory;
  • the hardware feature information includes: a CPU ID, a CPU model, a CPU frequency, a CPU core number, a screen resolution, and a sensor type.
  • a terminal authenticity verification device integrated in a client includes:
  • An acquiring unit configured to acquire feature information of the terminal to be tested
  • a sending unit configured to send, to the server, a verification request that includes the feature information of the terminal to be tested
  • a second feedback unit configured to receive a first verification result fed back by the server
  • the first verification result is determined by the server performing authenticity verification on the feature information of the terminal to be tested according to the preset feature information model; the preset feature information model is based on feature information of a plurality of terminals.
  • the training sample set consisting of the category results is trained to distinguish the genuine terminal and the pirated terminal classifier according to the feature information; wherein the first verification result and the category result are one of a genuine terminal or a pirated terminal .
  • the acquiring unit includes:
  • a establishing unit configured to establish a communication connection with the terminal to be tested after establishing a physical connection with the terminal to be tested
  • a scanning unit configured to scan the terminal to be tested and obtain feature information of the terminal to be tested.
  • the feature information includes software feature information and hardware feature information.
  • the software feature information includes a system software version, a network frequency, a data service, a body memory, and a running memory;
  • the hardware feature information includes: a CPU ID, a CPU model, a CPU frequency, a CPU core number, a screen resolution, and a sensor type.
  • the method further includes:
  • a display unit configured to display, by using a human-machine display interface, a first verification result of the terminal to be tested.
  • a terminal authenticity verification system includes:
  • the client is configured to acquire feature information of the terminal to be tested, send a verification request including the feature information of the terminal to be tested to the server, and receive a first verification result fed back by the server;
  • the server is configured to receive an authentication request that is sent by the client and includes the feature information of the terminal to be tested, perform authenticity verification on the feature information of the terminal to be tested according to the preset feature information model, and determine the terminal of the terminal to be tested. a first verification result; and feeding back the first verification result to the client;
  • the preset feature information model is trained according to the training sample set composed of the feature information and the category result of the plurality of terminals, and is used for distinguishing the classifier of the genuine terminal and the pirated terminal according to the feature information, wherein the first The verification result and the result of the category are both one of a genuine terminal or a pirated terminal.
  • the present application does not pre-set the feature information of the genuine terminal, but uses the preset feature information model to determine the authenticity of the terminal to be tested. Therefore, with respect to the above manner of determining the authenticity of the terminal, the present application does not rely on the genuine feature information preset on the server.
  • the preset feature information model of the present application is a classifier obtained by training the training sample set and used to distinguish the genuine terminal from the pirated terminal. Since the training sample set can contain the feature information of the mainstream design terminal and the feature information of the small batch design terminal, the preset feature information model can accurately determine not The category result of the same batch terminal. Therefore, regardless of whether the terminal to be tested is a batch terminal, the present application can utilize the preset feature information model to accurately verify the terminal.
  • FIG. 1 is a flowchart of constructing a preset feature information model in a terminal authenticity verification method provided by the present application
  • FIG. 3 is a flowchart of still another terminal authenticity verification method provided by the present application.
  • FIG. 5 is a schematic structural diagram of a terminal authenticity verification apparatus provided by the present application.
  • FIG. 6 is a schematic structural diagram of still another terminal authenticity verification apparatus provided by the present application.
  • FIG. 7 is a schematic structural diagram of still another terminal authenticity verification apparatus provided by the present application.
  • FIG. 8 is a schematic structural diagram of still another terminal authenticity verification apparatus provided by the present application.
  • FIG. 9 is a schematic structural diagram of a terminal authenticity verification system provided by the present application.
  • the present application constructs a preset feature information model on the server; wherein the preset feature information model is a training based on the feature information and category results of several terminals.
  • the sample set is trained to distinguish the genuine terminal and the pirated terminal classifier based on the feature information.
  • Step S101 Acquire a set of training samples composed of feature information and category results of a plurality of terminals.
  • the server may acquire feature information of several terminals on the client, or acquire feature information of several terminals in other collection systems.
  • the present application can collect feature information of both the software feature information and the hardware feature information of the terminal, so as to accurately determine the authenticity of the terminal by using the terminal software feature information and the hardware feature information.
  • the software feature information includes a system software version, a network frequency, a data service, a body memory, and a running memory;
  • the hardware feature information includes: a CPU ID, a CPU model, a CPU frequency, a CPU core number, a screen resolution, and a sensor. kind.
  • the manual analysis method is used to analyze the characteristic information of each terminal, and the category result of each terminal is accurately analyzed, that is, whether the terminal is a genuine terminal or a pirated terminal.
  • the purpose of the manual analysis method for determining the category result of each terminal is to make the category result of each terminal in the training sample set accurate, thereby ensuring that the preset feature information model obtained after the training is accurate.
  • the server takes the feature information of one terminal and the class result of the terminal as a set of training samples, and then groups the training samples into a training sample set to train the classifier with the training sample set.
  • Step S102 training the classifier with the training sample set.
  • the training sample set is ⁇ Xi,Zi ⁇ , where Xi is feature information and the corresponding Zi is ⁇ -1, 1 ⁇ .
  • the "-1" indicates that the terminal corresponding to the feature information is a pirated terminal
  • the "1” indicates that the terminal corresponding to the feature information is a genuine terminal.
  • "-1" and "1" are only used as an example. In actual operation, different characters can be used to distinguish between genuine terminals and pirated terminals.
  • the specific number of parameters is related to the type of classifier.
  • the purpose of the training classifier of the present application is to adjust the size of the parameter, so that the adjusted curve can be used to accurately demarcate the feature information of the genuine terminal and the feature information of the pirate terminal, thereby realizing the purpose of distinguishing the genuine terminal from the pirated terminal.
  • the specific training process has been related to the prior art and will not be described in detail herein.
  • Step S103 The trained classifier is determined as a preset feature information model.
