WO2020140937A1 - 物联网标识的识别方法、装置及终端设备 - Google Patents

物联网标识的识别方法、装置及终端设备 Download PDF

Info

Publication number
WO2020140937A1
WO2020140937A1 PCT/CN2020/070091 CN2020070091W WO2020140937A1 WO 2020140937 A1 WO2020140937 A1 WO 2020140937A1 CN 2020070091 W CN2020070091 W CN 2020070091W WO 2020140937 A1 WO2020140937 A1 WO 2020140937A1
Authority
WO
WIPO (PCT)
Prior art keywords
identification
polygon
iot
internet
identified
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2020/070091
Other languages
English (en)
French (fr)
Inventor
李小涛
游树娟
牛亚文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Mobile Communications Group Co Ltd
Research Institute of China Mobile Communication Co Ltd
Original Assignee
China Mobile Communications Group Co Ltd
Research Institute of China Mobile Communication Co Ltd
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 China Mobile Communications Group Co Ltd, Research Institute of China Mobile Communication Co Ltd filed Critical China Mobile Communications Group Co Ltd
Publication of WO2020140937A1 publication Critical patent/WO2020140937A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/24—Character recognition characterised by the processing or recognition method
    • G06V30/242—Division of the character sequences into groups prior to recognition; Selection of dictionaries
    • G06V30/244—Division of the character sequences into groups prior to recognition; Selection of dictionaries using graphical properties, e.g. alphabet type or font
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2431—Multiple classes
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries

Definitions

  • the present disclosure relates to the field of Internet of Things technology, and in particular, to a method, device, and terminal device for identifying an Internet of Things identifier.
  • the IoT ID is a name tag used to identify different IoT objects, such as commodity codes, device serial numbers, device network addresses and page uniform resource identifiers (Uniform Resource Identifier, URI), etc. are all IoT IDs.
  • the IoT logo can be divided into two categories: proprietary logo and comprehensive logo.
  • the proprietary identification has an independent coding structure and has a fixed identification field or identification object, such as GS1 (EAN.UCC), EPC, sensor node identification, IPv4/6, etc.
  • the comprehensive identification supports the identification of any object in different fields, and is a comprehensive identification system.
  • Common comprehensive identification systems include Handle, Object Identifier (OID, also known as Internet of Things domain name) and entity code. (Entity, Code, Ecode) Three types.
  • Embodiments of the present disclosure provide a method, device, and terminal device for identifying an Internet of Things identifier, to solve the problem that the identification process of a heterogeneous Internet of Things identifier in the related art is cumbersome and inefficient.
  • an embodiment of the present disclosure provides a method for identifying an Internet of Things identifier, including:
  • the to-be-identified IoT identifier is parsed.
  • an identification device for an Internet of Things identifier including:
  • the first obtaining module is used to obtain the identification of the Internet of Things to be identified
  • a first conversion module configured to convert the to-be-identified IoT logo into a polygonal graphic
  • a recognition module which is used to recognize the polygon graphics by using a pre-trained graphics classification model to obtain a recognition result representing the coding category of the to-be-recognized Internet of Things identifier;
  • the parsing module is configured to parse the to-be-identified IoT identifier according to the coding category of the to-be-identified IoT identifier.
  • an embodiment of the present disclosure provides a terminal device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is processed by the When the device is executed, the steps of the above-mentioned identification method of the Internet of Things logo can be realized.
  • an embodiment of the present disclosure provides a computer-readable storage medium on which a computer program is stored, wherein, when the computer program is executed by a processor, the steps of the above-mentioned identification method of the Internet of Things can be implemented.
  • a recognition result representing the coding category of the to-be-recognized IoT logo can be obtained.
  • the recognition method of the embodiment of the present disclosure it is not necessary to force the IoT objects to adopt a unified coding system, and the IoT logos of different coding systems can be converted into unified polygon graphics, and a pre-trained graphics classification model can be used to identify different The polygon graphics category corresponding to the coding system, so as to realize the identification of the IoT logos of different coding systems.
  • a pre-trained graphics classification model can be used to identify different The polygon graphics category corresponding to the coding system, so as to realize the identification of the IoT logos of different coding systems.
  • it can have better scalability and can continuously increase the number of supporting automatic recognition. Identify the type.
  • FIG. 1 is a flowchart of a method for identifying an Internet of Things identifier according to an embodiment of the present disclosure
  • FIG. 2 is a flowchart of converting a logo into a polygonal graphic according to an embodiment of the present disclosure
  • 3A, 3B and 3C are schematic diagrams of a process of converting a logo into a polygonal graphic of a specific example of the present disclosure
  • FIG. 4 is a schematic structural diagram of an identification device for an Internet of Things identifier according to an embodiment of the present disclosure
  • FIG. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present disclosure.
  • the embodiments of the present disclosure provide an automatic identification method for heterogeneous Internet of Things identification, which does not require additional creation of a new identification system or change of the identification structure in related technologies.
  • IoT logos are converted into unified polygonal graphics, and pre-trained graphic classification models can be used to identify the graphic categories corresponding to different coding systems, thereby automatically identifying the coding categories of IoT logos, thereby simplifying the identification process of heterogeneous IoT logos To improve recognition efficiency.
  • FIG. 1 is a flowchart of a method for identifying an Internet of Things identifier provided by an embodiment of the present disclosure. As shown in FIG. 1, the identification method includes the following steps:
  • Step 101 Obtain the identification of the Internet of Things to be identified.
  • the above-mentioned to-be-identified IoT identifier can be understood as a heterogeneous IoT identifier.
  • the above-mentioned IoT identification to be identified may be on different carriers.
  • the carrier on which the IoT identification to be identified may be located includes, but is not limited to, a two-dimensional code, a bar code, and a radio frequency identification (Radio Frequency Identification, RFID) tag.
  • RFID Radio Frequency Identification
  • Step 102 Convert the to-be-identified IoT logo into a polygonal shape.
  • the identifier of the Internet of Things to be recognized can be converted into a multi-deformation graph that meets the preset condition based on the preset rule.
  • the multi-deformed graphics can be embodied in the form of an image, that is, in a specific implementation, the logo of the Internet of Things to be recognized can be converted into an image including a corresponding polygonal graphic.
  • Step 103 Use the pre-trained graphic classification model to identify the polygon graphics to obtain a recognition result representing the coding category of the IoT logo to be recognized.
  • the aforementioned graph classification model can be pre-trained based on the machine learning object recognition (or graph recognition) method.
  • the converted polygon graphics may be input into a pre-trained graphics classification model to identify the input polygon graphics, and output a recognition result representing the coding category of the IoT logo to be recognized.
  • the automatic recognition problem of the coding category of the heterogeneous Internet of Things logo can be converted into a graphics-based object recognition problem, thereby simplifying the logo recognition process.
  • Step 104 According to the coding category of the to-be-identified IoT identifier, parse the to-be-identified IoT identifier.
  • the coding category of the IoT logo to be recognized can be known, and according to the coding category of the IoT logo to be recognized, the corresponding logo resolution service can be called to treat Recognize the IoT ID for analysis, so as to obtain the description information of the IoT object corresponding to the IoT ID to be identified. For example, if the coding category of the IoT identification to be identified is Ecode encoding, the China Article Coding Center can be called to resolve the IoT identification to be identified.
  • a recognition result representing the coding category of the to-be-recognized IoT logo can be obtained.
  • the recognition method of the embodiment of the present disclosure it is not necessary to force the IoT objects to adopt a unified coding system, and the IoT logos of different coding systems can be converted into unified polygon graphics, and a pre-trained graphics classification model can be used to identify different The polygon graphics category corresponding to the coding system, so as to realize the identification of the IoT logos of different coding systems.
  • a pre-trained graphics classification model can be used to identify different The polygon graphics category corresponding to the coding system, so as to realize the identification of the IoT logos of different coding systems.
  • it can have better scalability and can continuously increase the number of supporting automatic recognition. Identify the type.
  • the process of converting the to-be-recognized IoT logo into a polygon graphic in step 102 may include:
  • the number of vertices of the polygon in the polygon graphic is equal to the number of encoded bits
  • the encoded bits of the to-be-identified IoT identifier correspond one-to-one with the vertices of the polygon
  • each vertex reaches a reference point in the polygon
  • the distance is a preset multiple relationship with the reference value of the coding bit corresponding to the vertex, and the angle between each adjacent two vertices and the reference point is the same.
  • the above reference points are uniquely determined in the corresponding polygons.
  • the corresponding polygon graphics can be constructed in advance and combined with the maximum reference value among the reference values of all the coding bits of the IoT identification to be recognized, for example, first
  • the predetermined reference point is the center of the circle, and the circle is drawn with the maximum reference value as the radius, and then the corresponding polygon shape is constructed based on the drawn circle.
  • the logo of the Internet of Things to be recognized can be converted into a multi-deformed graphic that meets the preset conditions.
  • each coded bit of the to-be-recognized Internet of Things identifier to a reference value may be selected as: conversion of each coded bit of the to-be-recognized Internet of Things identifier to an ASCII code.
  • the above process of converting the to-be-identified IoT logo into a polygonal graphic may include the following steps:
  • Step 201 Determine the number of coding bits n of the identifier of the Internet of Things to be recognized (hereinafter referred to as the identifier), and convert each encoded bit of the identifier into an ASCII code;
  • Step 202 Among the ASCII codes that identify all coded bits, select the largest ASCII code and create a blank image whose length and width are equal to twice the maximum ASCII code;
  • Step 203 Draw a circle in the blank image with the center of the blank image as the center and the maximum ASCII code as the radius;
  • Step 204 Divide the above-mentioned circle n into equal parts according to the number of identified coding bits n, and connect the center of the circle and the equal points on the circle respectively;
