TW201942766A

TW201942766A - Device model identification method and apparatus, and processing device

Info

Publication number: TW201942766A
Application number: TW108104369A
Authority: TW
Inventors: 任偲; 向東
Original assignee: 香港商阿里巴巴集團服務有限公司
Priority date: 2018-04-02
Filing date: 2019-02-11
Publication date: 2019-11-01
Also published as: WO2019192260A1; CN108681667A; TWI709866B

Abstract

A device model identification method and apparatus, and a processing device. The method comprises: obtaining device request data of a device to be identified, the device request data at least comprising device hardware information; and identifying the device request data by using a constructed device identification model to obtain a real device model of the device to be identified, the device identification model using training data at least comprising the device hardware information for training, and outputting a classification algorithm of device brand models. The behavior of falsifying brand model information can be effectively identified.

Description

Equipment model identification method, device and processing equipment

本說明書實施例方案屬於電腦資料處理的技術領域，尤其有關一種設備型號識別方法、裝置及處理設備。The solutions in the embodiments of the present specification belong to the technical field of computer data processing, and more particularly, to a method, a device, and a processing device for identifying a device model.

目前，移動通信終端(如智慧型手機)對用戶的日常工作、生活、社交、消費等影響越來越重要。而智慧型手機品牌和型號種類繁多，往往不同價值的智慧型手機的用戶對應不同的用戶消費能力，如高價值的手機，對應的用戶的消費能力可能會更強。在手機保險產品中，不同的手機型號對應的賠償金額通常也是會有很大的差異。
因移動通信終端的設備型號在一些產品中關聯著利益，因而存在著透過修改設備資訊實現修改設備型號，進而騙取行銷資源或者騙保等行為。如用戶結合PC(personal computer)，個人電腦)端或終端的root(獲取系統最高好權項)工具，透過系統API(Application Programming Interface，應用程式編程介面)讀取、修改硬體資訊。
因此，業內亟需一種可以有效識別設備真實型號資訊的解決方案。At present, mobile communication terminals (such as smart phones) are increasingly important for users' daily work, life, socialization, and consumption. There are many types and brands of smart phones. Often, users of different value smart phones correspond to different consumer spending capabilities. For example, high-value phones may have stronger consumer spending capabilities. In mobile phone insurance products, the compensation amount corresponding to different mobile phone models usually also varies greatly.
Because the device model of the mobile communication terminal is associated with interests in some products, there is an act of modifying the device model by modifying the device information, thereby defrauding marketing resources or deceiving insurance. For example, a user can read and modify hardware information through a system API (Application Programming Interface) using a PC (personal computer), or a root (getting the highest system rights) tool of a terminal.
Therefore, the industry urgently needs a solution that can effectively identify the true model information of the device.

本說明書實施例目的在於提供一種設備型號識別方法、裝置及處理設備，可以用設備基本的硬體屬性，透過建構分類模型，對真實的品牌型號進行識別。能夠有效地識別出篡改品牌型號資訊的行為，標識出真實的品牌和型號。
本說明書實施例提供的一種設備型號識別方法、裝置及處理設備是包括以下方式來實現的：
一種設備型號識別方法，所述方法包括：
獲取待識別設備的設備請求資料，所述設備請求資料至少包括設備硬體資訊；
利用建構的設備識別模型對所述設備請求資料進行識別處理，得到所述待識別設備的真實設備型號，所述設備識別模型採用至少包括所述設備硬體資訊的訓練資料進行訓練、輸出設備品牌型號的分類演算法
一種設備型號識別裝置，所述裝置包括：
設備資料獲取模組，用以獲取待識別設備的設備請求資料，所述設備請求資料至少包括設備硬體資訊；
識別模型處理模組，利用建構的設備識別模型對所述設備請求資料進行識別處理，得到所述待識別設備的真實設備型號，所述設備識別模型採用至少包括所述設備硬體資訊的訓練資料進行訓練、輸出設備品牌型號的分類演算法。
一種識別設備型號的處理設備，包括處理器以及用以儲存處理器可執行指令的記憶體，所述處理器執行所述指令時實現：
獲取待識別設備的設備請求資料，所述設備請求資料至少包括設備硬體資訊；
利用建構的設備識別模型對所述設備請求資料進行識別處理，得到所述待識別設備的真實設備型號，所述設備識別模型採用至少包括所述設備硬體資訊的訓練資料進行訓練、輸出設備品牌型號的分類演算法。
本說明書實施例提供的一種設備型號識別方法、裝置及處理設備，基本的多種硬體屬性，利用已知可靠的硬體屬性資料來訓練設備識別模型，確定模型中的參數，然後線上使用，在接收到待識別設備的設備請求資料時可以標識出真實的設備品牌型號，有效識別出篡改品牌或型號資訊的行為。The purpose of the embodiments of the present specification is to provide a method, a device, and a processing device for identifying a device model. The basic hardware attributes of the device can be used to identify a real brand model by constructing a classification model. Can effectively identify the behavior of tampering with brand model information and identify the real brand and model.
The device model identification method, device and processing device provided in the embodiments of this specification are implemented in the following ways:
A device model identification method, the method includes:
Obtaining device request data of a device to be identified, the device request data including at least device hardware information;
Use the constructed device identification model to identify and process the device request data to obtain the real device model of the device to be identified. The device identification model uses training data including at least the device hardware information to train and output the device brand. Model classification algorithm A device model identification device, the device includes:
A device data acquisition module for obtaining device request data of a device to be identified, the device request data including at least device hardware information;
The recognition model processing module uses the constructed device recognition model to identify and process the device request data to obtain the real device model of the device to be identified. The device recognition model uses training data including at least the device hardware information. Classify algorithms for training and output device brands.
A processing device for identifying a device model includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, the processor implements:
Obtaining device request data of a device to be identified, the device request data including at least device hardware information;
Use the constructed device identification model to identify and process the device request data to obtain the real device model of the device to be identified. The device identification model uses training data including at least the device hardware information to train and output the device brand. Classification algorithm for models.
An embodiment of the present specification provides a device model identification method, device, and processing device. The basic multiple hardware attributes are used to train the device identification model using known and reliable hardware attribute data, determine the parameters in the model, and then use it online. When the device request data of the device to be identified is received, the real device brand model can be identified, and the behavior of tampering with the brand or model information can be effectively identified.

