WO2019192260A1 - 一种设备型号识别方法、装置及处理设备 - Google Patents

一种设备型号识别方法、装置及处理设备 Download PDF

Info

Publication number
WO2019192260A1
WO2019192260A1 PCT/CN2019/073913 CN2019073913W WO2019192260A1 WO 2019192260 A1 WO2019192260 A1 WO 2019192260A1 CN 2019073913 W CN2019073913 W CN 2019073913W WO 2019192260 A1 WO2019192260 A1 WO 2019192260A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
identified
data
identification
request data
Prior art date
Application number
PCT/CN2019/073913
Other languages
English (en)
French (fr)
Inventor
任偲
向东
Original Assignee
阿里巴巴集团控股有限公司
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 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2019192260A1 publication Critical patent/WO2019192260A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/70—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
    • G06F21/71—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer to assure secure computing or processing of information
    • G06F21/73—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer to assure secure computing or processing of information by creating or determining hardware identification, e.g. serial numbers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/44—Program or device authentication
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance

Definitions

  • the embodiment of the present specification belongs to the technical field of computer data processing, and in particular, to a device model identification method, device, and processing device.
  • mobile communication terminals such as smart phones
  • smartphones are increasingly important to the daily work, life, social, and consumption of users.
  • smartphone brands and models Users of different value smartphones often have different user consumption abilities, such as high-value mobile phones, and the corresponding users may have stronger spending power.
  • mobile phone insurance products the compensation amount corresponding to different mobile phone models is usually also very different.
  • the device model of the mobile communication terminal is associated with interests in some products, there is a behavior of modifying the device model by modifying the device information, thereby defrauding marketing resources or defrauding insurance. For example, if the user combines a PC (personal computer), a personal computer, or a root (get the system's highest priority) tool, the hardware information is read and modified through a system API (Application Programming Interface).
  • PC personal computer
  • root get the system's highest priority
  • the embodiment of the present specification aims to provide a device model identification method, device and processing device, which can identify a real brand model by constructing a classification model by using basic hardware attributes of the device. It can effectively identify the behavior of tampering with brand model information and identify the real brand and model.
  • a device model identification method, device and processing device provided by embodiments of the present specification are implemented by the following methods:
  • a device model identification method comprising:
  • a device model identification device comprising:
  • a device data obtaining module configured to acquire device request data of the device to be identified, where the device request data includes at least device hardware information
  • Identifying a model processing module performing identification processing on the device request data by using the constructed device identification model, and obtaining a real device model of the device to be identified, wherein the device identification model is trained by using training data including at least the device hardware information. , the classification algorithm of the output device brand model.
  • a processing device for identifying a device model comprising a processor and a memory for storing processor-executable instructions, the processor implementing the instructions to:
  • the device model identification method, device and processing device provided by the embodiments of the present specification have basic hardware attributes, and the device identification model is trained by using known reliable hardware attribute data, and the parameters in the model are determined, and then used online.
  • the real device brand model can be identified, and the behavior of tampering with the brand or model information is effectively recognized.
  • FIG. 1 is a schematic diagram of a process of model training using the GBM algorithm in the method described in the present specification
  • FIG. 2 is a schematic flow chart of an embodiment of a device model identification method provided by the present specification
  • FIG. 3 is a schematic diagram of a processing procedure for identifying a brand and a model of a mobile terminal based on a GBM algorithm provided by the present specification
  • FIG. 4 is a block diagram showing the hardware structure of a server for identifying a damaged component of a vehicle according to an embodiment of the present invention
  • FIG. 5 is a schematic structural diagram of a module of an apparatus model identification apparatus provided by the present specification.
  • the hardware attribute information of the terminal device may be collected in advance, and then the classification model is constructed, and the real brand model is identified (identifying the real brand and model), and the tampering can be effectively recognized.
  • the behavior of equipment brand and model information 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.
  • the reliability of the results depends primarily on the model algorithm employed and the training data used.
  • the "real" device model information may be allowed to differ from the actual brand model of the actual device.
  • a device identification model can be constructed by using multiple classification algorithms.
  • the GBM algorithm Gram Tree Boosting Algorithm
  • GBDT Gram Boosting Decision Tree
  • xgboost Extreme Gradient Boosting
  • an algorithm such as LR (Logistic, Logistic Regression) or deep learning (depth learning) may be used to construct the model.
  • the training data used in the implementation of the present specification includes at least the device hardware information of the terminal device, and uses the known reliable hardware attribute data to train the device identification model, determine the parameters in the model, and then use it online.
  • the real device brand model can be identified, and the behavior of tampering with the brand or model information is effectively recognized.
  • the hardware device attribute information of different brands and models of the mobile phone can be collected.
  • a mobile phone brand can correspond to multiple models of mobile phones.
  • the minimum number of devices corresponding to each brand model can be set to ensure the reliability of training data and the accuracy of output results.
  • at least 100 devices corresponding to each brand may be set, and the number of devices of each model is at least 10.
  • the training data used by the device identification model may include multiple types of data information, but at least one device hardware information.
  • the device hardware information may include an identification identifier of a unit component or a combination of components on the terminal device, such as a motherboard model, an international mobile device identity code IMEI, a MAC address, a ROM name, and the like.
  • the training data generally uses multiple pieces of hardware device information, which can more effectively and reliably identify the behavior of tampering with one or more hardware device information.
  • the training data may further include identification information formed by combining other software or software + hardware on the terminal device, such as an international mobile subscriber identity (IMSI), device system version information, and the like.
  • IMSI international mobile subscriber identity
  • the device request data for acquiring the device to be identified may be requested, and then the processor inputs the device request data into the device identification model constructed for processing.
  • the device identification model may output a corresponding brand model classification result based on the acquired device request data.
  • the identification device in the case where the computer processing capability is running, the identification device may be identified and processed while the device identification model is being constructed and trained, that is, the implementation manner provided by the present specification may be completed after the device identification model line is completed.
  • the device identification model may also be updated or maintained online, or the online system (server, server cluster, or distributed server) has multiple types of device identification models, and may first analyze the processing device request data, and then match and The device identification model corresponding to the device request data is optimally selected according to the data information included in the actually acquired device request data to select the most suitable device identification model.
  • the online system server, server cluster, or distributed server
  • FIG. 2 is a schematic flowchart diagram of an embodiment of a device model identification method provided by the present specification.
  • the present specification provides method operation steps or device structures as shown in the following embodiments or figures, there may be more or partial merged fewer operational steps in the method or device based on conventional or no inventive labor. Or module unit.
  • the execution order of the steps or the module structure of the device is not limited to the execution order or the module structure shown in the embodiment or the drawings.
  • server or terminal product of the method or module structure When the device, server or terminal product of the method or module structure is applied, it may be executed sequentially or in parallel according to the method or module structure shown in the embodiment or the drawing (for example, parallel processor or multi-thread processing). Environment, even including distributed processing, server cluster implementation environment).
  • a device model identification method provided by the present specification may include:
  • S0 acquiring device request data of the device to be identified, where the device request data includes at least device hardware information;
  • S2 performing identification processing on the device request data by using the constructed device identification model, and obtaining a real device model of the device to be identified, where the device identification model uses training data including at least the device hardware information to perform training and output devices. Classification algorithm for brand models.
  • the method provided in this embodiment can be used on the server side.
  • the server may comprise a separate server, a server cluster, a distributed system server, or a server that processes device request data in combination with other associated data processing system servers (eg, a server that identifies the device to be processed and a server that trains the device identification model) ).
  • the server may obtain device request data of the device to be identified.
  • the device request data may include device hardware information.
  • the terminal device in the device model identification process, the terminal device may be specified to upload a predetermined plurality of device hardware information. However, due to the rights or other reasons, the device information uploaded by the terminal device may include some predetermined device request data. And even device information has no device hardware information. At this time, the corresponding prompt information may be sent to request the open hardware device information acquisition permission or other processing may be performed because there is no device hardware information, and the corresponding policy may be formulated according to the actual application scenario.
  • the training data used for model training may include type device hardware and software data information.
  • the training data may include at least one of the following:
  • training data composed of other hardware data information may be included.
  • the IMEI usually includes the following data fields:
  • SNR Serial Number serial number
  • the IMSI number is in E.212 format, and the total length of the number is 16 bits. It consists of MCC+MNC+MSIN, among which:
  • MCC Mobile country code, three numbers, such as China 460;
  • MNC mobile network number, two numbers, such as China Mobile's MNC is 00 (Unicom is 01, mobile 159 new segment is 02), which can effectively identify the device bound to the mobile communication carrier.
  • PLMN Public Land Mobile Network
  • the IMEI and IMSI training data can be divided into the above parts, and some of the field information can be identified to reflect the information related to the mobile phone brand.
  • the training data may include at least one of the following:
  • 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, and the output may be a brand information “millet” or “millet”. -note2", even in some application scenarios, it is also possible to output only model information (applicable to different model information under different brand names).
  • the output of the device identification model may be collectively referred to as device model information, but is not limited to including one of the device, the brand, and the model.
  • FIG. 3 is a schematic diagram of a processing procedure for identifying a brand and a model of a mobile terminal based on the GBM algorithm provided by the present specification.
  • the training tag may be generated based on the model attribute data of the active acquisition or the device reporting, and the tag data may specifically be “xiaomi note2”, “oppo r9”, “vivo x7”, and the like.
  • a new subtree can be constructed by learning the last tree residual.
  • Weight value optimization can refer to algorithms such as classic human adaboosting.
  • the tree construction process is mainly a standard tree generation algorithm.
  • the probability of each classification can be calculated for each sample, and the maximum probability is taken as the prediction classification, and then compared with the real classification, and then the accuracy, coverage and other indicators can be determined. Through the relevant indicators, the model effects can be evaluated, parameter adjustment, optimization, and so on.
  • the corresponding device information may be extracted, and the device request data is obtained. Then, using the learned GBM model, the device request data is scored, and the highest score is classified as the real brand model.
  • the training data can be further filtered and filtered using raw, real hardware data information of the device.
