WO2019144416A1 - 信息处理方法、系统、云处理设备以及计算机程序产品 - Google Patents

信息处理方法、系统、云处理设备以及计算机程序产品 Download PDF

Info

Publication number
WO2019144416A1
WO2019144416A1 PCT/CN2018/074489 CN2018074489W WO2019144416A1 WO 2019144416 A1 WO2019144416 A1 WO 2019144416A1 CN 2018074489 W CN2018074489 W CN 2018074489W WO 2019144416 A1 WO2019144416 A1 WO 2019144416A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
vehicle
information
image information
abnormal feature
Prior art date
Application number
PCT/CN2018/074489
Other languages
English (en)
French (fr)
Inventor
廉士国
南一冰
Original Assignee
深圳前海达闼云端智能科技有限公司
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 深圳前海达闼云端智能科技有限公司 filed Critical 深圳前海达闼云端智能科技有限公司
Priority to CN201880000066.7A priority Critical patent/CN108323209B/zh
Priority to PCT/CN2018/074489 priority patent/WO2019144416A1/zh
Publication of WO2019144416A1 publication Critical patent/WO2019144416A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08Insurance
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • G06N20/10Machine learning using kernel methods, e.g. support vector machines [SVM]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/60Type of objects
    • G06V20/62Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/625License plates
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08Detecting or categorising vehicles