為了使本技術領域的人員更好地理解本說明書中的技術方案，下面將結合本說明書實施例中的附圖，對本說明書實施例中的技術方案進行清楚、完整地描述，顯然，所描述的實施例僅僅是本說明書中的一部分實施例，而不是全部的實施例。基於本說明書中的一個或多個實施例，本領域普通技術人員在沒有作出創造性勞動前提下所獲得的所有其他實施例，都應當屬於本說明書實施例保護的範圍。
本說明書提供的一個或多個實施方案中，可以預先採集終端設備的硬體屬性資訊，然後建構分類模型，對真實的品牌型號進行識別(標識出真實的品牌和型號)，能夠有效地識別出篡改設備品牌、型號資訊的行為。需要說明的是，本發明實施例中所提及的設備識別模型識別出的真實設備型號資訊是指設備識別模型回應於待識別設備的設備請求資料而輸出的設備品牌、型號資訊，最終輸出結果的可靠性主要依賴於採用的模型演算法和使用的訓練資料。所述的“真實”設備型號資訊可以允許與實際設備的真實品牌型號不同。
本說明書實施例中可以採用多種分類演算法來建構設備識別模型。例如一個實施例中可以採用GBM演算法(Gradient Tree Boosting Algorithm，梯度樹增強演算法)來進行模型訓練，如圖1所示的處理過程。當然也可以採用GBDT(Gradient Boosting Decision Tree，梯度提升決策樹)或者xgboost(極端梯度提升 Extreme Gradient Boosting)等基於boosting演算法(用來提高弱分類演算法準確度的方法)。或者，其他的實施例中也可以採用LR(Logistic Regression，邏輯迴歸)、deep learning(深度學習)等演算法來建構模型。本說明書提供的實施方案在模型建構訓練時採用的訓練資料至少包括終端設備的設備硬體資訊，使用已知可靠的硬體屬性資料來訓練設備識別模型，確定模型中的參數，然後線上使用，在接收到待識別設備的設備請求資料時可以標識出真實的設備品牌型號，有效識別出篡改品牌或型號資訊的行為。
以手機品牌和型號的移動通信終端設備型號識別應用場景為例，在模型訓練階段，可以採集不同品牌和型號的手機的硬體設備屬性資訊。通常一個手機品牌下可以對應多個型號的手機，在訓練資料獲取過程中，可以設定每個品牌型號對應的設備最低設備數量，以保障訓練資料的可靠性和輸出結果的準確性。考慮到手機品牌和型號的種類分佈和發展狀況，在本發明的一個實施例中，可以設定每一個品牌對應的設備數量至少有100台，其中，每個型號的設備數量至少有10台。經過實際實驗效果對比，採用上述方式獲取到的訓練資料，既可以無需大量訓練樣本的資料獲取，減少成本，同時又可以使得設備識別模型有較高識別準確性的結果輸出。
設備識別模型使用的訓練資料可以包括多種類型的資料資訊，但至少包括一種設備硬體資訊。所述的設備硬體資訊可以包括終端設備上某個單元部件或部件組合的識別標識，如主機板型號、國際移動設備身份碼IMEI、MAC位址、ROM名稱等。在實際場景中，所述的訓練資料通常採用多個硬體設備資訊，可以更加有效、可靠地識別出篡改其中一個或多個硬體設備資訊的行為。當然，所述的訓練資料還可以包括終端設備上其他軟體或軟體+硬體結合形成的標識資訊，如國際移動用戶識別碼IMSI、設備系統版本資訊等。
使用訓練資料對採用的設備識別模型進行訓練後，可以線上進行使用。當需要對待識別設備的設備型號進行判識時，可以請求獲取待識別設備的設備請求資料，然後處理器將該設備請求資料輸入建構的設備識別模型中進行處理。設備識別模型可以基於獲取的設備請求資料輸出對應的品牌型號分類結果。在一些實施場景中，在電腦處理能力運行的情況下，也可以在設備識別模型建構、訓練的同時對待識別設備進行識別處理，亦即，本說明書提供的實施方式可以在設備識別模型線下訓練完成後線上使用，也可以基於平臺或雲端計算系統等即時的建構或訓練設備識別模型，用以對待識別設備的設備請求資料進行處理。或者，所述的設備識別模型也可以線上更新、維護，或者線上系統(伺服器、伺服器集群或分散式伺服器)有多個類型的設備識別模型，可以先分析處理設備請求資料，然後匹配與設備請求資料對應的最優(根據實際獲取的設備請求資料包括的資料資訊來選擇最適用的設備識別模型)的設備識別模型進行處理。
下面以一個具體的手機品牌型號應用場景為例對本說明書實施方案來進行說明。具體地說，圖2是本說明書提供的所述一種設備型號識別方法實施例的流程示意圖。雖然本說明書提供了如下述實施例或附圖所示的方法操作步驟或裝置結構，但基於習知或者無需創造性的勞動在所述方法或裝置中可以包括更多或者部分合併後更少的操作步驟或模組單元。在邏輯性上不存在必要因果關係的步驟或結構中，這些步驟的執行順序或裝置的模組結構不限於本說明書實施例或附圖所示的執行順序或模組結構。所述的方法或模組結構的在實際中的裝置、伺服器或終端產品應用時，可以按照實施例或者附圖所示的方法或模組結構進行循序執行或者並存執行(例如，並行處理器或者多執行緒處理的環境、甚至包括分散式處理、伺服器集群的實施環境)。
當然，下述實施例的描述並不對基於本說明書的其他可擴展到的技術方案構成限制。例如其他的實施場景中，本說明書提供的實施方案同樣可以應用到非移動終端設備型號識別的實施場景中，如PC終端、共用車輛設備、其他專用設備等。具體的一種實施例如圖2所示，本說明書提供的一種設備型號識別方法可以包括：
S0：獲取待識別設備的設備請求資料，所述設備請求資料至少包括設備硬體資訊；
S2：利用建構的設備識別模型對所述設備請求資料進行識別處理，得到所述待識別設備的真實設備型號，所述設備識別模型採用至少包括所述設備硬體資訊的訓練資料進行訓練、輸出設備品牌型號的分類演算法。
本實施例提供的方法可以用於伺服器側。所說的伺服器可以包括單獨的伺服器、伺服器集群、分散式系統伺服器或者處理設備請求資料的伺服器與其他相關聯資料處理的系統伺服器組合(如識別待處理設備的伺服器與訓練建構設備識別模型的伺服器)。伺服器可以獲取待識別設備的設備請求資料，當然，所述的設備請求資料可以包括設備硬體資訊。在一些應用場景中，在進行設備型號識別處理中，通常可以指定終端設備上傳預定的多種設備硬體資訊，但由於權項或其他原因，終端設備上傳的設備資訊中可能包括部分預定的設備請求資料，甚至設備資訊中無設備硬體資訊。此時可以下發相應的提示資訊請求開放硬體設備資訊獲取許可權或者因為無設備硬體資訊而執行其他的處理，具體地說，可以根據實際應用場景制定相應的策略。
如前所述，本說明書實施例所述的方法中，模型訓練所使用的訓練資料可以包括類型的設備硬體以及軟體的資料資訊。本說明書提供的一個實施例中，所述訓練資料可以至少包括下屬中的一種：
國際移動設備身份碼IMEI、國際移動用戶識別碼IMSI、有線/無線媒體存取控制位址MAC/WIFI-MAC、藍牙位址Bluetooth、解析度、主機板型號、唯讀記憶體rom名稱。
當然，除上述所述外，還可以包括其他的硬體資料資訊構成的訓練資料。在上述的訓練資料中，IMEI通常包括下述的資料欄位：
TAC = Type Approval Code (first 2 digits = country code) 設備型號核准號碼；
FAC = Final Assembly Code (For Nokia phones FAC =51)最後裝配號；
SNR = Serial Number序號；
SP = Spare (always SP=0)備用號碼。
一般的，IMSI 號碼採用E.212格式，號碼總長度為16位，它由MCC+MNC+MSIN三部分組成，其中：
MCC：移動國家碼，三個數字，如中國為460；
MNC：移動網號，兩個數字，如中國移動的MNC為00(聯通是01，移動159新號段是02)，可以有效針對終端綁定移動通信運營商的設備進行識別。
MSIN：移動客戶識別號，如在某一個PLMN(Public Land Mobile Network，公共陸地移動網路)中移動台的唯一識別碼，MSIN=H0H1H2H3(S)XXXXXX(共11位)。
使用IMEI、IMSI訓練資料時，可以透過把IMEI、IMSI切分成成上述部分，透過識別其中的一些欄位資訊可以一定程式上反應手機品牌相關的資訊。
當然，還可以包括有線或無線的MAC位址、手機螢幕解析度、使用的主機板廠商和型號等。因此，本說明書提供的所述方法的另一個實施例中，所述訓練資料可以至少包括下述中的一種：
國際移動設備身份碼、國際移動用戶識別碼、有線/無線媒體存取控制位址、藍牙位址、解析度、主機板型號、唯讀記憶體名稱。
這樣，既可以保障資料獲取的有效性，同時也可以減少終端資料獲取種類和網路開銷。
需要說明是的，設備識別模型輸出的所述的設備型號可以包括設備名稱、型號名稱、品牌名稱等中的一個或多個，如輸出的結果可以為品牌資訊“小米”，也可以為“小米-note2”，甚至，在一些應用場景中也可以僅輸出型號資訊(適用於不同的品牌名下的型號資訊均不相同的情況)。為便於統一描述，本說明書的一些實施例中可以將設備識別模型輸出的結果統一稱為設備型號資訊，但並不限定一定是包括設備、品牌、型號中的一種資訊。
圖3是本說明書提供的一種基於GBM演算法進行手機終端的品牌和型號識別的處理過程示意圖。在圖3中，可以基於主動獲取或設備上報的型號屬性資料產生訓練標籤，標籤資料具體地說可以為“xiaomi note2”、“oppo r9”、“vivo x7”等。在GBM演算法中，可以透過對上一次樹殘差的學習，建構新的子樹。權重值最佳化可以參考經典人adaboosting等演算法。樹的建構過程主要為標準的樹產生演算法。模型計算完後，可以對每個樣本，計算出每個分類的機率，取最大的機率作為預測分類，然後跟真實分類進行對照，進而可以確定準確率，覆蓋率等指標。透過相關指標可以對模型效果進行評估、參數調整、最佳化等。對於待識別設備，可以提取對應的設備資訊，獲取設備請求資料。然後利用學習得到的GBM模型對設備請求資料進行評分，得分最高的分類作為真實的品牌型號。
本說明書提供的所述方法的另一個實施例中，可以進一步對訓練資料進行過濾和篩選，使用設備原始、真實的硬體資料資訊。具體地說，所述方法的另一個實施例中，所述的訓練資料至少經過下述之一的篩選處理：
刪除獲取系統最高許可權操作(root)的訓練資料；
刪除經過鉤子機制(hook)截獲後的訊息中包含的訓練資料。
經過hook和root的設備資訊可能包含虛假資料，所以在本實施例中可以濾掉這些虛假資料。其中，hook(鉤子)實際上是一個處理訊息的程式段，透過系統調用，把它掛入系統。每當特定的訊息發出，在沒有到達目的視窗前，鉤副程式就先捕獲該訊息，亦即鉤子函數先得到控制權。本實施例中執行root和hook的設備請求資料的過濾，可以進一步提升模型訓練精度和輸出結果的可靠性。當然，實際的訓練資料獲取可以設定資料種類或數量可以設定相應的採集要求，例如至少三種硬體資訊、一個品牌對應的設備數至少到100台。採集完成後對訓練資料進行篩選或者在採集的過程中採用一定的策略識別資料是否經過root或hook修改。
如前所述，本說明書一個或多個實施例中，所述的設備識別模型，可以採用離線預先建構的方式來產生，可以採用訓練資料進行訓練打標後再在線上使用。本說明書不排除所述設備識別模型採用線上建構或更新/維護的方式，在電腦能力足夠的情況下，可以線上建構出設備識別模型。當然，在電腦性能允許的情況下，也可以透過即時流引擎即時計算獲得硬體設備可以同步線上使用，識別設備品牌型號。
在一些實施例中，設備識別模型基於設備請求資料可以計算出多個設備型號的分類標籤，每個分類標籤可以有對應的機率取值或者分值(分值的高低也可以認為是機率大小的一種)。一些可選的實施例中，計算得到的分類標籤可以全部或者部分輸出，由用戶人工或者進一步判斷真實品牌型號。本說明書提供的所述方法的另一個實施例中，可以設定一個機率取值範圍，將符合機率取值範圍內的分類標籤作為識別出的真實設備型號。具體地說，所述得到所述待識別設備的真實設備型號可以包括：
基於所述設備請求資料計算所述待識別設備對應於所述設備識別模型相應分類標籤的機率取值；
將預定機率取值範圍對應的分類標籤作為所述待識別設備的真實設備型號。
這樣，在一些情況下，可以輸出兩個或者更多識別出的待識別設備所屬的真實設備型號資訊。若所有的識別結果均不符合預定機率取值，則可以判定為無法識別或設備資訊資料無效，或者其他的處理方式。當然，另一些實施例中，設備請求資料對應多個分類標籤時，可以將評分最高或機率值最高的對應的分類標籤作為待識別設備的真實設備型號。
本說明書提供的另一個實施例中，輸出的所述真實設備型號還可以包括所述待識別設備屬於所述分類標籤的可靠性評估資料，所述可靠性評估資料基於所述分類標籤對應的機率取值確定。如輸出手機型號的同時，還輸出手機是這個型號的可靠性評估資料，例如基於上傳的設備請求資料識別為輸出為xiaomi note2，但評分僅為41分(或機率取值為0.41)，可以作為是否將該模型得到真實設備型號的輸出結果作為實際真實的型號的參考依據，為設備的識別提供更多的資料支援，方便用戶決策。
具體的分類標籤可以根據實際應用場景確定。在本說明書的一些手機真實品牌型號識別的應用場景中，分類標籤可以包括終端設備的品牌名稱、對應於品牌名稱的型號。本實施例中可以包括品牌名稱缺省或型號名稱缺省的任意一種情況。這樣，在手機品牌型號識別的實施場景中，可以更加直覺輸出的品牌和型號資訊，以及對應的評分(或機率)，便於用戶決策，提高用戶使用體驗。
本說明書實施例所提供的方法實施例可以在移動終端、電腦終端、伺服器或者類似的計算裝置中執行。以運行在伺服器上為例，圖4是本發明實施例的一種識別車輛受損部件的伺服器的硬體結構方塊圖。如圖4所示，伺服器10可以包括一個或多個(圖中僅示出一個)處理器102(處理器102可以包括但不限於微處理器MCU或可程式設計邏輯裝置FPGA等的處理裝置)、用以儲存資料的記憶體104、以及用於通信功能的傳輸模組106。本領域普通技術人員可以理解，圖4所示的結構僅為示意，其並不對上述電子裝置的結構造成限定。例如，伺服器10還可包括比圖4中所示更多或者更少的元件，例如還可以包括其他的處理硬體，如資料庫或多級緩存，或者具有與圖4所示不同的配置。
記憶體104可用以儲存應用軟體的軟體程式以及模組，如本發明實施例中的搜索方法對應的程式指令/模組，處理器102透過運行儲存在記憶體104內的軟體程式以及模組，從而執行各種功能應用以及資料處理，亦即實現上述導航互動介面內容展示的處理方法。記憶體104可包括高速隨機記憶體，還可包括非易失性記憶體，如一個或者多個磁性儲存裝置、快閃記憶體、或者其他非易失性固態記憶體。在一些實例中，記憶體104可進一步包括相對於處理器102遠端設置的記憶體，這些遠端儲存器可以透過網路而被連接至電腦終端10。上述網路的實例包括但不限於互聯網、企業內部網、局域網、移動通信網及其組合。
傳輸模組106用以經由一個網路來接收或者發送資料。上述的網路具體實例可包括電腦終端10的通信供應商提供的無線網路。在一個實例中，傳輸模組106包括一個網路介面卡(Network Interface Controller，NIC)，其可透過基站與其他網路設備相連從而可與互聯網進行通訊。在一個實例中，傳輸模組106可以為射頻(Radio Frequency，RF)模組，其用以透過無線方式與互聯網進行通訊。
基於上述所述的設備型號識別方法，本說明書還提供一種設備型號識別裝置。所述的裝置可以包括使用了本說明書實施例所述方法的系統(包括分散式系統)、軟體(應用)、模組、元件、伺服器、用戶端等並結合必要的實施硬體的設備裝置。基於同一個創新構思，本說明書提供的一種實施例中的處理裝置如下面的實施例所述。由於裝置解決問題的實現方案與方法相似，因此本說明書實施例具體的處理裝置的實施可以參見前述方法的實施，重複之處不再贅述。儘管以下實施例所描述的裝置較佳地以軟體來實現，但是硬體，或者軟體和硬體的組合的實現也是可能並被構想的。具體地說，如圖5所示，圖5是本說明書提供的可以用於伺服器側的一種設備型號識別裝置實施例的模組結構示意圖，具體地說可以包括：
設備資料獲取模組101，可以用來獲取待識別設備的設備請求資料，所述設備請求資料至少包括設備硬體資訊；
識別模型處理模組102，可以利用建構的設備識別模型對所述設備請求資料進行識別處理，得到所述待識別設備的真實設備型號，所述設備識別模型採用至少包括所述設備硬體資訊的訓練資料進行訓練、輸出設備品牌型號的分類演算法。
所述的設備識別模型可以採用離線預先建構的方式來產生，可以採用訓練資料進行訓練打標後再在線上使用。本說明書不排除所述設備識別模型採用線上建構或更新/維護的方式，在電腦能力足夠的情況下，可以線上建構出設備識別模型。當然，在電腦性能允許的情況下，也可以透過即時流引擎即時計算獲得硬體設備可以同步線上使用，識別設備品牌型號。
一種實施例中，所述識別處理模組102中建構所述設備識別模型所使用的訓練資料至少包括下述中的一種：
國際移動設備身份碼、國際移動用戶識別碼、有線/無線媒體存取控制位址、藍牙位址、解析度、主機板型號、唯讀記憶體名稱。
另一種實施例中，所述的訓練資料至少經過下述之一的篩選處理：
刪除獲取系統最高許可權操作的訓練資料；
刪除經過鉤子機制截獲後的訊息中包含的訓練資料。
另一種實施例中，所述識別處理模組102得到的所述待識別設備的真實設備型號可以包括：
基於所述設備請求資料計算所述待識別設備對應於所述設備識別模型相應分類標籤的機率取值；
將預定機率取值範圍對應的分類標籤作為所述待識別設備的真實設備型號。
所述的預定機率範圍可以是一個區間，也可以是最大的機率取值。
所述裝置的另一個實施例中，不僅可以輸出待識別設備的真實設備型號，還可以輸出對應該輸出結果相應的機率值或分值。因此，所述真實設備型號還可以包括所述待識別設備屬於所述分類標籤的可靠性評估資料，所述可靠性評估資料基於所述分類標籤對應的機率取值來確定。
所述裝置具體的一個手機品牌型號識別應用場景的一個實施例中，所述分類標籤包括終端設備的品牌名稱、對應品牌名稱的型號。
上述實施例所述的裝置具體的實施可以參照相關方法實施例的描述，在此不做贅述。
本說明書實施例提供的設備型號識別方法可以在電腦中由處理器執行相應的程式指令來實現，如使用windows作業系統的c++語言在PC端或伺服器端實現，或其他例如Linux、系統相對應的應用設計語言集合必要的硬體來實現，或者基於量子電腦的處理邏輯來實現等。具體地說，本說明書提供的一種識別設備型號的處理設備實現上述方法的實施例中，所述處理設備可以包括處理器以及用以儲存處理器可執行指令的記憶體，所述處理器執行所述指令時實現：
獲取待識別設備的設備請求資料，所述設備請求資料至少包括設備硬體資訊；
利用建構的設備識別模型對所述設備請求資料進行識別處理，得到所述待識別設備的真實設備型號，所述設備識別模型採用至少包括所述設備硬體資訊的訓練資料進行訓練、輸出設備品牌型號的分類演算法。
上述的指令可以儲存在多種電腦可讀儲存媒體中。所述電腦可讀儲存媒體可以包括用以儲存資訊的物理裝置，可以將資訊數位化後再以利用電、磁或者光學等方式的媒體來加以儲存。本實施例所述的電腦可讀儲存媒體有可以包括：利用電能方式儲存資訊的裝置如，各式記憶體，如RAM、ROM等；利用磁能方式儲存資訊的裝置如，硬碟、軟碟、磁帶、磁芯記憶體、磁泡記憶體、U碟；利用光學方式來儲存資訊的裝置如，CD或DVD。當然，還有其他方式的可讀儲存媒體，例如量子記憶體、石墨烯記憶體等等。上述所述的裝置或伺服器或用戶端或處理設備中的所涉及的指令同上描述。
需要說明的是，本說明書實施例上述所述的裝置、處理設備，根據相關方法實施例的描述還可以包括其他的實施方式，如刪除獲取系統最高許可權操作的訓練資料，或者刪除經過鉤子機制截獲後的訊息中包含的訓練資料。具體的實現方式可以參照方法實施例的描述，在此不作一一贅述。
本說明書中的各個實施例均採用漸進的方式來描述，各個實施例之間相同相似的部分互相參見即可，每個實施例重點說明的都是與其他實施例的不同之處。尤其，對於硬體+程式類實施例而言，由於其基本相似於方法實施例，所以描述的比較簡單，相關之處參見方法實施例的部分說明即可。
上述對本說明書特定實施例進行了描述。其它實施例在所附申請專利範圍的範疇內。在一些情況下，在申請專利範圍中記載的動作或步驟可以按照不同於實施例中的順序來執行並且仍然可以實現期望的結果。另外，在附圖中描繪的過程不一定要求示出的特定順序或者連續順序才能實現期望的結果。在某些實施方式中，多工處理和並行處理也是可以的或者可能是有利的。
雖然本發明提供了如實施例或流程圖所述的方法操作步驟，但基於習知或者無創造性的勞動可以包括更多或者更少的操作步驟。實施例中列舉的步驟順序僅僅為眾多步驟執行順序中的一種方式，不代表唯一的執行順序。在實際中的裝置或系統伺服器產品執行時，可以按照實施例或者附圖所示的方法循序執行或者並存執行(例如，並行處理器或者多執行緒處理的環境)。
儘管本說明書實施例內容中提到利用GBM演算法來進行模型訓練、IMEI和MAC的硬體設備資訊、離線或線上建構模型、訓練資料獲取要求和篩選處理等之類的資料獲取、儲存、互動、計算、判斷等操作和資料描述，但是，本說明書實施例並不局限於必須是符合行業通信標準、標準分類模型處理、通信協定和標準資料模型/範本或本說明書實施例所描述的情況。某些行業標準或者使用自訂方式或實施例描述的實施基礎上略加修改後的實施方案也可以實現上述實施例相同、等同或相近、或變形後可預料的實施效果。應用這些修改或變形後的資料獲取、儲存、判斷、處理方式等獲取的實施例，仍然可以屬於本說明書的可選實施方案範圍之內。