  • the classifier After the classifier training is completed, the classifier can realize the purpose of outputting the genuine terminal or the pirated terminal after analyzing and calculating according to the input feature information. Therefore, the trained classifier can be determined as a preset feature information model that is required to be used in the subsequent process of the present application.
  • FIG. 2 is a flowchart of an embodiment of the terminal authenticity verification method provided by the present application. This embodiment can be applied to the server. The embodiment can include the following steps:
  • Step S201 Receive an authentication request sent by the client that includes the feature information of the terminal to be tested.
  • the client can scan the feature information of the terminal to be tested, and construct the verification request by using the feature information of the terminal to be tested.
  • the client can then send the verification request to the server, and the server further analyzes the feature information of the terminal to be tested in the verification request.
  • the feature information of the terminal to be tested may include software feature information and hardware feature information.
  • the software feature information includes a system software version, a network frequency, a data service, a body memory, and a running memory;
  • the hardware feature information includes: a CPU ID, a CPU model, a CPU frequency, a CPU core number, and a screen resolution. And the type of sensor.
  • the server may obtain the feature information of the terminal to be tested in the verification request, and determine the authenticity of the terminal to be tested by using the preset feature information model.
  • Step S202 Perform authenticity verification on the feature information of the terminal to be tested according to the preset feature information model, and determine a first verification result of the terminal to be tested; wherein the first verification result is a genuine terminal or a pirated terminal.
  • the preset feature information model is based on characteristic information of several terminals
  • the training sample set consisting of interest and category results is trained to distinguish the classifiers of genuine terminals and pirated terminals based on the feature information.
  • the preset feature information model is a pre-trained classifier for distinguishing genuine terminals from pirated terminals based on feature information. Therefore, in this embodiment, the preset feature information model is equivalent to a black box, and the input data is the feature information of one terminal, and the output data is the verification result of the terminal.
  • the feature information of the terminal to be tested can be input to the preset feature information model, and the feature information of the terminal to be tested is analyzed by the preset feature information model according to the previously trained criteria, thereby determining and outputting the first terminal to be tested. Validation results.
  • the first verification result output is a genuine terminal; if the preset feature information model is analyzed and the terminal to be tested is determined to be a pirated terminal, the output is output.
  • the first verification result is a pirate terminal.
  • Step S203 Feed back the first verification result to the client.
  • the server may send the first verification result to the client, so that the user can know the first verification result of the terminal to be tested on the client.
  • the present application does not pre-set the feature information of the genuine terminal, but uses the preset feature information model to determine the authenticity of the terminal to be tested. Therefore, with respect to the above manner of determining the authenticity of the terminal, the present application does not rely on the genuine feature information preset on the server.
  • the preset feature information model of the present application is a classifier obtained by training the training sample set and used to distinguish the genuine terminal from the pirated terminal. Since the training sample set can contain the feature information of the mainstream design terminal and the feature information of the small batch design terminal, the preset feature information model can accurately determine the category result of the different batch terminals. Therefore, regardless of whether the terminal to be tested is a batch terminal, the present application can utilize the preset feature information model to accurately verify the terminal.
  • the training sample set of the preset feature information model on the server cannot contain the feature information of all models.
  • the server sends the authenticity information that cannot be judged by the server.
  • the server categorizes the terminal to be tested as a pirate terminal when the server cannot accurately determine whether the feature information of the terminal to be tested is determined to be a genuine terminal or a pirated terminal.
  • the terminal to be tested may be determined as a pirated terminal because it is indeed a pirated terminal, or may be caused by the server failing to accurately verify the verification result of the terminal.
  • the server determines that the verification result of the terminal to be tested is a pirate terminal. Therefore, in the case where the server determines that the verification result of the terminal to be tested is a pirate terminal, the following processing procedure can be performed. As shown in FIG. 3, the following steps are specifically included:
  • Step S301 Receive a second verification result of the terminal to be tested, where the second verification result is determined by using a manual analysis manner.
  • the server cannot continue to accurately determine the verification result of the terminal to be tested, the feature information of the terminal to be tested is analyzed in detail by a manual method, and the second verification result of the terminal to be tested is determined. It can be understood that the second verification result can be consistent with the first verification result, that is, the second verification result is also a pirate terminal. In this case, the first verification result is not misjudged.
  • the preset feature information model may not be retrained at this time.
  • the second verification result may be inconsistent with the first verification result, that is, the second verification result is a genuine terminal.
  • the first verification result is erroneous. That is, the server training sample set does not have the feature information of the terminal to be tested, so that a misjudgment situation occurs.
  • Step S302 If the second verification result is a genuine terminal, add the feature information of the terminal to be tested and the second verification result to the training sample set.
  • the server may form the feature information of the terminal to be tested and the second verification result (ie, the genuine terminal) into a group of training samples, and then add the group of training samples to the training sample set.
  • Step S303 Retrain the preset feature information model according to the training sample set.
  • the original preset feature information model is obtained after training according to the original training sample set, after adding the training sample corresponding to the terminal to be tested in the training sample set, since the training sample set changes, it is necessary to re-based the training sample.
  • the set trains the classifier. Then, the classifier after the training is re-determined as the preset feature information model used in the present application; so that after the feature information similar to the terminal to be tested appears, the verification result of the terminal to be tested can be accurately output.
  • the present application provides a terminal authenticity verification method, which is applied to a client, and the method includes:
  • Step S401 Acquire feature information of the terminal to be tested.
  • the user can establish a physical connection with the client through the data connection line, and then the client can establish a communication connection with the terminal to be tested. Thereafter, the client can scan the terminal to be tested and obtain the feature information of the terminal to be tested.
  • the feature information of the terminal to be tested may include software feature information and hardware feature information.
  • the software feature information includes a system software version, a network frequency, a data service, a body memory, and a running memory;