Definitions

  • the present application relates to the field of information processing technologies, and in particular, to an information processing method, system, cloud processing device, and computer program product.
  • the application based on the Internet of Vehicles is mainly embodied in the following fields: insurance field--the insurance company realizes the risk assessment of the vehicle through the relevant information of the vehicle obtained from the vehicle network, the calculation of the vehicle premium, and the online loss determination. And other related business processing.
  • the on-site evidence can be obtained by photographing, and then the staff of the insurance company conducts a loss calculation on the on-site evidence.
  • the embodiment of the present application provides an information processing method, system, cloud processing device, and computer program product, which can improve the accuracy and reliability of the authenticity determination of the on-site evidence, reduce the labor cost, and reduce the loss of the insurance company.
  • an embodiment of the present application provides an information processing method, including:
  • the cloud processing device acquires image information collected by the terminal
  • the embodiment of the present application further provides an information processing system, including:
  • An acquiring unit configured to acquire image information collected by the terminal
  • a determining unit configured to identify the image information, and determine whether the image information has an abnormal feature
  • a sending unit configured to send image information with an abnormal feature to the manual module
  • a receiving unit configured to receive a result returned by the manual module.
  • the embodiment of the present application further provides a cloud processing device, where the device includes a processor and a memory; the memory is configured to store an instruction, when the instruction is executed by the processor, causing the device to perform, for example, The method of any of the first aspects.
  • the embodiment of the present application further provides a computer program product, which can be directly loaded into an internal memory of a computer and includes software code. After the computer program is loaded and executed by a computer, the first aspect can be implemented. One such method.
  • the information processing method, system, cloud processing device, and computer program product provided by the embodiments of the present application obtain image information collected by the terminal, and then identify the image information to determine whether the image information has an abnormal feature.
  • the method is sent to the manual module, and the second judgment is manually assisted.
  • the accuracy and reliability of the authenticity determination of the on-site evidence can be improved, the labor cost can be reduced, and the loss of the insurance company can be reduced, thereby solving the problem.
  • the user creates the on-site evidence that is inconsistent with the actual situation, in exchange for higher insurance compensation, which brings a great loss to the insurance company.
  • FIG. 1 is a flowchart of an embodiment of an information processing method according to an embodiment of the present application
  • FIG. 2 is another flowchart of an embodiment of an information processing method according to an embodiment of the present disclosure
  • FIG. 3 is a schematic structural diagram of an embodiment of an information processing system according to an embodiment of the present disclosure.
  • FIG. 4 is another schematic structural diagram of an embodiment of an information processing system according to an embodiment of the present disclosure.
  • FIG. 5 is a schematic structural diagram of an embodiment of a cloud processing device according to an embodiment of the present disclosure.
  • the word “if” as used herein may be interpreted as “when” or “when” or “in response to determining” or “in response to detecting.”
  • the phrase “if determined” or “if detected (conditions or events stated)” may be interpreted as “when determined” or “in response to determination” or “when detected (stated condition or event) “Time” or “in response to a test (condition or event stated)”.
  • the specific operation of the vehicle is to take pictures of the accident scene by the insurance claims clerk or the traffic control personnel, and then determine the corresponding claims information, and enter the quotation and maintenance list of the repair shop/4S shop into the claim system.
  • the owner can take photos of the scene of the accident through a terminal such as a mobile phone, and submit a photo of the scene of the case, so that the insurance company can determine the damage according to the scene of the case and determine the result of the claim.
  • FIG. 1 is a flowchart of an embodiment of an information processing method according to an embodiment of the present disclosure. As shown in FIG. 1 , the information processing method in this embodiment may include the following steps:
  • the cloud processing device acquires image information collected by the terminal.
  • the user first uses the terminal to collect image information, and the process of collecting may be to collect an image of the accident scene by using a camera or a sensor of the terminal, and then the user operates the corresponding page in the terminal, and the collected image, and
  • the image information such as the text information related to the accident scene is uploaded to the cloud processing device, and the cloud processing device receives the image information uploaded by the user.
  • the image information of the accident scene may include at least one vehicle image
  • the vehicle image includes license plate information, for example, an image including a license plate and a front position, an image of a damaged position of the vehicle, and the like, and position information and pressure information of the terminal. , text information related to the case, etc.
  • the image is classified and identified to determine whether the image is a forged image; when the image is a forged image, it is determined that the image information has an abnormal feature.
  • the secondary processed image may be processed by an image processing software.
  • the remake image may be a photograph of a printed photo, an electronic display device, etc., since the shooting environment of the remake image may not be completely consistent with the shooting environment of the original image, the illumination type, the illumination direction, the illumination intensity, and the difference of the photographic subject may cause remake There are some differences in the colors, textures, and other features between the image and the original image. With these differences, the detection of remake images can be achieved.
  • the detection of the remake image can be implemented at least by one of the following methods:
  • the original image ie, the vehicle image in the image information captured by the user in the foregoing content
  • the color, texture, or spectrum of the corresponding forged image are first extracted, and then the features are classified using parsing or machine learning.
  • the original image only undergoes one imaging process, while the forged image undergoes at least two imaging processes, the imaging process is different, and the frequency distribution of the finally acquired image is also different.
  • the original image and the forged image are transformed by Fourier transform. Converting to a spectrogram, extracting features of these spectrograms, and then using a machine learning method to train a classifier, such as an SVM, to classify the features to identify forged images.
  • the training classifier can be color, A combination of different features such as texture or spectrum.
  • the original image and the forged image are directly used as two categories, input convolutional neural network (CNN) for classification and identification.
  • CNN convolutional neural network
  • the implementation process is also divided into two parts: training and deployment.
  • training the original image and the forged image are classified into two categories.
  • the data sample is input into CNN training.
  • the classification model CNN1 is obtained.
  • the model is deployed in the cloud, and an image is input to output whether the recognition result is a forged image.
  • the image is compared with the image in the vehicle damage map. If the image is the same as the image in the vehicle damage map, it is determined that the image information has an abnormal feature.
  • the image in the image information is obtained by copying the vehicle damage gallery image, and therefore, the feature matching method or the map searching method can be used.
  • the features of all the images in the existing vehicle damage gallery may be extracted, and the features may be SIFT corner points, color histograms, hash values, etc., and the feature library is established.
  • the search match is performed in the library.
  • the feature matching degree of the search exceeds the set threshold, it indicates that the image is the same as the image in the vehicle damage map, and is copied, and it is determined that the image information has an abnormal feature.