  • Step 205 Map each coded bit identified as a point on the line connecting the center of the circle and the bisectors in sequence (for example, counterclockwise or clockwise), and the distance from the point to the center of the circle is equal to the ASCII code of the corresponding coded bit;
  • Step 206 Connect all the mapped points to obtain the polygon graphic corresponding to the mark.
  • the reference value of the coded bit is the ASCII code; the center of the circle is the reference point in the polygon, which is determined according to the maximum ASCII code; the center of each coded bit map is connected to the point on the connecting line That is the vertices of the polygon.
  • the number of vertices of the polygon is equal to the number of coded bits; the angle between each adjacent two vertices and the center of the circle is the same.
  • the above embodiment takes the example that the distance from the vertex of the polygon to the center of the circle (reference point) is equal to the ASCII code of the corresponding code bit (that is, the preset multiple is 1), but in addition, other preset multiples are also selected, such as 0.5, 1.5 or 2, etc., the embodiments of the present disclosure do not limit this.
  • the to-be-recognized identifier of an EAN-8 barcode is 87217582
  • the number of encoding digits of the identifier is 8, and each encoding digit of the identifier can be converted to ASCII code to obtain 38, 37, 32, 31, 37, 35, 38 32, where the maximum ASCII code is 38, so when converting polygon graphics, a blank image with a size of 76 ⁇ 76 can be created first, with the blank image center o as the center of the circle, and the maximum ASCII code 38 as the radius, in the blank image Draw a circle; secondly, divide the circle 8 into 8 equal parts according to the number of coding digits, and connect the circle center and 8 equal points on the circle; again, according to the ASCII code of each code bit, encode each one in a clockwise direction Bits are mapped to a point on the connecting line between the center of the circle and each bisector, and the distance from the point to the center of
  • the method may further include:
  • the identification sample set includes at least two types of identification sample subsets, and each type of identification sample subset corresponds to a coding category;
  • the classification model is trained to obtain the graphic classification model.
  • the coding category corresponding to the above-mentioned identification sample subset may be Ecode, EAN-8, EAN-13, EAN-128, URL or OID, etc.
  • the above-mentioned multi-deformation graphics can be embodied in the form of an image, that is, all the identification samples in the identification sample set can be converted into image samples including corresponding polygon graphics, and the classification model can be trained according to the image samples.
  • CNN Convolutional Neural Networks
  • the automatic recognition of the logo coding category can be converted into a graphic classification problem, so that the current more mature object or graphic classification technology can achieve accurate classification of the logo, simplify the recognition process, and improve recognition efficiency .
  • the above process of training the classification model based on the polygon graphics of all the identification samples, and the process of obtaining the graphic classification model may include:
  • the normalization processing method can be selected to normalize the polygonal graphics to a uniform size
  • the classification model is trained to obtain the graphic classification model.
  • FIG. 4 is a schematic structural diagram of an identification device for an Internet of Things identifier provided by an embodiment of the present disclosure. As shown in FIG. 4, the identification device includes:
  • the first obtaining module 41 is used to obtain the identification of the Internet of Things to be identified;
  • the first conversion module 42 is configured to convert the to-be-identified IoT logo into a polygonal graphic
  • the recognition module 43 is used to recognize the polygon graphics using a pre-trained graphics classification model to obtain a recognition result representing the coding category of the to-be-recognized Internet of Things identifier;
  • the parsing module 44 is configured to parse the to-be-recognized Internet of Things identifier according to the coding category of the to-be-recognized Internet of Things identifier.
  • a recognition result representing the coding category of the to-be-recognized IoT logo can be obtained.
  • the first conversion module 42 includes:
  • a determining unit configured to determine the number of encoded bits of the IoT identification to be identified, and convert each encoded bit of the IoT identification to be identified into a reference value
  • a construction unit configured to construct the polygon graphics according to the number of coding bits and the reference value of each coding bit
  • the number of vertices of the polygon in the polygon graphic is equal to the number of encoded bits
  • the encoded bits of the to-be-identified IoT identifier correspond one-to-one with the vertices of the polygon
  • each vertex reaches a reference point in the polygon
  • the distance is a preset multiple relationship with the reference value of the coding bit corresponding to the vertex, and the angle between each adjacent two vertices and the reference point is the same.
  • the determining unit is also used to:
  • the identification device further includes:
  • a second obtaining module configured to obtain an identification sample set, wherein the identification sample set includes at least two types of identification sample subsets, and each type of identification sample subset corresponds to a coding category;
  • a second conversion module configured to convert all the identification samples in the identification sample set into polygon graphics
  • the training module is used for training the classification model according to the polygon graphics corresponding to all the identification samples to obtain the graphics classification model.
  • the training module includes:
  • the processing unit is used to normalize the polygon graphics of all identification samples
  • the training unit is configured to train the classification model according to the polygon graphics of all the identification samples after the normalization processing to obtain the graphics classification model.
  • an embodiment of the present disclosure also provides a terminal device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is used by the processor During execution, each process of the above-mentioned IoT identification method embodiment can be achieved, and the same technical effect can be achieved. To avoid repetition, details are not described here.
  • an embodiment of the present disclosure further provides a terminal device, including a bus 51, a transceiver 52, an antenna 53, a bus interface 54, a processor 55, and a memory 56.
  • the terminal device further includes: a computer program stored on the memory 56 and executable on the processor 55. Specifically, when the computer program is executed by the processor 55, the processes of the foregoing method identification method embodiments of the Internet of Things can be implemented, and the same technical effect can be achieved. To avoid repetition, details are not described herein.
  • bus 51 may include any number of interconnected buses and bridges, and bus 51 will include one or more processors represented by processor 55 and memory represented by memory 56
  • the various circuits are linked together.
  • the bus 51 can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, etc., which are well known in the art, and therefore, they will not be further described herein.
  • the bus interface 54 provides an interface between the bus 51 and the transceiver 52.
  • the transceiver 52 may be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium.
  • the data processed by the processor 55 is transmitted on the wireless medium through the antenna 53. Further, the antenna 53 also receives the data and transmits the data to the processor 55.
  • the processor 55 is responsible for managing the bus 51 and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions.
  • the memory 56 may be used to store data used by the processor 55 when performing operations.
  • the processor 55 may be a CPU, an application specific integrated circuit (Application Specific Integrated Circuits, ASIC), a field programmable gate array (Field-Programmable Gate Array, FPGA), or a complex programmable logic device (Complex Programmable Logic Device, CPLD ).
  • ASIC Application Specific Integrated Circuits
  • FPGA Field-Programmable Gate Array
  • CPLD Complex Programmable Logic Device
  • Embodiments of the present disclosure also provide a computer-readable storage medium on which a computer program is stored.
  • a computer program is stored on which a computer program is stored.
  • the computer program is executed by a processor, each process of the above-mentioned identification method embodiment of the Internet of Things identification is realized, and the same The technical effect is not repeated here in order to avoid repetition.
  • Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be achieved by any method or technology.
  • the information may 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 technologies, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices.
  • computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.
  • the embodiments described in the embodiments of the present disclosure may be implemented by hardware, software, firmware, middleware, microcode, or a combination thereof.
  • units, modules, subunits, submodules, etc. can be implemented in one or more application specific integrated circuits (Application Specific Integrated Circuits, ASIC), digital signal processors (Digital Signal Processing, DSP), digital signal processing equipment ( DSP, Device (DSPD), Programmable Logic Device (PLD), Field-Programmable Gate Array (FPGA), general-purpose processor, controller, microcontroller, microcontroller, microprocessor, In other electronic units or combinations thereof that perform the functions described in this disclosure.
  • the technology described in the embodiments of the present disclosure may be implemented through modules (eg, procedures, functions, etc.) that perform the functions described in the embodiments of the present disclosure.
  • the software codes can be stored in the memory and executed by the processor.
  • the memory may be implemented in the processor or external to the processor.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

