WO2020164331A1 - 理赔业务的处理方法及装置 - Google Patents

理赔业务的处理方法及装置 Download PDF

Info

Publication number
WO2020164331A1
WO2020164331A1 PCT/CN2020/070032 CN2020070032W WO2020164331A1 WO 2020164331 A1 WO2020164331 A1 WO 2020164331A1 CN 2020070032 W CN2020070032 W CN 2020070032W WO 2020164331 A1 WO2020164331 A1 WO 2020164331A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
settlement
business
target
authenticated
Prior art date
Application number
PCT/CN2020/070032
Other languages
English (en)
French (fr)
Inventor
陶彬贤
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 WO2020164331A1 publication Critical patent/WO2020164331A1/zh

Links

Images

Classifications

    • 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
    • G06Q10/10—Office automation; Time 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance

Definitions

  • This application relates to the field of image processing technology, and in particular to a method and device for processing claims business.
  • the purpose of the embodiments of this specification is to provide a method and device for processing claims business.
  • the image identification rules corresponding to the target claims business are The claim image is identified, and the image identification technology is applied to the claims business, which realizes the automatic identification of the images to be identified, saves labor costs, improves the identification efficiency of the images to be identified, and improves the processing efficiency of the online claims business. This reduces the user's waiting time in the process of processing claims and improves the user experience.
  • the embodiment of this specification provides a method for processing claims business, including:
  • the embodiment of this specification also provides a processing device for claims settlement business, the device includes:
  • the obtaining module is used to obtain the claims image to be authenticated uploaded by the user for the target claims business;
  • An identification module configured to identify the claims image to be authenticated according to the image identification rules corresponding to the target claims business, to determine whether the claims image to be authenticated is an abnormal image for the target claims business;
  • the determining module is configured to determine the processing mode for the target claims settlement business according to the authentication result of the to-be-identified claims settlement image.
  • the embodiment of this specification also provides an authentication device for claims settlement business, including:
  • a memory arranged to store computer-executable instructions which, when executed, cause the processor to:
  • the embodiments of this specification also provide a storage medium for storing computer-executable instructions, which, when executed, implement the following processes:
  • the claims image to be authenticated is identified according to the image authentication rules corresponding to the target claims business, and the image authentication technology is applied
  • the claims business automatic identification of the images to be identified for the claims is realized, labor costs are saved, and the efficiency of the identification of the images to be authenticated is improved, thereby improving the processing efficiency of the online claims business, thereby reducing the number of users in the process of processing the claims.
  • the waiting time improves the user experience.
  • Fig. 1 is one of the method flowcharts of the claims settlement business processing method provided by the embodiment of this specification;
  • Figure 2 is the second method flowchart of the claims settlement business processing method provided by the embodiment of this specification.
  • Fig. 3 is the third method flowchart of the claims settlement business processing method provided by the embodiment of this specification.
  • FIG. 4 is the fourth method flowchart of the claims settlement business processing method provided by the embodiment of this specification.
  • FIG. 5 is a schematic diagram of the module composition of the device for processing claims business provided by an embodiment of the specification
  • Fig. 6 is a schematic structural diagram of a processing device for claim settlement services provided by an embodiment of this specification.
  • the embodiment of this specification provides a method, device, equipment and storage medium for processing claims business.
  • the automatic identification of the proof images uploaded by users in the claims business is realized, and the processing efficiency of the claims business is improved. , Reducing user waiting time, thereby improving user experience.
  • the method provided in the embodiments of this specification is applied to the server side of claims settlement applications, that is, the execution body of the method is the server, specifically, the execution body of the method is the processing device of the claims settlement service set on the server.
  • Fig. 1 is one of the method flowcharts of the claims settlement business processing method provided by the embodiment of this specification.
  • the method shown in Fig. 1 at least includes the following steps:
  • Step 102 Obtain a claim settlement image to be authenticated uploaded by the user for the target claim settlement service.
  • the user When a user needs to settle a claim, he can settle the claim online through the claims client installed on the terminal device.
  • the user In the process of online claim settlement, the user is required to upload an image corresponding to the claim settlement business.
  • the image may be a photo of the claim settlement object.
  • the uploaded claim image to be authenticated is a photo of the vehicle, and the photo needs to include the area where the vehicle is scratched.
  • the user may take multiple photos of the claim object from different angles. Therefore, in the embodiment of the present specification, there may be one or more claim settlement images to be authenticated uploaded for the target claims settlement service user.
  • the user may send a claim settlement request to the server when making a claim settlement, and the aforementioned claim settlement image to be authenticated may be carried in the claim settlement request and sent to the server.
  • the server receives the claim settlement request sent by the user through the client, it obtains the to-be-identified claim settlement image from the claim settlement request.
  • the aforementioned claim image to be authenticated can be carried in the claim request as part of the claim request and sent to the server, or it can be when the server prompts the user to upload the claim image to be authenticated after receiving the claim request sent by the user through the claims client.
  • the server prompts the user to upload the claim image to be authenticated after receiving the claim request sent by the user through the claims client.
  • follow the prompts to upload can be carried in the claim request as part of the claim request and sent to the server, or it can be when the server prompts the user to upload the claim image to be authenticated after receiving the claim request sent by the user through the claims client.
  • Step 104 Discriminate the to-be-identified claims image according to the image identification rules corresponding to the target claims business to determine whether the to-be-identified claims image is an abnormal image for the target claims business.
  • the above abnormal image may be understood as not a real image corresponding to the target claims settlement business, and may be some images used by certain users for claim settlement fraud, for example, images stolen from the Internet.
  • the corresponding image identification rules for different claims business will be different.
  • simpler image identification rules may be used for identification to shorten the time spent on image identification;
  • simpler image identification rules may also be used for identification, reducing the amount of data processing.
  • Step 106 Determine a processing method for the target claims settlement business according to the authentication result of the to-be-identified claims settlement image.
  • the claim image to be authenticated is an abnormal image for the target claims business
  • the claim can be rejected for the target claims business. If the authentication result indicates that the claim image to be authenticated is not for the target claims business
  • the target claims business can be settled.
  • the method for processing claims business realizes the automatic identification of the claims image to be authenticated during the process of processing the claims business, improves the identification efficiency of the claims image to be authenticated, and shortens the processing time of the claims business.
  • the waiting time of the user is improved, and the user experience is improved.
  • the to-be-identified claims image is identified according to the image identification rules corresponding to the target claims business to determine whether the to-be-identified claims image is an abnormal image for the target claims business, including one of the following Or more:
  • any one, two or three of the above (1), (2) and (3) can be used according to the image identification rules corresponding to the target claims business.
  • the image is identified.
  • the object contained in the claim image to be authenticated refers to the content contained in the claim image to be authenticated.
  • the claim image to be authenticated is a car image
  • the car is the object contained in it.
  • a combination of the above three methods may be used to identify the to-be-identified claims image.
  • FIG. 2 is the second method flowchart of the claims settlement business processing method provided by the embodiment of this specification. The method shown in Fig. 2 includes at least the following steps:
  • Step 202 Obtain a claim settlement image to be authenticated uploaded by the user for the target claim settlement service.
  • Step 204 Identify whether the object contained in the to-be-identified claim settlement image matches the claim settlement object of the target claims settlement business; if yes, go to step 206; otherwise, go to step 210.
  • Step 206 Identify whether the image to be claimed is a pirated image; if so, proceed to step 210; otherwise, proceed to step 208.
  • Step 208 Discriminate whether the claim settlement image to be identified and the claim settlement image in the historical claim settlement service are duplicate images; if so, go to step 210; otherwise, go to step 212.
  • Step 210 Refuse to settle the claim for the target claim settlement business.
  • Step 212 Perform a claim settlement operation for the target claim settlement business.
  • the identification of whether the object contained in the to-be-identified claim settlement image matches the claim settlement object of the target claims settlement business includes at least the following two situations:
  • some objects in the same category are relatively similar, but it may not be morphologically able to identify which of the objects contained in the image to be identified belongs to the category. In this case, Even if the object contained in the image to be authenticated is identified, the accuracy of identification may be low. Therefore, in order to reduce the amount of calculation, only the type of object contained in the image to be authenticated and the claim of the target claims business need to be identified Whether the types of objects are the same.
  • the object contained in the claim image to be identified is a chicken
  • the claim object corresponding to the target claims business is a duck
  • It can be used to identify whether the type of the object contained in the claim image to be authenticated is consistent with the type of the claim object of the target claims business.
  • the object included in the claim object to be identified is an office chair, since the shapes of various types of office chairs are not much different, for this case, the type and target of the object contained in the image to be identified can be identified Whether the types of claims for the claims business are consistent.
  • image recognition can be used to identify whether the object contained in the claim image to be authenticated is the same as the type of the claim object by extracting the contour of the object contained in the claim image to be authenticated.
  • the claim settlement object is a car and the claim settlement is to be authenticated. If the object contained in the image is a motorcycle, you can filter out such clearly inconsistent claims images to be authenticated. That is, in this case, the claims images to be authenticated can be regarded as abnormal images for the target claims business. Refuse to make claims for the target claims business.
  • identifying whether the claim image to be authenticated is a fraudulent image includes:
  • the above-mentioned target image library may be any image library accessed from other servers or systems, for example, it may be Baidu image library, Ali ecological image library, etc.
  • the similarity value between the to-be-identified claims image and each image stored in the target picture library can be calculated, and the calculated similarity values can be compared with the set threshold. If there is greater than or If the similarity value is equal to the set threshold, it can be considered that the claim image to be identified is an image stolen from the target image library.
  • the foregoing process of calculating the similarity value between the to-be-identified claims image and the image in the target picture library can refer to the calculation method of the similarity value between the images in the prior art, which will not be repeated here.
  • the images in the target picture library can be classified and stored. In this way, when identifying whether the claims image to be identified is a pirated image, the object contained in the image to be identified can be identified first. Then, calculate the similarity value between the claim image to be authenticated and the image of the same category in the target image library, so as to determine whether the claim image to be authenticated is a fraudulent image according to the calculated similarity value.
  • the images in the target image library can be classified and stored according to the categories of cars, seafood, poultry, computers, mobile phones, etc.
  • the image in the claim image to be authenticated can be identified first. Contains the category of the object. If it is recognized that the object contained in the claim image to be identified belongs to the automobile category, the similarity value between the claim image to be identified and the image belonging to the automobile category in the target image library is directly calculated, so as to calculate according to the The similarity value determines whether the claim image to be identified is an image stolen from the target picture library.
  • the category of the claim image to be authenticated is first identified, and then the claim image to be authenticated is similar to the image of the same category in the set picture.
  • Degree comparisons can reduce the workload of similarity comparisons, thereby further improving the efficiency of identifying claims images to be identified, thereby improving the processing efficiency of claims business, reducing user waiting time, and improving user experience.
  • identifying whether the claim image to be identified and the claim image in the historical claims business are duplicate images specifically includes the following steps:
  • some users may embezzle or cut some of the images from successful claims cases as the to-be-identified claims images corresponding to the target claims business. Therefore, in order to prevent this from happening, the At the time of identification, it is also necessary to identify whether the claim image to be identified has appeared in a historical claim case.
  • the similarity value between the claim image to be identified and each claim image in the historical claims image library it is possible to calculate the similarity value between the claim image to be identified and each claim image in the historical claims image library, and determine whether there is a similarity value greater than or equal to the set threshold. If it exists, it is considered to be identified
  • the claim image has appeared in the historical claim image library, that is, the claim image to be identified is a repeated claim image.
  • the authentication result indicates that the object contained in the claim image to be authenticated does not match the claim object of the target claim settlement business, or it is determined that the claim image to be authenticated is a fraudulent image, then the claim image to be authenticated is determined to be against the target An abnormal image of the claims business. If it is determined that the to-be-identified claim settlement image is an abnormal image for the target claims settlement business, the target claims settlement business is rejected.
  • the processing method for the target claims business is determined according to the authentication result of the claim image to be authenticated, including:
  • the image is the claim business corresponding to the repeated claim image.
  • the so-called related claims business can refer to claims cases that occurred in different periods for the same claimant, the same claim object, etc.
  • the target claims business and the historical claims business are related claims business by matching the target claims business with the historical claims business corresponding to the foregoing repeated claims image.
  • key information such as the claim object, claim adjuster, claim event, time and location of the claim event in the target claims business, and match the key information with the key information corresponding to the historical claims business. If the key information matches, it is considered that the target claims business and the historical claims business are related claims business. In this case, the claim settlement operation for the target claim settlement business is executed. If it is determined that the target claims settlement business and the historical claims settlement business are not related claims settlement services, it means that the claim settlement image to be identified is an image stolen from the historical claims settlement business. If the claim image to be identified is considered to be an abnormal image for the target claims business, the target claims business is rejected.