  • the image is compared with the image in the license plate information gallery. If the image is different from the image in the license plate information gallery, it is determined that the image information has an abnormal feature.
  • the vehicle CNN2 detects the position of the vehicle body region in the image information, and inputs the vehicle body image into the classification network CNN3 to identify information such as the manufacturer and model, such as the Audi A4L, the BMW 520Li, and the like, and extracts a fixed body region (such as an engine cover).
  • the input classification network CNN4 recognizes the body color, and all of the above CNNs are obtained through a pre-training process. Further identifying the license plate number, and searching for the relevant information in the pre-stored vehicle information database through the license plate number, and comparing the information recognized by the CNN with the retrieved information. If the information is inconsistent, the license plate number information has a problem, and the vehicle is The deck determines that the image information has an abnormal feature.
  • the image is compared with the image in the vehicle brand feature library. If the image is different from the image in the vehicle brand feature library, it is determined that the image information has an abnormal feature.
  • the position of each component of the vehicle body is detected, and the image can be input into the detection network CNN5 by using a deep learning method to obtain the position and name of each component of the vehicle, and the location of the corresponding name is retrieved in the vehicle brand feature database.
  • the standard image is extracted separately for each component region in the image in the image information and the SIFT feature of the corresponding standard image. If they are different, it indicates that there is a fake, and the image information is determined to have an abnormal feature.
  • the position information of the vehicle in the text information related to the case is extracted; and the position information of the vehicle and the position information of the terminal are compared, and when the two are different, it is determined that the image information has an abnormal feature.
  • the location information in the text information is manually filled by the user, and the corresponding location is the location of the accident. If the text information is inconsistent with the location information of the user terminal, the user is not in the accident place, and the accident authenticity Lower, it is determined that the image information has an abnormal feature.
  • the foregoing five situations can be judged at the same time, and can be judged according to a certain order, and can also determine whether the next situation needs to be performed according to the judgment result of the previous situation.
  • the various combinations are all within the scope of protection in the embodiments of the present application.
  • the manual module is used to assist in judging, and the image information of the abnormal feature is manually determined to determine whether there is an abnormal feature. When there is an abnormal feature, the corresponding result is returned.
  • the information processing method provided by the embodiment of the present application obtains the image information collected by the terminal, and then identifies the image information to determine whether the image information has an abnormal feature, and if there is an abnormal feature, the method is sent to the manual module, and is manually assisted.
  • the second judgment by adopting the method provided by the present application, can improve the accuracy and reliability of the authenticity judgment of the on-site evidence, reduce the labor cost, thereby reducing the loss of the insurance company, and solving the user's production and actual situation in the prior art. Inconsistent on-site evidence, in exchange for higher insurance compensation, has brought a lot of losses to the insurance company.
  • the embodiment of the present application may further include the following steps, and the purpose thereof is to further improve the accuracy and reliability of the authenticity determination of the on-site evidence.
  • FIG. 2 is provided by the embodiment of the present application. Another flowchart of the embodiment of the information processing method, as shown in FIG. 2, the information processing method of the embodiment may further include the following steps:
  • FIG. 3 is a schematic structural diagram of an embodiment of an information processing system according to an embodiment of the present disclosure. As shown in FIG. 3, the system of this embodiment may be used.
  • the method includes an obtaining unit 11, a determining unit 12, a transmitting unit 13, and a receiving unit 14.
  • the obtaining unit 11 is configured to acquire image information collected by the terminal.
  • the determining unit 12 is configured to identify the image information, and determine whether the image information has an abnormal feature.
  • the sending unit 13 is configured to send the image information with the abnormal feature to the manual module.
  • the receiving unit 14 is configured to receive a result returned by the manual module.
  • the image information includes: at least one vehicle image
  • the determining unit 12 is specifically configured to:
  • the vehicle image is a forged image
  • the forged image includes a reticle image or a secondary processed image.
  • the image information includes: at least one vehicle image
  • the determining unit 12 is specifically configured to:
  • the vehicle image is compared with the image in the vehicle damage map. If the vehicle image is the same as the image in the vehicle damage map, it is determined that the image information has an abnormal feature.
  • the image information includes: at least one vehicle image
  • the determining unit 12 is specifically configured to:
  • the vehicle image is compared with the image in the license plate information gallery. If the vehicle image is different from the image in the license plate information gallery, it is determined that the image information has an abnormal feature.
  • the image information includes: at least one vehicle image
  • the determining unit 12 is specifically configured to:
  • the vehicle image is compared with the image in the vehicle brand feature library. If the vehicle image is different from the image in the vehicle brand feature library, it is determined that the image information has an abnormal feature.
  • the image information includes: location information of the terminal and location information of the vehicle;
  • the determining unit 12 is specifically configured to:
  • the system of the present embodiment can be used to implement the technical solution of the method embodiment shown in FIG. 1 , and the implementation principle and technical effects are similar, and details are not described herein again.
  • FIG. 4 is another schematic structural diagram of an embodiment of an information processing system according to an embodiment of the present application. As shown in FIG. 4, the system of this embodiment is shown in FIG. It may also include: a training unit 15.
  • a training unit for adding results to the training set to train the recognition algorithm.
  • the system of the present embodiment can be used to implement the technical solution of the method embodiment shown in FIG. 2, and the implementation principle and technical effects are similar, and details are not described herein again.
  • FIG. 5 is a schematic structural diagram of an embodiment of a cloud processing device according to an embodiment of the present disclosure.
  • the cloud processing device includes a processor 21 and a memory 22; the memory 22 is for storing instructions that, when executed by the processor 21, cause the device to perform any of the methods described above.
  • the cloud processing device provided by the embodiment of the present application may be used to implement the technical solution of the method embodiment shown in FIG. 1 or FIG. 2, and the implementation principle and the technical effect are similar, and details are not described herein again.
  • the embodiment of the present application further provides a computer program product, which can be directly loaded into an internal memory of a computer and contains software code, and the computer program can be implemented by being loaded and executed by a computer. Any method.
  • the computer program product provided by the embodiment of the present application may be used to implement the technical solution of the method embodiment shown in FIG. 1 or FIG. 2, and the implementation principle and the technical effect are similar, and details are not described herein again.
  • the aforementioned program can be stored in a computer readable storage medium.
  • the program when executed, performs the steps including the foregoing method embodiments; and the foregoing storage medium includes various media that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Multimedia (AREA)
  • Accounting & Taxation (AREA)
  • Technology Law (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Image Analysis (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