  • the hardware feature information includes: a CPU ID, a CPU model, a CPU frequency, a CPU core number, and a screen resolution. And the type of sensor.
  • Step S402 Send a verification request including the feature information of the terminal to be tested to the server.
  • the client may send a verification request containing the feature information of the terminal to be tested to the server, and the server performs further analysis.
  • Step S403 Receive a first verification result fed back by the server.
  • the first verification result is determined by the server performing authenticity verification on the feature information of the terminal to be tested according to the preset feature information model; the first verification result is a genuine terminal or a pirated terminal;
  • the preset feature information model is trained according to the training sample set composed of the feature information and the category result of a plurality of terminals, and is used for distinguishing the classifiers of the genuine terminal and the pirated terminal according to the feature information.
  • the first verification result may be sent to the client, so that the client receives the first verification result.
  • the user can view the first verification result of the terminal to be tested, and the client can display the first verification result of the terminal to be tested by using the human-machine display interface.
  • the present application does not pre-set the feature information of the genuine terminal, but uses the preset feature information model to determine the authenticity of the terminal to be tested. Therefore, with respect to the above manner of determining the authenticity of the terminal, the present application does not rely on the genuine feature information preset on the server.
  • the preset feature information model of the present application is a classifier obtained by training the training sample set and used to distinguish the genuine terminal from the pirated terminal. Since the training sample set can contain the feature information of the mainstream design terminal and the feature information of the small batch design terminal, the preset feature information model can accurately determine the category result of the different batch terminals. Therefore, regardless of whether the terminal to be tested is a batch terminal, the present application can utilize the preset feature information model to accurately verify the terminal.
  • the present application provides a terminal authenticity verification apparatus integrated in a server.
  • the specific includes:
  • the first receiving unit 51 is configured to receive a verification request that is sent by the client and includes feature information of the terminal to be tested.
  • the verification unit 52 is configured to perform authenticity verification on the feature information of the terminal to be tested according to the preset feature information model, and determine a first verification result of the terminal to be tested; wherein the first verification result is a genuine terminal Or the pirated terminal; the preset feature information model is trained according to the training sample set composed of the feature information and the category result of the plurality of terminals, and is used for distinguishing the classifier of the genuine terminal and the pirated terminal according to the feature information;
  • the first feedback unit 53 is configured to feed back the first verification result to the client.
  • the terminal authenticity verification device further includes:
  • the second receiving unit 54 is configured to receive a second verification result of the terminal to be tested, where the second verification result is determined by using a manual analysis manner;
  • the adding unit 55 is configured to add the feature information of the terminal to be tested and the second verification result to the training sample set if the second verification result is a genuine terminal;
  • the training unit 56 is configured to retrain the preset feature information model according to the training sample set.
  • the feature information in the present application includes software feature information and hardware feature information.
  • the software feature information includes a system software version, a network frequency, a data service, a body memory, and a running memory;
  • the hardware feature information includes: a CPU ID, a CPU model, a CPU frequency, a CPU core number, a screen resolution, and a sensor. kind.
  • the present application provides a terminal authenticity verification apparatus integrated in a server.
  • the specific includes:
  • the obtaining unit 71 is configured to acquire feature information of the terminal to be tested.
  • the sending unit 72 is configured to send, to the server, a verification request that includes the feature information of the terminal to be tested;
  • a second feedback unit 73 configured to receive a first verification result fed back by the server
  • the first verification result is determined by the server performing authenticity verification on the feature information of the terminal to be tested according to the preset feature information model; the first verification result is a genuine terminal or a pirated terminal;
  • the preset feature information model is trained according to the training sample set composed of the feature information and the category result of a plurality of terminals, and is used for distinguishing the classifiers of the genuine terminal and the pirated terminal according to the feature information.
  • the terminal authenticity verification apparatus further includes:
  • the display unit 74 is configured to display a first verification result of the terminal to be tested by using a human-machine display interface.
  • the obtaining unit 71 includes:
  • the establishing unit 81 is configured to establish a communication connection with the terminal to be tested after establishing a physical connection with the terminal to be tested;
  • the scanning unit 82 is configured to scan the terminal to be tested and acquire feature information of the terminal to be tested.
  • the feature information in this embodiment includes software feature information and hardware feature information.
  • the software feature information includes a system software version, a network frequency, a data service, a body memory, and a running memory;
  • the hardware feature information includes: a CPU ID, a CPU model, a CPU frequency, a CPU core number, a screen resolution, and a sensor. kind.
  • the present application provides a terminal authenticity verification system, including:
  • server 100 a server 100 and a client 200 connected to the server 100;
  • the client 200 is configured to acquire feature information of the terminal to be tested, send an authentication request including the feature information of the terminal to be tested to the server 100, and receive a first verification result fed back by the server 100.
  • the server 100 is configured to receive a verification request that includes the feature information of the terminal to be tested sent by the client 200, perform authenticity verification on the feature information of the terminal to be tested according to the preset feature information model, and determine the to-be-tested a first verification result of the terminal; and feeding back the first verification result to the client 200;
  • the first verification result is a genuine terminal or a pirated terminal; the preset feature information model is trained according to the training sample set composed of the feature information and the category result of the plurality of terminals, and is used to distinguish the genuine terminal according to the feature information. And classifiers for pirated terminals.
  • the functions described in the method of the present embodiment can be stored in a computing device readable storage medium if implemented in the form of a software functional unit and sold or used as a standalone product. Based on such understanding, a portion of the embodiments of the present application that contributes to the prior art or a portion of the technical solution may be embodied in the form of a software product stored in a storage medium, including a plurality of instructions for causing a
  • the computing device (which may be a personal computer, server, mobile computing device, or network device, etc.) performs all or part of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Facsimiles In General (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