  • the training data is subjected to at least one of the following screening processes:
  • the training data contained in the message intercepted by the hook mechanism is deleted.
  • the device information that has been hooked and root may contain spurious data, so these spurious data can be filtered out in this embodiment.
  • hook is actually a program segment that processes the message, and it is hooked into the system through system calls. Whenever a specific message is sent, the hook program first captures the message before it reaches the destination window, that is, the hook function first gains control.
  • the filtering of the request data of the root and hook devices can further improve the training precision of the model and the reliability of the output result.
  • the actual training data collection can set the type or quantity of data to set the corresponding collection requirements, for example, at least three kinds of hardware information, and the number of devices corresponding to one brand is at least 100. After the acquisition is completed, the training data is filtered or a certain strategy is used in the process of collecting to identify whether the data has been modified by root or hook.
  • the device identification model may be generated in an offline pre-built manner, and may be trained and marked using training data and then used online. This specification does not exclude that the device identification model adopts online construction or update/maintenance. When the computer capability is sufficient, the device identification model can be constructed online. Of course, in the case of computer performance, real-time streaming engine real-time calculation can also be used to obtain hardware devices that can be used online simultaneously to identify the device brand model.
  • the device identification model may calculate the classification labels of the multiple device models based on the device request data, and each of the classification labels may have a corresponding probability value or a score (the level of the score may also be regarded as a probability size).
  • the calculated classification label may be output in whole or in part, and the user may manually or further determine the real brand model.
  • a probability value range may be set, and the classification label in the range of the probability value is used as the identified real device model.
  • the obtaining the real device model of the device to be identified may include:
  • the classification label corresponding to the predetermined probability value range is used as the real device model of the device to be identified.
  • the device to be identified belongs. If all the recognition results do not meet the predetermined probability value, it may be determined that the identification is unrecognizable or the device information data is invalid, or other processing methods.
  • the corresponding classification label with the highest score or the highest probability value may be used as the real device model of the device to be identified.
  • the outputted real device model may further include reliability assessment data that the to-be-identified device belongs to the classification label, and the reliability evaluation data is based on a probability corresponding to the classification label. The value is determined. If the mobile phone model is output, the output mobile phone is the reliability evaluation data of this model. For example, based on the uploaded device request data, the output is identified as xiaomi note2, but the score is only 41 points (or the probability value is 0.41), which can be used as Whether the model obtains the output result of the real device model as the reference basis of the actual real model, provides more data support for the device identification, and is convenient for the user to make decisions.
  • the specific classification label can be determined according to the actual application scenario.
  • the classification tag may include the brand name of the terminal device and the model number corresponding to the brand name.
  • any one of the brand name default or the model name default may be included.
  • the brand and model information can be more intuitively outputted, and the corresponding scores (or probabilities) are convenient for the user to make decisions and improve the user experience.
  • FIG. 4 is a block diagram showing the hardware structure of a server for identifying a damaged component of a vehicle according to an embodiment of the present invention.
  • server 10 may include one or more (only one shown) processor 102 (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. It will be understood by those skilled in the art that the structure shown in FIG.
  • server 10 may also include more or fewer components than those shown in FIG. 4, for example, may also include other processing hardware, such as a database or multi-level cache, or have a different configuration than that shown in FIG.
  • the memory 104 can 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, and the processor 102 executes various functions by running software programs and modules stored in the memory 104.
  • Application and data processing that is, a processing method for realizing the content display of the above navigation interaction interface.
  • Memory 104 may include high speed random access memory, and may also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory.
  • memory 104 may further include memory remotely located relative to processor 102, which may be coupled to computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the transmission module 106 is configured to receive or transmit data via a network.
  • the network specific examples described above may include a wireless network provided by a communication provider of the computer terminal 10.
  • the transport module 106 includes a Network Interface Controller (NIC) that can be connected to other network devices through a base station to communicate with the Internet.
  • the transmission module 106 can be a Radio Frequency (RF) module for communicating with the Internet wirelessly.
  • NIC Network Interface Controller
  • RF Radio Frequency
  • the present specification also provides a device model identification device.
  • the apparatus may include a system (including a distributed system), software (applications), modules, components, servers, clients, etc., using the methods described in the embodiments of the present specification, in conjunction with necessary device hardware for implementing the hardware.
  • the processing device in one embodiment provided by this specification is as described in the following embodiments.
  • the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.
  • FIG. 5 is a schematic structural diagram of a module of an apparatus model identification apparatus that can be used on the server side, which may be included in the present disclosure.
  • the device data obtaining module 101 may be configured to acquire device request data of the device to be identified, where the device request data includes at least device hardware information;
  • the identification model processing module 102 may perform identification processing on the device request data by using the constructed device identification model to obtain a real device model of the device to be identified, and the device identification model adopts training data including at least the hardware information of the device.
  • the device identification model may be generated in an offline pre-built manner, and may be trained and marked using training data and then used online. This specification does not exclude that the device identification model adopts online construction or update/maintenance. When the computer capability is sufficient, the device identification model can be constructed online. Of course, in the case of computer performance, real-time streaming engine real-time calculation can also be used to obtain hardware devices that can be used online simultaneously to identify the device brand model.
  • the training data used in the identification processing module 102 to construct the device identification model includes at least one of the following:
  • the training data is subjected to at least one of the following screening processes:
  • the training data contained in the message intercepted by the hook mechanism is deleted.
  • the real device model of the device to be identified obtained by the identification processing module 102 may include:
  • 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.
  • the real device model may further include reliability evaluation data that the device to be identified belongs to the classification label, and the reliability evaluation data is determined based on a probability value corresponding to the classification label.
  • the classification label includes a brand name of the terminal device and a model number corresponding to the brand name.
  • the device model identification method provided by the embodiment of the present specification may be implemented by a processor executing a corresponding program instruction in a computer, such as using a C++ language of a Windows operating system on a PC or a server, or other corresponding to, for example, Linux or a system. Apply the design language to the necessary hardware implementations, or to implement processing logic based on quantum computers.
  • the processing device for identifying the device model provided by the present specification implements the foregoing method
  • the processing device may include a processor and a memory for storing processor executable instructions, and the processor performs the When implemented by instructions:
  • the above instructions may be stored in a variety of computer readable storage media.
  • the computer readable storage medium may include physical means for storing information, which may be digitized and stored in a medium utilizing electrical, magnetic or optical means.
  • the computer readable storage medium of this embodiment may include: means for storing information by means of electrical energy, such as various types of memories, such as RAM, ROM, etc.; means for storing information by magnetic energy means, such as hard disk, floppy disk, magnetic tape, magnetic Core memory, bubble memory, U disk; means for optically storing information such as CD or DVD.
  • electrical energy such as various types of memories, such as RAM, ROM, etc.
  • magnetic energy means such as hard disk, floppy disk, magnetic tape, magnetic Core memory, bubble memory, U disk
  • means for optically storing information such as CD or DVD.
  • quantum memories graphene memories, and the like.
  • the apparatus and the processing device described in the foregoing embodiments of the present disclosure may further include other implementation manners according to the description of the related method embodiments, such as deleting the training data of the highest authority operation of the acquiring system, or deleting the intercepted mechanism.
  • the training data contained in the subsequent message may be made to the description of the method embodiments, and details are not described herein.
  • 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 embodiments of the specification. Certain industry standards, or modifications may be made to the same, equivalent or similar, or post-deformation implementations of the above-described embodiments, even if the modified embodiments are implemented based on the implementations described in the embodiments. Embodiments obtained by applying such modified or modified data acquisition, storage, judgment, processing, etc., may still fall within the scope of alternative embodiments of the present specification.
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • the controller can be implemented in any suitable manner, for example, the controller can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (eg, software or firmware) executable by the (micro)processor.
  • computer readable program code eg, software or firmware
  • examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, The Microchip PIC18F26K20 and the Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic.
  • the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding.
  • a controller can be considered a hardware component, and the means for implementing various functions included therein can also be considered as a structure within the hardware component.
  • a device for implementing various functions can be considered as a software module that can be both a method of implementation and a structure within a hardware component.
  • the processing device, device, module or unit set forth in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function.
  • a typical implementation device is a computer.
  • the computer can be, for example, a personal computer, a laptop computer, a car-mounted human-machine interaction device, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet.
  • a computer, wearable device, or a combination of any of these devices are examples of these devices.
  • the above devices are described as being separately divided into various modules by function.
  • the functions of the modules may be implemented in the same software or software, or the modules that implement the same function may be implemented by multiple sub-modules or a combination of sub-units.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or integrated. Go to another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the 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), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • embodiments of the present specification can be provided as a method, system, or computer program product.
  • embodiments of the present specification can take the form of an entirely hardware embodiment, an entirely software embodiment or a combination of software and hardware.
  • embodiments of the present specification can take the form of a computer program product embodied on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • Embodiments of the present description can be described in the general context of computer-executable instructions executed by a computer, such as a program module.
  • program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types.
  • Embodiments of the present specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network.
  • program modules can be located in both local and remote computer storage media including storage devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Hardware Design (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Software Systems (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Human Resources & Organizations (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Mathematical Physics (AREA)
  • Technology Law (AREA)
  • Telephone Function (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