本公开提供一种物联网标识的识别方法、装置及终端设备，该物联网标识的识别方法包括：获取待识别物联网标识；将所述待识别物联网标识转换为多边形图形；利用预先训练的图形分类模型，对所述多边形图形进行识别，得到表示所述待识别物联网标识的编码类别的识别结果；根据所述待识别物联网标识的编码类别，对所述待识别物联网标识进行解析。

Description

物联网标识的识别方法、装置及终端设备
相关申请的交叉引用
本申请主张在2019年1月2日在中国提交的中国专利申请号No.201910000936.7的优先权，其全部内容通过引用包含于此。
技术领域
本公开涉及物联网技术领域，尤其涉及一种物联网标识的识别方法、装置及终端设备。
背景技术
随着物联网的飞速发展，不同国家和不同领域正在不断推出物联网标识体系，带来了多种异构物联网标识共存的局面。物联网标识是用于识别不同物联网对象的名称标记，比如商品编码、设备序列号、设备网络地址和页面统一资源标识符(Uniform Resource Identifier，URI)等均为物联网标识。
通常，每种物联网标识的编码格式及解析方法都存在差异，使得物联网系统之间的数据互认和资源共享面临严峻的挑战，阻碍物联网的进一步发展。根据标识体系的兼容性和可扩展性，物联网标识可分为专有性标识和综合性标识两大类。其中专有性标识具有独立的编码结构，有固定的标识领域或标识对象，如GS1(EAN.UCC)、EPC、传感器节点标识、IPv4/6等。而综合性标识支持对不同领域任意对象的标识，是一种综合性的标识体系，常见的综合性标识体系包括Handle、对象标识符(Object Identifier，OID，又称为物联网域名)和实体代码(Entity Code，Ecode)三种。
目前，对于异构物联网标识的自动识别，主要是通过综合性标识(比如Handle、OID或Ecode)提前约定其它编码的映射规则，来实现异构物联网标识的兼容，进而完成异构物联网标识的自动识别与解析。然而，由于不同综合性标识体系之间是互为竞争的关系，且各自独立成体系，因此无法使用统一的标识体系来完成不同编码的解析和互通，造成异构物联网标识的识别过程繁琐且效率低。
发明内容
本公开实施例提供一种物联网标识的识别方法、装置及终端设备，以解决相关技术中的异构物联网标识的识别过程繁琐且效率低的问题。
第一方面，本公开实施例提供了一种物联网标识的识别方法，包括：
获取待识别物联网标识；
将所述待识别物联网标识转换为多边形图形；
利用预先训练的图形分类模型，对所述多边形图形进行识别，得到表示所述待识别物联网标识的编码类别的识别结果；
根据所述待识别物联网标识的编码类别，对所述待识别物联网标识进行解析。
第二方面，本公开实施例提供了一种物联网标识的识别装置，包括：
第一获取模块，用于获取待识别物联网标识；
第一转换模块，用于将所述待识别物联网标识转换为多边形图形；
识别模块，用于利用预先训练的图形分类模型，对所述多边形图形进行识别，得到表示所述待识别物联网标识的编码类别的识别结果；
解析模块，用于根据所述待识别物联网标识的编码类别，对所述待识别物联网标识进行解析。
第三方面，本公开实施例提供了一种终端设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，其中，所述计算机程序被所述处理器执行时可实现上述物联网标识的识别方法的步骤。
第四方面，本公开实施例提供了一种计算机可读存储介质，其上存储有计算机程序，其中，所述计算机程序被处理器执行时可实现上述物联网标识的识别方法的步骤。
本公开实施例中，通过将待识别物联网标识转换为多边形图形，并利用预先训练的图形分类模型，对转换的多边形图形进行识别，得到表示待识别物联网标识的编码类别的识别结果，可以在不额外创建新的标识体系，和不改变相关技术中的标识结构的情况下，实现对不同编码体系的物联网标识的自动识别，从而简化异构物联网标识的识别过程，提高识别效率。
进一步的，本公开实施例的识别方法，不用强制物联网对象采用统一的编码体系，且可以将不同编码体系的物联网标识转换为统一的多边形图形，并利用预先训练的图形分类模型来识别不同编码体系对应的多边形图形类别，从而实现识别不同编码体系的物联网标识，相比于相关技术中的综合性标识的识别方式，可以具有更好的可扩展性，能够不断的增加支持自动识别的标识种类。
附图说明
为了更清楚地说明本公开实施例的技术方案，下面将对本公开实施例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公开的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本公开实施例的物联网标识的识别方法的流程图；
图2为本公开实施例的将标识转换多边形图形的流程图；
图3A、图3B和图3C为本公开具体实例的将标识转换多边形图形的过程示意图；
图4为本公开实施例的物联网标识的识别装置的结构示意图；
图5为本公开实施例的终端设备的结构示意图。
具体实施方式
下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例，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，都属于本公开保护的范围。
首先指出的是，本公开实施例提供了一种针对异构物联网标识的自动识别方法，既不需要额外创建新的标识体系，也不需要改变相关技术中的标识结构，通过将不同编码体系的物联网标识转换为统一的多边形图形，可以利用预先训练的图形分类模型来识别不同编码体系对应的图形类别，从而自动识别出物联网标识的编码类别，从而简化异构物联网标识的识别过程，提高 识别效率。
请参见图1，图1是本公开实施例提供的一种物联网标识的识别方法的流程图，如图1所示，该识别方法包括以下步骤：
步骤101：获取待识别物联网标识。
其中，上述待识别物联网标识可以理解为异构物联网标识。上述待识别物联网标识可以处于不同的载体上。比如，上述待识别物联网标识可处于的载体包括但不限于二维码、条码，以及射频识别(Radio Frequency Identification，RFID)标签等。
步骤102：将待识别物联网标识转换为多边形图形。
可以理解的，在执行步骤102时，可以基于预设规则，将待识别物联网标识转换为满足预设条件的多变形图形。该多变形图形可以图像的形式体现，即具体实现时，可将待识别物联网标识转换为包括相应多边形图形的图像。
步骤103：利用预先训练的图形分类模型，对所述多边形图形进行识别，得到表示待识别物联网标识的编码类别的识别结果。
其中，上述图形分类模型可基于机器学习的物体识别(或图形识别)方法预先训练得到。在执行步骤103时，可将转换得到的多边形图形输入到预先训练的图形分类模型中，以对输入的多边形图形进行识别，并输出表示待识别物联网标识的编码类别的识别结果。