本申请提供了一种终端真伪验证方法、装置及***，其中一种方法包括接收客户端发送的包含待测终端的特征信息的验证请求；依据预设特征信息模型对所述待测终端的特征信息进行真伪验证，并确定所述待测终端的第一验证结果；其中，所述第一验证结果为正版终端或盗版终端；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器；向所述客户端反馈所述第一验证结果。因此，本申请不论待测终端是那种批次的终端，本申请均可以利用预设特征信息模型来准确终端的验证结果。

Description

终端真伪验证方法、装置及*** 技术领域
本申请涉及互联网技术领域，尤其涉及一种终端真伪验证方法、装置及***。
背景技术
随着科学技术的飞速发展，手机等各种终端不断地丰富大众生活。由于利用终端处理信息具有方便快捷、节省资源等优势，终端现已成为人们生活或工作中不可或缺的一部分。伴随着各种终端的普及，市面上逐渐出现仿造正版终端的盗版终端。由于盗版终端与正版终端的功能及样式非常相似，容易被消费者误认为是正版终端。因此，逐渐出现对终端进行真伪验证应用软件，利用可以利用应用软件确定一个终端的真伪。
目前，现有技术在验证终端真伪时，通常在终端所属的官方网站或特定验证网站中输入终端的IMEI(International Mobile Equipment Identity，国际移动装备辨识码)，如果IMEI注册成功则证明该终端为正版终端，否则表示该终端为盗版终端。
但是，伴随着仿造技术的提高，可以盗版终端上伪造可被注册成功的IMEI，这导致单单通过IMEI验证终端真伪的方式准确性较低。
发明内容
本申请发明人在研究过程中发现，可以在服务器上自动准确的验证终端真伪。服务器上的具体执行过程如下：
服务器可以预先采集大量终端各个机型的硬件参数信息，其中，硬件参数信息可以包括多个硬件项目的硬件参数。服务器可以针对每个硬件项目确定各个硬件参数所占比例。下面以一个X机型终端的硬件项目1为例，对服务器确定各个硬件参数所占比例的过程进行说明。
例如，服务器采集100个X机型的终端关于硬件项目1的硬件参数，假设80个终端针对硬件项目1的硬件参数为a，10个终端针对硬件项目1的硬件参数为b，10个终端针对硬件项目1的硬件参数为c。那么，该硬件项目1各个硬件参数比例为：硬件参数a占80％，硬件参数b占10％，以及硬件参数c占10％。
由于服务器所采集硬件参数信息的大量终端中有的为正版终端、有的为盗版终端，按通常理解硬件参数的所占比例越高，则代表其为正版终端的几率越大。因此，服务器将硬件项目所占比例最大的硬件参数，作为正版硬件参数。例如，服务器针对X机型终端的硬件项目1而言，将硬件参数a作为硬件项目1的正版硬件参数信息。
在服务器验证待测终端真伪的过程中，服务器可以扫描终端多个硬件项目的待测硬件参数信息，然后将待测硬件参数信息与服务器上同款机型的正版硬件参数信息进行对比，若一致则确定待测终端为正版终端，若不一致则表示待测终端为盗版终端。在本方式中由于服务器可以基于终端的多种硬件参数来判断终端真伪，相比于现有技术仅仅采用IMEI而言，可以大大提高验证终端真伪的和准确率。
但是，在上述方式中服务器确定正版硬件参数信息的方式为：选择所占比例最大的硬件参数信息作为正版硬件参数信息。例如，选择所占比例为80％的硬件参数a作为正版硬件参数信息，硬件参数b和硬件参数c为盗版硬件参数信息。
但是，本申请发明人在研究过程中发现上述方式在一定程度上可以验证终端真伪，但是仍然具有准确率不高的问题。因为，目前市面上针对同一款机型有一种生产量很大的主流设计，还有一些生产量较小的小批次设计。
目前，归属于小批次设计的终端也是正版终端，但是由于其生产量较少，所以市面上的流通量较少。如果服务器按照上述方式确定正版硬件参数，则很可能将小批次设计的正版终端误判为盗版终端，即上述验证终端真伪的方式不准确。
因此，本申请一种终端真伪验证方法、装置及***，以便针对不同批次的终端均可以准确验证出终端真伪。
为了实现上述目的，本申请提供了以下技术手段：
一种终端真伪验证方法，应用于服务器，包括：
接收客户端发送的包含待测终端的特征信息的验证请求；
依据预设特征信息模型对所述待测终端的特征信息进行真伪验证，并确定所述待测终端的第一验证结果；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器；
向所述客户端反馈所述第一验证结果；
其中，所述第一验证结果和所述类别结果均为正版终端或盗版终端中的一个。
优选的，在所述待测终端的第一验证结果为盗版终端的情况下，所述方法还包括：
接收所述待测终端的第二验证结果；其中，所述第二验证结果利用人工分析方式确定；
若所述第二验证结果为正版终端，则将所述待测终端的特征信息和所述第二验证结果添加所述训练样本集；
依据所述训练样本集，重新训练所述预设特征信息模型。
优选的，所述特征信息包括软件特征信息和硬件特征信息。
优选的，所述软件特征信息包括操作***软件版本、网络频率、数据业务、机身内存和运行内存；
所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
一种终端真伪验证方法，应用于客户端，所述方法包括：
获取待测终端的特征信息；
向服务器发送包含所述待测终端的特征信息的验证请求；
接收所述服务器反馈的第一验证结果；
其中，所述第一验证结果为所述服务器依据预设特征信息模型对所述待测终端的特征信息进行真伪验证后确定的；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器；其中，所述第一验证结果和所述类别结果均为正版终端或盗版终端中的一个。
优选的，所述获取待测终端的特征信息，包括：
在与所述待测终端建立物理连接之后，与所述待测终端建立通信连接；
扫描所述待测终端并获取所述待测终端的特征信息。
优选的，所述特征信息包括软件特征信息和硬件特征信息。
优选的，所述软件特征信息包括***软件版本、网络频率、数据业务、机身内存和运行内存；
所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
优选的，在所述接收所述服务器反馈的第一验证结果之后，还包括：
利用人机显示界面显示所述待测终端的第一验证结果。
一种终端真伪验证装置，集成于服务器，包括：
第一接收单元，用于接收客户端发送的包含待测终端的特征信息的验证请求；
验证单元，用于依据预设特征信息模型对所述待测终端的特征信息进行真伪验证，并确定所述待测终端的第一验证结果；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器；其中，所述第一验证结果和所述类别结果均为正版终端或盗版终端中的一个；
第一反馈单元，用于向所述客户端反馈所述第一验证结果。
优选的，还包括：
第二接收单元，用于接收所述待测终端的第二验证结果；其中，所述第二验证结果利用人工分析方式确定；
添加单元，用于若所述第二验证结果为正版终端，则将所述待测终端的特征信息和所述第二验证结果添加所述训练样本集；
训练单元，用于依据所述训练样本集，重新训练所述预设特征信息模型。
优选的，所述特征信息包括软件特征信息和硬件特征信息。
优选的，所述软件特征信息包括***软件版本、网络频率、数据业务、机身内存和运行内存；
所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
一种终端真伪验证装置，集成于客户端，包括：
获取单元，用于获取待测终端的特征信息；
发送单元，用于向服务器发送包含所述待测终端的特征信息的验证请求；
第二反馈单元，用于接收所述服务器反馈的第一验证结果；
其中，所述第一验证结果为所述服务器依据预设特征信息模型对所述待测终端的特征信息进行真伪验证后确定的；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器；其中，所述第一验证结果和所述类别结果均为正版终端或盗版终端中的一个。
优选的，所述获取单元，包括：
建立单元，用于在与所述待测终端建立物理连接之后，与所述待测终端建立通信连接；
扫描单元，用于扫描所述待测终端并获取所述待测终端的特征信息。