一种设备型号识别方法、装置及处理设备，所述方法可以包括：获取待识别设备的设备请求数据，所述设备请求数据至少包括设备硬件信息（S0）；利用构建的设备识别模型对所述设备请求数据进行识别处理，得到所述待识别设备的真实设备型号，所述设备识别模型采用至少包括所述设备硬件信息的训练数据进行训练、输出设备品牌型号的分类算法（S2）。能够有效的识别出篡改品牌型号信息的行为。

Description

一种设备型号识别方法、装置及处理设备 技术领域
本说明书实施例方案属于计算机数据处理的技术领域，尤其涉及一种设备型号识别方法、装置及处理设备。
背景技术
目前，移动通信终端(如智能手机)对用户的日常工作、生活、社交、消费等影响越来越重要。而智能手机品牌和型号种类繁多，往往不同价值的智能手机的用户对应不同的用户消费能力，如高价值的手机，对应的用户的消费能力可能会更强。在手机保险产品中，不同的手机型号对应的赔偿金额通常也是会有很大的差异。
因移动通信终端的设备型号在一些产品中关联着利益，因而存在着通过修改设备信息实现修改设备型号，进而骗取营销资源或者骗保等行为。如用户结合PC(personal computer)，个人计算机)端或终端的root(获取系统最高好权项)工具，通过系统API(Application Programming Interface，应用程序编程接口)读取、修改硬件信息。
因此，业内亟需一种可以有效识别设备真实型号信息的解决方案。
发明内容
本说明书实施例目的在于提供一种设备型号识别方法、装置及处理设备，可以用设备基本的硬件属性，通过构建分类模型，对真实的品牌型号进行识别。能够有效的识别出篡改品牌型号信息的行为，标识出真实的品牌和型号。
本说明书实施例提供的一种设备型号识别方法、装置及处理设备是包括以下方式实现的：
一种设备型号识别方法，所述方法包括：
获取待识别设备的设备请求数据，所述设备请求数据至少包括设备硬件信息；
利用构建的设备识别模型对所述设备请求数据进行识别处理，得到所述待识别设备的真实设备型号，所述设备识别模型采用至少包括所述设备硬件信息的训练数据进行训练、输出设备品牌型号的分类算法
一种设备型号识别装置，所述装置包括：
设备数据获取模块，用于获取待识别设备的设备请求数据，所述设备请求数据至少包括设备硬件信息；
识别模型处理模块，利用构建的设备识别模型对所述设备请求数据进行识别处理，得到所述待识别设备的真实设备型号，所述设备识别模型采用至少包括所述设备硬件信息的训练数据进行训练、输出设备品牌型号的分类算法。
一种识别设备型号的处理设备，包括处理器以及用于存储处理器可执行指令的存储器，所述处理器执行所述指令时实现：
获取待识别设备的设备请求数据，所述设备请求数据至少包括设备硬件信息；
利用构建的设备识别模型对所述设备请求数据进行识别处理，得到所述待识别设备的真实设备型号，所述设备识别模型采用至少包括所述设备硬件信息的训练数据进行训练、输出设备品牌型号的分类算法。
本说明书实施例提供的一种设备型号识别方法、装置及处理设备，基本的多种硬件属性，利用已知可靠的硬件属性数据来训练设备识别模型，确定模型中的参数，然后线上使用，在接收到待识别设备的设备请求数据时可以标识出真实的设备品牌型号，有效识别出篡改品牌或型号信息的行为。
附图说明
为了更清楚地说明本说明书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说明书中记载的一些实施例，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是本说明书所述方法中一个采用GBM算法进行模型训练的处理示意图；
图2是本说明书提供的所述一种设备型号识别方法实施例的流程示意图；
图3是本说明书提供的一种基于GBM算法进行手机终端的品牌和型号识别的处理过程示意图；
图4是本发明实施例的一种识别车辆受损部件的服务器的硬件结构框图；
图5是本说明书提供的一种设备型号识别装置实施例的模块结构示意图。
具体实施方式
为了使本技术领域的人员更好地理解本说明书中的技术方案，下面将结合本说明书实施例中的附图，对本说明书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说明书中的一部分实施例，而不是全部的实施例。基于本说明书中的一个或多个实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都应当属于本说明书实施例保护的范围。
本说明书提供的一个或多个实施方案中，可以预先采集终端设备的硬件属性信息，然后构建分类模型，对真实的品牌型号进行识别(标识出真实的品牌和型号)，能够有效的识别出篡改设备品牌、型号信息的行为。需要说明是的是，本申请实施例中所提及的设备识别模型识别出的真实设备型号信息是指设备识别模型响应于待识别设备的设备请求数据而输出的设备品牌、型号信息，最终输出结果的可靠性主要依赖于采用的模型算法和使用的训练数据。所述的“真实”设备型号信息可以允许与实际设备的真实品牌型号不同。
本说明书实施例中可以采用多种分类算法构建设备识别模型。例如一个实施例中可以采用GBM算法(Gradient Tree Boosting Algorithm，梯度树增强算法)进行模型训练，如图1所示的处理过程。当然也可以采用GBDT(Gradient Boosting Decision Tree，梯度提升决策树)或者xgboost(极端梯度上升Extreme Gradient Boosting)等基于boosting算法(用来提高弱分类算法准确度的方法)。或者，其他的实施例中也可以采用LR(Logistic，逻辑回归)、deep learning(深度学习)等算法构建模型。本说明书提供的实施方案在模型构建训练时采用的训练数据至少包括终端设备的设备硬件信息，使用已知可靠的硬件属性数据来训练设备识别模型，确定模型中的参数，然后线上使用，在接收到待识别设备的设备请求数据时可以标识出真实的设备品牌型号，有效识别出篡改品牌或型号信息的行为。
以手机品牌和型号的移动通信终端设备型号识别应用场景为例，在模型训练阶段，可以采集不同品牌和型号的手机的硬件设备属性信息。通常一个手机品牌下可以对应多个型号是手机，在训练数据采集过程中，可以设置每个品牌型号对应的设备最低设备数量，以保障训练数据的可靠性和输出结果的准确性。考虑到手机品牌和型号的种类分布和发展状况，在本申请的一个实施例中，可以设置每一个品牌对应的设备数量至少有100台，其中每个型号的设备数量至少有10台。经过实际实验效果对比，采用上述方式获取到的训练数据，既可以无需大量训练样本的数据采集，减少成本，同时又可以使得设 备识别模型有较高识别准确性的结果输出。
设备识别模型使用的训练数据可以包括多种类型的数据信息，但至少包括一种设备硬件信息。所述的设备硬件信息可以包括终端设备上某个单元部件或部件组合的识别标识，如主板型号、国际移动设备身份码IMEI、MAC地址、ROM名称等。在实际场景中，所述的训练数据通常采用多个硬件设备信息，可以更加有效、可靠的识别出篡改其中一个或多个硬件设备信息的行为。当然，所述的训练数据还可以包括终端设备上其他软件或软件+硬件结合形成的标识信息，如国际移动用户识别码IMSI、设备系统版本信息等。
使用训练数据对采用的设备识别模型进行训练后，可以线上进行使用。当需要对待识别设备的设备型号进行判识时，可以请求获取待识别设备的设备请求数据，然后处理器将该设备请求数据输入构建的设备识别模型中进行处理。设备识别模型可以基于获取的设备请求数据输出对应的品牌型号分类结果。一些实施场景中，在计算机处理能力运行的情况下，也可以在设备识别模型构建、训练的同时对待识别设备进行识别处理，即，本说明书提供的实施方式可以在设备识别模型线下训练完成后线上使用，也可以基于平台或云计算系统等实时的构建或训练设备识别模型，用于对待识别设备的设备请求数据进行处理。或者，所述的设备识别模型也可以线上更新、维护，或者线上系统(服务器、服务器集群或分布式服务器)有多个类型的设备识别模型，可以先分析处理设备请求数据，然后匹配与设备请求数据对应的最优(根据实际获取的设备请求数据包括的数据信息来选择最适用的设备识别模型)的设备识别模型进行处理。