这样，通过利用预先训练的图形分类模型，对转换得到的多边形图形进行识别，可以将异构物联网标识的编码类别的自动识别问题，转换为基于图形的物体识别问题，从而简化标识识别过程。
步骤104：根据待识别物联网标识的编码类别，对待识别物联网标识进行解析。
具体的，在得到表示待识别物联网标识的编码类别的识别结果后，可获知待识别物联网标识的编码类别，而根据待识别物联网标识的编码类别，可以调用对应的标识解析服务，对待识别物联网标识进行解析，从而获得待识别物联网标识对应的物联网对象的描述信息。比如，若待识别物联网标识的编码类别为Ecode编码，则可调用中国物品编码中心解析待识别物联网标识。
本公开实施例中，通过将待识别物联网标识转换为多边形图形，并利用 预先训练的图形分类模型，对转换的多边形图形进行识别，得到表示待识别物联网标识的编码类别的识别结果，可以在不额外创建新的标识体系，和不改变相关技术中的标识结构的情况下，实现对不同编码体系的物联网标识的自动识别，从而简化异构物联网标识的识别过程，提高识别效率。
进一步的，本公开实施例的识别方法，不用强制物联网对象采用统一的编码体系，且可以将不同编码体系的物联网标识转换为统一的多边形图形，并利用预先训练的图形分类模型来识别不同编码体系对应的多边形图形类别，从而实现识别不同编码体系的物联网标识，相比于相关技术中的综合性标识的识别方式，可以具有更好的可扩展性，能够不断的增加支持自动识别的标识种类。
本公开实施例中，可选的，步骤102中将待识别物联网标识转换为多边形图形的过程可包括：
确定待识别物联网标识的编码位数，并将所述待识别物联网标识的每一个编码位转换为基准值；
根据所述编码位数和所述每一个编码位的基准值，构建所述多边形图形；
其中，所述多边形图形中多边形的顶点的个数等于所述编码位数，所述待识别物联网标识的编码位与所述多边形的顶点一一对应，每一个顶点到所述多边形中基准点的距离与所述顶点对应的编码位的基准值成预设倍数关系，每相邻两个顶点与所述基准点所成的夹角之间相同。
可以理解的，上述基准点在相应多边形中是唯一确定的，具体实现时，可预先确定并结合待识别物联网标识所有编码位的基准值中的最大基准值构建相应的多边形图形，比如首先以预先确定的基准点为圆心，且以最大基准值为半径画圆，然后基于所画的圆，构建相应的多边形图形。
这样，可以将待识别物联网标识转换为满足预设条件的多变形图形。
进一步的，上述将待识别物联网标识的每一个编码位转换为基准值可选为：将待识别物联网标识的每一个编码位转换为ASCII码。
一种实施方式中，参见图2所示，上述将待识别物联网标识转换为多边形图形的过程可包括如下步骤：
步骤201：确定待识别物联网标识(以下简称为标识)的编码位数n，并 将标识的每一个编码位转换为ASCII码；
步骤202：在标识所有编码位的ASCII码中，选取最大ASCII码，并创建空白图像，该空白图像的长和宽等于两倍的最大ASCII码；
步骤203：以该空白图像的中心为圆心，且以最大ASCII码为半径，在该空白图像中画圆；
步骤204：根据标识的编码位数n，将上述圆n等分，并分别连接圆心和圆上的各等分点；
步骤205：按照顺序(比如，逆时针或者顺时针)将标识的每一个编码位分别映射为圆心与各等分点连接线上的一点，该点到圆心的距离等于相应编码位的ASCII码；
步骤206：将所有映射的点进行连接，即得到该标识对应的多边形图形。
可以理解的，上述实施方式中，编码位的基准值即是ASCII码；圆心即是多边形中的基准点，根据最大ASCII码确定；每一个编码位映射的圆心与等分点连接线上的点即是多边形的顶点，多边形的顶点的个数等于标识的编码位数；每相邻两个顶点与圆心所成的夹角之间相同。上述实施方式是以多边形顶点到圆心(基准点)的距离等于相应编码位的ASCII码(即预设倍数为1)为例，但除此之外，也选择其它的预设倍数，比如0.5、1.5或2等，本公开实施例不对此进行限制。
下面以EAN-8条形码为例，结合图3A、图3B和图3C对本公开具体实例的将标识转换多边形图形的过程进行说明。
假设如图3A所示，某EAN-8条形码的待识别标识为87217582，则该标识的编码位数为8，将标识的每一个编码位转换为ASCII码后可得到38 37 32 31 37 35 38 32，其中最大ASCII码为38，因此在转换多边形图形时，可首先创建大小为76×76的空白图像，并以空白图像中心o为圆心，且以最大ASCII码38为半径，在空白图像中画圆；其次，根据编码位数8，将圆8等分，并分别连接圆心和圆上的8个等分点；再次，根据每一个编码位的ASCII码，按照顺时针方向将每一个编码位分别映射为圆心与各等分点连接线上的一点，该点到圆心的距离等于相应编码位的ASCII码；然后，将所有映射的点进行连接，即得到包含多边形图形的图像，如图3B所示；最后，根据包含多边形 图形的图像，可进一步得到所需的多边形图形，即标识87217582对应的多边形图形，如图3C所示。
本公开实施例中，可选的，步骤101之前，所述方法还可包括：
获取标识样本集，其中，所述标识样本集中包括至少两类标识样本子集，每一类标识样本子集对应于一种编码类别；
将所述标识样本集中的所有标识样本转换为多边形图形；此转换为多边形图形的方式与上述将待识别物联网标识转换为多边形图形的方式相同，可参见上述转换方式，在此不再赘述；
根据所有标识样本对应的多边形图形，进行分类模型的训练，得到图形分类模型。
其中，上述标识样本子集对应的编码类别可选为Ecode、EAN-8、EAN-13、EAN-128、URL或OID等等。上述多变形图形可以图像的形式体现，即可将标识样本集中的所有标识样本转换为包括相应多边形图形的图像样本，并根据图像样本进行分类模型的训练。在进行分类模型的训练时，可首先利用卷积神经网络(CNN)从图像样本中提取图像特征，然后基于深度学习算法或者经典机器学习算法进行分类模型的训练，以得到所需的图形分类模型。
这样，基于标识-图形的转换方法，可以将标识编码类别的自动识别转换为图形的分类问题，从而能够通过目前比较成熟的物体或图形分类技术实现标识的准确分类，简化识别过程，提高识别效率。
进一步的，为了提高训练效率，上述根据所有标识样本的多边形图形，进行分类模型的训练，得到图形分类模型的过程可包括：
对所有标识样本的多边形图形进行归一化处理；其中，该归一化处理方式可选为将多边形图归一化为统一的尺寸大小；
根据归一化处理后的所有标识样本的多边形图形，进行分类模型的训练，得到图形分类模型。
这样，通过上述归一化处理过程，可以在训练过程中提高效率。
上述实施例对本公开的物联网标识的识别方法进行了说明，下面将结合实施例和附图对本公开的物联网标识的识别装置进行说明。
请参见图4，图4是本公开实施例提供的一种物联网标识的识别装置的 结构示意图，如图4所示，该识别装置包括：