  • the above judgment results can also be corrected through manual judgment. That is, while judging whether the target claims business and the historical claims business are related claims business, the target claims business and the historical claims business are sent to the manual review node for manual judgment.
  • the result of manual judgment shall prevail.
  • the result of manual review indicates that the target claims settlement business and the historical claims settlement business are not related claims settlement businesses, then it is ultimately deemed that the target claims settlement business and the historical claims settlement business are not Related claims business.
  • the algorithm for judging the aforementioned related claims business can also be modified through the result of manual review, thereby improving the accuracy of the judgment algorithm of the related claims business.
  • FIG. 3 is the third method flowchart of the claims settlement business processing method provided by the embodiment of this specification.
  • the method shown in FIG. 3 at least includes the following steps:
  • Step 302 Obtain a claim settlement image to be authenticated uploaded by the user for the target claim settlement service.
  • Step 304 Identify whether the type of the object included in the claim settlement object to be identified is consistent with the type of the claim settlement object of the target claims settlement business; if so, go to step 306; otherwise, go to step 314.
  • Step 306 Identify whether the image to be claimed is a fraudulent image; if yes, go to step 314; otherwise, go to step 308;
  • Step 308 Identify whether the claim image to be identified and the claim image in the historical claims business are duplicate images; if so, go to step 312; otherwise, go to step 310;
  • Step 310 Perform a claim settlement operation for the target claims settlement business.
  • Step 312 Determine whether the target claims settlement business and the target historical claims settlement business are related claims settlement services; where the target historical claims settlement business is the business corresponding to the claims settlement image whose claim settlement image to be identified is a repeated image; if yes, go to step 310, otherwise, Go to step 314.
  • Step 314 Refuse to settle the claim for the target claim settlement business.
  • each step in the embodiment corresponding to FIG. 3 can refer to the method embodiments corresponding to FIG. 1 and FIG. 2, which will not be repeated here.
  • Fig. 4 is the fourth method flowchart of the claims settlement business processing method provided by the embodiment of this specification.
  • the method shown in Fig. 4 at least includes the following steps:
  • Step 402 Obtain a claim settlement image to be authenticated uploaded by the user for the target claim settlement service.
  • Step 404 Identify whether the object included in the claim settlement object to be identified is consistent with the claim settlement object of the target claims settlement business; if so, proceed to step 406; otherwise, proceed to step 416.
  • Step 406 Identify whether the image to be claimed is a pirated image; if yes, go to step 416; otherwise, go to step 408;
  • Step 408 Identify whether the claims image to be identified and the claims image in the historical claims business are duplicate images; if so, go to step 412; otherwise, go to step 410;
  • Step 410 Perform a claim settlement operation for the target claims settlement business.
  • Step 412 Judge whether the target claims business and the target historical claims business are related claims business, obtain a first judgment result, and obtain a second judgment result of manually judging whether the target claims business and the target historical claims business are related claims business; Among them, the target historical claims business is a business corresponding to a claim image whose claim image to be identified is a duplicate image.
  • Step 414 Determine whether the target claims settlement business and the target historical claims settlement business are related claims settlement services according to the first judgment result and the second judgment result; if so, go to step 410; otherwise, go to step 416.
  • the second judgment result is determined as the final judgment result.
  • Step 416 Refuse to settle the claim for the target claim settlement business.
  • each step in the embodiment corresponding to FIG. 4 can refer to the method embodiments corresponding to FIG. 1 and FIG. 2, which will not be repeated here.
  • the claims image to be authenticated is identified according to the image identification rules corresponding to the target claims business, and
  • the application of image identification technology in the claims business realizes the automatic identification of the images to be authenticated, saves labor costs, improves the identification efficiency of the images to be authenticated, and improves the processing efficiency of the online claims business, thereby reducing the number of claims
  • the waiting time of users in the business process improves the user experience.
  • the embodiment of this specification also provides a device for processing claims business, which is used to implement the method provided by the embodiment of this specification.
  • Figure 5 is the specification.
  • the module composition diagram of the device for processing claims business provided by the embodiment includes:
  • the obtaining module 502 is used to obtain the claim settlement image to be authenticated uploaded by the user for the target claim settlement business;
  • the identification module 504 is configured to identify the claims image to be authenticated according to the image identification rules corresponding to the target claims business, to determine whether the claims image to be authenticated is an abnormal image for the target claims business;
  • the determining module 506 is configured to determine the processing method for the target claims settlement business according to the authentication result of the to-be-identified claims settlement image.
  • the aforementioned authentication module 504 includes one or more of the following units:
  • the first identification unit is used to identify whether the object contained in the claim settlement image to be authenticated matches the claim settlement object of the target claims settlement business; if they do not match, determine that the claim settlement image to be authenticated is an abnormal image for the target claims settlement business;
  • the second identification unit is used to identify whether the claim image to be authenticated is a fraudulent image; if so, it is determined that the claim image to be authenticated is an abnormal image for the target claims business;
  • the third identification unit is used to identify whether the claims image to be authenticated and the claims image in the historical claims business are duplicate images; if so, determine that the claim image to be identified is an abnormal image for the target claims business.
  • the above-mentioned first authentication unit is specifically used for:
  • the above-mentioned second identification unit is specifically used for:
  • the aforementioned third authentication unit is specifically used for:
  • the authentication result indicates that the claim image to be authenticated and the claim image in the historical claims business are duplicate images
  • the above determining module 506 includes:
  • the judging unit is used to judge whether the target claim settlement business and the historical claims settlement business are related claims settlement services; among them, the historical claims settlement business is the business corresponding to the claim settlement image in which the claim settlement image to be identified is a repeated image;
  • the execution unit is configured to, if it is determined that the target claims settlement business and the historical claims settlement business are related claims settlement businesses, then execute the claims settlement operation for the target settlement settlement business; otherwise, refuse to settle the claims for the target settlement settlement business.
  • the claims processing device of the embodiment of this specification can also execute the method executed by the claims processing device in Figures 1 to 4, and realize the functions of the claims processing device in the embodiment shown in Figures 1 to 4, here No longer.
  • the claims processing device in the process of processing the claims business, for the claims image to be authenticated uploaded by the user, the claims image to be authenticated is identified according to the image identification rules corresponding to the target claims business, and the The application of image identification technology in the claims business realizes the automatic identification of the images to be authenticated, saves labor costs, improves the identification efficiency of the images to be authenticated, and improves the processing efficiency of the online claims business, thereby reducing the number of claims
  • the waiting time of users in the business process improves the user experience.
  • an embodiment of this specification also provides a processing device for claims settlement services, as shown in FIG. 6.
  • the processing equipment for claims settlement services may have relatively large differences due to different configurations or performances, and may include one or more processors 601 and a memory 602, and the memory 602 may store one or more storage applications or data. Among them, the memory 602 may be short-term storage or persistent storage.
  • the application program stored in the memory 602 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instruction information in a processing device for claims settlement services.
  • the processor 601 may be configured to communicate with the memory 602, and execute a series of computer-executable instruction information in the memory 602 on the processing device of the claims settlement service.
  • the processing equipment for claims settlement services may also include one or more power supplies 603, one or more wired or wireless network interfaces 604, one or more input and output interfaces 605, one or more keyboards 606, and so on.
  • the processing device for claims settlement services includes a memory and one or more programs, wherein one or more programs are stored in the memory, and the one or more programs may include one or more modules, And each module may include a series of computer-executable instruction information in the processing equipment of the claims business, and is configured to be executed by one or more processors to execute the one or more programs including the following computer-executable instruction information :
  • the to-be-identified claims image is identified according to the image identification rules corresponding to the target claims business to determine whether the to-be-identified claims image is an abnormal image for the target claims business, including the following content One or more of:
  • identifying whether the object contained in the to-be-identified claim settlement image matches the claim settlement object of the target claims settlement business includes:
  • identifying whether the claim image to be authenticated is a pirated image, including:
  • the computer-executable instruction information when executed, it can identify whether the claims image to be identified and the claims image in the historical claims business are duplicate images, including:
  • the claim image to be authenticated is determined to be a repeated claim image.
  • the computer-executable instruction information when executed, if the authentication result indicates that the claim image to be authenticated and the claim image in the historical claims business are duplicate images;
  • determine the processing method for the target claims business including:
  • the historical claims settlement business is the business corresponding to the claims settlement image whose claim settlement image to be identified is a duplicate image;
  • the claims image to be authenticated is identified according to the image identification rules corresponding to the target claims business, and
  • the application of image identification technology in the claims business realizes the automatic identification of the images to be authenticated, saves labor costs, improves the identification efficiency of the images to be authenticated, and improves the processing efficiency of the online claims business, thereby reducing the number of claims
  • the waiting time of users in the business process improves the user experience.
  • an embodiment of this specification also provides a storage medium for storing computer-executable instruction information.
  • the storage medium may be U Disk, optical disk, hard disk, etc., when the computer executable instruction information stored in the storage medium is executed by the processor, the following process can be realized:
  • the to-be-identified claims image is identified according to the image identification rules corresponding to the target claims business to determine whether the to-be-identified claims image is for the target claims business
  • identifying whether the object contained in the to-be-identified claim settlement image matches the claim settlement object of the target claims settlement business includes:
  • identifying whether the claim image to be authenticated is a stolen image includes:
  • identifying whether the claim image to be identified and the claim image in the historical claims business are duplicate images including:
  • the claim image to be authenticated is determined to be a repeated claim image.
  • the computer-executable instruction information stored in the storage medium is executed by the processor, if the authentication result indicates that the claim image to be authenticated and the claim image in the historical claims business are duplicate images;
  • determine the processing method for the target claims business including:
  • the historical claims settlement business is the business corresponding to the claims settlement image whose claim settlement image to be identified is a duplicate image;
  • a programmable logic device Programmable Logic Device, PLD
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • ABEL Advanced Boolean Expression Language
  • AHDL Altera Hardware Description Language
  • HDCal JHDL
  • Lava Lava
  • Lola MyHDL
  • PALASM RHDL
  • VHDL Very-High-Speed Integrated Circuit Hardware Description Language
  • Verilog Verilog
  • the controller can be implemented in any suitable manner.
  • the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program codes (such as software or firmware) executable by the (micro)processor. , Logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers.
  • controllers include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicon Labs C8051F320, the memory controller can also be implemented as a part of the memory control logic.
  • controller in addition to implementing the controller in a purely computer-readable program code manner, it is entirely possible to program the method steps to make the controller use logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded The same function can be realized in the form of a microcontroller, etc. Therefore, such a controller can be regarded as a hardware component, and the devices included in it for realizing various functions can also be regarded as a structure within the hardware component. Or even, the device for realizing various functions can be regarded as both a software module for realizing the method and a structure within a hardware component.
  • a typical implementation device is a computer.
  • the computer may be, for example, a personal computer, a laptop computer, a cell 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 computer, a wearable device, or Any combination of these devices.
  • the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
  • a computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instruction information can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instruction information stored in the computer-readable memory generates a manufactured product including the instruction information device.
  • the instruction information device realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instruction information can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, which can be executed on the computer or other programmable equipment.
  • the instruction information of provides the steps used to implement the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • the computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.
  • processors CPU
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-permanent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology.
  • the information can be computer-readable instruction information, data structures, program modules, 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, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic 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. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.
  • this application can be provided as methods, systems, or computer program products. Therefore, this application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types.
  • This application can also be practiced in distributed computing environments. In these distributed computing environments, remote processing devices connected through a communication network perform tasks.
  • program modules can be located in local and remote computer storage media including storage devices.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Finance (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Technology Law (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Facsimiles In General (AREA)