在20世紀90年代，對於一個技術的改進可以很明顯地區分是硬體上的改進(例如，對二極體、電晶體、開關等電路結構的改進)還是軟體上的改進(對於方法流程的改進)。然而，隨著技術的發展，當今的很多方法流程的改進已經可以視為硬體電路結構的直接改進。設計人員幾乎都透過將改進的方法流程程式設計到硬體電路中來得到相應的硬體電路結構。因此，不能說一個方法流程的改進就不能用硬體實體模組來實現。例如，可程式設計邏輯裝置(Programmable Logic Device, PLD)(例如，現場可程式設計閘陣列(Field Programmable Gate Array，FPGA))就是這樣一種積體電路，其邏輯功能由用戶對裝置程式設計來確定。由設計人員自行程式設計來把一個數位系統“整合”在一片PLD上，而不需要請晶片製造廠商來設計和製作專用的積體電路晶片。而且，如今，取代手工地製作積體電路晶片，這種程式設計也多半改用“邏輯編譯器(logic compiler)”軟體來實現，它與程式開發撰寫時所用的軟體編譯器相類似，而要編譯之前的原始代碼也得用特定的程式設計語言來撰寫，此稱之為硬體描述語言(Hardware Description Language，HDL)，而HDL也並非僅有一種，而是有許多種，如ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language)等，目前最普遍使用的是VHDL(Very-High-Speed Integrated Circuit Hardware Description Language)與Verilog。本領域技術人員也應該清楚，只需要將方法流程用上述幾種硬體描述語言稍作邏輯程式設計並程式設計到積體電路中，就可以很容易得到實現該邏輯方法流程的硬體電路。
控制器可以按任何適當的方式來實現，例如，控制器可以採取例如微處理器或處理器以及儲存可由該(微)處理器執行的電腦可讀程式碼(例如，軟體或韌體)的電腦可讀媒體、邏輯閘、開關、特殊應用積體電路(Application Specific Integrated Circuit，ASIC)、可程式設計邏輯控制器和嵌入式微控制器的形式，控制器的例子包括但不限於以下微控制器：ARC 625D、Atmel AT91SAM、Microchip PIC18F26K20 以及Silicone Labs C8051F320，記憶體控制器還可以被實現為記憶體的控制邏輯的一部分。本領域技術人員也知道，除了以純電腦可讀程式碼方式來實現控制器以外，完全可以透過將方法步驟進行邏輯程式設計來使得控制器以邏輯閘、開關、特殊應用積體電路、可程式設計邏輯控制器和嵌入式微控制器等的形式來實現相同功能。因此這種控制器可以被認為是一種硬體部件，而對其內包括的用以實現各種功能的裝置也可以視為硬體部件內的結構。或者甚至，可以將用以實現各種功能的裝置視為既可以是實現方法的軟體模組又可以是硬體部件內的結構。
上述實施例闡明的處理設備、裝置、模組或單元，具體可以由電腦晶片或實體實現，或者由具有某種功能的產品來實現。一種典型的實現設備為電腦。具體地說，電腦例如可以為個人電腦、膝上型電腦、車載人機互動設備、蜂巢式電話、相機電話、智慧型電話、個人數位助理、媒體播放機、導航設備、電子郵件設備、遊戲控制台、平板電腦、可穿戴式設備或者這些設備中的任何設備的組合。
雖然本說明書實施例提供了如實施例或流程圖所述的方法操作步驟，但基於習知或者無創造性的手段可以包括更多或者更少的操作步驟。實施例中列舉的步驟順序僅僅為眾多步驟執行順序中的一種方式，不代表唯一的執行順序。在實際中的裝置或終端產品執行時，可以按照實施例或者附圖所示的方法循序執行或者並存執行(例如，並行處理器或者多執行緒處理的環境，甚至為分散式資料處理環境)。術語“包括”、“包含”或者其任何其他變體意在涵蓋非排他性的包含，從而使得包括一系列要素的過程、方法、產品或者設備不僅包括那些要素，而且還包括沒有明確列出的其他要素，或者是還包括為這種過程、方法、產品或者設備所固有的要素。在沒有更多限制的情況下，並不排除在包括所述要素的過程、方法、產品或者設備中還存在另外的相同或等同要素。
為了描述的方便，描述以上裝置時以功能分為各種模組分別描述。當然，在實施本說明書實施例時可以把各模組的功能在同一個或多個軟體和/或硬體中實現，也可以將實現同一個功能的模組由多個子模組或子單元的組合來實現等。以上所描述的裝置實施例僅僅是示意性的，例如，所述單元的劃分，僅僅為一種邏輯功能劃分，實際實現時可以有另外的劃分方式，例如多個單元或元件可以被結合或者可以整合到另一個系統，或一些特徵可以忽略，或不執行。另一點，所顯示或討論的相互之間的耦合或直接耦合或通信連接可以是透過一些介面，裝置或單元的間接耦合或通信連接，可以是電性，機械或其它的形式。
本領域技術人員也知道，除了以純電腦可讀程式碼方式實現控制器以外，完全可以透過將方法步驟進行邏輯程式設計來使得控制器以邏輯閘、開關、特殊應用積體電路、可程式設計邏輯控制器和嵌入式微控制器等的形式來實現相同功能。因此這種控制器可以被認為是一種硬體部件，而對其內部包括的用以實現各種功能的裝置也可以視為硬體部件內的結構。或者甚至，可以將用以實現各種功能的裝置視為既可以是實現方法的軟體模組又可以是硬體部件內的結構。
本發明是參照根據本發明實施例的方法、設備(系統)、和電腦程式產品的流程圖和/或方塊圖來描述的。應理解可由電腦程式指令來實現流程圖和/或方塊圖中的每一個流程和/或方塊、以及流程圖和/或方塊圖中的流程和/或方塊的結合。可提供這些電腦程式指令到通用電腦、專用電腦、嵌入式處理機或其他可程式設計資料處理設備的處理器以產生一個機器，使得透過電腦或其他可程式設計資料處理設備的處理器執行的指令產生用以實現在流程圖中的一個流程或多個流程和/或方塊圖中的一個方塊或多個方塊中指定的功能的裝置。
這些電腦程式指令也可被儲存在能引導電腦或其他可程式設計資料處理設備以特定方式操作的電腦可讀記憶體中，使得儲存在該電腦可讀記憶體中的指令產生包括指令裝置的製造品，該指令裝置實現在流程圖中的一個流程或多個流程和/或方塊圖中的一個方塊或多個方塊中指定的功能。
這些電腦程式指令也可被裝載到電腦或其他可程式設計資料處理設備上，使得在電腦或其他可程式設計設備上執行一系列操作步驟以產生電腦實現的處理，從而在電腦或其他可程式設計設備上執行的指令提供用以實現在流程圖中的一個流程或多個流程和/或方塊圖中的一個方塊或多個方塊中指定的功能的步驟。
在一個典型的配置中，計算設備包括一個或多個處理器(CPU)、輸入/輸出介面、網路介面和記憶體。
記憶體可能包括電腦可讀媒體中的非永久性記憶體，隨機存取記憶體(RAM)和/或非易失性記憶體等形式，如唯讀記憶體(ROM)或快閃記憶體(flash RAM)。記憶體是電腦可讀媒體的示例。
電腦可讀媒體包括永久性和非永久性、可移動和非可移動媒體可以由任何方法或技術來實現資訊儲存。資訊可以是電腦可讀指令、資料結構、程式的模組或其他資料。電腦的儲存媒體的例子包括，但不限於相變記憶體(PRAM)、靜態隨機存取記憶體(SRAM)、動態隨機存取記憶體(DRAM)、其他類型的隨機存取記憶體(RAM)、唯讀記憶體(ROM)、電可擦除可程式設計唯讀記憶體(EEPROM)、快閃記憶體或其他記憶體技術、唯讀光碟唯讀記憶體(CD-ROM)、數位多功能光碟(DVD)或其他光學儲存、磁盒式磁帶，磁帶磁磁片儲存或其他磁性儲存裝置或任何其他非傳輸媒體，可用來儲存可以被計算設備訪問的資訊。按照本文中的界定，電腦可讀媒體不包括暫態性電腦可讀媒體(transitory media)，如調變的資料信號和載波。
本領域技術人員應明白，本說明書的實施例可提供為方法、系統或電腦程式產品。因此，本說明書實施例可採用完全硬體實施例、完全軟體實施例或結合軟體和硬體態樣的實施例的形式。而且，本說明書實施例可採用在一個或多個其中包含有電腦可用程式碼的電腦可用儲存媒體(包括但不限於磁碟記憶體、CD-ROM、光學記憶體等)上實施的電腦程式產品的形式。
本說明書實施例可以在由電腦執行的電腦可執行指令的一般上下文中描述，例如程式模組。一般地，程式模組包括執行特定任務或實現特定抽象資料類型的常式、程式、物件、元件、資料結構等等。也可以在分散式計算環境中實踐本說明書實施例，在這些分散式計算環境中，由透過通信網路而被連接的遠端處理設備來執行任務。在分散式計算環境中，程式模組可以位於包括儲存裝置在內的本地和遠端電腦儲存媒體中。
本說明書中的各個實施例均採用漸進的方式來描述，各個實施例之間相同相似的部分互相參見即可，每個實施例重點說明的都是與其他實施例的不同之處。尤其，對於系統實施例而言，由於其基本相似於方法實施例，所以描述的比較簡單，相關之處參見方法實施例的部分說明即可。在本說明書的描述中，參考術語“一個實施例”、“一些實施例”、“示例”、“具體示例”、或“一些示例”等的描述意指結合該實施例或示例描述的具體特徵、結構、材料或者特點包含於本說明書實施例的至少一個實施例或示例中。在本說明書中，對上述術語的示意性表述不必須針對的是相同的實施例或示例。而且，描述的具體特徵、結構、材料或者特點可以在任一個或多個實施例或示例中以合適的方式結合。此外，在不相互矛盾的情況下，本領域的技術人員可以將本說明書中描述的不同實施例或示例以及不同實施例或示例的特徵進行結合和組合。
以上所述僅為本說明書實施例的實施例而已，並不用來限制本說明書實施例。對於本領域技術人員來說，本說明書實施例可以有各種更改和變化。凡在本說明書實施例的精神和原理之內所作的任何修改、等同替換、改進等，均應被包含在本說明書實施例的申請專利範圍的範疇之內。In order to enable those skilled in the art to better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present specification. Obviously, the described The examples are only a part of examples in this specification, but not all examples. Based on one or more embodiments in the present specification, all other embodiments obtained by a person having ordinary skill in the art without creative efforts should fall within the protection scope of the embodiments of the present specification.
In one or more embodiments provided in this specification, the hardware attribute information of the terminal device can be collected in advance, and then a classification model can be constructed to identify the real brand model (identify the real brand and model), which can effectively identify Tampering with device brand and model information. It should be noted that the real device model information identified by the device identification model mentioned in the embodiments of the present invention refers to the device brand and model information output by the device identification model in response to the device request data of the device to be identified, and the final output result Reliability depends mainly on the model algorithm used and the training data used. The "real" device model information may be different from the actual brand model of the actual device.
In the embodiments of the present specification, multiple classification algorithms may be used to construct a device identification model. For example, in one embodiment, a GBM algorithm (Gradient Tree Boosting Algorithm) can be used for model training, as shown in the processing procedure shown in FIG. 1. Of course, you can also use GBDT (Gradient Boosting Decision Tree) or xgboost (Extreme Gradient Boosting) based boosting algorithms (methods used to improve the accuracy of weak classification algorithms). Or, in other embodiments, algorithms such as LR (Logistic Regression, logistic regression), and deep learning (deep learning) may be used to construct the model. The training data used in the model construction training provided by the embodiment provided in this specification includes at least the device hardware information of the terminal device. The known and reliable hardware attribute data is used to train the device identification model, determine the parameters in the model, and then use it online. When the device request data of the device to be identified is received, the real device brand model can be identified, and the behavior of tampering with the brand or model information can be effectively identified.
Taking the application scenario of mobile phone terminal equipment model recognition as an example, during the model training phase, hardware device attribute information of different brands and models of mobile phones can be collected. Generally, a mobile phone brand can correspond to multiple models of mobile phones. During the training data acquisition process, the minimum number of devices corresponding to each brand model can be set to ensure the reliability of the training data and the accuracy of the output results. Considering the type distribution and development status of mobile phone brands and models, in one embodiment of the present invention, it is possible to set at least 100 devices corresponding to each brand, and among them, there are at least 10 devices per model. After the comparison of actual experimental results, the training data obtained by the above method can not only obtain data of a large number of training samples, reduce costs, and at the same time enable the device recognition model to output results with higher recognition accuracy.
The training data used by the device identification model can include multiple types of data information, but at least one piece of device hardware information. The device hardware information may include an identification mark of a unit component or a combination of components on the terminal device, such as a motherboard model, an international mobile equipment identity code IMEI, a MAC address, a ROM name, and the like. In an actual scenario, the training data usually uses multiple hardware device information, which can more effectively and reliably identify the behavior of tampering with one or more of the hardware device information. Of course, the training data may also include identification information formed by other software or software + hardware combination on the terminal device, such as International Mobile Subscriber Identity IMSI, equipment system version information, and the like.