第一获取模块41，用于获取待识别物联网标识；
第一转换模块42，用于将所述待识别物联网标识转换为多边形图形；
识别模块43，用于利用预先训练的图形分类模型，对所述多边形图形进行识别，得到表示所述待识别物联网标识的编码类别的识别结果；
解析模块44，用于根据所述待识别物联网标识的编码类别，对所述待识别物联网标识进行解析。
本公开实施例中，通过将待识别物联网标识转换为多边形图形，并利用预先训练的图形分类模型，对转换的多边形图形进行识别，得到表示待识别物联网标识的编码类别的识别结果，可以在不额外创建新的标识体系，和不改变相关技术中的标识结构的情况下，实现对不同编码体系的物联网标识的自动识别，从而简化异构物联网标识的识别过程，提高识别效率。
本公开实施例中，可选的，所述第一转换模块42包括：
确定单元，用于确定所述待识别物联网标识的编码位数，并将所述待识别物联网标识的每一个编码位转换为基准值；
构建单元，用于根据所述编码位数和所述每一个编码位的基准值，构建所述多边形图形；
其中，所述多边形图形中多边形的顶点的个数等于所述编码位数，所述待识别物联网标识的编码位与所述多边形的顶点一一对应，每一个顶点到所述多边形中基准点的距离与所述顶点对应的编码位的基准值成预设倍数关系，每相邻两个顶点与所述基准点所成的夹角之间相同。
可选的，所述确定单元还用于：
将所述待识别物联网标识的每一个编码位转换为ASCII码。
可选的，所述识别装置还包括：
第二获取模块，用于获取标识样本集，其中，所述标识样本集中包括至少两类标识样本子集，每一类标识样本子集对应于一种编码类别；
第二转换模块，用于将所述标识样本集中的所有标识样本转换为多边形图形；
训练模块，用于根据所有标识样本对应的多边形图形，进行分类模型的 训练，得到所述图形分类模型。
可选的，所述训练模块包括：
处理单元，用于对所有标识样本的多边形图形进行归一化处理；
训练单元，用于根据归一化处理后的所有标识样本的多边形图形，进行分类模型的训练，得到所述图形分类模型。
此外，本公开实施例还提供了一种终端设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，其中，所述计算机程序被所述处理器执行时可实现上述物联网标识的识别方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
具体的，参见图5所示，本公开实施例还提供了一种终端设备，包括总线51、收发机52、天线53、总线接口54、处理器55和存储器56。
在本公开实施例中，所述终端设备还包括：存储在存储器56上并可在处理器55上运行的计算机程序。具体的，所述计算机程序被处理器55执行时可实现上述物联网标识的识别方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
在图5中，总线架构(用总线51来代表)，总线51可以包括任意数量的互联的总线和桥，总线51将包括由处理器55代表的一个或多个处理器和存储器56代表的存储器的各种电路链接在一起。总线51还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其他电路链接在一起，这些都是本领域所公知的，因此，本文不再对其进行进一步描述。总线接口54在总线51和收发机52之间提供接口。收发机52可以是一个元件，也可以是多个元件，比如多个接收器和发送器，提供用于在传输介质上与各种其他装置通信的单元。经处理器55处理的数据通过天线53在无线介质上进行传输，进一步，天线53还接收数据并将数据传送给处理器55。
处理器55负责管理总线51和通常的处理，还可以提供各种功能，包括定时，外围接口，电压调节、电源管理以及其他控制功能。而存储器56可以被用于存储处理器55在执行操作时所使用的数据。
可选的，处理器55可以是CPU、专用集成电路(Application Specific Integrated Circuits，ASIC)、现场可编程门阵列(Field-Programmable Gate Array， FPGA)或复杂可编程逻辑设备(Complex Programmable Logic Device，CPLD)。
本公开实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现上述物联网标识的识别方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
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。
需要说明的是，在本文中，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、物品或者装置不仅包括那些要素，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、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
上述本公开实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更可选的实施方式。基于这样的理解，本公开的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本公开各个实施例所述的方法。
可以理解的是，本公开实施例描述的这些实施例可以用硬件、软件、固 件、中间件、微码或其组合来实现。对于硬件实现，单元、模块、子单元、子模块等可以实现在一个或多个专用集成电路(Application Specific Integrated Circuits，ASIC)、数字信号处理器(Digital Signal Processing，DSP)、数字信号处理设备(DSP Device，DSPD)、可编程逻辑设备(Programmable Logic Device，PLD)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)、通用处理器、控制器、微控制器、微处理器、用于执行本公开所述功能的其它电子单元或其组合中。
对于软件实现，可通过执行本公开实施例所述功能的模块(例如过程、函数等)来实现本公开实施例所述的技术。软件代码可存储在存储器中并通过处理器执行。存储器可以在处理器中或在处理器外部实现。
以上所述仅是本公开的可选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本公开原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本公开的保护范围。