Abstract

一种理赔业务的处理方法及装置，该方法包括：获取用户针对目标理赔业务上传的待鉴别理赔图像（102）；根据目标理赔业务所对应的图像鉴别规则对上述待鉴别理赔图像进行鉴别，以确定该待鉴别理赔图像是否为针对目标理赔业务的异常图像（104）；根据待鉴别理赔图像的鉴别结果，确定针对目标理赔业务的处理方式（106）。

Description

理赔业务的处理方法及装置 技术领域
本申请涉及图像处理技术领域，尤其涉及一种理赔业务的处理方法及装置。
背景技术
随着互联网及信息技术的快速发展，越来越多行业的业务可以在线进行办理，例如，针对保险行业，可以进行在线理赔，用户在线理赔时需要上传理赔所需的举证内容(如相关照片)，这样保险工作人员无需现场审核，即可完成理赔的处理。
但是，在通过在线进行理赔时，总会有一些不法分子采用网络盗图、历史理赔案件中所使用的图片等作为举证图片进行理赔诈骗，从而骗取保险公司理赔款。为了减少或此类情况的发生，保险公司需要对用户上传的举证图片进行审核。
因此，亟需提出一种方案，以实现快速、高效的对理赔业务中用户上传的举证图片进行鉴别。
发明内容
本说明书实施例的目的是提供一种理赔业务的处理方法及装置，在处理理赔业务的过程中，对于用户上传的待鉴别理赔图像，则根据目标理赔业务所对应的图像鉴别规则对该待鉴别理赔图像进行鉴别，将图像鉴别技术应用于理赔业务中，实现了对待鉴别理赔图像的自动化鉴别，节省了人工成本，提高了待鉴别理赔图像的鉴别效率，从而提高了在线理赔业务的处理效率，从而减少了在处理理赔业务过程中用户等待时间，提高了用户体验。
为解决上述技术问题，本说明书实施例是这样实现的：
本说明书实施例提供了一种理赔业务的处理方法，包括：
获取用户针对目标理赔业务上传的待鉴别理赔图像；
根据所述目标理赔业务所对应的图像鉴别规则对所述待鉴别理赔图像进行鉴别，以确定所述待鉴别理赔图像是否为针对所述目标理赔业务的异常图像；
根据所述待鉴别理赔图像的鉴别结果，确定针对所述目标理赔业务的处理方式。
本说明书实施例还提供了一种理赔业务的处理装置，所述装置包括：
获取模块，用于获取用户针对目标理赔业务上传的待鉴别理赔图像；
鉴别模块，用于根据所述目标理赔业务所对应的图像鉴别规则对所述待鉴别理赔图像进行鉴别，以确定所述待鉴别理赔图像是否为针对所述目标理赔业务的异常图像；
确定模块，用于根据所述待鉴别理赔图像的鉴别结果，确定针对所述目标理赔业务的处理方式。
本说明书实施例还提供了一种理赔业务的鉴别设备，包括：
处理器；以及
被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行时使所述处理器：
获取用户针对目标理赔业务上传的待鉴别理赔图像；
根据所述目标理赔业务所对应的图像鉴别规则对所述待鉴别理赔图像进行鉴别，以确定所述待鉴别理赔图像是否为针对所述目标理赔业务的异常图像；
根据所述待鉴别理赔图像的鉴别结果，确定针对所述目标理赔业务的处理方式。
本说明书实施例还提供了一种存储介质，用于存储计算机可执行指令，所述可执行指令在被执行时实现以下流程：
获取用户针对目标理赔业务上传的待鉴别理赔图像；
根据所述目标理赔业务所对应的图像鉴别规则对所述待鉴别理赔图像进行鉴别，以确定所述待鉴别理赔图像是否为针对所述目标理赔业务的异常图像；
根据所述待鉴别理赔图像的鉴别结果，确定针对所述目标理赔业务的处理方式。
本实施例中的技术方案，在处理理赔业务的过程中，对于用户上传的待鉴别理赔图像，则根据目标理赔业务所对应的图像鉴别规则对该待鉴别理赔图像进行鉴别，将图像鉴别技术应用于理赔业务中，实现了对待鉴别理赔图像的自动化鉴别，节省了人工成本，提高了待鉴别理赔图像的鉴别效率，从而提高了在线理赔业务的处理效率，从而减少了在处理理赔业务过程中用户等待时间，提高了用户体验。
附图说明
为了更清楚地说明本说明书实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请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为本说明书实施例提供的理赔业务的处理方法的方法流程图之一；
图2为本说明书实施例提供的理赔业务的处理方法的方法流程图之二；
图3为本说明书实施例提供的理赔业务的处理方法的方法流程图之三；
图4为本说明书实施例提供的理赔业务的处理方法的方法流程图之四；
图5为本说明书实施例提供的理赔业务的处理装置的模块组成示意图；
图6为本说明书实施例提供的理赔业务的处理设备的结构示意图。
具体实施方式
为了使本技术领域的人员更好地理解本申请中的技术方案，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，都应当属于本申请保护的范围。
本说明书实施例提供了一种理赔业务的处理方法、装置、设备及存储介质，在本说明书实施例中，实现了对理赔业务中用户上传的举证图像的自动化鉴别，提高了理赔业务的处理效率，减少了用户等待时间，从而提高了用户体验。
本说明书实施例提供的方法应用于理赔类应用程序的服务器侧，即该方法的执行主体为服务器，具体的，该方法的执行主体为设置于服务器上的理赔业务的处理装置。
图1为本说明书实施例提供的理赔业务的处理方法的方法流程图之一，图1所示的方法至少包括如下步骤：
步骤102，获取用户针对目标理赔业务上传的待鉴别理赔图像。
当用户需要进行理赔时，可以通过安装在终端设备上的理赔客户端在线进行理赔。 在通过在线进行理赔的过程中，需要用户上传理赔业务所对应的图像，该图像可以为理赔对象的照片等。例如，若是用户针对车辆剐蹭进行理赔，则上传的待鉴别理赔图像则为剐蹭车辆的照片，其中，在该照片中需要包含车辆被剐蹭的区域。
当然，在具体实施时，在某些情况下，为了更清楚的反映理赔对象的当前状况，用户可能会通过不同角度对理赔对象拍摄多张照片。因此，在本说明书实施例中，上述针对目标理赔业务用户上传的待鉴别理赔图像可以为一个或者多个。
在具体实施方式中，用户在进行理赔时，可以向服务器发送理赔请求，上述待鉴别理赔图像可以携带在理赔请求中发送给服务器。相应的，当服务器接收到用户通过客户端发送的理赔请求后，从该理赔请求中获取待鉴别理赔图像。
当然，上述待鉴别理赔图像可以作为理赔请求的一部分携带在理赔请求中发送给服务器，也可以是在服务器接收到用户通过理赔客户端发送的理赔请求后，提示用户上传待鉴别理赔图像时，用户根据提示进行上传的。
步骤104，根据目标理赔业务所对应的图像鉴别规则对待鉴别理赔图像进行鉴别，以确定待鉴别理赔图像是否为针对目标理赔业务的异常图像。
其中，上述异常图像可以理解为并不是目标理赔业务所对应的真实图像，可能为某些用户进行理赔诈骗所使用的一些图像，例如，从网络盗用的图像等。
在具体实施时，针对不同的理赔业务可能所对应的图像鉴别规则会有所差别，例如，针对紧急类业务，可能采用较简单的图像鉴别规则进行鉴别，以缩短图像鉴别所耗费的时间；还例如，针对理赔金额较低的理赔业务，可能也会采用较简单的图像鉴别规则进行鉴别，减少数据处理量。
因此，在本说明书实施例中，为了满足不同理赔业务的需求，可以为不同类别的理赔业务设置不同的图像鉴别规则。这样，在处理该类别的理赔业务时，则采用对应的图像鉴别规则对待鉴别图像进行鉴别即可。
步骤106，根据待鉴别理赔图像的鉴别结果，确定针对目标理赔业务的处理方式。
在本说明书实施例中，若是鉴别结果指示待鉴别理赔图像为针对目标理赔业务的异常图像，则可以拒绝针对目标理赔业务进行理赔，若是待鉴别结果指示待鉴别理赔图像并不是针对目标理赔业务的异常图像，则在其他信息均符合理赔要求的情况下，可以对目标理赔业务进行理赔。
本说明书实施例提供的理赔业务的处理方法，在处理理赔业务的过程中，实现了对待鉴别理赔图像的自动化鉴别，提高了待鉴别理赔图像的鉴别效率，从而缩短了理赔业务的处理时间，减少了用户的等待时间，提高了用户体验。
为便于理解本说明书实施例提供的方法，下述将详细介绍上述各个步骤的具体实现过程。
在具体实施时，上述步骤104中，根据目标理赔业务所对应的图像鉴别规则对待鉴别理赔图像进行鉴别，以确定待鉴别理赔图像是否为针对目标理赔业务的异常图像，包括以下内容中的一种或多种：
(一)、鉴别待鉴别理赔图像所包含的对象与目标理赔业务的理赔对象是否相匹配；若不相匹配，则确定待鉴别理赔图像为针对目标理赔业务的异常图像；
(二)、鉴别待鉴别理赔图像是否为盗用图像；若是，则确定待鉴别理赔图像为针对目标理赔业务的异常图像；
(三)、鉴别待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像；若是，则确定待鉴别理赔图像为针对目标理赔业务的异常图像。