本申请实施例提供一种信息处理方法、系统、云处理设备以及计算机程序产品,涉及及信息处理技术领域,在一定程度上可以提高对现场证据真实性判定的准确性和可靠性,降低人工成本,降低保险公司的损失。本申请实施例提供的信息处理方法,包括:获取终端采集的图像信息;对所述图像信息进行识别,确定所述图像信息是否存在异常特征;存在异常特征的图像信息发送至人工模块;接收所述人工模块返回的结果。

Description

信息处理方法、系统、云处理设备以及计算机程序产品 技术领域
本申请涉及信息处理技术领域,尤其涉及一种信息处理方法、系统、云处理设备以及计算机程序产品。
背景技术
随着车联网相关技术的不断成熟,传感器技术、移动通信技术、大数据技术和智能计算技术等均开始与车联网深度融合。在市场需求带动下,区别于传统的交通系统,车联网更加注重车与车、车与路、车与人之间的交互通信,可以说车联网的出现重新定义了车辆交通的运行方式。
现有技术中,基于车联网的应用主要体现在如下几个领域:保险领域—保险公司通过从车联网中获取到的车辆的相关信息,实现对车辆的风险评估,车辆保费计算、在线定损等相关业务处理。现有技术中,在发生交通事故后,可以通过拍照等方式获取现场证据,然后保险公司的工作人员对现场证据进行定损核算。
但由于用户可以使用伪造的照片、从互联网上获取的照片、伪造现场等方式,制作与实际情况不符合的现场证据,换取更高的保险赔偿,给保险公司带来了很大的损失。
发明内容
本申请实施例提供一种信息处理方法、系统、云处理设备以及计算机程序产品,可以提高对现场证据真实性判定的准确性和可靠性,降低人工成本,降低保险公司的损失。
第一方面,本申请实施例提供一种信息处理方法,包括:
云处理设备获取终端采集的图像信息;
对所述图像信息进行识别,确定所述图像信息是否存在异常特征;
将存在异常特征的图像信息发送至人工模块;
接收所述人工模块返回的结果。
第二方面,本申请实施例还提供一种信息处理系统,包括:
获取单元,用于获取终端采集的图像信息;
确定单元,用于对所述图像信息进行识别,确定所述图像信息是否存在异常特征;
发送单元,用于将存在异常特征的图像信息发送至人工模块;
接收单元,用于接收所述人工模块返回的结果。
第三方面,本申请实施例还提供一种云处理设备,所述设备包括处理器以及存储器;所述存储器用于存储指令,所述指令被所述处理器执行时,使得所述设备执行如第一方面中任一种所述的方法。
第四方面,本申请实施例还提供一种计算机程序产品,可直接加载到计算机的内部存储器中,并含有软件代码,所述计算机程序经由计算机载入并执行后能够实现如第一方面中任一种所述的方法。
本申请实施例提供的信息处理方法、系统、云处理设备以及计算机程序产品,通过获取终端采集的图像信息,然后对图像信息进行识别,确定图像信息是否存在异常特征,在存在异常特征的情况下,发送至人工模块,由人工辅助进行二次判断,通过采用本申请提供的方法,能够提高对现场证据真实性判定的准确性和可靠性,降低人工成本,进而降低保险公司的损失,解决了现有技术中用户制作与与实际情况不符合的现场证据,换取更高的保险赔偿,给保险公司带来了很大的损失的问题。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的信息处理方法实施例的流程图;
图2为本申请实施例提供的信息处理方法实施例的另一流程图;
图3为本申请实施例提供的信息处理系统实施例的结构示意图;
图4为本申请实施例提供的信息处理系统实施例的另一结构示意图;
图5为本申请实施例提供的云处理设备实施例的结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚,下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
在本申请实施例中使用的术语是仅仅出于描述特定实施例的目的,而非旨在限制本申请。在本申请实施例和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式,除非上下文清楚地表示其他含义。
应当理解,本文中使用的术语“和/或”仅仅是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中字符“/”,一般表示前后关联对象是一种“或”的关系。
取决于语境,如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”或“响应于检测”。类似地,取决于语境,短语“如果确定”或“如果检测(陈述的条件或事件)”可以被解释成为“当确定时”或“响应于确定”或“当检测(陈述的条件或事件)时”或“响应于检测(陈述的条件或事件)”。
随着家用汽车的普及,汽车数量不断增加,车辆出现事故的几率也在不断的增加,这给保险行业的工作带来了巨大压力。通常情况下,车辆出险的具体操作是由保险理赔业务员或者交管人员对事故现场拍照,然后确定相应的理赔信息,将维修厂/4S店的报价单、维修清单等录入理赔系统中。顺应网络的发展,在现有技术中,车主可以通过手机等终端对事故现场进行拍照,自行提交案件现场照片,使得保险公司根据案件现场照片来进行定损,确定理赔的结果。但是,采用这种方式给用户带来了方便的同时,又为用户提供了骗取保险的机会,例如,用户使用伪造的照片伪造事故现场、用户从互联网下载图像伪造事故现场等。因此,为了解决这个问题,本申请实施例提供一种信息处理方法,通过对用户采集的图像等信息进行处理,确定是否存在异常,在存在异常时,由人工辅助进行确认,可以提高对现场证据真实性判定的准确性和可靠性,降低人工成本,降低保险公司的损失。具体的,图1为本申请实施例提供的信息处理方法实施例的流程图,如图1所示,本实施例的信息处理方法,具体可以包括如下步骤:
101、云处理设备获取终端采集的图像信息。
在本申请实施例中,首先由用户使用终端采集图像信息,采集的过程可以是使用终端的摄像头或者传感器采集事故现场的图像,然后,用户在终端中操作相应的页面,将采集的图像、与事故现场相关的文字信息等图像信息一并上传至云处理设备,云处理设备接收用户上传的图像信息。
需要说明的是,事故现场的图像信息可以包含至少一张车辆图像,车 辆图像中包含车牌信息,例如,包含车牌与车头位置的图像、车辆损伤位置的图像等,以及终端的位置信息、气压信息、与案件相关的文字信息等。
102、对图像信息进行识别,确定图像信息是否存在异常特征。
在本申请实施例中,由于图像信息存在异常特征的情况较多,因此,重点介绍如下四种识别图像信息是否存在异常特征的方式:
第一种情况,对图像进行分类识别,确定图像是否为伪造图像;当图像为伪造图像时,确定图像信息存在异常特征。
可以理解的是,现有技术中,常见的伪造图像包括翻拍图像、二次加工图像等。其中,二次加工图像,可以是利用图像处理软件对某一张图像进行处理。翻拍图像可以是对打印的照片、电子显示设备等进行拍摄,由于翻拍图像的拍摄环境与原始图像的拍摄环境不可能完全一致,光照类型、光照方向、光照强度、拍摄对象的不同,会导致翻拍图像和原始图像之间的颜色、纹理等特征存在一定程度的差异。利用这些差异即可实现翻拍图像的检测。在本申请实施例中,至少可以通过如下方式的一种来实现翻拍图像的检测:
其一,首先提取原始图像(即前述内容中由用户拍摄的图像信息中的车辆图像)和对应伪造图像的颜色、纹理或频谱等特征,然后使用解析或机器学习的方法对这些特征进行分类,例如,原始图像只经历了一次成像过程,而伪造图像则至少经历两次成像过程,成像过程不同,最终获取的图像的频率分布也不尽相同,通过傅里叶变换,将原始图像和伪造图像转换为频谱图,提取这些频谱图的特征,然后利用机器学习的方法训练分类器,如SVM等,对这些特征进行分类,从而识别出伪造图像,需要说明的是,训练分类器可以是颜色、纹理或频谱等不同特征的组合。
其二,直接将原始图像和伪造图像作为两个类别,输入卷积神经网络(CNN)进行分类识别,实施过程同样分为训练和部署两个部分,训练时, 将原始图像和伪造图像两类数据样本输入CNN训练,训练完成后得到分类模型CNN1,将模型部署在云端,输入一张图像,即可输出是否为伪造图像的识别结果。
可以理解的是,前述两种方式仅为可以实现的方式,在实际应用中并不能限制于本申请实施例提供的两种方法。
第二种情况,将图像与车损图库中的图像进行对比,若图像与车损图库中的图像相同,则确定图像信息存在异常特征。
可以理解的是,现有技术中,图像与车损图库中的图像相同,则可以理解为图像信息中的图像为复制车损图库图像得到的,因此,可以特征匹配方法或以图搜图方法来确定图像信息是否存在异常特征。具体的,可以提取现有车损图库中所有图像的特征,特征可以是SIFT角点、颜色直方图、哈希值等,建立特征库,当输入新的图像时,提取其相应特征,在特征库中做检索匹配,当查找的特征匹配度超过设定阈值时,说明该图像与车损图库中的图像相同,是复制的,则确定图像信息存在异常特征。
第三种情况,将图像与车牌信息图库中的图像进行对比,若图像与车牌信息图库中的图像不同,则确定图像信息存在异常特征。
可以理解的是,由于同一车型的车都会大批量的生产,因此,存在套牌或者盗图的可能性,因此,为了确定是否是套牌等现象,可以根据车牌信息库中与存储的车辆相关信息来进行判断,车辆相关信息至少包括车牌、车辆颜色、车辆品牌、型号等信息。具体的,通过检测网络CNN2检测得到图像信息中车身区域位置,将车身图像输入分类网络CNN3识别其厂商和型号等信息,例如奥迪A4L、宝马520Li等等,提取车身固定区域(如发动机盖),将其输入分类网络CNN4识别车身颜色,以上所有CNN均通过预训练过程得到。进一步识别车牌号,并通过车牌号在预存储的车辆信息库中查找其相关信息,将CNN识别得到的信息和检索得到的信息做对比,如信息 不一致,说明车牌号信息有问题,该车为套牌,确定图像信息存在异常特征。
第四种情况,将图像与车辆品牌特征库中的图像进行对比,若图像与车辆品牌特征库中的图像不同,则确定图像信息存在异常特征。
在本申请实施例中,首先检测车身各个部件的位置,可以采用深度学习的方法,将图像输入检测网络CNN5,得到车辆每个部件的位置和名称,在车辆品牌特征库中检索对应名称的部位标准图像,分别提取用图像信息中图像中各部件区域和对应标准图像的SIFT特征做对比,如果不同,则说明有假件,确定图像信息存在异常特征。
第五种情况,提取与案件相关的文字信息中的车辆的位置信息;对比车辆的位置信息与终端的位置信息,当二者不同时,确定图像信息存在异常特征。
可以理解的是,文字信息中的位置信息为用户手动填写的,其对应的是事故发生的位置,若文字信息与用户终端的位置信息不一致,则说明用户未在事故发生地,其事故真实性较低,确定图像信息存在异常特征。
需要说明的是,在本申请实施例中,前述五种情况既可以同时进行判断,又可以按照一定的顺序进行判断,还可以根据前一个情况的判断结果,确定下一个情况是否需要执行,其各种结合方式,均属于本申请实施例中的保护范围。