下面以一个具体的手机品牌型号应用场景为例对本说明书实施方案进行说明。具体的，图2是本说明书提供的所述一种设备型号识别方法实施例的流程示意图。虽然本说明书提供了如下述实施例或附图所示的方法操作步骤或装置结构，但基于常规或者无需创造性的劳动在所述方法或装置中可以包括更多或者部分合并后更少的操作步骤或模块单元。在逻辑性上不存在必要因果关系的步骤或结构中，这些步骤的执行顺序或装置的模块结构不限于本说明书实施例或附图所示的执行顺序或模块结构。所述的方法或模块结构的在实际中的装置、服务器或终端产品应用时，可以按照实施例或者附图所示的方法或模块结构进行顺序执行或者并行执行(例如并行处理器或者多线程处理的环境、甚至包括分布式处理、服务器集群的实施环境)。
当然，下述实施例的描述并不对基于本说明书的其他可扩展到的技术方案构成限制。例如其他的实施场景中，本说明书提供的实施方案同样可以应用到非移动终端设备 型号识别的实施场景中，如PC终端、共享车辆设备、其他专用设备等。具体的一种实施例如图2所示，本说明书提供的一种设备型号识别方法可以包括：
S0：获取待识别设备的设备请求数据，所述设备请求数据至少包括设备硬件信息；
S2：利用构建的设备识别模型对所述设备请求数据进行识别处理，得到所述待识别设备的真实设备型号，所述设备识别模型采用至少包括所述设备硬件信息的训练数据进行训练、输出设备品牌型号的分类算法。
本实施例提供的方法可以用于服务器一侧。所说的服务器可以包括单独的服务器、服务器集群、分布式系统服务器或者处理设备请求数据的服务器与其他相关联数据处理的系统服务器组合(如识别待处理设备的服务器与训练构建设备识别模型的服务器)。服务器可以获取待识别设备的设备请求数据，当然，所述的设备请求数据可以包括设备硬件信息。一些应用场景中，在进行设备型号识别处理中，通常可以指定终端设备上传预定的多种设备硬件信息，但由于权项或其他原因，终端设备上传的设备信息中可能包括部分预定的设备请求数据，甚至设备信息中无设备硬件信息。此时可以下发相应的提示信息请求开放硬件设备信息获取权限或者因为无设备硬件信息而执行其他的处理，具体的可以根据实际应用场景制定相应的策略。
如前所述，本说明书实施例所述的方法中，模型训练所使用的训练数据可以包括类型的设备硬件以及软件的数据信息。本说明书提供的一个实施例中，所述训练数据可以至少包括下属中的一种：
国际移动设备身份码IMEI、国际移动用户识别码IMSI、有线/无线媒体访问控制地址MAC/WIFI-MAC、蓝牙地址Bluetooth,、分辨率、主板型号、只读存储器rom名称。
当然，除上述所述外，还可以包括其他的硬件数据信息构成的训练数据。在上述的训练数据中，IMEI通常包括下述的数据字段：
TAC＝Type Approval Code(first 2digits＝country code)设备型号核准号码；
FAC＝Final Assembly Code(For Nokia phones FAC＝51)最后装配号；
SNR＝Serial Number序列号；
SP＝Spare(always SP＝0)备用号码。
一般的，IMSI号码采用E.212格式，号码总长度为16位，它由MCC+MNC+MSIN三部分组成，其中：
MCC：移动国家码，三个数字，如中国为460；
MNC：移动网号，两个数字，如中国移动的MNC为00(联通是01，移动159新号段是02)，可以有效针对终端绑定移动通信运营商的设备进行识别。
MSIN：移动客户识别号，如在某一PLMN(Public Land Mobile Network，公共陆地移动网络)中移动台的唯一识别码，MSIN＝H0H1H2H3(S)XXXXXX(共11位)。
使用IMEI、IMSI训练数据时，可以通过把IMEI、IMSI切分成成上述部分，通过识别其中的一些字段信息可以一定程序上反应手机品牌相关的信息。
当然，还可以包括有线或无线的MAC地址、手机屏幕分辨率、使用的主板厂商和型号等。因此，本说明书提供的所述方法的另一个实施例中，所述训练数据可以至少包括下述中的一种：
国际移动设备身份码、国际移动用户识别码、有线/无线媒体访问控制地址、蓝牙地址、分辨率、主板型号、只读存储器名称。
这样，既可以保障数据采集的有效性，同时也可以减少终端数据采集种类和网络开销。
需要说明是的，设备识别模型输出的所述的设备型号可以包括设备名称、型号名称、品牌名称等中的一个或多个，如输出的结果可以为品牌信息“小米”，也可以为“小米-note2”，甚至，在一些应用场景中也可以仅输出型号信息(适用于不同的品牌名下的型号信息均不相同的情况)。为便于统一描述，本说明书的一些实施例中可以将设备识别模型输出的结果统一称为设备型号信息，但并不限定一定是包括设备、品牌、型号中的一种信息。
图3是本说明书提供的一种基于GBM算法进行手机终端的品牌和型号识别的处理过程示意图。在图3中，可以基于主动获取或设备上报的型号属性数据生成训练标签，标签数据具体的可以为“xiaomi note2”、“oppo r9”、“vivo x7”等。在GBM算法中，可以通过对上一次树残差的学习，构建新的子树。权重值优化可以参考经典人adaboosting等算法。树的构建过程主要为标准的树生成算法。模型计算完后，可以对每个样本，计算出每个分类的概率，取最大的概率作为预测分类，然后跟真实分类进行对照，进而可以确定准确率，覆盖率等指标。通过相关指标可以对模型效果进行评估、参数调整、优化等。对于待识别设备，可以提取对应的设备信息，获取设备请求数据。然后利用学习得到的GBM模型对设备请求数据进行打分，得分最高的分类作为真实的品 牌型号。
本说明书提供的所述方法的另一个实施例中，可以进一步对训练数据进行过滤和筛选，使用设备原始、真实的硬件数据信息。具体的，所述方法的另一个实施例中，所述的训练数据至少经过下述之一的筛选处理：
删除获取系统最高权限操作(root)的训练数据；
删除经过钩子机制(hook)截获后的消息中包含的训练数据。
经过hook和root的设备信息可能包含虚假数据，所以在本实施例中可以滤掉这些虚假数据。其中，hook(钩子)实际上是一个处理消息的程序段，通过系统调用，把它挂入系统。每当特定的消息发出，在没有到达目的窗口前，钩子程序就先捕获该消息，亦即钩子函数先得到控制权。本实施例中执行root和hook的设备请求数据的过滤，可以进一步提升模型训练精度和输出结果的可靠性。当然，实际的训练数据采集可以设置数据种类或数量可以设置相应的采集要求，例如至少三种硬件信息、一个品牌对应的设备数至少到100台。采集完成后对训练数据进行筛选或者在采集的过程中采用一定的策略识别数据是否经过root或hook修改。
如前所述，本说明书一个或多个实施例中，所述的设备识别模型，可以采用离线预先构建的方式生成，可以采用训练数据进行训练打标后再在线上使用。本说明书不排除所述设备识别模型采用在线构建或更新/维护的方式，在计算机能力足够的情况下，可以在线构建出设备识别模型。当然，在计算机性能允许的情况下，也可以通过实时流引擎实时计算获得硬件设备可以同步在线使用，识别设备品牌型号。
一些实施例中，设备识别模型基于设备请求数据可以计算出多个设备型号的分类标签，每个分类标签可以有对应的概率取值或者分值(分值的高低也可以认为是概率大小的一种)。一些可选的实施例中，计算得到的分类标签可以全部或者部分输出，由用户人工或者进一步判断真实品牌型号。本说明书提供的所述方法的另一个实施例中，可以设定一个概率取值范围，将符合概率取值范围内的分类标签作为识别出的真实设备型号。具体的，所述得到所述待识别设备的真实设备型号可以包括：