在执行本说明书实施例提供的方法时，可以根据目标理赔业务所对应的图像鉴别规则，采用上述(一)、(二)和(三)中的任意一种、两种或者三种对待鉴别理赔图像进行鉴别。
其中，在(一)中，待鉴别理赔图像所包含的对象则指的是待鉴别理赔图像所包含的内容，例如，待鉴别理赔图像为汽车图像，则汽车则为其包含的对象。
优选的，在一种具体实施方式中，可以采用上述三种方式的组合对待鉴别理赔图像进行鉴别，针对上述三种方式的组合的一种具体实现方式如图2所示。图2为本说明书实施例提供的理赔业务的处理方法的方法流程图之二，图2所示的方法，至少包括如下步骤：
步骤202，获取用户针对目标理赔业务上传的待鉴别理赔图像。
步骤204，鉴别待鉴别理赔图像所包含的对象与目标理赔业务的理赔对象是否相匹配；若是，则执行步骤206；否则执行步骤210。
步骤206，鉴别待理赔图像是否为盗用图像；若是，则执行步骤210，否则执行步骤208。
步骤208，鉴别待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像；若是，则执行步骤210，否则，执行步骤212。
步骤210，拒绝对目标理赔业务进行理赔。
步骤212，执行对目标理赔业务进行理赔的理赔操作。
当然，上述图2只是介绍了上述(一)、(二)、(三)三种方式组合的一种具体实施方式，除此之外，上述三种方式的执行顺序还可以进行调整，本说明书实施例不再一一列举。
具体的，在上述(一)中，鉴别待鉴别理赔图像所包含对象与目标理赔业务的理赔对象是否相匹配，至少包括如下两种情况：
鉴别待鉴别理赔图像所包含对象的类型与目标理赔业务的理赔对象的类型是否一致；或者，鉴别待鉴别理赔图像所包含对象与目标理赔业务的理赔对象是否一致。
在具体实施时，有的同一类别内的对象相似度比较大，但从形态上可能无法识别出该待鉴别图像中所包含的对象究竟属于该类别中的哪一种，在该种情况下，即使识别待鉴别图像中所包含的对象究竟为哪一种，可能识别的准确性也较低，因此，为了减少运算量，则只需要鉴别待鉴别图像所包含对象的类型与目标理赔业务的理赔对象的类型是否一致即可。
例如，若是待鉴别理赔图像所包含的对象为鸡，目标理赔业务所对应的理赔对象为鸭，由于鸡和鸭的外形比较相似，则无法识别出两者究竟是否一致，在该种情况下，则可以采用识别待鉴别理赔图像所包含对象的类型与目标理赔业务的理赔对象的类型是否一致即可。
还例如，若是待鉴别理赔对象所包含的对象为办公椅，由于各种类型的办公椅的外形相差不大，因此，针对该种情况，则可以鉴别待鉴别理赔图像所包含对象的类型与目标理赔业务的理赔对象的类型是否一致即可。
另外，需要说明的是，在本说明书实施例中，上述对象的类型一般指的是汽车、禽类、桌子、椅子、电脑等划分得到的。
在具体实施时，可以通过图像识别的方式，对提取待鉴别理赔图像中所包含对象的轮廓的方式鉴别待鉴别理赔图像所包含的对象与理赔对象的类型是否一致。
在本说明书实施例中，通过鉴别待鉴别理赔图像所包含的对象与目标理赔业务所 对应的理赔对象是否相匹配的方式，可以筛除明显异常的图片，例如，理赔对象为汽车，待鉴别理赔图像所包含的对象则为摩托车，则可以将这类明显不符合的待鉴别理赔图像筛除，即在该种情况下，可以认为待鉴别理赔图像为针对目标理赔业务的异常图像，可以直接拒绝对目标理赔业务进行理赔。
具体的，在上述(二)中，鉴别待鉴别理赔图像是否为盗用图像，具体包括：
将待鉴别理赔图像与目标图片库中所存储的图像进行相似度比对；若是目标图片库中存在与待鉴别理赔图像之间的相似度大于或等于设定阈值的图像，则确定待鉴别理赔图像为盗用图像。
其中，上述目标图片库可以为从其他服务器或者系统接入的任意图片库，例如，可以为百度图片库、阿里生态图片库等。
在具体实施时，可以计算待鉴别理赔图像与目标图片库中所存储的每个图像之间的相似度值，并将所计算出的各个相似度值与设定阈值进行比较，若是存在大于或等于该设定阈值的相似度值，则可以认为待鉴别理赔图像为从目标图片库中盗用的图像。
其中，上述计算待鉴别理赔图像和目标图片库中的图像之间的相似度值的过程可参考现有技术中图像之间相似度值的计算方式，此处不再赘述。
另外，在具体实施时，为了减少工作量，可以将目标图片库中的图像分类进行存储，这样，在鉴别待鉴别理赔图像是否为盗用图像时，可以先识别出待鉴别理赔图像所包含对象的类别，然后，计算待鉴别理赔图像与目标图片库中相同类别的图像之间的相似度值，从而依据所计算的相似度值判断待鉴别理赔图像是否为盗用图像。
例如，可以将目标图片库中的图像按照汽车类、海鲜类、禽类、电脑类、手机类等分类进行存储，在确定待鉴别理赔图像是否为盗用图像时，可以先识别待鉴别理赔图像中所包含对象的类别，若是识别出待鉴别理赔图像中所包含的对象属于汽车类，则直接计算待鉴别理赔图像与目标图片库中属于汽车类的图像之间的相似度值，从而根据所计算出的相似度值判断待鉴别理赔图像是否为从目标图片库中盗用的图像。
在本说明书实施例中，通过将待鉴别理赔图像与目标图片库中的各个图像进行相似度比对，可以识别出待鉴别理赔图像是否为从目标图片库中盗用的图像，从而可以减少用户通过盗用图像进行理赔欺诈的情况的发生。
另外，在本说明书实施例中，通过将目标图片库中所存储的图像分类进行存储，先识别待鉴别理赔图像的类别，再将待鉴别理赔图像与设定图片里中相同类别的图像进 行相似度比对，可以减少进行相似度比对的工作量，从而进一步提高对待鉴别理赔图像进行鉴别的效率，从而提高理赔业务的处理效率，减少用户等待时间，提高用户体验。
其中，在上述(三)中，鉴别待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像，具体包括如下步骤：
将待鉴别理赔图像与历史理赔图片库中的各理赔图像进行相似度比对；若是历史理赔图片库中存在与待鉴别理赔图像的相似度大于或等于设定阈值的理赔图像，则确定待鉴别理赔图像为重复理赔图像。
在某些情况下，有的用户可能会从成功理赔案件中盗用或者剪切部分图像作为目标理赔业务所对应的待鉴别理赔图像，因此，为了防止该种情况的发生，在对待鉴别理赔图像进行鉴别时，还需要鉴别待鉴别理赔图像是否在历史理赔案件中出现过。
在具体实施时，可以计算待鉴别理赔图像与历史理赔图片库中的各理赔图像之间的相似度值，判断是否存在大于或等于设定阈值的相似度值，若是存在，则认为该待鉴别理赔图像在历史理赔图片库中出现过，即待鉴别理赔图像为重复理赔图像。
同样的，在该种情况下，为了减少进行相似度匹配时的计算量，也可以先识别出待鉴别理赔图像所包含对象的类型，然后筛选出历史理赔图片库中属于该类型的图像，然后，将待鉴别理赔图像与该类型的图像进行相似度匹配，从而识别出待鉴别理赔图像是否在历史理赔图片库中出现过。
在本说明书实施例中，若是鉴别结果指示待鉴别理赔图像中所包含对象与目标理赔业务的理赔对象不相匹配、或者确定出待鉴别理赔图像为盗用图像则将待鉴别理赔图像确定为针对目标理赔业务的异常图像。若是确定出待鉴别理赔图像为针对目标理赔业务的异常图像，则拒绝对目标理赔业务进行理赔。
另外，若是鉴别结果指示待鉴别理赔图像为重复理赔图像，根据待鉴别理赔图像的鉴别结果，确定针对目标理赔业务的处理方式，包括：
判断目标理赔业务与历史理赔业务是否为关联理赔业务；若是，确定执行针对目标理赔业务的理赔操作；否则，拒绝对目标理赔业务进行理赔；其中，所述历史理赔业务为与所述待鉴别理赔图像为重复理赔图像所对应的理赔业务。
其中，所谓关联理赔业务可以为针对同一理赔人、同一理赔对象等在不同时期发生的理赔案件。
在具体实施时，可以通过将目标理赔业务与上述重复理赔图像所对应的历史理赔业务进行匹配的方式判断目标理赔业务与历史理赔业务是否为关联理赔业务。具体的，可以筛选目标理赔业务中的理赔对象、理赔人、理赔事件、理赔事件所发生的时间、地点等关键信息，将该关键信息与历史理赔业务相对应的关键信息进行匹配，若是确定出该关键信息相匹配，则认为目标理赔业务与该历史理赔业务为关联理赔业务。在该种情况下，则执行针对目标理赔业务的理赔操作，若是确定出目标理赔业务与历史理赔业务并不是关联理赔业务，则说明待鉴别理赔图像为从该历史理赔业务中盗用的图像，因此，认为该待鉴别理赔图像为针对目标理赔业务的异常图像，则拒绝对目标理赔业务进行理赔。
另外，在具体实施时，为了进一步提高对目标理赔业务对历史理赔业务是否是关联理赔业务的判断的准确性，还可以通过人工判断的方式对上述判断结果进行校正。即在判断目标理赔业务与历史理赔业务是否为关联理赔业务的同时，将目标理赔业务和历史理赔业务发送给人工审核节点通过人工进行判断。