103、将存在异常特征的图像信息发送至人工模块。
在本申请实施例中,人工模块用于辅助进行判断,由人工对存在异常特征的图像信息进行判断,确定是否存在异常特征,当存在异常特征时,返回对应的结果。
104、接收人工模块返回的结果。
本申请实施例提供的信息处理方法,通过获取终端采集的图像信息, 然后对图像信息进行识别,确定图像信息是否存在异常特征,在存在异常特征的情况下,发送至人工模块,由人工辅助进行二次判断,通过采用本申请提供的方法,能够提高对现场证据真实性判定的准确性和可靠性,降低人工成本,进而降低保险公司的损失,解决了现有技术中用户制作与与实际情况不符合的现场证据,换取更高的保险赔偿,给保险公司带来了很大的损失的问题。
进一步地,结合前述内容,本申请实施例还可以包括如下步骤,其目的在于能够更进一步的提高对现场证据真实性判定的准确性和可靠性,具体的,图2为本申请实施例提供的信息处理方法实施例的另一流程图,如图2所示,本实施例的信息处理方法,还可以包括如下步骤:
105、将结果添加至训练集中,对识别算法进行训练。
可以理解的是,人工增加的训练集,
对于本申请实施例提供的方法来说,相当于增加了更多的样本,通过更多的样本对算法进行训练,能够有利于提高算法的精度和准确性。
为了实现前述内容的方法流程,本申请实施例还提供一种信息处理系统,图3为本申请实施例提供的信息处理系统实施例的结构示意图,如图3所示,本实施例的系统可以包括:获取单元11、确定单元12、发送单元13和接收单元14。
获取单元11,用于获取终端采集的图像信息。
确定单元12,用于对图像信息进行识别,确定图像信息是否存在异常特征。
发送单元13,用于将存在异常特征的图像信息发送至人工模块。
接收单元14,用于接收人工模块返回的结果。
在一个具体的实现过程中,图像信息包括:至少一张车辆图像;
确定单元12,具体用于:
对车辆图像进行分类识别,确定车辆图像是否为伪造图像;
当车辆图像为伪造图像时,确定图像信息存在异常特征。
在一个具体的实现过程中,伪造图像包括翻拍图像或二次加工图像。
在一个具体的实现过程中,图像信息包括:至少一张车辆图像;
确定单元12,具体用于:
将车辆图像与车损图库中的图像进行对比,若车辆图像与车损图库中的图像相同,则确定图像信息存在异常特征。
在一个具体的实现过程中,图像信息包括:至少一张车辆图像;
确定单元12,具体用于:
将车辆图像与车牌信息图库中的图像进行对比,若车辆图像与车牌信息图库中的图像不同,则确定图像信息存在异常特征。
在一个具体的实现过程中,图像信息包括:至少一张车辆图像;
确定单元12,具体用于:
将车辆图像与车辆品牌特征库中的图像进行对比,若车辆图像与车辆品牌特征库中的图像不同,则确定图像信息存在异常特征。
在一个具体的实现过程中,图像信息包括:终端的位置信息以及车辆的位置信息;
确定单元12,具体用于:
对比车辆的位置信息与终端的位置信息,当二者不同时,确定图像信息存在异常特征。
本实施例的系统,可以用于执行图1所示方法实施例的技术方案,其实现原理和技术效果类似,此处不再赘述。
在前述内容的基础上,本申请实施例还提供一种信息处理系统,图4为本申请实施例提供的信息处理系统实施例的另一结构示意图,如图4所示,本实施例的系统,还可以包括:训练单元15。
训练单元,用于将结果添加至训练集中,对识别算法进行训练。
本实施例的系统,可以用于执行图2所示方法实施例的技术方案,其实现原理和技术效果类似,此处不再赘述。
为了实现前述内容的方法流程,本申请实施例还提供一种云处理设备,图5为本申请实施例提供的云处理设备实施例的结构示意图,如图5所示,本申请实施例提供的云处理设备包括处理器21以及存储器22;存储器22用于存储指令,指令被处理器21执行时,使得设备执行如前述内容中任一种方法。
本申请实施例提供的云处理设备,可以用于执行图1或图2所示方法实施例的技术方案,其实现原理和技术效果类似,此处不再赘述。
为了实现前述内容的方法流程,本申请实施例还提供一种计算机程序产品,可直接加载到计算机的内部存储器中,并含有软件代码,计算机程序经由计算机载入并执行后能够实现如前述内容中任一种方法。
本申请实施例提供的计算机程序产品,可以用于执行图1或图2所示方法实施例的技术方案,其实现原理和技术效果类似,此处不再赘述。
本领域普通技术人员可以理解:实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时,执行包括上述各方法实施例的步骤;而前述的存储介质包括:ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
以上所描述的系统实施例仅仅是示意性的,其中作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到至少两个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况 下,即可以理解并实施。
最后应说明的是:以上各实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述各实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分或者全部技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。