Claims (10)

  1. 一种物联网标识的识别方法，包括：
    获取待识别物联网标识；
    将所述待识别物联网标识转换为多边形图形；
    利用预先训练的图形分类模型，对所述多边形图形进行识别，得到表示所述待识别物联网标识的编码类别的识别结果；
    根据所述待识别物联网标识的编码类别，对所述待识别物联网标识进行解析。
  2. 根据权利要求1所述的识别方法，其中，所述将所述待识别物联网标识转换为多边形图形，包括：
    确定所述待识别物联网标识的编码位数，并将所述待识别物联网标识的每一个编码位转换为基准值；
    根据所述编码位数和所述每一个编码位的基准值，构建所述多边形图形；
    其中，所述多边形图形中多边形的顶点的个数等于所述编码位数，所述待识别物联网标识的编码位与所述多边形的顶点一一对应，每一个顶点到所述多边形中基准点的距离与所述顶点对应的编码位的基准值成预设倍数关系，每相邻两个顶点与所述基准点所成的夹角之间相同。
  3. 根据权利要求2所述的识别方法，其中，所述将所述待识别物联网标识的每一个编码位转换为基准值，包括：
    将所述待识别物联网标识的每一个编码位转换为ASCII码。
  4. 根据权利要求1所述的识别方法，其中，所述获取待识别物联网标识之前，所述识别方法还包括：
    获取标识样本集，其中，所述标识样本集中包括至少两类标识样本子集，每一类标识样本子集对应于一种编码类别；
    将所述标识样本集中的所有标识样本转换为多边形图形；
    根据所有标识样本对应的多边形图形，进行分类模型的训练，得到所述图形分类模型。
  5. 根据权利要求1所述的识别方法，其中，所述根据所有标识样本的多 边形图形，进行分类模型的训练，得到所述图形分类模型，包括：
    对所有标识样本的多边形图形进行归一化处理；
    根据归一化处理后的所有标识样本的多边形图形，进行分类模型的训练，得到所述图形分类模型。
  6. 一种物联网标识的识别装置，包括：
    第一获取模块，用于获取待识别物联网标识；
    第一转换模块，用于将所述待识别物联网标识转换为多边形图形；
    识别模块，用于利用预先训练的图形分类模型，对所述多边形图形进行识别，得到表示所述待识别物联网标识的编码类别的识别结果；
    解析模块，用于根据所述待识别物联网标识的编码类别，对所述待识别物联网标识进行解析。
  7. 根据权利要求6所述的识别装置，其中，所述第一转换模块包括：
    确定单元，用于确定所述待识别物联网标识的编码位数，并将所述待识别物联网标识的每一个编码位转换为基准值；
    构建单元，用于根据所述编码位数和所述每一个编码位的基准值，构建所述多边形图形；
    其中，所述多边形图形中多边形的顶点的个数等于所述编码位数，所述待识别物联网标识的编码位与所述多边形的顶点一一对应，每一个顶点到所述多边形中基准点的距离与所述顶点对应的编码位的基准值成预设倍数关系，每相邻两个顶点与所述基准点所成的夹角之间相同。
  8. 根据权利要求7所述的识别装置，其中，所述确定单元还用于：
    将所述待识别物联网标识的每一个编码位转换为ASCII码。
  9. 一种终端设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行时实现如权利要求1至5中任一项所述的物联网标识的识别方法的步骤。
  10. 一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1至5中任一项所述的物联网标识的识别方法的步骤。
PCT/CN2020/070091 2019-01-02 2020-01-02 物联网标识的识别方法、装置及终端设备 Ceased WO2020140937A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910000936.7A CN111401486B (zh) 2019-01-02 2019-01-02 一种物联网标识的识别方法、装置及终端设备
CN201910000936.7 2019-01-02