若是人工判断的结果与上述判断结果出现差异，则以人工判断结果为准。例如，若是上述判断结果指示目标理赔业务和历史理赔业务为关联理赔业务，但是人工审核的结果指示目标理赔业务和历史理赔业务并不是关联理赔业务，则最终认为目标理赔案件与历史理赔案件并不是关联理赔业务。
当然，若是当人工审核结果与上述判断结果存在差异时，还可以通过人工审核的结果对上述关联理赔业务进行判断的算法进行修正，从而提高关联理赔业务判断算法的准确性。
图3为本说明书实施例提供的理赔业务的处理方法的方法流程图之三，图3所示的方法至少包括如下步骤：
步骤302，获取用户针对目标理赔业务上传的待鉴别理赔图像。
步骤304，鉴别待鉴别理赔对象所包含对象的类型与目标理赔业务的理赔对象的类型是否一致；若是，则执行步骤306；否则，执行步骤314。
步骤306，鉴别待理赔图像是否为盗用图像；若是，则执行步骤314；否则，执行步骤308；
步骤308，鉴别待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像；若是，则执行步骤312；否则，执行步骤310；
步骤310，执行对目标理赔业务进行理赔的操作。
步骤312，判断目标理赔业务与目标历史理赔业务是否为关联理赔业务；其中，目标历史理赔业务为与待鉴别理赔图像为重复图像的理赔图像所对应的业务；若是，则执行步骤310，否则，执行步骤314。
步骤314，拒绝对目标理赔业务进行理赔。
其中，图3所对应实施例中各个步骤的具体实现方式可参考图1、图2所对应方法实施例，此处不再赘述。
图4为本说明书实施例提供的理赔业务的处理方法的方法流程图之四，图4所示的方法至少包括如下步骤：
步骤402，获取用户针对目标理赔业务上传的待鉴别理赔图像。
步骤404，鉴别待鉴别理赔对象所包含对象与目标理赔业务的理赔对象是否一致；若是，则执行步骤406；否则，执行步骤416。
步骤406，鉴别待理赔图像是否为盗用图像；若是，则执行步骤416；否则，执行步骤408；
步骤408，鉴别待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像；若是，则执行步骤412；否则，执行步骤410；
步骤410，执行对目标理赔业务进行理赔的操作。
步骤412，判断目标理赔业务与目标历史理赔业务是否为关联理赔业务，得到第一判断结果，以及，获取通过人工方式判断目标理赔业务与目标历史理赔业务是否为关联理赔业务的第二判断结果；其中，目标历史理赔业务为与待鉴别理赔图像为重复图像的理赔图像所对应的业务。
步骤414，根据第一判断结果和第二判断结果确定目标理赔业务与目标历史理赔业务是否为关联理赔业务；若是，则执行步骤410，否则，执行步骤416。
其中，若是第一判断结果和第二判断结果不同时，则将第二判断结果确定为最终判断结果。
步骤416，拒绝对目标理赔业务进行理赔。
其中，图4所对应实施例中各个步骤的具体实现方式可参考图1、图2所对应方法 实施例，此处不再赘述。
本说明书实施例提供的理赔业务的处理方法，在处理理赔业务的过程中，对于用户上传的待鉴别理赔图像，则根据目标理赔业务所对应的图像鉴别规则对该待鉴别理赔图像进行鉴别，将图像鉴别技术应用于理赔业务中，实现了对待鉴别理赔图像的自动化鉴别，节省了人工成本，提高了待鉴别理赔图像的鉴别效率，从而提高了在线理赔业务的处理效率，从而减少了在处理理赔业务过程中用户等待时间，提高了用户体验。
对应于本说明书实施例提供的理赔业务的处理方法，基于相同的思路，本说明书实施例还提供了一种理赔业务的处理装置，用于执行本说明书实施例提供的方法，图5为本说明书实施例提供的理赔业务的处理装置的模块组成示意图，包括：
获取模块502，用于获取用户针对目标理赔业务上传的待鉴别理赔图像；
鉴别模块504，用于根据目标理赔业务所对应的图像鉴别规则对待鉴别理赔图像进行鉴别，以确定待鉴别理赔图像是否为针对目标理赔业务的异常图像；
确定模块506，用于根据待鉴别理赔图像的鉴别结果，确定针对目标理赔业务的处理方式。
可选的，上述鉴别模块504包括以下单元中的一种或多种：
第一鉴别单元，用于鉴别待鉴别理赔图像所包含的对象与目标理赔业务的理赔对象是否相匹配；若不相匹配，则确定待鉴别理赔图像为针对目标理赔业务的异常图像；
第二鉴别单元，用于鉴别待鉴别理赔图像是否为盗用图像；若是，则确定待鉴别理赔图像为针对目标理赔业务的异常图像；
第三鉴别单元，用于鉴别待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像；若是，则确定待鉴别理赔图像为针对目标理赔业务的异常图像。
可选的，上述第一鉴别单元，具体用于：
鉴别待鉴别理赔图像所包含对象的类型与目标理赔业务的理赔对象的类型是否一致；或者，鉴别待鉴别理赔图像所包含的对象与目标理赔业务的理赔对象是否一致。
可选的，上述第二鉴别单元，具体用于：
将待鉴别理赔图像与目标图片库中所存储的图像进行相似度比对；若是目标图片库中存在与待鉴别理赔图像的相似度大于或等于设定阈值的图像，则确定待鉴别理赔图像为盗用图像。
可选的，上述第三鉴别单元，具体用于：
分别将待鉴别理赔图像与历史理赔图片库中的各个理赔图像进行相似度比对；若是历史理赔图片库中存在与待鉴别理赔图像的相似度大于或等于设定阈值的理赔图像，则确定待鉴别理赔图像为重复理赔图像。
可选的，若鉴别结果指示待鉴别理赔图像与历史理赔业务中的理赔图像为重复图像；
上述确定模块506，包括：
判断单元，用于判断目标理赔业务与历史理赔业务是否为关联理赔业务；其中，历史理赔业务为与待鉴别理赔图像为重复图像的理赔图像所对应的业务；
执行单元，用于若是判断出目标理赔业务与历史理赔业务为关联理赔业务，则执行针对目标理赔业务的理赔操作；否则，拒绝对目标理赔业务进行理赔。
本说明书实施例的理赔业务的处理装置还可执行图1-图4中理赔业务的处理装置执行的方法，并实现理赔业务的处理装置在图1-图4所示实施例的功能，在此不再赘述。
本说明书实施例提供的理赔业务的处理装置，在处理理赔业务的过程中，对于用户上传的待鉴别理赔图像，则根据目标理赔业务所对应的图像鉴别规则对该待鉴别理赔图像进行鉴别，将图像鉴别技术应用于理赔业务中，实现了对待鉴别理赔图像的自动化鉴别，节省了人工成本，提高了待鉴别理赔图像的鉴别效率，从而提高了在线理赔业务的处理效率，从而减少了在处理理赔业务过程中用户等待时间，提高了用户体验。
进一步地，基于上述图1至图4所示的方法，本说明书实施例还提供了一种理赔业务的处理设备，如图6所示。
理赔业务的处理设备可因配置或性能不同而产生比较大的差异，可以包括一个或一个以上的处理器601和存储器602，存储器602中可以存储有一个或一个以上存储应用程序或数据。其中，存储器602可以是短暂存储或持久存储。存储在存储器602的应用程序可以包括一个或一个以上模块(图示未示出)，每个模块可以包括对理赔业务的处理设备中的一系列计算机可执行指令信息。更进一步地，处理器601可以设置为与存储器602通信，在理赔业务的处理设备上执行存储器602中的一系列计算机可执行指令信息。理赔业务的处理设备还可以包括一个或一个以上电源603，一个或一个以上有线或无线网络接口604，一个或一个以上输入输出接口605，一个或一个以上键盘606等。
在一个具体的实施例中，理赔业务的处理设备包括有存储器，以及一个或一个以上的程序，其中一个或者一个以上程序存储于存储器中，且一个或者一个以上程序可以包括一个或一个以上模块，且每个模块可以包括对理赔业务的处理设备中的一系列计算机可执行指令信息，且经配置以由一个或者一个以上处理器执行该一个或者一个以上程序包含用于进行以下计算机可执行指令信息：
获取用户针对目标理赔业务上传的待鉴别理赔图像；
根据目标理赔业务所对应的图像鉴别规则对待鉴别理赔图像进行鉴别，以确定待鉴别理赔图像是否为针对目标理赔业务的异常图像；
根据待鉴别理赔图像的鉴别结果，确定针对目标理赔业务的处理方式。
可选的，计算机可执行指令信息在被执行时，根据目标理赔业务所对应的图像鉴别规则对待鉴别理赔图像进行鉴别，以确定待鉴别理赔图像是否为针对目标理赔业务的异常图像，包括以下内容中的一种或多种：
鉴别待鉴别理赔图像所包含的对象与目标理赔业务的理赔对象是否相匹配；若不相匹配，则确定待鉴别理赔图像为针对目标理赔业务的异常图像；
鉴别待鉴别理赔图像是否为盗用图像；若是，则确定待鉴别理赔图像为针对目标理赔业务的异常图像；
鉴别待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像；若是，则确定待鉴别理赔图像为针对目标理赔业务的异常图像。