Claims (18)

  1. 一种信息处理方法,其特征在于,包括:
    云处理设备获取终端采集的图像信息;
    对所述图像信息进行识别,确定所述图像信息是否存在异常特征;
    将存在异常特征的图像信息发送至人工模块;
    接收所述人工模块返回的结果。
  2. 根据权利要求1所述的方法,其特征在于,所述方法还包括:
    将所述结果添加至训练集中,对识别算法进行训练。
  3. 根据权利要求1所述的方法,其特征在于,所述图像信息包括:至少一张车辆图像;
    所述对所述图像信息进行识别,确定所述图像信息是否存在异常特征,包括:
    对所述车辆图像进行分类识别,确定所述车辆图像是否为伪造图像;
    当所述车辆图像为伪造图像时,确定所述图像信息存在异常特征。
  4. 根据权利要求3所述的方法,其特征在于,所述伪造图像包括翻拍图像或二次加工图像。
  5. 根据权利要求1所述的方法,其特征在于,所述图像信息包括:至少一张车辆图像;
    所述对所述图像信息进行识别,确定所述图像信息是否存在异常特征,包括:
    将所述车辆图像与车损图库中的图像进行对比,若所述车辆图像与所述车损图库中的图像相同,则确定所述图像信息存在异常特征。
  6. 根据权利要求1所述的方法,其特征在于,所述图像信息包括:至少一张车辆图像;
    所述对所述图像信息进行识别,确定所述图像信息是否存在异常特征, 包括:
    将所述车辆图像与车牌信息图库中的图像进行对比,若所述车辆图像与所述车牌信息图库中的图像不同,则确定所述图像信息存在异常特征。
  7. 根据权利要求1所述的方法,其特征在于,所述图像信息包括:至少一张车辆图像;
    所述对所述图像信息进行识别,确定所述图像信息是否存在异常特征,包括:
    将所述车辆图像与车辆品牌特征库中的图像进行对比,若所述车辆图像与所述车辆品牌特征库中的图像不同,则确定所述图像信息存在异常特征。
  8. 根据权利要求1所述的方法,其特征在于,所述图像信息包括:所述终端的位置信息以及车辆的位置信息;
    所述对所述图像信息进行识别,确定所述图像信息是否存在异常特征,包括:
    对比所述车辆的位置信息与所述终端的位置信息,当二者不同时,确定所述图像信息存在异常特征。
  9. 一种信息处理系统,其特征在于,包括:
    获取单元,用于获取终端采集的图像信息;
    确定单元,用于对所述图像信息进行识别,确定所述图像信息是否存在异常特征;
    发送单元,用于将存在异常特征的图像信息发送至人工模块;
    接收单元,用于接收所述人工模块返回的结果。
  10. 根据权利要求9所述的系统,其特征在于,所述系统还包括:
    训练单元,用于将所述结果添加至训练集中,对识别算法进行训练。
  11. 根据权利要求9所述的系统,其特征在于,所述图像信息包括: 至少一张车辆图像;
    所述确定单元,具体用于:
    对所述车辆图像进行分类识别,确定所述车辆图像是否为伪造图像;
    当所述车辆图像为伪造图像时,确定所述图像信息存在异常特征。
  12. 根据权利要求11所述的系统,其特征在于,所述伪造图像包括翻拍图像或二次加工图像。
  13. 根据权利要求9所述的系统,其特征在于,所述图像信息包括:至少一张车辆图像;
    所述确定单元,具体用于:
    将所述车辆图像与车损图库中的图像进行对比,若所述车辆图像与所述车损图库中的图像相同,则确定所述图像信息存在异常特征。
  14. 根据权利要求9所述的系统,其特征在于,所述图像信息包括:至少一张车辆图像;
    所述确定单元,具体用于:
    将所述车辆图像与车牌信息图库中的图像进行对比,若所述车辆图像与所述车牌信息图库中的图像不同,则确定所述图像信息存在异常特征。
  15. 根据权利要求9所述的系统,其特征在于,所述图像信息包括:至少一张车辆图像;
    所述确定单元,具体用于:
    将所述车辆图像与车辆品牌特征库中的图像进行对比,若所述车辆图像与所述车辆品牌特征库中的图像不同,则确定所述图像信息存在异常特征。
  16. 根据权利要求9所述的系统,其特征在于,所述图像信息包括:所述终端的位置信息以及车辆的位置信息;
    所述确定单元,具体用于:
    对比所述车辆的位置信息与所述终端的位置信息,当二者不同时,确定所述图像信息存在异常特征。
  17. 一种云处理设备,其特征在于,所述设备包括处理器以及存储器;所述存储器用于存储指令,所述指令被所述处理器执行时,使得所述设备执行如权利要求1~8中任一种所述的方法。
  18. 一种计算机程序产品,其特征在于,可直接加载到计算机的内部存储器中,并含有软件代码,所述计算机程序经由计算机载入并执行后能够实现如权利要求1~8中任一种所述的方法。
PCT/CN2018/074489 2018-01-29 2018-01-29 信息处理方法、系统、云处理设备以及计算机程序产品 WO2019144416A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201880000066.7A CN108323209B (zh) 2018-01-29 2018-01-29 信息处理方法、系统、云处理设备以及计算机存储介质
PCT/CN2018/074489 WO2019144416A1 (zh) 2018-01-29 2018-01-29 信息处理方法、系统、云处理设备以及计算机程序产品

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/074489 WO2019144416A1 (zh) 2018-01-29 2018-01-29 信息处理方法、系统、云处理设备以及计算机程序产品

Publications (1)

Publication Number Publication Date
WO2019144416A1 true WO2019144416A1 (zh) 2019-08-01

Family

ID=62895865

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/074489 WO2019144416A1 (zh) 2018-01-29 2018-01-29 信息处理方法、系统、云处理设备以及计算机程序产品

Country Status (2)

Country Link
CN (1) CN108323209B (zh)
WO (1) WO2019144416A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113408319A (zh) * 2020-03-16 2021-09-17 广州汽车集团股份有限公司 一种城市道路异常感知处理方法、装置、系统及存储介质

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109886275A (zh) * 2019-01-16 2019-06-14 深圳壹账通智能科技有限公司 翻拍图像识别方法、装置、计算机设备和存储介质
CN109615549A (zh) * 2019-01-18 2019-04-12 河南奥菲斯电子科技有限公司 农业保险保费补贴绩效的计算方法、系统及存储介质
CN109829832B (zh) * 2019-01-18 2021-09-17 河南奥菲斯电子科技有限公司 大数据维护农业保险投保数据的方法、系统及存储介质
CN110009296A (zh) * 2019-02-11 2019-07-12 阿里巴巴集团控股有限公司 理赔业务的处理方法及装置
CN113178032A (zh) * 2021-03-03 2021-07-27 北京迈格威科技有限公司 一种视频处理方法、系统及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101546416A (zh) * 2009-04-27 2009-09-30 谢谦 一种远程处理汽车保险业务的方法及其系统
CN103310223A (zh) * 2013-03-13 2013-09-18 四川天翼网络服务有限公司 一种基于图像识别的车辆定损系统及方法
US20150106133A1 (en) * 2013-10-15 2015-04-16 Audatex North America, Inc. Mobile system for generating a damaged vehicle insurance estimate
CN105405054A (zh) * 2015-12-11 2016-03-16 平安科技(深圳)有限公司 基于理赔照片深度学习实现保险理赔反欺诈的方法及服务器
CN105719188A (zh) * 2016-01-22 2016-06-29 平安科技(深圳)有限公司 基于多张图片一致性实现保险理赔反欺诈的方法及服务器
CN107067328A (zh) * 2017-04-11 2017-08-18 武汉华创欣网科技有限公司 一种手机拍摄并上传取证照片或视频的车险理赔集成系统