基于所述设备请求数据计算所述待识别设备对应于所述设备识别模型相应分类标签的概率取值；
将预定概率取值范围对应的分类标签作为所述待识别设备的真实设备型号。
这样，在一些情况下，可以输出两个或者更多识别出的待识别设备所属的真实设 备型号信息。若所有的识别结果均不符合预定概率取值，则可以判定为无法识别或设备信息数据无效，或者其他的处理方式。当然，另一些实施例中，设备请求数据对应多个分类标签时，可以将打分最高或概率值最高的对应的分类标签作为待识别设备的真实设备型号。
本说明书提供的另一个实施例中，输出的所述真实设备型号还可以包括所述待识别设备属于所述分类标签的可靠性评估数据，所述可靠性评估数据基于所述分类标签对应的概率取值确定。如输出手机型号的同时，还输出手机是这个型号的可靠性评估数据，例如基于上传的设备请求数据识别为输出为xiaomi note2，但评分仅为41分(或概率取值为0.41)，可以作为是否将该模型得到真实设备型号的输出结果作为实际真实的型号的参考依据，为设备的识别提供更多的数据支持，方便用户决策。
具体的分类标签可以根据实际应用场景确定。在本说明书的一些手机真实品牌型号识别的应用场景中，分类标签可以包括终端设备的品牌名称、对应于品牌名称的型号。本实施例中可以包括品牌名称缺省或型号名称缺省的任意一种情况。这样，在手机品牌型号识别的实施场景中，可以更加直观输出的品牌和型号信息，以及对应的打分(或概率)，便于用户决策，提高用户使用体验。
本说明书实施例所提供的方法实施例可以在移动终端、计算机终端、服务器或者类似的运算装置中执行。以运行在服务器上为例，图4是本发明实施例的一种识别车辆受损部件的服务器的硬件结构框图。如图4所示，服务器10可以包括一个或多个(图中仅示出一个)处理器102(处理器102可以包括但不限于微处理器MCU或可编程逻辑器件FPGA等的处理装置)、用于存储数据的存储器104、以及用于通信功能的传输模块106。本领域普通技术人员可以理解，图4所示的结构仅为示意，其并不对上述电子装置的结构造成限定。例如，服务器10还可包括比图4中所示更多或者更少的组件，例如还可以包括其他的处理硬件，如数据库或多级缓存，或者具有与图4所示不同的配置。
存储器104可用于存储应用软件的软件程序以及模块，如本发明实施例中的搜索方法对应的程序指令/模块，处理器102通过运行存储在存储器104内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述导航交互界面内容展示的处理方法。存储器104可包括高速随机存储器，还可包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器104可进一步包括相对于处理器102远程设置的存储器，这些远程存储器可以通过网络连接至计算 机终端10。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
传输模块106用于经由一个网络接收或者发送数据。上述的网络具体实例可包括计算机终端10的通信供应商提供的无线网络。在一个实例中，传输模块106包括一个网络适配器(Network Interface Controller，NIC)，其可通过基站与其他网络设备相连从而可与互联网进行通讯。在一个实例中，传输模块106可以为射频(Radio Frequency，RF)模块，其用于通过无线方式与互联网进行通讯。
基于上述所述的设备型号识别方法，本说明书还提供一种设备型号识别装置。所述的装置可以包括使用了本说明书实施例所述方法的系统(包括分布式系统)、软件(应用)、模块、组件、服务器、客户端等并结合必要的实施硬件的设备装置。基于同一创新构思，本说明书提供的一种实施例中的处理装置如下面的实施例所述。由于装置解决问题的实现方案与方法相似，因此本说明书实施例具体的处理装置的实施可以参见前述方法的实施，重复之处不再赘述。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。具体的，如图5所示，图5是本说明书提供的可以用于服务器一侧的一种设备型号识别装置实施例的模块结构示意图，具体的可以包括：
设备数据获取模块101，可以用于获取待识别设备的设备请求数据，所述设备请求数据至少包括设备硬件信息；
识别模型处理模块102，可以利用构建的设备识别模型对所述设备请求数据进行识别处理，得到所述待识别设备的真实设备型号，所述设备识别模型采用至少包括所述设备硬件信息的训练数据进行训练、输出设备品牌型号的分类算法。
所述的设备识别模型可以采用离线预先构建的方式生成，可以采用训练数据进行训练打标后再在线上使用。本说明书不排除所述设备识别模型采用在线构建或更新/维护的方式，在计算机能力足够的情况下，可以在线构建出设备识别模型。当然，在计算机性能允许的情况下，也可以通过实时流引擎实时计算获得硬件设备可以同步在线使用，识别设备品牌型号。
一种实施例中，所述识别处理模块102中构建所述设备识别模型所使用的训练数据至少包括下述中的一种：
国际移动设备身份码、国际移动用户识别码、有线/无线媒体访问控制地址、蓝牙 地址、分辨率、主板型号、只读存储器名称。
另一种实施例中，所述的训练数据至少经过下述之一的筛选处理：
删除获取系统最高权限操作的训练数据；
删除经过钩子机制截获后的消息中包含的训练数据。
另一种实施例中，所述识别处理模块102得到的所述待识别设备的真实设备型号可以包括：
基于所述设备请求数据计算所述待识别设备对应于所述设备识别模型相应分类标签的概率取值；
将预定概率取值范围对应的分类标签作为所述待识别设备的真实设备型号。
所述的预定概率范围可以是一个区间，也可以是最大的概率取值。
所述装置的另一个实施例中，不仅可以输出待识别设备的真实设备型号，还可以输出对应该输出结果相应的概率值或分值。因此，所述真实设备型号还可以包括所述待识别设备属于所述分类标签的可靠性评估数据，所述可靠性评估数据基于所述分类标签对应的概率取值确定。
所述装置具体的一个手机品牌型号识别应用场景的一个实施例中，所述分类标签包括终端设备的品牌名称、对应品牌名称的型号。
上述实施例所述的装置具体的实施可以参照相关方法实施例的描述，在此不做赘述。
本说明书实施例提供的设备型号识别方法可以在计算机中由处理器执行相应的程序指令来实现，如使用windows操作系统的c++语言在PC端或服务器端实现，或其他例如Linux、系统相对应的应用设计语言集合必要的硬件实现，或者基于量子计算机的处理逻辑实现等。具体的，本说明书提供的一种识别设备型号的处理设备实现上述方法的实施例中，所述处理设备可以包括处理器以及用于存储处理器可执行指令的存储器，所述处理器执行所述指令时实现：
获取待识别设备的设备请求数据，所述设备请求数据至少包括设备硬件信息；
利用构建的设备识别模型对所述设备请求数据进行识别处理，得到所述待识别设备的真实设备型号，所述设备识别模型采用至少包括所述设备硬件信息的训练数据进行训练、输出设备品牌型号的分类算法。
上述的指令可以存储在多种计算机可读存储介质中。所述计算机可读存储介质可以包括用于存储信息的物理装置，可以将信息数字化后再以利用电、磁或者光学等方式的媒体加以存储。本实施例所述的计算机可读存储介质有可以包括：利用电能方式存储信息的装置如，各式存储器，如RAM、ROM等；利用磁能方式存储信息的装置如，硬盘、软盘、磁带、磁芯存储器、磁泡存储器、U盘；利用光学方式存储信息的装置如，CD或DVD。当然，还有其他方式的可读存储介质，例如量子存储器、石墨烯存储器等等。上述所述的装置或服务器或客户端或处理设备中的所涉及的指令同上描述。