可选的，计算机可执行指令信息在被执行时，鉴别待鉴别理赔图像所包含的对象与目标理赔业务的理赔对象是否相匹配，包括：
鉴别待鉴别理赔图像所包含对象的类型与目标理赔业务的理赔对象的类型是否一致；或者，鉴别待鉴别理赔图像所包含的对象与目标理赔业务的理赔对象是否一致。
可选的，计算机可执行指令信息在被执行时，鉴别待鉴别理赔图像是否为盗用图像，包括：
将待鉴别理赔图像与目标图片库中所存储的图像进行相似度比对；
若是目标图片库中存在与待鉴别理赔图像的相似度大于或等于设定阈值的图像，则确定待鉴别理赔图像为盗用图像。
可选的，计算机可执行指令信息在被执行时，鉴别待鉴别理赔图像与历史理赔业 务中的理赔图像是否为重复图像，包括：
分别将待鉴别理赔图像与历史理赔图片库中的各个理赔图像进行相似度比对；
若是历史理赔图片库中存在与待鉴别理赔图像的相似度大于或等于设定阈值的理赔图像，则确定待鉴别理赔图像为重复理赔图像。
可选的，计算机可执行指令信息在被执行时，若鉴别结果指示待鉴别理赔图像与历史理赔业务中的理赔图像为重复图像；
根据待鉴别理赔图像的鉴别结果，确定针对目标理赔业务的处理方式，包括：
判断目标理赔业务与历史理赔业务是否为关联理赔业务；其中，历史理赔业务为与待鉴别理赔图像为重复图像的理赔图像所对应的业务；
若是，执行针对目标理赔业务的理赔操作；否则，拒绝对目标理赔业务进行理赔。
本说明书实施例提供的理赔业务的处理设备，在处理理赔业务的过程中，对于用户上传的待鉴别理赔图像，则根据目标理赔业务所对应的图像鉴别规则对该待鉴别理赔图像进行鉴别，将图像鉴别技术应用于理赔业务中，实现了对待鉴别理赔图像的自动化鉴别，节省了人工成本，提高了待鉴别理赔图像的鉴别效率，从而提高了在线理赔业务的处理效率，从而减少了在处理理赔业务过程中用户等待时间，提高了用户体验。
进一步地，基于上述图1至图4所示的方法，本说明书实施例还提供了一种存储介质，用于存储计算机可执行指令信息，一种具体的实施例中，该存储介质可以为U盘、光盘、硬盘等，该存储介质存储的计算机可执行指令信息在被处理器执行时，能实现以下流程：
获取用户针对目标理赔业务上传的待鉴别理赔图像；
根据目标理赔业务所对应的图像鉴别规则对待鉴别理赔图像进行鉴别，以确定待鉴别理赔图像是否为针对目标理赔业务的异常图像；
根据待鉴别理赔图像的鉴别结果，确定针对目标理赔业务的处理方式。
可选的，该存储介质存储的计算机可执行指令信息在被处理器执行时，根据目标理赔业务所对应的图像鉴别规则对待鉴别理赔图像进行鉴别，以确定待鉴别理赔图像是否为针对目标理赔业务的异常图像，包括以下内容中的一种或多种：
鉴别待鉴别理赔图像所包含的对象与目标理赔业务的理赔对象是否相匹配；若不相匹配，则确定待鉴别理赔图像为针对目标理赔业务的异常图像；
鉴别待鉴别理赔图像是否为盗用图像；若是，则确定待鉴别理赔图像为针对目标理赔业务的异常图像；
鉴别待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像；若是，则确定待鉴别理赔图像为针对目标理赔业务的异常图像。
可选的，该存储介质存储的计算机可执行指令信息在被处理器执行时，鉴别待鉴别理赔图像所包含的对象与目标理赔业务的理赔对象是否相匹配，包括：
鉴别待鉴别理赔图像所包含对象的类型与目标理赔业务的理赔对象的类型是否一致；或者，鉴别待鉴别理赔图像所包含的对象与目标理赔业务的理赔对象是否一致。
可选的，该存储介质存储的计算机可执行指令信息在被处理器执行时，鉴别待鉴别理赔图像是否为盗用图像，包括：
将待鉴别理赔图像与目标图片库中所存储的图像进行相似度比对；
若是目标图片库中存在与待鉴别理赔图像的相似度大于或等于设定阈值的图像，则确定待鉴别理赔图像为盗用图像。
可选的，该存储介质存储的计算机可执行指令信息在被处理器执行时，鉴别待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像，包括：
分别将待鉴别理赔图像与历史理赔图片库中的各个理赔图像进行相似度比对；
若是历史理赔图片库中存在与待鉴别理赔图像的相似度大于或等于设定阈值的理赔图像，则确定待鉴别理赔图像为重复理赔图像。
可选的，该存储介质存储的计算机可执行指令信息在被处理器执行时，若鉴别结果指示待鉴别理赔图像与历史理赔业务中的理赔图像为重复图像；
根据待鉴别理赔图像的鉴别结果，确定针对目标理赔业务的处理方式，包括：
判断目标理赔业务与历史理赔业务是否为关联理赔业务；其中，历史理赔业务为与待鉴别理赔图像为重复图像的理赔图像所对应的业务；
若是，执行针对目标理赔业务的理赔操作；否则，拒绝对目标理赔业务进行理赔。
本说明书实施例提供的存储介质存储的计算机可执行指令信息在被处理器执行时，在处理理赔业务的过程中，对于用户上传的待鉴别理赔图像，则根据目标理赔业务所对应的图像鉴别规则对该待鉴别理赔图像进行鉴别，将图像鉴别技术应用于理赔业务中， 实现了对待鉴别理赔图像的自动化鉴别，节省了人工成本，提高了待鉴别理赔图像的鉴别效率，从而提高了在线理赔业务的处理效率，从而减少了在处理理赔业务过程中用户等待时间，提高了用户体验。
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。
上述实施例阐明的系统、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、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。
为了描述的方便，描述以上装置时以功能分为各种单元分别描述。当然，在实施本申请时可以把各单元的功能在同一个或多个软件和/或硬件中实现。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请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，本申请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。
本申请是参照根据本说明书实施例的方法、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信息实现流程图和/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信息到通用计算机、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信息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信息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信息产生包括指令信息装置的制造品，该指令信息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信息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信息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信息、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。
还需要说明的是，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、商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、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本申请的实施例可提供为方法、系统或计算机程序产品。因此，本申请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，本申请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。
本申请可以在由计算机执行的计算机可执行指令信息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申请，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。
以上所述仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。