After using the training data to train the adopted device recognition model, it can be used online. When the device model of the device to be identified needs to be identified, the device request data of the device to be identified may be requested, and then the processor inputs the device request data into the constructed device identification model for processing. The device identification model may output a corresponding brand model classification result based on the obtained device request data. In some implementation scenarios, when the computer processing capability is running, the identification device can also be identified and processed while the device identification model is being constructed and trained. That is, the embodiments provided in this specification can be trained offline under the device identification model. After completion, it can be used online. It can also be used to build or train device identification models based on platforms or cloud computing systems in real time to process the device request data of the identified devices. Alternatively, the device identification model can also be updated and maintained online, or there are multiple types of device identification models in the online system (server, server cluster, or decentralized server). The device request data can be analyzed and processed first, and then matched. The device identification model that is optimal (selects the most applicable device identification model based on the material information included in the device request data actually obtained) corresponding to the device request data is processed.
The following describes a specific implementation scenario of a mobile phone brand and model as an example. Specifically, FIG. 2 is a schematic flowchart of an embodiment of a device model identification method provided in this specification. Although this specification provides method operation steps or device structures as shown in the following embodiments or drawings, based on the knowledge or without creative labor, the method or device may include more or less operations after the merger Step or module unit. Among the steps or structures that do not logically have the necessary causal relationship, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments of the present specification or the drawings. When the method or the module structure is applied to an actual device, server, or end product, the method or the module structure shown in the embodiment or the drawings may be executed sequentially or concurrently (for example, a parallel processor). Or multi-threaded processing environment, even including distributed processing, server cluster implementation environment).
Of course, the description of the following embodiments does not limit other technical solutions that can be extended based on this specification. For example, in other implementation scenarios, the implementation provided in this specification can also be applied to implementation scenarios of non-mobile terminal device model identification, such as PC terminals, shared vehicle equipment, and other special equipment. A specific embodiment is shown in FIG. 2. A method for identifying a device model provided in this specification may include:
S0: Obtain device request data of the device to be identified, where the device request data includes at least device hardware information;
S2: Use the constructed device identification model to identify the device request data to obtain the real device model of the device to be identified. The device identification model uses training data including at least the device hardware information for training and output. Classification algorithm of device brand model.
The method provided in this embodiment can be used on the server side. The server may include a separate server, a server cluster, a decentralized system server, or a server that processes data requested by the device in combination with other related data processing system servers (such as a server identifying the device to be processed and a server Train the server building the device recognition model). The server may obtain the device request data of the device to be identified. Of course, the device request data may include device hardware information. In some application scenarios, in the process of identifying the device model, the terminal device can usually be designated to upload a predetermined number of device hardware information, but due to rights or other reasons, the device information uploaded by the terminal device may include some of the predetermined device requests Data, or even device hardware information. At this time, the corresponding prompt information can be issued to request permission to open hardware device information or perform other processing because there is no device hardware information. Specifically, a corresponding policy can be formulated according to the actual application scenario.
As mentioned above, in the method described in the embodiment of the present specification, the training data used for model training may include data information of types of device hardware and software. In an embodiment provided in this specification, the training data may include at least one of the following:
International Mobile Equipment Identity IMEI, International Mobile Subscriber Identity IMSI, wired / wireless media access control address MAC / WIFI-MAC, Bluetooth address Bluetooth, resolution, motherboard model, read-only memory rom name.
Of course, in addition to the above, training data composed of other hardware data information may also be included. In the above training materials, IMEI usually includes the following data fields:
TAC = Type Approval Code (first 2 digits = country code)
FAC = Final Assembly Code (For Nokia phones FAC = 51)
SNR = Serial Number
SP = Spare (always SP = 0) standby number.
Generally, the IMSI number is in E.212 format, with a total length of 16 digits. It consists of three parts: MCC + MNC + MSIN, of which:
MCC: mobile country code, three digits, such as 460 for China;
MNC: mobile network number, two digits. For example, China Mobile's MNC is 00 (01 for China Unicom and 02 for Mobile 159 new number), which can effectively identify the device bound to the mobile communication operator terminal.
MSIN: mobile customer identification number, such as the unique identification code of a mobile station in a PLMN (Public Land Mobile Network, Public Land Mobile Network), MSIN = H0H1H2H3 (S) XXXXXX (11 digits in total).
When using IMEI and IMSI training data, you can cut IMEI and IMSI into the above sections, and by identifying some of the field information, you can programmatically reflect the information related to the mobile phone brand.
Of course, it can also include wired or wireless MAC address, mobile phone screen resolution, motherboard manufacturer and model used, etc. Therefore, in another embodiment of the method provided in this specification, the training data may include at least one of the following:
International Mobile Equipment Identity, International Mobile Subscriber Identity, Wired / Wireless Media Access Control Address, Bluetooth Address, Resolution, Motherboard Model, Read-Only Memory Name.
In this way, not only the validity of data acquisition can be guaranteed, but also the type of terminal data acquisition and network overhead can be reduced.
It should be noted that the device model output by the device identification model may include one or more of a device name, a model name, a brand name, and the like. For example, the output result may be brand information "Xiaomi", or "Xiaomi" -note2 ", even in some application scenarios, you can only output the model information (applicable to cases where the model information under different brand names are different). In order to facilitate uniform description, in some embodiments of the present specification, the results output by the device recognition model may be collectively referred to as device model information, but it is not limited to including information of a device, a brand, and a model.
FIG. 3 is a schematic diagram of a process of identifying a brand and a model of a mobile phone terminal based on a GBM algorithm provided in this specification. In FIG. 3, a training label may be generated based on the model attribute data obtained actively or reported by the device, and the label data may specifically be “xiaomi note2”, “oppo r9”, “vivo x7”, and the like. In the GBM algorithm, a new subtree can be constructed by learning from the previous tree residuals. The optimization of weight value can refer to classical algorithms such as adaboosting. The tree construction process is mainly a standard tree generation algorithm. After the model is calculated, the probability of each classification can be calculated for each sample, the maximum probability is taken as the predicted classification, and then compared with the real classification to determine the accuracy, coverage and other indicators. Relevant indicators can be used to evaluate the effect of the model, adjust parameters, and optimize it. For the device to be identified, the corresponding device information can be extracted to obtain the device request data. Then use the learned GBM model to score the device request data, and the classification with the highest score is used as the real brand model.