优选的，所述特征信息包括软件特征信息和硬件特征信息。
优选的，所述软件特征信息包括***软件版本、网络频率、数据业务、机身内存和运行内存；
所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
优选的，还包括：
显示单元，用于利用人机显示界面显示所述待测终端的第一验证结果。
一种终端真伪验证***，包括：
服务器和与所述服务器相连的客户端；
所述客户端，用于获取待测终端的特征信息；向服务器发送包含所述待测终端的特征信息的验证请求；并接收所述服务器反馈的第一验证结果；
所述服务器，用于接收客户端发送的包含待测终端的特征信息的验证请求；依据预设特征信息模型对所述待测终端的特征信息进行真伪验证，并确定所述待测终端的第一验证结果；并向所述客户端反馈所述第一验证结果；
其中，所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器，其中，所述第一验证结果和所述类别结果均为正版终端或盗版终端中的一个。
通过以上技术特征，可以看出本申请具有以下有益效果：
本申请并未预先设置正版终端的特征信息，而是利用预设特征信息模型来判定待测终端的真伪。因此，相对于上述确定终端真伪的方式而言，本申请不依赖于服务器上预先设置的正版特征信息。本申请的预设特征信息模型是利用训练样本集训练后得到的、用于区分正版终端和盗版终端的分类器。由于训练样本集中既可以包含主流设计终端的特征信息，又可以包含小批次设计终端的特征信息，所以预设特征信息模型可以准确确定不 同批次终端的类别结果。因此，不论待测终端是那种批次的终端，本申请均可以利用预设特征信息模型来准确终端的验证结果。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请提供的一种终端真伪验证方法中构建预设特征信息模型的流程图；
图2为本申请提供的一种终端真伪验证方法的流程图；
图3为本申请提供的又一种终端真伪验证方法的流程图；
图4为本申请提供的又一种终端真伪验证方法的流程图；
图5为本申请提供的一种终端真伪验证装置的结构示意图；
图6为本申请提供的又一种终端真伪验证装置的结构示意图；
图7为本申请提供的又一种终端真伪验证装置的结构示意图；
图8为本申请提供的又一种终端真伪验证装置的结构示意图；
图9为本申请提供的一种终端真伪验证***的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
为了针对不同批次的终端均可以准确验证出终端真伪目的，本申请在服务器上构建一个预设特征信息模型；其中，预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器。
下面介绍构建预设特征信息模型的具体过程，如图1所示，具体包括以下步骤：
步骤S101：获取若干终端的特征信息和类别结果组成的训练样本集。
服务器可以在客户端上获取若干个终端的特征信息，或者，在其它采集***中获取若干终端的特征信息。为了准确的确定终端的真伪，本申请可以采集终端的软件特征信息和硬件特征信息两方面的特征信息，以便利用终端软件特征信息和硬件特征信息来准确确定终端的真伪。
其中，所述软件特征信息包括***软件版本、网络频率、数据业务、机身内存和运行内存；所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
然后，利用人工分析方式分析依据每个终端的特征信息，准确分析每个终端的类别结果，即终端为正版终端还是为盗版终端。本申请采用人工分析方式来确定每个终端的类别结果的目的为，使得训练样本集中的每个终端的类别结果是准确的，进而保证训练后得到的预设特征信息模型是准确的。
服务器将一个终端的特征信息和该终端的类别结果作为一组训练样本，然后将多组训练样本组成训练样本集，以便利用训练样本集来训练分类器。
步骤S102：利用训练样本集来训练分类器。
假设训练样本集为{Xi，Zi}，其中Xi为特征信息，对应的Zi为{-1,1}。其中“－1”表示该特征信息对应的终端为盗版终端，“1”表示特征信息对应的终端为正版终端。“-1”和“1”仅仅作为举例说明，在实际操作中可以采用不同字符来区分正版终端和盗版终端即可。
分类器中具有一些参数，参数的具体数量与分类器的种类有关。本申请训练分类器目的为调整参数的大小，以使得利用调整后参数构建拟合曲线可以准确将正版终端的特征信息和盗版终端的特征信息进行划界，从而实现区分正版终端和盗版终端的目的。具体训练过程已有相关现有技术，在此不再详细介绍。
步骤S103：将训练完成的分类器确定为预设特征信息模型。
在分类器训练完成之后，分类器便可以实现依据输入的特征信息进行分析计算后输出正版终端或盗版终端的目的。因此，可以将训练完成的分类器确定为本申请在后续过程中所需使用的预设特征信息模型。
在介绍预设特征信息模型的训练过程之后，参考图2为本申请提供的一种终端真伪验证方法实施例的流程图。本实施例可以应用于服务器端，本实施例可以包括以下步骤：
步骤S201：接收客户端发送的包含待测终端的特征信息的验证请求。
客户端可以扫描待测终端的特征信息，并利用待测终端的特征信息构建验证请求。然后客可以将验证请求发送至服务器，由服务器来对验证请求中待测终端的特征信息进行进一步的分析。
其中，待测终端的特征信息可以包括软件特征信息和硬件特征信息。具体而言，所述软件特征信息包括***软件版本、网络频率、数据业务、机身内存和运行内存；所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
服务器在接收包含待测终端的特征信息的验证请求之后，可以在验证请求中获取待测终端的特征信息，并利用预设特征信息模型判定待测终端的真伪。
步骤S202：依据预设特征信息模型对所述待测终端的特征信息进行真伪验证，并确定所述待测终端的第一验证结果；其中，所述第一验证结果为正版终端或盗版终端；所述预设特征信息模型为依据若干终端的特征信 息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器。
由于预设特征信息模型是预先训练好的、用于依据特征信息来区分正版终端和盗版终端的分类器。因此，在本实施例预设特征信息模型相当于一个黑匣子，其输入数据为一个终端的特征信息，输出数据为该终端的验证结果。
因此，可以将待测终端的特征信息输入至预设特征信息模型，由预设特征信息模型依据预先已训练好的准则对待测终端的特征信息进行分析，从而确定并输出待测终端的第一验证结果。
可以理解的是，如果预设特征信息模型分析后确定待测终端为正版终端，则输出的第一验证结果为正版终端；如果预设特征信息模型分析后确定待测终端为盗版终端，则输出的第一验证结果为盗版终端。
步骤S203：向所述客户端反馈所述第一验证结果。
服务器在利用预设特征信息模型确定待测终端的第一验证结果之后，可以向客户端发送第一验证结果，以便用户可以在客户端上得知待测终端的第一验证结果。
通过以上技术特征，可以看出本申请具有以下有益效果：
本申请并未预先设置正版终端的特征信息，而是利用预设特征信息模型来判定待测终端的真伪。因此，相对于上述确定终端真伪的方式而言，本申请不依赖于服务器上预先设置的正版特征信息。本申请的预设特征信息模型是利用训练样本集训练后得到的、用于区分正版终端和盗版终端的分类器。由于训练样本集中既可以包含主流设计终端的特征信息，又可以包含小批次设计终端的特征信息，所以预设特征信息模型可以准确确定不同批次终端的类别结果。因此，不论待测终端是那种批次的终端，本申请均可以利用预设特征信息模型来准确终端的验证结果。
可以理解的是，目前终端机型非常多，所以服务器上构建预设特征信息模型的训练样本集中不可能包含所有机型的特征信息。当待测终端机型 的特征信息未包含训练样本集时，服务器则发送无法判断该终端的真伪信息。
为了保证服务器利用预设特征信息模型确定出的正版终端必然是正版终端，则在服务器无法准确确定待测终端的特征信息判定为正版终端还是盗版终端时，服务器将待测终端归属为盗版终端。
由于服务器待测终端的验证结果为盗版终端的情况下，待测终端可能是由于确实是盗版终端而被确定为盗版终端的，也有可能是由于服务器无法准确待测终端的验证结果导致的。