Claims (14)

  1. 一种理赔业务的处理方法，所述方法包括：
    获取用户针对目标理赔业务上传的待鉴别理赔图像；
    根据所述目标理赔业务所对应的图像鉴别规则对所述待鉴别理赔图像进行鉴别，以确定所述待鉴别理赔图像是否为针对所述目标理赔业务的异常图像；
    根据所述待鉴别理赔图像的鉴别结果，确定针对所述目标理赔业务的处理方式。
  2. 如权利要求1所述的方法，根据所述目标理赔业务所对应的图像鉴别规则对所述待鉴别理赔图像进行鉴别，以确定所述待鉴别理赔图像是否为针对所述目标理赔业务的异常图像，包括以下内容中的一种或多种：
    鉴别所述待鉴别理赔图像所包含的对象与所述目标理赔业务的理赔对象是否相匹配；若不相匹配，则确定所述待鉴别理赔图像为针对所述目标理赔业务的异常图像；
    鉴别所述待鉴别理赔图像是否为盗用图像；若是，则确定所述待鉴别理赔图像为针对所述目标理赔业务的异常图像；
    鉴别所述待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像；若是，则确定所述待鉴别理赔图像为针对所述目标理赔业务的异常图像。
  3. 如权利要求2所述的方法，鉴别所述待鉴别理赔图像所包含的对象与所述目标理赔业务的理赔对象是否相匹配，包括：
    鉴别所述待鉴别理赔图像所包含对象的类型与所述目标理赔业务的理赔对象的类型是否一致；或者，
    鉴别所述待鉴别理赔图像所包含的对象与所述目标理赔业务的理赔对象是否一致。
  4. 如权利要求2所述的方法，鉴别所述待鉴别理赔图像是否为盗用图像，包括：
    将所述待鉴别理赔图像与目标图片库中所存储的图像进行相似度比对；
    若是所述目标图片库中存在与所述待鉴别理赔图像的相似度大于或等于设定阈值的图像，则确定所述待鉴别理赔图像为所述盗用图像。
  5. 如权利要求2所述的方法，鉴别所述待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像，包括：
    分别将所述待鉴别理赔图像与历史理赔图片库中的各个理赔图像进行相似度比对；
    若是所述历史理赔图片库中存在与所述待鉴别理赔图像的相似度大于或等于设定阈值的理赔图像，则确定所述待鉴别理赔图像为重复理赔图像。
  6. 如权利要求2所述的方法，若鉴别结果指示所述待鉴别理赔图像与历史理赔业务中的理赔图像为重复图像；
    所述根据所述待鉴别理赔图像的鉴别结果，确定针对所述目标理赔业务的处理方式，包括：
    判断所述目标理赔业务与所述历史理赔业务是否为关联理赔业务；其中，所述历史理赔业务为与所述待鉴别理赔图像为重复图像的理赔图像所对应的业务；
    若是，执行针对所述目标理赔业务的理赔操作；否则，拒绝对所述目标理赔业务进行理赔。
  7. 一种理赔业务的处理装置，所述装置包括：
    获取模块，用于获取用户针对目标理赔业务上传的待鉴别理赔图像；
    鉴别模块，用于根据所述目标理赔业务所对应的图像鉴别规则对所述待鉴别理赔图像进行鉴别，以确定所述待鉴别理赔图像是否为针对所述目标理赔业务的异常图像；
    确定模块，用于根据所述待鉴别理赔图像的鉴别结果，确定针对所述目标理赔业务的处理方式。
  8. 如权利要求7所述的装置，所述鉴别模块包括以下单元中的一种或多种：
    第一鉴别单元，用于鉴别所述待鉴别理赔图像所包含的对象与所述目标理赔业务的理赔对象是否相匹配；若不相匹配，则确定所述待鉴别理赔图像为针对所述目标理赔业务的异常图像；
    第二鉴别单元，用于鉴别所述待鉴别理赔图像是否为盗用图像；若是，则确定所述待鉴别理赔图像为针对所述目标理赔业务的异常图像；
    第三鉴别单元，用于鉴别所述待鉴别理赔图像与历史理赔业务中的理赔图像是否为重复图像；若是，则确定所述待鉴别理赔图像为针对所述目标理赔业务的异常图像。
  9. 如权利要求8所述的装置，所述第一鉴别单元，具体用于：
    鉴别所述待鉴别理赔图像所包含对象的类型与所述目标理赔业务的理赔对象的类型是否一致；或者，
    鉴别所述待鉴别理赔图像所包含的对象与所述目标理赔业务的理赔对象是否一致。
  10. 如权利要求8所述的装置，所述第二鉴别单元，具体用于：
    将所述待鉴别理赔图像与目标图片库中所存储的图像进行相似度比对；若是所述目标图片库中存在与所述待鉴别理赔图像的相似度大于或等于设定阈值的图像，则确定所述待鉴别理赔图像为所述盗用图像。
  11. 如权利要求8所述的装置，所述第三鉴别单元，具体用于：
    分别将所述待鉴别理赔图像与历史理赔图片库中的各个理赔图像进行相似度比对；若是所述历史理赔图片库中存在与所述待鉴别理赔图像的相似度大于或等于设定阈值 的理赔图像，则确定所述待鉴别理赔图像为重复理赔图像。
  12. 如权利要求8所述的装置，若鉴别结果指示所述待鉴别理赔图像与历史理赔业务中的理赔图像为重复图像；
    所述确定模块，包括：
    判断单元，用于判断所述目标理赔业务与所述历史理赔业务是否为关联理赔业务；其中，所述历史理赔业务为与所述待鉴别理赔图像为重复图像的理赔图像所对应的业务；
    执行单元，用于若是判断出所述目标理赔业务与所述历史理赔业务为关联理赔业务，则执行针对所述目标理赔业务的理赔操作；否则，拒绝对所述目标理赔业务进行理赔。
  13. 一种理赔业务的处理设备，包括：
    处理器；以及
    被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行时使所述处理器：
    获取用户针对目标理赔业务上传的待鉴别理赔图像；
    根据所述目标理赔业务所对应的图像鉴别规则对所述待鉴别理赔图像进行鉴别，以确定所述待鉴别理赔图像是否为针对所述目标理赔业务的异常图像；
    根据所述待鉴别理赔图像的鉴别结果，确定针对所述目标理赔业务的处理方式。
  14. 一种存储介质，用于存储计算机可执行指令，所述可执行指令在被执行时实现以下流程：
    获取用户针对目标理赔业务上传的待鉴别理赔图像；
    根据所述目标理赔业务所对应的图像鉴别规则对所述待鉴别理赔图像进行鉴别，以确定所述待鉴别理赔图像是否为针对所述目标理赔业务的异常图像；
    根据所述待鉴别理赔图像的鉴别结果，确定针对所述目标理赔业务的处理方式。
PCT/CN2020/070032 2019-02-11 2020-01-02 理赔业务的处理方法及装置 WO2020164331A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910110220.2A CN110009296A (zh) 2019-02-11 2019-02-11 理赔业务的处理方法及装置
CN201910110220.2 2019-02-11