In another embodiment of the method provided in this specification, training data may be further filtered and filtered, using original and real hardware data information of the device. Specifically, in another embodiment of the method, the training data is subjected to at least one of the following filtering processes:
Delete training data to obtain the system's highest permission operation (root);
The training data contained in the message intercepted by the hook mechanism is deleted.
The device information passing through the hook and root may contain false data, so in this embodiment, these false data can be filtered out. Among them, the hook (hook) is actually a program segment that processes messages. It is hooked into the system through system calls. Whenever a specific message is sent, the hook subroutine captures the message before reaching the destination window, that is, the hook function gets control first. In this embodiment, filtering of the request data of the device that performs root and hook can further improve the accuracy of model training and the reliability of output results. Of course, the actual training data acquisition can set the type or quantity of data and corresponding acquisition requirements, such as at least three types of hardware information and at least 100 devices corresponding to a brand. After the collection is completed, the training data is screened or a certain strategy is used to identify whether the data has been modified by root or hook during the collection.
As mentioned above, in one or more embodiments of the present specification, the device identification model can be generated in an offline pre-built manner, and can be used for training and marking after using training data. This specification does not exclude that the device identification model is constructed or updated / maintained online. With sufficient computer capabilities, the device identification model can be constructed online. Of course, when the performance of the computer permits, the hardware device can also be obtained through real-time calculation by the real-time streaming engine. The hardware device can be used online and synchronized to identify the device brand model.
In some embodiments, the device identification model can calculate classification labels for multiple device models based on device request data, and each classification label can have a corresponding probability value or score (the value of the score can also be considered as the probability size) A). In some optional embodiments, the calculated classification labels may be output in whole or in part, and the user may manually or further determine the real brand model. In another embodiment of the method provided in this specification, a probability value range may be set, and a classification label within the probability value range is used as the identified real device model. Specifically, the obtaining the real device model of the device to be identified may include:
Calculating the probability value of the device to be identified corresponding to the corresponding classification label of the device identification model based on the device request data;
The classification label corresponding to the predetermined probability value range is used as the real device model of the device to be identified.
In this way, in some cases, it is possible to output real device model information to which two or more identified devices to be identified belong. If all the recognition results do not meet the predetermined probability value, it can be determined as unrecognizable or the equipment information is invalid, or other processing methods. Of course, in other embodiments, when the device request data corresponds to multiple classification tags, the corresponding classification tag with the highest score or the highest probability value may be used as the real device model of the device to be identified.
In another embodiment provided in this specification, the outputted real device model may further include reliability evaluation data of the device to be identified belonging to the classification label, and the reliability evaluation data is based on a probability corresponding to the classification label The value is determined. For example, when the mobile phone model is output, the reliability evaluation data of the mobile phone is also output. For example, based on the uploaded device request information, it is identified as the output of xiaomi note2, but the score is only 41 points (or the probability value is 0.41), which can be used as Whether to use the model to obtain the output of the actual device model as a reference for the actual model, to provide more data support for the identification of the device and facilitate the user's decision.
The specific classification label can be determined according to the actual application scenario. In some application scenarios of real phone model identification in this manual, the classification label may include the brand name of the terminal device and the model corresponding to the brand name. This embodiment may include any one of a default brand name or a default model name. In this way, in the implementation scenario of mobile phone brand and model identification, the brand and model information and the corresponding score (or probability) can be output more intuitively, which is convenient for the user to make decisions and improve the user experience.
The method embodiments provided in the embodiments of this specification may be executed in a mobile terminal, a computer terminal, a server, or a similar computing device. Taking running on a server as an example, FIG. 4 is a block diagram of a hardware structure of a server for identifying damaged parts of a vehicle according to an embodiment of the present invention. As shown in FIG. 4, the server 10 may include one or more (only one shown in the figure) a processor 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) ), A memory 104 for storing data, and a transmission module 106 for communication functions. Persons of ordinary skill in the art can understand that the structure shown in FIG. 4 is only schematic, and it does not limit the structure of the electronic device. For example, the server 10 may further include more or fewer components than those shown in FIG. 4, and may further include other processing hardware, such as a database or a multi-level cache, or have a configuration different from that shown in FIG. 4. .
The memory 104 may be used to store software programs and modules of application software, such as program instructions / modules corresponding to the search method in the embodiment of the present invention. The processor 102 runs the software programs and modules stored in the memory 104. Therefore, various functional applications and data processing are performed, that is, the processing method for displaying the content of the navigation interactive interface is implemented. The memory 104 may include high-speed random access memory, and may further include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely disposed with respect to the processor 102, and these remote memories may be connected to the computer terminal 10 through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
The transmission module 106 is used to receive or send data through a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network interface controller (NIC), which can be connected to other network devices through a base station to communicate with the Internet. In one example, the transmission module 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
Based on the device type identification method described above, this specification also provides a device type identification device. The device may include a system (including a distributed system), software (application), a module, a component, a server, a client, etc. that uses the method described in the embodiments of the present specification, and a device device that combines necessary implementation hardware . Based on the same innovative concept, the processing device in one embodiment provided in this specification is as described in the following embodiments. Since the implementation solution of the device to solve the problem is similar to the method, the implementation of the specific processing device in the embodiment of this specification may refer to the implementation of the foregoing method, and the duplicated details are not described again. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and conceived. Specifically, as shown in FIG. 5, FIG. 5 is a schematic diagram of a module structure of an embodiment of a device type identification device provided on the server side provided in this specification, and may specifically include:
The device data obtaining module 101 may be used to obtain device request data of a device to be identified, where the device request data includes at least device hardware information;
The identification model processing module 102 may use the constructed device identification model to identify and process the device request data to obtain the real device model of the device to be identified, and the device identification model uses at least the device hardware information. The training data is used to train and output the classification algorithm of the device brand model.