因此，在服务器确定待测终端的验证结果为盗版终端的情况下，可以执行以下处理过程。如图3所示，具体包括以下步骤：
步骤S301：接收所述待测终端的第二验证结果；其中，所述第二验证结果利用人工分析方式确定。
由于服务器无法继续准确确定待测终端的验证结果，因此，由人工方式来详细分析待测终端的特征信息，并确定待测终端的第二验证结果。可以理解的是，第二验证结果可以与第一验证结果一致，即第二验证结果同样为盗版终端，在此情况下，说明第一验证结果未出现误判。此时可以不对预设特征信息模型进行重新训练。
第二验证结果可以与第一验证结果不一致，即第二验证结果为正版终端。在此情况下，说明第一验证结果错误的。即，服务器训练样本集中未具有待测终端的特征信息，所以导致出现误判情况。
步骤S302：若所述第二验证结果为正版终端，则将所述待测终端的特征信息和所述第二验证结果添加所述训练样本集。
因此，在第二验证结果为正版终端的情况下，服务器可以将待测终端的特征信息和第二验证结果(即正版终端)组成一组训练样本，然后将该组训练样本添加训练样本集中。
步骤S303：依据所述训练样本集，重新训练所述预设特征信息模型。
由于原有的预设特征信息模型是依据原有的训练样本集训练后得到的，在训练样本集中添加与待测终端对应的训练样本之后，由于训练样本集发生变化，所以需要重新依据训练样本集对分类器进行训练。然后，将训练结束后的分类器重新确定为本申请所使用的预设特征信息模型；以便后续在出现与待测终端类似的特征信息之后，可以准确输出待测终端的验证结果。
如图4所示，本申请提供了一种终端真伪验证方法，应用于客户端，所述方法包括：
步骤S401：获取待测终端的特征信息。
可以理解的是，在实际应用过程中，用户可以将待测终端通过数据连接线与客户端建立物理连接，然后客户端可以与待测终端建立通信连接。此后，客户端便可以扫描待测终端并获取所述待测终端的特征信息。
其中，待测终端的特征信息可以包括软件特征信息和硬件特征信息。具体而言，所述软件特征信息包括***软件版本、网络频率、数据业务、机身内存和运行内存；所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
步骤S402：向服务器发送包含所述待测终端的特征信息的验证请求。
为了验证终端真伪，客户端可以将包含待测终端的特征信息的验证请求发送至服务器，由服务器来进行进一步的分析。
步骤S403：接收所述服务器反馈的第一验证结果。其中，所述第一验证结果为所述服务器依据预设特征信息模型对所述待测终端的特征信息进行真伪验证后确定的；所述第一验证结果为正版终端或盗版终端；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器。
在服务器利用图2所示的实施例，确定待测终端的第一验证结果之后，可以向客户端发送第一验证结果，以便客户端接收第一验证结果。为了方 便用户查看待测终端的第一验证结果，客户端可以利用利用人机显示界面显示所述待测终端的第一验证结果。
通过以上技术特征，可以看出本申请具有以下有益效果：
本申请并未预先设置正版终端的特征信息，而是利用预设特征信息模型来判定待测终端的真伪。因此，相对于上述确定终端真伪的方式而言，本申请不依赖于服务器上预先设置的正版特征信息。本申请的预设特征信息模型是利用训练样本集训练后得到的、用于区分正版终端和盗版终端的分类器。由于训练样本集中既可以包含主流设计终端的特征信息，又可以包含小批次设计终端的特征信息，所以预设特征信息模型可以准确确定不同批次终端的类别结果。因此，不论待测终端是那种批次的终端，本申请均可以利用预设特征信息模型来准确终端的验证结果。
与图2所示的实施例相对应，本申请提供了一种终端真伪验证装置，集成于服务器。如图5所示，具体包括：
第一接收单元51，用于接收客户端发送的包含待测终端的特征信息的验证请求；
验证单元52，用于依据预设特征信息模型对所述待测终端的特征信息进行真伪验证，并确定所述待测终端的第一验证结果；其中，所述第一验证结果为正版终端或盗版终端；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器；
第一反馈单元53，用于向所述客户端反馈所述第一验证结果。
如图6所示，所述一种终端真伪验证装置在图5的基础上还包括：
第二接收单元54，用于接收所述待测终端的第二验证结果；其中，所述第二验证结果利用人工分析方式确定；
添加单元55，用于若所述第二验证结果为正版终端，则将所述待测终端的特征信息和所述第二验证结果添加所述训练样本集；
训练单元56，用于依据所述训练样本集，重新训练所述预设特征信息模型。
本申请中的所述特征信息包括软件特征信息和硬件特征信息。其中，所述软件特征信息包括***软件版本、网络频率、数据业务、机身内存和运行内存；所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
与图4所示的实施例相对应，本申请提供了一种终端真伪验证装置，集成于服务器。如图7所示，具体包括：
获取单元71，用于获取待测终端的特征信息；
发送单元72，用于向服务器发送包含所述待测终端的特征信息的验证请求；
第二反馈单元73，用于接收所述服务器反馈的第一验证结果；
其中，所述第一验证结果为所述服务器依据预设特征信息模型对所述待测终端的特征信息进行真伪验证后确定的；所述第一验证结果为正版终端或盗版终端；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器。
此外，本申请提供的终端真伪验证装置还包括：
显示单元74，用于利用人机显示界面显示所述待测终端的第一验证结果。
如图8所示，所述获取单元71，包括：
建立单元81，用于在与所述待测终端建立物理连接之后，与所述待测终端建立通信连接；
扫描单元82，用于扫描所述待测终端并获取所述待测终端的特征信息。
本实施例中所述特征信息包括软件特征信息和硬件特征信息。其中，所述软件特征信息包括***软件版本、网络频率、数据业务、机身内存和运行内存；所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
如图9所示，本申请提供了一种终端真伪验证***，包括：
服务器100和与所述服务器100相连的客户端200；
所述客户端200，用于获取待测终端的特征信息；向服务器100发送包含所述待测终端的特征信息的验证请求；并接收所述服务器100反馈的第一验证结果。
所述服务器100，用于接收客户端200发送的包含待测终端的特征信息的验证请求；依据预设特征信息模型对所述待测终端的特征信息进行真伪验证，并确定所述待测终端的第一验证结果；并向所述客户端200反馈所述第一验证结果；
其中，所述第一验证结果为正版终端或盗版终端；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器。
本实施例方法所述的功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算设备可读取存储介质中。基于这样的理解，本申请实施例对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该软件产品存储在一个存储介质中，包括若干指令用以使得一台计算设备(可以是个人计算机，服务器，移动计算设备或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
本说明书中各个实施例采用递进的方式描述，每个实施例重点说明的都是与其它实施例的不同之处，各个实施例之间相同或相似部分互相参见即可。
对所公开的实施例的上述说明，使本领域专业技术人员能够实现或使用本申请。对这些实施例的多种修改对本领域的专业技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本申请的精神或范围的情况下，在其它实施例中实现。因此，本申请将不会被限制于本文所示的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。