Publications (1)

Publication Number Publication Date
WO2020164331A1 true WO2020164331A1 (zh) 2020-08-20

Family

ID=67165722

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/070032 WO2020164331A1 (zh) 2019-02-11 2020-01-02 理赔业务的处理方法及装置

Country Status (3)

Country Link
CN (1) CN110009296A (zh)
TW (1) TWI730399B (zh)
WO (1) WO2020164331A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN110688514A (zh) * 2019-08-30 2020-01-14 中国人民财产保险股份有限公司 一种保险理赔图像数据的查重方法及装置
CN111178309B (zh) * 2019-12-31 2023-03-28 蚂蚁财富(上海)金融信息服务有限公司 业务处理方法及装置
CN113763187B (zh) * 2020-12-02 2023-11-07 北京京东振世信息技术有限公司 理赔结果确定方法、理赔请求发送方法和装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106203461A (zh) * 2015-05-07 2016-12-07 中国移动通信集团公司 一种图像处理方法及装置
CN107085814A (zh) * 2017-04-11 2017-08-22 武汉华创欣网科技有限公司 一种车险理赔照片的分析方法及系统
CN107798514A (zh) * 2017-11-22 2018-03-13 阿里巴巴集团控股有限公司 基于信用实现理赔的方法和装置
CN108323209A (zh) * 2018-01-29 2018-07-24 深圳前海达闼云端智能科技有限公司 信息处理方法、系统、云处理设备以及计算机程序产品
CN108573286A (zh) * 2018-05-10 2018-09-25 阿里巴巴集团控股有限公司 一种理赔业务的数据处理方法、装置、设备及服务器
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

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001076055A (ja) * 2000-07-28 2001-03-23 Casio Comput Co Ltd 査定金額算出方法及び損害査定システム
US20090138290A1 (en) * 2006-09-26 2009-05-28 Holden Johnny L Insurance adjustment through digital imaging system and method
US20180182041A1 (en) * 2016-12-27 2018-06-28 Aon Global Operations Ltd (Singapore Branch) Systems and Methods for Wide-Scale Mapping of Neighborhood Property Geolocations and Estimating Property Values Thereof
TWM560650U (zh) * 2017-10-20 2018-05-21 富邦產物保險股份有限公司 車輛保險系統
CN113139524A (zh) * 2017-12-14 2021-07-20 创新先进技术有限公司 一种数据处理的方法、装置及设备
CN108734479A (zh) * 2018-04-12 2018-11-02 阿里巴巴集团控股有限公司 保险欺诈识别的数据处理方法、装置、设备及服务器
CN109035044A (zh) * 2018-09-06 2018-12-18 波奇（上海）信息科技有限公司 一种宠物保险理赔的审核方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106203461A (zh) * 2015-05-07 2016-12-07 中国移动通信集团公司 一种图像处理方法及装置
CN107085814A (zh) * 2017-04-11 2017-08-22 武汉华创欣网科技有限公司 一种车险理赔照片的分析方法及系统
CN107798514A (zh) * 2017-11-22 2018-03-13 阿里巴巴集团控股有限公司 基于信用实现理赔的方法和装置
CN108323209A (zh) * 2018-01-29 2018-07-24 深圳前海达闼云端智能科技有限公司 信息处理方法、系统、云处理设备以及计算机程序产品
CN108573286A (zh) * 2018-05-10 2018-09-25 阿里巴巴集团控股有限公司 一种理赔业务的数据处理方法、装置、设备及服务器
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

Also Published As

Publication number Publication date
TW202030684A (zh) 2020-08-16
CN110009296A (zh) 2019-07-12
TWI730399B (zh) 2021-06-11

Similar Documents

Publication Publication Date Title
WO2020164331A1 (zh) 理赔业务的处理方法及装置
EP3780541B1 (en) Identity information identification method and device
TWI759536B (zh) 聲紋認證方法、帳號註冊方法及裝置
WO2021068636A1 (zh) 基于区块链的可验证声明的创建方法、装置、设备及系统
TWI782205B (zh) 識別二手門號帳戶盜用的風控模型訓練、風控方法、裝置以及設備
CN108763952B (zh) 一种数据分类方法、装置及电子设备
WO2019214308A1 (zh) 一种理赔业务的数据处理方法、装置、设备及服务器
US11128668B2 (en) Hybrid network infrastructure management
TWI764148B (zh) 風險預測和風險預測模型的訓練方法、裝置及電子設備
TWI686759B (zh) 車險定損資料的處理方法、裝置和處理設備
CN110633991A (zh) 风险识别方法、装置和电子设备
CN111968625A (zh) 融合文本信息的敏感音频识别模型训练方法及识别方法
CN113516480B (zh) 一种支付风险识别方法、装置及设备
WO2023231785A1 (zh) 数据处理方法、装置及设备
CN113887615A (zh) 图像处理方法、装置、设备和介质
CN109919357B (zh) 一种数据确定方法、装置、设备及介质
US9785724B2 (en) Secondary queue for index process
US20190018868A1 (en) Method of inputting document information, device, server, and storage medium
WO2024060852A1 (zh) 一种模型的所有权验证方法、装置、存储介质及电子设备
CN109063967B (zh) 一种风控场景特征张量的处理方法、装置及电子设备
TWI818427B (zh) 使用基於文本的說話者變更檢測的說話者劃分糾正方法及系統
US11880405B2 (en) Method for searching similar images in an image database using global values of a similarity measure for discarding partitions of the image database
CN114626798A (zh) 任务流程确定方法及装置、计算机可读存储介质、终端
WO2021098346A1 (zh) 人体朝向检测方法、装置、电子设备和计算机存储介质
TW202032484A (zh) 模型合併方法和裝置

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: 20756540

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: 20756540

Country of ref document: EP

Kind code of ref document: A1