The device identification model can be generated in an offline pre-built manner, and can be used for training and marking by using training data. This specification does not exclude that the device identification model is constructed or updated / maintained online. With sufficient computer capabilities, the device identification model can be constructed online. Of course, when the performance of the computer permits, the hardware device can also be obtained through real-time calculation by the real-time streaming engine. The hardware device can be used online and synchronized to identify the device brand model.
In one embodiment, the training data used to construct the device identification model in the recognition processing module 102 includes at least one of the following:
International Mobile Equipment Identity, International Mobile Subscriber Identity, Wired / Wireless Media Access Control Address, Bluetooth Address, Resolution, Motherboard Model, Read-Only Memory Name.
In another embodiment, the training data is subjected to at least one of the following filtering processes:
Delete training materials for obtaining the system's highest permission;
Delete training data contained in messages intercepted by the hook mechanism.
In another embodiment, the real device model of the device to be identified obtained by the identification processing module 102 may include:
Calculating the probability value of the device to be identified corresponding to the corresponding classification label of the device identification model based on the device request data;
The classification label corresponding to the predetermined probability value range is used as the real device model of the device to be identified.
The predetermined probability range may be an interval or a maximum probability value.
In another embodiment of the device, not only the real device model of the device to be identified, but also the probability value or score corresponding to the output result can be output. Therefore, the real device model may further include reliability evaluation data of the device to be identified belonging to the classification label, and the reliability evaluation data is determined based on a probability value corresponding to the classification label.
In an embodiment of a specific mobile phone brand and model identification application scenario of the device, the classification label includes a brand name of a terminal device and a model corresponding to the brand name.
For specific implementation of the device described in the foregoing embodiments, reference may be made to the description of the related method embodiments, and details are not described herein.
The device model identification method provided by the embodiments of this specification can be implemented by a processor executing corresponding program instructions in a computer, such as using the C ++ language of a Windows operating system on a PC or server, or other systems such as Linux Application design language integrates the necessary hardware to implement, or based on the processing logic of quantum computers to implement. Specifically, in the embodiment in which a processing device for identifying a device model provided in this specification implements the foregoing method, the processing device may include a processor and a memory for storing processor-executable instructions, and the processor executes all Implemented when describing the instruction:
Obtaining device request data of a device to be identified, the device request data including at least device hardware information;
Use the constructed device identification model to identify and process the device request data to obtain the real device model of the device to be identified. The device identification model uses training data including at least the device hardware information to train and output the device brand. Classification algorithm for models.
The above instructions can be stored in a variety of computer-readable storage media. The computer-readable storage medium may include a physical device for storing information, and the information may be digitized and then stored by using a medium such as electricity, magnetism, or optics. The computer-readable storage medium described in this embodiment may include: a device for storing information using electric energy, such as various types of memory, such as RAM, ROM, etc .; a device for storing information using magnetic energy, such as hard disk, floppy disk, Magnetic tape, core memory, bubble memory, U disk; devices that use optical methods to store information, such as CDs or DVDs. Of course, there are other ways of readable storage media, such as quantum memory, graphene memory, and so on. The instructions involved in the device or server or client or processing device described above are the same as described above.
It should be noted that the device and processing equipment described in the embodiments of the present specification, according to the description of the related method embodiments, may also include other implementations, such as deleting training data for obtaining the system's highest permission operation, or deleting the hook mechanism. Training data included in the intercepted message. For specific implementation manners, reference may be made to the description of the method embodiments, and details are not described herein.
Each embodiment in this specification is described in a gradual manner, and the same or similar parts between the various embodiments may be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the hardware + programming embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts may refer to the description of the method embodiment.
The specific embodiments of the present specification have been described above. Other embodiments are within the scope of the accompanying patent applications. In some cases, the actions or steps described in the scope of the patent application may be performed in a different order than in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In some embodiments, multiplexing and parallel processing are also possible or may be advantageous.
Although the present invention provides the operation steps of the method as described in the embodiment or the flowchart, more or less operation steps may be included based on conventional or uninvented labor. The sequence of steps listed in the embodiments is only one way of executing the steps, and does not represent the only sequence of execution. When the actual device or system server product is executed, it may be executed sequentially or concurrently according to the method shown in the embodiment or the accompanying drawings (for example, a parallel processor or a multi-threaded processing environment).
Although the content of the examples in this specification mentions the use of GBM algorithms for model training, IMEI and MAC hardware device information, offline or online construction of models, training data acquisition requirements and screening processing, etc. for data acquisition, storage, interaction, etc. Operations, data descriptions, calculations, judgments, etc. However, the embodiments of the present specification are not limited to situations that must conform to industry communication standards, standard classification model processing, communication protocols and standard data models / templates, or the embodiments described in this specification. Certain industry standards or implementations that are modified based on implementations using custom methods or examples can also achieve the same, equivalent or similar, or predictable implementation effects of the above embodiments. Embodiments obtained by applying these modified or deformed data acquisition, storage, judgment, processing methods, etc., may still fall within the scope of optional implementations of this specification.
In the 1990s, for a technical improvement, it can be clearly distinguished whether it is an improvement in hardware (for example, the improvement of circuit structures such as diodes, transistors, switches, etc.) or an improvement in software (for method and process Improve). However, with the development of technology, the improvement of many methods and processes can be regarded as a direct improvement of the hardware circuit structure. Designers almost always get the corresponding hardware circuit structure by designing the improved method flow program into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user's programming of the device . Designers can program a digital system to "integrate" it on a PLD without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, today, instead of making integrated circuit chips manually, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development. The original source code before compilation must also be written in a specific programming language. This is called the Hardware Description Language (HDL), and HDL is not only one, but there are many types, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used are Very-High-Speed Integrated Circuit Hardware Description Language (VHDL) and Verilog. Those skilled in the art should also be clear that as long as the method flow is logically programmed and integrated into the integrated circuit using the above-mentioned several hardware description languages, the hardware circuit implementing the logic method flow can be easily obtained.