Claims (19)

  1. 一种终端真伪验证方法，其特征在于，应用于服务器，包括：
    接收客户端发送的包含待测终端的特征信息的验证请求；
    依据预设特征信息模型对所述待测终端的特征信息进行真伪验证，并确定所述待测终端的第一验证结果；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器；
    向所述客户端反馈所述第一验证结果；
    其中，所述第一验证结果和所述类别结果均为正版终端或盗版终端中的一个。
  2. 如权利要求1所述的方法，其特征在于，在所述待测终端的第一验证结果为盗版终端的情况下，所述方法还包括：
    接收所述待测终端的第二验证结果；其中，所述第二验证结果利用人工分析方式确定；
    若所述第二验证结果为正版终端，则将所述待测终端的特征信息和所述第二验证结果添加所述训练样本集；
    依据所述训练样本集，重新训练所述预设特征信息模型。
  3. 如权利要求1或2任一项所述的方法，其特征在于，所述特征信息包括软件特征信息和硬件特征信息。
  4. 如权利要求3所述的方法，其特征在于，所述软件特征信息包括操作***软件版本、网络频率、数据业务、机身内存和运行内存；
    所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
  5. 一种终端真伪验证方法，其特征在于，应用于客户端，所述方法包括：
    获取待测终端的特征信息；
    向服务器发送包含所述待测终端的特征信息的验证请求；
    接收所述服务器反馈的第一验证结果；
    其中，所述第一验证结果为所述服务器依据预设特征信息模型对所述待测终端的特征信息进行真伪验证后确定的；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器；其中，所述第一验证结果和所述类别结果均为正版终端或盗版终端中的一个。
  6. 如权利要求5所述的方法，其特征在于，所述获取待测终端的特征信息，包括：
    在与所述待测终端建立物理连接之后，与所述待测终端建立通信连接；
    扫描所述待测终端并获取所述待测终端的特征信息。
  7. 如权利要求5或6所述的方法，其特征在于，所述特征信息包括软件特征信息和硬件特征信息。
  8. 如权利要求7所述的方法，其特征在于，所述软件特征信息包括***软件版本、网络频率、数据业务、机身内存和运行内存；
    所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
  9. 如权利要求5所述的方法，其特征在于，在所述接收所述服务器反馈的第一验证结果之后，还包括：
    利用人机显示界面显示所述待测终端的第一验证结果。
  10. 一种终端真伪验证装置，其特征在于，集成于服务器，包括：
    第一接收单元，用于接收客户端发送的包含待测终端的特征信息的验证请求；
    验证单元，用于依据预设特征信息模型对所述待测终端的特征信息进行真伪验证，并确定所述待测终端的第一验证结果；所述预设特征信息模 型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器；其中，所述第一验证结果和所述类别结果均为正版终端或盗版终端中的一个；
    第一反馈单元，用于向所述客户端反馈所述第一验证结果。
  11. 如权利要求10所述的装置，其特征在于，还包括：
    第二接收单元，用于接收所述待测终端的第二验证结果；其中，所述第二验证结果利用人工分析方式确定；
    添加单元，用于若所述第二验证结果为正版终端，则将所述待测终端的特征信息和所述第二验证结果添加所述训练样本集；
    训练单元，用于依据所述训练样本集，重新训练所述预设特征信息模型。
  12. 如权利要求10或11任一项所述的装置，其特征在于，所述特征信息包括软件特征信息和硬件特征信息。
  13. 如权利要求12所述的装置，其特征在于，所述软件特征信息包括***软件版本、网络频率、数据业务、机身内存和运行内存；
    所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
  14. 一种终端真伪验证装置，其特征在于，集成于客户端，包括：
    获取单元，用于获取待测终端的特征信息；
    发送单元，用于向服务器发送包含所述待测终端的特征信息的验证请求；
    第二反馈单元，用于接收所述服务器反馈的第一验证结果；
    其中，所述第一验证结果为所述服务器依据预设特征信息模型对所述待测终端的特征信息进行真伪验证后确定的；所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依 据特征信息来区分正版终端和盗版终端的分类器；其中，所述第一验证结果和所述类别结果均为正版终端或盗版终端中的一个。
  15. 如权利要求14所述的装置，其特征在于，所述获取单元，包括：
    建立单元，用于在与所述待测终端建立物理连接之后，与所述待测终端建立通信连接；
    扫描单元，用于扫描所述待测终端并获取所述待测终端的特征信息。
  16. 如权利要求14或15所述的装置，其特征在于，所述特征信息包括软件特征信息和硬件特征信息。
  17. 如权利要求16所述的装置，其特征在于，所述软件特征信息包括***软件版本、网络频率、数据业务、机身内存和运行内存；
    所述硬件特征信息包括：CPU ID、CPU型号、CPU频率、CPU核数、屏幕分辨率和传感器种类。
  18. 如权利要求14所述的装置，其特征在于，还包括：
    显示单元，用于利用人机显示界面显示所述待测终端的第一验证结果。
  19. 一种终端真伪验证***，其特征在于，包括：
    服务器和与所述服务器相连的客户端；
    所述客户端，用于获取待测终端的特征信息；向服务器发送包含所述待测终端的特征信息的验证请求；并接收所述服务器反馈的第一验证结果；
    所述服务器，用于接收客户端发送的包含待测终端的特征信息的验证请求；依据预设特征信息模型对所述待测终端的特征信息进行真伪验证，并确定所述待测终端的第一验证结果；并向所述客户端反馈所述第一验证结果；
    其中，所述预设特征信息模型为依据若干终端的特征信息和类别结果组成的训练样本集训练得到的，用于依据特征信息来区分正版终端和盗版终端的分类器，其中，所述第一验证结果和所述类别结果均为正版终端或盗版终端中的一个。
PCT/CN2016/110066 2015-12-28 2016-12-15 终端真伪验证方法、装置及*** WO2017114167A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201511001107.9 2015-12-28
CN201511001107.9A CN106921969A (zh) 2015-12-28 2015-12-28 终端真伪验证方法、装置及***