需要说明的是，本说明书实施例上述所述的装置、处理设备，根据相关方法实施例的描述还可以包括其他的实施方式，如删除获取系统最高权限操作的训练数据，或者删除经过钩子机制截获后的消息中包含的训练数据。具体的实现方式可以参照方法实施例的描述，在此不作一一赘述。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于硬件+程序类实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
上述对本说明书特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中，多任务处理和并行处理也是可以的或者可能是有利的。
虽然本申请提供了如实施例或流程图所述的方法操作步骤，但基于常规或者无创造性的劳动可以包括更多或者更少的操作步骤。实施例中列举的步骤顺序仅仅为众多步骤执行顺序中的一种方式，不代表唯一的执行顺序。在实际中的装置或系统服务器产品执行时，可以按照实施例或者附图所示的方法顺序执行或者并行执行(例如并行处理器或者多线程处理的环境)。
尽管本说明书实施例内容中提到利用GBM算法进行模型训练、IMEI和MAC的硬件设备信息、离线或在线构建模型、训练数据采集要求和筛选处理等之类的数据获取、存储、交互、计算、判断等操作和数据描述，但是，本说明书实施例并不局限于必须是符合行业通信标准、标准分类模型处理、通信协议和标准数据模型/模板或本说明书实施例所描述的情况。某些行业标准或者使用自定义方式或实施例描述的实施基础上略加修 改后的实施方案也可以实现上述实施例相同、等同或相近、或变形后可预料的实施效果。应用这些修改或变形后的数据获取、存储、判断、处理方式等获取的实施例，仍然可以属于本说明书的可选实施方案范围之内。
在20世纪90年代，对于一个技术的改进可以很明显地区分是硬件上的改进(例如，对二极管、晶体管、开关等电路结构的改进)还是软件上的改进(对于方法流程的改进)。然而，随着技术的发展，当今的很多方法流程的改进已经可以视为硬件电路结构的直接改进。设计人员几乎都通过将改进的方法流程编程到硬件电路中来得到相应的硬件电路结构。因此，不能说一个方法流程的改进就不能用硬件实体模块来实现。例如，可编程逻辑器件(Programmable Logic Device,PLD)(例如现场可编程门阵列(Field Programmable Gate Array，FPGA))就是这样一种集成电路，其逻辑功能由用户对器件编程来确定。由设计人员自行编程来把一个数字系统“集成”在一片PLD上，而不需要请芯片制造厂商来设计和制作专用的集成电路芯片。而且，如今，取代手工地制作集成电路芯片，这种编程也多半改用“逻辑编译器(logic compiler)”软件来实现，它与程序开发撰写时所用的软件编译器相类似，而要编译之前的原始代码也得用特定的编程语言来撰写，此称之为硬件描述语言(Hardware Description Language，HDL)，而HDL也并非仅有一种，而是有许多种，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)与Verilog。本领域技术人员也应该清楚，只需要将方法流程用上述几种硬件描述语言稍作逻辑编程并编程到集成电路中，就可以很容易得到实现该逻辑方法流程的硬件电路。
控制器可以按任何适当的方式实现，例如，控制器可以采取例如微处理器或处理器以及存储可由该(微)处理器执行的计算机可读程序代码(例如软件或固件)的计算机可读介质、逻辑门、开关、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程逻辑控制器和嵌入微控制器的形式，控制器的例子包括但不限于以下微控制器：ARC 625D、Atmel AT91SAM、Microchip PIC18F26K20以及Silicone Labs C8051F320，存储器控制器还可以被实现为存储器的控制逻辑的一部分。本领域技术人员也知道，除了以纯计算机可读程序代码方式实现控制器以外，完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因此这种控制器可以被认为是一种硬件部件，而对其内包括的 用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至，可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
上述实施例阐明的处理设备、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的，计算机例如可以为个人计算机、膝上型计算机、车载人机交互设备、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
虽然本说明书实施例提供了如实施例或流程图所述的方法操作步骤，但基于常规或者无创造性的手段可以包括更多或者更少的操作步骤。实施例中列举的步骤顺序仅仅为众多步骤执行顺序中的一种方式，不代表唯一的执行顺序。在实际中的装置或终端产品执行时，可以按照实施例或者附图所示的方法顺序执行或者并行执行(例如并行处理器或者多线程处理的环境，甚至为分布式数据处理环境)。术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、产品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、产品或者设备所固有的要素。在没有更多限制的情况下，并不排除在包括所述要素的过程、方法、产品或者设备中还存在另外的相同或等同要素。
为了描述的方便，描述以上装置时以功能分为各种模块分别描述。当然，在实施本说明书实施例时可以把各模块的功能在同一个或多个软件和/或硬件中实现，也可以将实现同一功能的模块由多个子模块或子单元的组合实现等。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
本领域技术人员也知道，除了以纯计算机可读程序代码方式实现控制器以外，完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因此这种控制器可以被认为是一种硬件部件，而对其内部包括的用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至，可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
本领域技术人员应明白，本说明书的实施例可提供为方法、系统或计算机程序产品。因此，本说明书实施例可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本说明书实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本说明书实施例可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本说明书实施例，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本说明书实施例的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。
以上所述仅为本说明书实施例的实施例而已，并不用于限制本说明书实施例。对于本领域技术人员来说，本说明书实施例可以有各种更改和变化。凡在本说明书实施例的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本说明书实施例的权利要求范围之内。