The controller may be implemented in any suitable way, for example, the controller may adopt, for example, a microprocessor or processor and a computer storing computer-readable code (for example, software or firmware) executable by the (micro) processor. Readable media, logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, the memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable code manner, it is entirely possible to make the controller logically gate, switch, special application integrated circuit, and programmable design by logic programming the method steps. Logic controller and embedded microcontroller to achieve the same function. Therefore, the controller can be considered as a hardware component, and the devices included in it to implement various functions can also be considered as the structure inside the hardware component. Or even, a device for implementing various functions can be regarded as a structure that can be both a software module implementing the method and a hardware component.
The processing equipment, devices, modules, or units described in the above embodiments may be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation is a computer. Specifically, the computer may be, for example, a personal computer, a laptop, an in-vehicle human-machine interactive device, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, or a game control. Desk, tablet, wearable device, or a combination of any of these devices.
Although the embodiments of the present specification provide method operation steps as described in the embodiments or flowcharts, conventional or non-creative means may include more or fewer operation steps. The sequence of steps listed in the embodiments is only one way of executing the steps, and does not represent the only sequence of execution. When the actual device or terminal product is executed, it may be executed sequentially or concurrently according to the method shown in the embodiment or the accompanying drawings (for example, a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "including,""including," or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, product, or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed Elements, or elements that are inherent to such a process, method, product, or device. Without further limitation, it does not exclude that there are other identical or equivalent elements in the process, method, product or equipment including the elements.
For the convenience of description, when describing the above device, the functions are divided into various modules and described separately. Of course, when implementing the embodiments of this specification, the functions of each module may be implemented in the same software or multiple software and / or hardware, or the module that implements the same function may be implemented by multiple submodules or subunits. Combining to achieve etc. The device embodiments described above are only schematic. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or elements may be combined or integrated. To another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, which may be electrical, mechanical or other forms.
Those skilled in the art also know that, in addition to implementing the controller in pure computer-readable code, it is entirely possible to make the controller logic gates, switches, special application integrated circuits, and programmable logic by programming logic steps in the method steps. Controller and embedded microcontroller to achieve the same function. Therefore, such a controller can be considered as a hardware component, and the device included in the controller to implement various functions can also be considered as a structure within the hardware component. Or even, a device for implementing various functions can be regarded as a structure that can be both a software module implementing the method and a hardware component.
The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and a combination of the flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special purpose computer, embedded processor, or other programmable data processing device to generate a machine for instructions executed by the processor of the computer or other programmable data processing device Means are generated to implement the functions specified in one or more of the flowcharts and / or one or more of the blocks in the block diagrams.
These computer program instructions can also be stored in computer readable memory that can guide a computer or other programmable data processing device to operate in a specific manner, such that the generation of instructions stored in the computer readable memory includes the manufacture of a command device The instruction device implements a function specified in one or more processes in the flowchart and / or in one or more blocks in the block diagram.
These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operating steps can be performed on the computer or other programmable equipment to generate computer-implemented processing, thereby designing the computer or other programmable The instructions executed on the device provide steps to implement the functions specified in one or more processes in the flowchart and / or one or more blocks in the block diagram.
In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.
Memory may include non-permanent memory, random access memory (RAM), and / or non-volatile memory in computer-readable media, such as read-only memory (ROM) or flash memory ( flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media includes permanent and non-permanent, removable and non-removable media. Information can be stored by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), and other types of random access memory (RAM) , Read-only memory (ROM), electrically erasable and programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only disc read-only memory (CD-ROM), digital multifunction Optical discs (DVDs) or other optical storage, magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transmitting media may be used to store information that can be accessed by computing devices. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
Those skilled in the art should understand that the embodiments of the present specification may be provided as a method, a system, or a computer program product. Therefore, the embodiments of the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present specification may use a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable code. form.
The embodiments of this specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The embodiments of the present specification can also be practiced in decentralized computing environments. In these decentralized computing environments, tasks are performed by remote processing devices connected through a communication network. In a decentralized computing environment, program modules can be located in local and remote computer storage media, including storage devices.
Each embodiment in this specification is described in a gradual manner, and the same or similar parts between the various embodiments may be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For the relevant part, refer to the description of the method embodiment. In the description of this specification, the description with reference to the terms “one embodiment”, “some embodiments”, “examples”, “specific examples”, or “some examples” and the like means specific features described in conjunction with the embodiments or examples , Structure, materials, or features are included in at least one embodiment or example of an embodiment of the present specification. In this specification, the schematic expressions of the above terms are not necessarily directed to the same embodiment or example. Moreover, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. In addition, without any contradiction, those skilled in the art may combine and combine different embodiments or examples and features of the different embodiments or examples described in this specification.
The above descriptions are merely examples of the embodiments of the present specification, and are not intended to limit the embodiments of the present specification. For those skilled in the art, the embodiments of the present specification may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present specification shall be included in the scope of patent application of the embodiments of the present specification.