Publications (1)

Publication Number Publication Date
WO2017114167A1 true WO2017114167A1 (zh) 2017-07-06

Family

ID=59225918

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/110066 WO2017114167A1 (zh) 2015-12-28 2016-12-15 终端真伪验证方法、装置及***

Country Status (2)

Country Link
CN (1) CN106921969A (zh)
WO (1) WO2017114167A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111046890A (zh) * 2018-10-11 2020-04-21 同济大学 通信***、服务器、基于传感器的设备识别方法及装置
CN112988480A (zh) * 2021-02-09 2021-06-18 山东英信计算机技术有限公司 基于云平台的服务器内存型号校验***、方法及存储介质

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108255651A (zh) * 2017-12-25 2018-07-06 深圳回收宝科技有限公司 一种终端检测的方法、终端以及存储介质
CN108241561A (zh) * 2017-12-25 2018-07-03 深圳回收宝科技有限公司 一种终端检测模型的生成方法、服务器以及存储介质
CN108234729B (zh) * 2017-12-25 2020-10-02 深圳回收宝科技有限公司 一种调整验证模型的方法、验证方法、服务器以及存储介质
CN108197955B (zh) * 2017-12-29 2021-05-25 珠海市君天电子科技有限公司 终端验证的方法、终端设备及计算机可读存储介质
CN108229975B (zh) * 2017-12-29 2021-05-25 珠海市君天电子科技有限公司 终端验证的方法、终端设备及计算机可读存储介质
CN108681667A (zh) * 2018-04-02 2018-10-19 阿里巴巴集团控股有限公司 一种设备型号识别方法、装置及处理设备
CN109597727B (zh) * 2018-11-14 2022-08-12 歌尔股份有限公司 电子设备的检测方法、检测装置、服务器及检测***
CN113132523B (zh) * 2021-04-19 2023-05-26 广州绿怡信息科技有限公司 通话检测模型训练方法及通话检测方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103500405A (zh) * 2013-09-26 2014-01-08 北京奇虎科技有限公司 用于对目标终端标称型号进行鉴别的方法及其设备
CN103841239A (zh) * 2014-03-12 2014-06-04 北京安兔兔科技有限公司 终端真伪验证方法及装置
CN105101180A (zh) * 2014-04-18 2015-11-25 北京安兔兔科技有限公司 终端真伪验证方法及装置
CN105142148A (zh) * 2014-05-30 2015-12-09 北京安兔兔科技有限公司 终端真伪验证方法及装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101500336B1 (ko) * 2007-09-12 2015-03-09 삼성전자주식회사 신뢰 컴퓨팅을 이용한 디지털 데이터의 검증 방법 및 장치
CN103020225B (zh) * 2012-12-12 2016-03-23 北京奇虎科技有限公司 一种cpu型号识别方法和硬件检测***
CN103646044A (zh) * 2013-11-19 2014-03-19 北京奇虎科技有限公司 移动终端鉴别方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103500405A (zh) * 2013-09-26 2014-01-08 北京奇虎科技有限公司 用于对目标终端标称型号进行鉴别的方法及其设备
CN103841239A (zh) * 2014-03-12 2014-06-04 北京安兔兔科技有限公司 终端真伪验证方法及装置
CN105101180A (zh) * 2014-04-18 2015-11-25 北京安兔兔科技有限公司 终端真伪验证方法及装置
CN105142148A (zh) * 2014-05-30 2015-12-09 北京安兔兔科技有限公司 终端真伪验证方法及装置

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111046890A (zh) * 2018-10-11 2020-04-21 同济大学 通信***、服务器、基于传感器的设备识别方法及装置
CN111046890B (zh) * 2018-10-11 2023-04-25 同济大学 通信***、服务器、基于传感器的设备识别方法及装置
CN112988480A (zh) * 2021-02-09 2021-06-18 山东英信计算机技术有限公司 基于云平台的服务器内存型号校验***、方法及存储介质

Also Published As

Publication number Publication date
CN106921969A (zh) 2017-07-04

Similar Documents

Publication Publication Date Title
WO2017114167A1 (zh) 终端真伪验证方法、装置及***
TWI752418B (zh) 伺服器、客戶端、用戶核身方法及系統
CN105279405B (zh) 触屏用户按键行为模式构建与分析***及其身份识别方法
CN108765131B (zh) 基于微表情的信贷审核方法、装置、终端及可读存储介质
US9747491B2 (en) Dynamic handwriting verification and handwriting-based user authentication
WO2020181824A1 (zh) 声纹识别方法、装置、设备以及计算机可读存储介质
CN108351932A (zh) 基于图像的captcha挑战
WO2014044052A1 (zh) 用户验证处理方法、用户设备和服务器
TW201907330A (zh) 身份認證的方法、裝置、設備及資料處理方法
CN105101180B (zh) 终端真伪验证方法及装置
WO2020024412A1 (zh) 基于滑块验证码验证的用户行为识别方法及装置
US11757870B1 (en) Bi-directional voice authentication
CN111626371A (zh) 一种图像分类方法、装置、设备及可读存储介质
CN111885375A (zh) 双录视频的检验方法、装置、服务器及***
JP2018532181A (ja) セグメントベース手書き署名認証システム及び方法
WO2022166532A1 (zh) 人脸识别方法、装置、电子设备及存储介质
Siddiqui et al. Continuous user authentication using mouse dynamics, machine learning, and minecraft
CN106921500B (zh) 一种移动设备的身份认证方法及装置
Siddiqui et al. Continuous authentication using mouse movements, machine learning, and Minecraft
CN109840494A (zh) 身份认证方法、装置、计算机程序、存储介质和电子设备
TWI734735B (zh) 終端真偽驗證方法、裝置及系統
CN109002441A (zh) 应用名称相似度的确定方法、异常应用检测方法及***
US20240095327A1 (en) Computer authentication using knowledge of former devices
CN109614844A (zh) 一种链路验证方法、装置及设备
CN110533297B (zh) 一种识别异常设备的方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16880957

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16880957

Country of ref document: EP

Kind code of ref document: A1