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6741168B2 (en) * 2001-12-13 2004-05-25 Samsung Electronics Co., Ltd. Method and apparatus for automated collection and transfer of collision information
US20080140599A1 (en) * 2006-11-10 2008-06-12 Debra Pacha System and method for detecting healthcare insurance fraud
CN101577653A (zh) * 2008-05-08 2009-11-11 韩军 使用定位技术进行车险理赔辅助认证的系统和方法
GB0813668D0 (en) * 2008-07-25 2008-09-03 Ixico Ltd Image data fraud detection systems
CN102521986B (zh) * 2011-12-05 2013-11-06 沈阳聚德视频技术有限公司 一种套牌车辆自动检测系统的控制方法
AU2014201350A1 (en) * 2013-07-23 2015-02-12 Palantir Technologies, Inc. Fraud Detection in Healthcare
CN104574999A (zh) * 2015-01-30 2015-04-29 余炳顺 一种机动车车牌身份认证的方法和系统
CN105488099B (zh) * 2015-11-03 2019-03-26 杭州全实鹰科技有限公司 一种基于相似度学习的车辆检索方法
CN105488517B (zh) * 2015-11-30 2019-03-26 杭州全实鹰科技有限公司 一种基于深度学习的车辆品牌型号识别方法
CN106021548A (zh) * 2016-05-27 2016-10-12 大连楼兰科技股份有限公司 基于分布式人工智能图像识别的远程定损方法及系统
CN106228449A (zh) * 2016-07-29 2016-12-14 深圳市永兴元科技有限公司 车险理赔防欺诈方法和装置
CN106570758A (zh) * 2016-10-28 2017-04-19 公安部交通管理科学研究所 车险理赔证据信息采集方法和装置
CN107087025A (zh) * 2017-04-11 2017-08-22 武汉华创欣网科技有限公司 一种基于移动网络通信的车辆定损理赔方法及装置
CN107346435A (zh) * 2017-06-15 2017-11-14 浙江捷尚视觉科技股份有限公司 一种基于车辆特征库的嫌疑套牌车捕获方法
CN107545239B (zh) * 2017-07-06 2021-01-12 南京理工大学 一种基于车牌识别与车辆特征匹配的套牌检测方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101546416A (zh) * 2009-04-27 2009-09-30 谢谦 一种远程处理汽车保险业务的方法及其系统
CN103310223A (zh) * 2013-03-13 2013-09-18 四川天翼网络服务有限公司 一种基于图像识别的车辆定损系统及方法
US20150106133A1 (en) * 2013-10-15 2015-04-16 Audatex North America, Inc. Mobile system for generating a damaged vehicle insurance estimate
CN105405054A (zh) * 2015-12-11 2016-03-16 平安科技(深圳)有限公司 基于理赔照片深度学习实现保险理赔反欺诈的方法及服务器
CN105719188A (zh) * 2016-01-22 2016-06-29 平安科技(深圳)有限公司 基于多张图片一致性实现保险理赔反欺诈的方法及服务器
CN107067328A (zh) * 2017-04-11 2017-08-18 武汉华创欣网科技有限公司 一种手机拍摄并上传取证照片或视频的车险理赔集成系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113408319A (zh) * 2020-03-16 2021-09-17 广州汽车集团股份有限公司 一种城市道路异常感知处理方法、装置、系统及存储介质

Also Published As

Publication number Publication date
CN108323209B (zh) 2023-10-31
CN108323209A (zh) 2018-07-24

Similar Documents

Publication Publication Date Title
WO2019144416A1 (zh) 信息处理方法、系统、云处理设备以及计算机程序产品
JP6873237B2 (ja) 画像ベースの車両損害評価方法、装置、およびシステム、ならびに電子デバイス
US20240087102A1 (en) Automatic Image Based Object Damage Assessment
KR20190060817A (ko) 이미지 기반의 차량 손상 판정 방법과 장치, 및 전자기기
WO2020038138A1 (zh) 样本标注方法及装置、损伤类别的识别方法及装置
US20150286884A1 (en) Machine learning approach for detecting mobile phone usage by a driver
Li et al. An anti-fraud system for car insurance claim based on visual evidence
KR101781358B1 (ko) 디지털 영상 내의 얼굴 인식을 통한 개인 식별 시스템 및 방법
EP3844668A1 (en) System and method for training a damage identification model
CN113971821A (zh) 驾驶员信息确定方法、装置、终端设备及存储介质
CN114663871A (zh) 图像识别方法、训练方法、装置、系统及存储介质
WO2020047316A1 (en) System and method for training a damage identification model
WO2019140641A1 (zh) 信息处理方法、系统、云处理设备以及计算机程序产品
CN115810134A (zh) 一种车险反欺诈的图像采集质检方法、系统和装置
US20230342937A1 (en) Vehicle image analysis
CN114821725A (zh) 一种基于神经网络的矿工人脸识别系统
CN111310751A (zh) 车牌识别方法、装置、电子设备和存储介质
US11887292B1 (en) Two-step anti-fraud vehicle insurance image collecting and quality testing method, system and device
Jain et al. Number plate detection using drone surveillance
Fakhrurroja et al. Automated License Plate Detection and Recognition using YOLOv8 and OCR With Tello Drone Camera
CN113343968A (zh) 多模板证书快速审证方法、系统、介质及装置
Park et al. Don’t Wait Until the Accident Happens: Few-Shot Classification Framework for Car Accident Inspection in a Real World
CN117592917B (zh) 一种基于移动执法的行驶证信息快速录入方法和装置
CN115017439A (zh) 针对敏感类网站图像的滤除方法、存储介质以及电子设备
US20220253932A1 (en) Method and system for obtaining information about an object based on a photograph thereof

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 201880000066.7

Country of ref document: CN

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

Ref document number: 18902419

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 PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 01.12.2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18902419

Country of ref document: EP

Kind code of ref document: A1