Publications (1)

Publication Number Publication Date
WO2020140937A1 true WO2020140937A1 (zh) 2020-07-09

Family

ID=71407268

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/070091 Ceased WO2020140937A1 (zh) 2019-01-02 2020-01-02 物联网标识的识别方法、装置及终端设备

Country Status (2)

Country Link
CN (1) CN111401486B (zh)
WO (1) WO2020140937A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112866375A (zh) * 2021-01-14 2021-05-28 国网上海市电力公司 一种编码解析系统和方法
CN114091616A (zh) * 2021-11-29 2022-02-25 南京华苏科技有限公司 基于深度学习网络的物联网设备的识别方法
CN114584522A (zh) * 2022-01-21 2022-06-03 中国人民解放军国防科技大学 一种物联网设备的识别方法、系统、介质及终端

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111327662B (zh) * 2018-12-17 2023-07-11 华为云计算技术有限公司 一种异构物联网平台的通信方法及管理装置
CN114444443B (zh) * 2020-11-06 2024-11-12 中国移动通信有限公司研究院 一种标识识别方法、装置及终端设备
CN113098992A (zh) * 2021-04-02 2021-07-09 周宏仁 编码方法及装置、存储介质及电子设备
CN115880550A (zh) * 2021-09-27 2023-03-31 中国移动通信有限公司研究院 一种物联网标识的识别、装置及设备
CN114328630B (zh) * 2022-01-24 2023-06-23 嘉应学院 一种基于物联网的设备识别系统
CN116935088A (zh) * 2022-04-02 2023-10-24 中国移动通信有限公司研究院 物联网标识识别方法、装置、设备及可读存储介质

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103491145A (zh) * 2013-09-09 2014-01-01 中国科学院计算机网络信息中心 一种物联网异构标识解析方法与系统
CN103929499A (zh) * 2014-05-05 2014-07-16 中国科学院计算机网络信息中心 一种物联网异构标识识别方法和系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103455574B (zh) * 2013-08-21 2015-10-14 中国物品编码中心 物联网统一标识编码多模式识别的方法和装置
CN105224598B (zh) * 2015-08-31 2018-11-27 中国互联网络信息中心 一种基于动态特征的异构物联网标识识别方法及系统
US20180227352A1 (en) * 2017-02-07 2018-08-09 Drumwave Inc. Distributed applications and related protocols for cross device experiences

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103491145A (zh) * 2013-09-09 2014-01-01 中国科学院计算机网络信息中心 一种物联网异构标识解析方法与系统
CN103929499A (zh) * 2014-05-05 2014-07-16 中国科学院计算机网络信息中心 一种物联网异构标识识别方法和系统

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112866375A (zh) * 2021-01-14 2021-05-28 国网上海市电力公司 一种编码解析系统和方法
CN112866375B (zh) * 2021-01-14 2024-01-23 国网上海市电力公司 一种编码解析系统和方法
CN114091616A (zh) * 2021-11-29 2022-02-25 南京华苏科技有限公司 基于深度学习网络的物联网设备的识别方法
CN114584522A (zh) * 2022-01-21 2022-06-03 中国人民解放军国防科技大学 一种物联网设备的识别方法、系统、介质及终端
CN114584522B (zh) * 2022-01-21 2024-02-06 中国人民解放军国防科技大学 一种物联网设备的识别方法、系统、介质及终端

Also Published As

Publication number Publication date
CN111401486B (zh) 2023-11-28
CN111401486A (zh) 2020-07-10

Similar Documents

Publication Publication Date Title
WO2020140937A1 (zh) 物联网标识的识别方法、装置及终端设备
CN111160012B (zh) 医学术语识别方法、装置和电子设备
CA3115581C (en) Automated architectural specification generation and hardware identification
CN103455574B (zh) 物联网统一标识编码多模式识别的方法和装置
CN107451106A (zh) 文本纠正方法及装置、电子设备
CN116775875A (zh) 问题语料库构建方法和装置、问答方法、设备及存储介质
CN115495489A (zh) 跨境物流订单轨迹查询方法、装置、终端设备和存储介质
CN113220949B (zh) 一种隐私数据识别系统的构建方法及装置
CN114338413A (zh) 网络中设备的拓扑关系的确定方法、装置以及存储介质
CN114444443B (zh) 一种标识识别方法、装置及终端设备
CN117539984A (zh) 一种回复文本的生成方法、装置及设备
CN116991875A (zh) 一种基于大模型的sql语句生成、别名映射方法及设备
CN117351995A (zh) 基于深度学习复合模型的环境声音识别方法及装置
CN112567347B (zh) 数据处理装置、数据处理方法和计算机可读存储介质
CN115719443A (zh) 利用2d预训练模型作为3d下游任务主干网络的方法及系统
CN112182320B (zh) 聚类数据处理方法、装置、计算机设备及存储介质
CN121125632A (zh) 网络流量分类方法、装置、设备、存储介质及程序产品
CN116663677B (zh) 模型训练方法、装置、电子设备及存储介质
CN109560964B (zh) 一种设备合规检查方法及装置
CN114461810B (zh) 关系三元组生成方法、装置、电子装置和存储介质
CN114492434B (zh) 一种基于运单号自动识别模型智能识别运单号方法
CN104036210A (zh) 一种超高频阅读器对多标签识别性能测试方法
CN115733903A (zh) 一种基于自然处理特征工程的网络资产识别方法和系统
CN116095187A (zh) 数据交互方法、设备及存储介质
CN113938819B (zh) 一种网络设备位置的确定方法及装置

Legal Events

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

Ref document number: 20736156

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS (EPO FORM 1205A DATED 15.10.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20736156

Country of ref document: EP

Kind code of ref document: A1