Claims (13)

  1. 一种设备型号识别方法，所述方法包括：
    获取待识别设备的设备请求数据，所述设备请求数据至少包括设备硬件信息；
    利用构建的设备识别模型对所述设备请求数据进行识别处理，得到所述待识别设备的真实设备型号，所述设备识别模型采用至少包括所述设备硬件信息的训练数据进行训练、输出设备品牌型号的分类算法。
  2. 如权利要求1所述的方法，所述训练数据至少包括下述中的一种：
    国际移动设备身份码、国际移动用户识别码、有线/无线媒体访问控制地址、蓝牙地址、分辨率、主板型号、只读存储器名称。
  3. 如权利要求1所述的方法，所述的训练数据至少经过下述之一的筛选处理：
    删除获取系统最高权限操作的训练数据；
    删除经过钩子机制截获后的消息中包含的训练数据。
  4. 如权利要求1所述的方法，所述得到所述待识别设备的真实设备型号包括：
    基于所述设备请求数据计算所述待识别设备对应于所述设备识别模型相应分类标签的概率取值；
    将预定概率取值范围对应的分类标签作为所述待识别设备的真实设备型号。
  5. 如权利要求4所述的方法，所述真实设备型号还包括所述待识别设备属于所述分类标签的可靠性评估数据，所述可靠性评估数据基于所述分类标签对应的概率取值确定。
  6. 如权利要求5所述的方法，其中，所述分类标签包括终端设备的品牌名称、对应品牌名称的型号。
  7. 一种设备型号识别装置，所述装置包括：
    设备数据获取模块，用于获取待识别设备的设备请求数据，所述设备请求数据至少包括设备硬件信息；
    识别模型处理模块，利用构建的设备识别模型对所述设备请求数据进行识别处理，得到所述待识别设备的真实设备型号，所述设备识别模型采用至少包括所述设备硬件信息的训练数据进行训练、输出设备品牌型号的分类算法。
  8. 如权利要求7所述的装置，所述识别处理模块中构建所述设备识别模型所使用的训练数据至少包括下述中的一种：
    国际移动设备身份码、国际移动用户识别码、有线/无线媒体访问控制地址、蓝牙地址、分辨率、主板型号、只读存储器名称。
  9. 如权利要求7所述的装置，所述的训练数据至少经过下述之一的筛选处理：
    删除获取系统最高权限操作的训练数据；
    删除经过钩子机制截获后的消息中包含的训练数据。
  10. 如权利要求7所述的装置，所述识别处理模块得到的所述待识别设备的真实设备型号可以包括：
    基于所述设备请求数据计算所述待识别设备对应于所述设备识别模型相应分类标签的概率取值；
    将预定概率取值范围对应的分类标签作为所述待识别设备的真实设备型号。
  11. 如权利要求10所述的装置，所述真实设备型号还包括所述待识别设备属于所述分类标签的可靠性评估数据，所述可靠性评估数据基于所述分类标签对应的概率取值确定。
  12. 如权利要求11所述的装置，所述分类标签包括终端设备的品牌名称、对应品牌名称的型号。
  13. 一种识别设备型号的处理设备，包括处理器以及用于存储处理器可执行指令的存储器，所述处理器执行所述指令时实现：
    获取待识别设备的设备请求数据，所述设备请求数据至少包括设备硬件信息；
    利用构建的设备识别模型对所述设备请求数据进行识别处理，得到所述待识别设备的真实设备型号，所述设备识别模型采用至少包括所述设备硬件信息的训练数据进行训练、输出设备品牌型号的分类算法。
PCT/CN2019/073913 2018-04-02 2019-01-30 一种设备型号识别方法、装置及处理设备 WO2019192260A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810281223.8A CN108681667A (zh) 2018-04-02 2018-04-02 一种设备型号识别方法、装置及处理设备
CN201810281223.8 2018-04-02