10‧‧‧伺服器10‧‧‧Server

101‧‧‧設備資料獲取 101‧‧‧ Acquisition of equipment information

102‧‧‧識別模型處理模組 102‧‧‧Identification model processing module

104‧‧‧非易失性記憶體 104‧‧‧Non-volatile memory

106‧‧‧傳輸模組 106‧‧‧Transmission Module

為了更清楚地說明本說明書實施例或現有技術中的技術方案，下面將對實施例或現有技術描述中所需要使用的附圖作簡單地介紹，顯而易見地，下面描述中的附圖僅僅是本說明書中記載的一些實施例，對於本領域普通技術人員來講，在不付出創造性勞動性的前提下，還可以根據這些附圖而獲得其他的附圖。In order to more clearly explain the embodiments of the present specification or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only the present invention. For some ordinary people skilled in the art, some embodiments described in the specification can also obtain other drawings according to these drawings without paying creative labor.

圖1是本說明書所述方法中一個採用GBM演算法進行模型訓練的處理示意圖； 1 is a schematic diagram of a model training process using a GBM algorithm in the method described in this specification;

圖2是本說明書提供的所述一種設備型號識別方法實施例的流程示意圖； FIG. 2 is a schematic flowchart of an embodiment of a device model identification method provided in this specification; FIG.

圖3是本說明書提供的一種基於GBM演算法進行手機終端的品牌和型號識別的處理過程示意圖； 3 is a schematic diagram of a process for identifying a brand and a model of a mobile phone terminal based on a GBM algorithm provided in the present specification;

圖4是本發明實施例的一種識別車輛受損部件的伺服器的硬體結構方塊圖； 4 is a block diagram of a hardware structure of a server for identifying damaged parts of a vehicle according to an embodiment of the present invention;

圖5是本說明書提供的一種設備型號識別裝置實施例的模組結構示意圖。 FIG. 5 is a schematic diagram of a module structure of an embodiment of a device model identification device provided in this specification.

Claims

A method for identifying a device model, the method includes: Obtain device request data for the device to be identified, the device request data including at least device hardware information; and The constructed device identification model is used to identify and process the device request data to obtain the real device model of the device to be identified. The device identification model is trained using training data including at least hardware information of the device, and the classification calculation of the output brand model is output. law.

The method according to claim 1, wherein the training data includes at least one of the following: International Mobile Equipment Identity, International Mobile Subscriber Identity, Wired / Wireless Media Access Control Address, Bluetooth Address, Resolution, Motherboard Model, Read-Only Memory Name.

According to the method described in claim 1, the training data is subjected to at least one of the following filtering processes: Delete training materials for obtaining the system's highest permission; and Delete the training data contained in the message intercepted by the hook mechanism.

According to the method described in claim 1, obtaining the real device model of the device to be identified includes: Calculating the probability value of the device to be identified corresponding to the corresponding classification label of the device identification model based on the device request data; and The classification label corresponding to the predetermined probability value range is used as the real device model of the device to be identified.

According to the method described in claim 4, the real device model further includes reliability evaluation data of the device to be identified belonging to the classification label, and the reliability evaluation data is determined based on the probability value corresponding to the classification label.

The method according to claim 5, wherein the classification label includes a brand name of the terminal device and a model corresponding to the brand name.

A device model identification device, the device includes: A device data acquisition module for obtaining device request data of a device to be identified, the device request data including at least device hardware information; and The recognition model processing module uses the constructed equipment recognition model to identify and process the equipment request data to obtain the real equipment model of the equipment to be identified. The equipment recognition model uses training data including at least hardware information of the equipment for training and output. Classification algorithm of device brand model.

The device according to claim 7, the training data used in constructing the device identification model in the recognition processing module includes at least one of the following: International Mobile Equipment Identity, International Mobile Subscriber Identity, Wired / Wireless Media Access Control Address, Bluetooth Address, Resolution, Motherboard Model, Read-Only Memory Name.

According to the device of claim 7, the training data is subjected to at least one of the following filtering processes: Delete training materials for obtaining the system's highest permission; and Delete training data contained in messages intercepted by the hook mechanism.

According to the apparatus described in claim 7, the real device model of the device to be identified obtained by the identification processing module may include: Calculating the probability value of the device to be identified corresponding to the corresponding classification label of the device identification model based on the device request data; and The classification label corresponding to the predetermined probability value range is used as the real device model of the device to be identified.

According to the device of claim 10, the real device model further includes reliability evaluation data of the classified label belonging to the classification label, and the reliability evaluation data is determined based on the probability value corresponding to the classification label.

The device according to claim 11, wherein the classification label includes a brand name of the terminal device and a model corresponding to the brand name.

A processing device for identifying a device model includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, it realizes: Obtain device request data for the device to be identified, the device request data including at least device hardware information; and The constructed device identification model is used to identify and process the device request data to obtain the real device model of the device to be identified. The device identification model is trained using training data including at least hardware information of the device, and the classification calculation of the output brand model is output. law.