Publications (1)

Publication Number Publication Date
WO2019192260A1 true WO2019192260A1 (zh) 2019-10-10

Family

ID=63799770

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/073913 WO2019192260A1 (zh) 2018-04-02 2019-01-30 一种设备型号识别方法、装置及处理设备

Country Status (3)

Country Link
CN (1) CN108681667A (zh)
TW (1) TWI709866B (zh)
WO (1) WO2019192260A1 (zh)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN111200534B (zh) * 2018-11-16 2022-01-18 中国电信股份有限公司 终端信息的确定方法和装置
CN109782631B (zh) * 2019-03-08 2021-06-18 重庆邮电大学 一种基于特征值比对的智能家居设备识别方法
CN109951354B (zh) * 2019-03-12 2021-08-10 北京奇虎科技有限公司 一种终端设备识别方法、系统及存储介质
CN109905292B (zh) * 2019-03-12 2021-08-10 北京奇虎科技有限公司 一种终端设备识别方法、系统及存储介质
CN111753578A (zh) * 2019-03-27 2020-10-09 北京外号信息技术有限公司 光通信装置的识别方法和相应的电子设备
CN110166462B (zh) * 2019-05-25 2022-02-25 深圳市元征科技股份有限公司 访问控制方法、系统、电子设备及计算机存储介质
CN110569764B (zh) * 2019-08-28 2023-12-22 北京工业大学 一种基于卷积神经网络的手机型号识别方法
CN113190277B (zh) * 2020-01-14 2024-06-14 深圳怡化电脑股份有限公司 设备识别方法、设备识别装置及终端设备
CN113873521A (zh) * 2020-06-30 2021-12-31 华为技术有限公司 一种设备型号识别方法、装置、网络设备及系统
CN112087744B (zh) * 2020-08-21 2023-07-25 宜通世纪科技股份有限公司 一种识别终端型号的方法、系统、装置及存储介质
CN111796583B (zh) * 2020-08-21 2021-06-11 上海星融汽车科技有限公司 车辆ecu识别方法、系统及车辆诊断设备
CN112966731A (zh) * 2021-03-01 2021-06-15 上海众言网络科技有限公司 用于网络问卷调查的手机识别方法和装置
CN113568668A (zh) * 2021-06-30 2021-10-29 北京达佳互联信息技术有限公司 信息识别方法及装置
CN115904916A (zh) * 2023-02-08 2023-04-04 天翼云科技有限公司 一种硬盘故障预测的方法、装置、电子设备以及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106897729A (zh) * 2016-06-28 2017-06-27 阿里巴巴集团控股有限公司 信息识别方法、模型训练方法、装置及处理设备
CN107480730A (zh) * 2017-09-05 2017-12-15 广州供电局有限公司 电力设备识别模型构建方法和系统、电力设备的识别方法
CN107622198A (zh) * 2017-07-11 2018-01-23 上海点融信息科技有限责任公司 用于实现设备指纹的方法、装置和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

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102932775A (zh) * 2012-11-16 2013-02-13 广州市通联技术发展有限公司 一种利用imei与ua结合进行终端识别的方法及装置
US20140149296A1 (en) * 2012-11-29 2014-05-29 Applied Materials, Inc. Enhanced preventative maintenance utilizing direct part marking
CN103136678A (zh) * 2013-03-04 2013-06-05 北京奇虎科技有限公司 智能终端的识别方法及装置、识别信息的处理方法及装置、识别系统
CN104079680B (zh) * 2014-06-30 2018-03-06 珠海市君天电子科技有限公司 设备的识别方法和装置
CN106921969A (zh) * 2015-12-28 2017-07-04 阿里巴巴集团控股有限公司 终端真伪验证方法、装置及系统
US9849364B2 (en) * 2016-02-02 2017-12-26 Bao Tran Smart device
CN105903682A (zh) * 2016-04-11 2016-08-31 深圳淘绿信息科技股份有限公司 手机自动化分拣系统及手机分拣方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106897729A (zh) * 2016-06-28 2017-06-27 阿里巴巴集团控股有限公司 信息识别方法、模型训练方法、装置及处理设备
CN107622198A (zh) * 2017-07-11 2018-01-23 上海点融信息科技有限责任公司 用于实现设备指纹的方法、装置和计算机可读存储介质
CN107480730A (zh) * 2017-09-05 2017-12-15 广州供电局有限公司 电力设备识别模型构建方法和系统、电力设备的识别方法
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

Also Published As

Publication number Publication date
CN108681667A (zh) 2018-10-19
TW201942766A (zh) 2019-11-01
TWI709866B (zh) 2020-11-11

Similar Documents

Publication Publication Date Title
WO2019192260A1 (zh) 一种设备型号识别方法、装置及处理设备
US12001475B2 (en) Mobile image search system
US11714853B2 (en) Efficient storage and searching of vector datasets
Strohbach et al. Towards a big data analytics framework for IoT and smart city applications
US10692492B2 (en) Techniques for client-side speech domain detection using gyroscopic data and a system using the same
WO2020087974A1 (zh) 生成模型的方法和装置
US12026937B2 (en) Method for generating classification model, electronic device, and medium
US10180864B2 (en) Increasing efficiency of an event processing system
US20200356462A1 (en) Systems and methods for determining performance metrics of remote relational databases
US9754015B2 (en) Feature rich view of an entity subgraph
TWI777035B (zh) 螺絲鎖附異常警報方法、裝置、電腦裝置及存儲介質
EP4073978B1 (en) Intelligent conversion of internet domain names to vector embeddings
WO2019109798A1 (zh) 资源加载的方法、装置、终端及存储介质
WO2018231472A1 (en) Identifying relationships from communication content
CN107665349B (zh) 一种分类模型中多个目标的训练方法和装置
CN112199374B (zh) 针对数据缺失的数据特征挖掘方法及其相关设备
WO2024045836A1 (zh) 参数调整方法及相关设备
WO2021087970A1 (zh) 标签数据的更新方法、装置、电子设备及存储介质
CN109754319B (zh) 信用分值确定系统、方法、终端及服务器
Klus et al. Crowdsourcing solutions for data gathering from wearables
US20220207284A1 (en) Content targeting using content context and user propensity
EP4281881A1 (en) Document sampling using prefetching and precomputing
CN108965039B (zh) 一种基于流量监控的告警方法以及电子设备
US20220345353A1 (en) Real-time monitoring of machine learning models in service orchestration plane
US10761900B1 (en) System and method for secure distributed processing across networks of heterogeneous processing nodes

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: 19780848

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: 19780848

Country of ref document: EP

Kind code of ref document: A1