Complaint processing method and related device

Abstract

The invention provides an appeal processing method and a related device. The embodiment of the invention can be applied to the field of intelligent payment. The method comprises the steps that in response to a complaint request for a target order sent by a target object, a shooting device of a target terminal is called to collect a feature image of the target object, the target terminal corresponds to the target object, the feature image comprises image data and shooting information, and the shooting information comprises the shooting time and the shooting position of the image data; obtaining payment time and a payment position of the target order; a first duration and a first distance are calculated, the first duration indicates the time difference between the payment time and the shooting time, and the first distance indicates the distance difference between the payment position and the shooting position; and if the first duration is less than the first preset duration and the first distance is greater than the preset distance, agreeing to the appeal request. The appeal efficiency of the order is improved based on the shooting information of the collected image and the order information.

Description

Technical Field

[0001] This application relates to the field of intelligent payment technologies, and particularly to an appeal handling method and related devices. Background Art

[0002] With the rapid development of network technologies, electronic payment has become a commonly used payment method in current life. Combining with the increasing progress of current Artificial Intelligence (AI) technologies, payment methods have gradually evolved from paperless to more intelligent biometric payments, such as face recognition payment, fingerprint payment, palm recognition payment, etc. With the implementation of such biometric payment methods, it is inevitable that there will be some situations where orders need to be appealed. Therefore, how to provide an appeal handling method to improve the appeal efficiency of orders and enhance the user experience is a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0003] Embodiments of this application provide an appeal handling method and related devices, which improve the appeal efficiency of orders based on the shooting information and order information of the captured images.

[0004] The first aspect of this application provides an appeal handling method, including:

[0005] In response to an appeal request for a target order sent by a target object, call the shooting device of the target terminal to capture a feature image of the target object. The target terminal corresponds to the target object, and the feature image includes image data and shooting information. The shooting information includes the shooting time and shooting location of the image data;

[0006] Obtain the payment time and payment location of the target order;

[0007] Calculate a first duration and a first distance. The first duration indicates the time difference between the payment time and the shooting time, and the first distance indicates the distance difference between the payment location and the shooting location;

[0008] If the first duration is less than a first preset duration and the first distance is greater than a preset distance, then agree to the appeal request.

[0009] In a possible implementation method, before calculating the first duration and the first distance, it further includes:

[0010] If the quality of the feature image does not meet the preset conditions, then call the shooting device again to capture the feature image.

[0011] In a possible implementation method, calling the shooting device of the target terminal to capture a feature image of the target object includes:

[0012] Call the shooting device to perform image capture to obtain a to-be-tested image;

[0013] Perform liveness detection based on the image to be tested;

[0014] Determine the image to be tested that passes the liveness detection as the feature image.

[0015] In a possible implementation method, the feature image indicates the biological information of the target object, and the biological information includes at least one of palmprint features, fingerprint features, face features, and pupil features.

[0016] In a possible implementation method, after calculating the first duration and the first distance, it further includes:

[0017] If the first duration is not less than the first preset duration and / or the first distance is not greater than the preset distance, then:

[0018] Compare the feature image with the first pre-stored information to obtain the first similarity, where the first pre-stored information corresponds to the biological information pre-stored for the target object;

[0019] Compare the feature image with the second pre-stored information to obtain the second similarity, where the second pre-stored information corresponds to the biological information for creating the target order;

[0020] If the first similarity is greater than the second preset value and the second similarity is less than the third preset value, then agree to the appeal request.

[0021] In a possible implementation method, if the first duration is less than the first preset duration and the first distance is greater than the preset distance, and agreeing to the appeal request includes:

[0022] If the first duration is less than the first preset duration and the first distance is greater than the preset distance, then:

[0023] Obtain the first similarity;

[0024] If the first similarity is greater than the fourth preset value, then agree to the appeal request, where the fourth preset value is less than the second preset value.

[0025] In a possible implementation method, the shooting information further includes the device information of the target terminal; after calling the shooting device of the target terminal to collect the feature image of the target object, it further includes:

[0026] Determine that the target terminal is the common terminal device of the target object according to the device information.

[0027] In a possible implementation method, before calculating the first duration and the first distance, it further includes:

[0028] Calculate the second duration between the shooting time and the current time;

[0029] If the second duration is greater than the second preset duration, then re-call the shooting device to collect the feature image.

[0030] The second aspect of the present application provides an appeal handling device, including:

[0031] A collection module, configured to, in response to an appeal request for a target order sent by a target object, call the photographing device of the target terminal to collect a feature image of the target object, where the target terminal corresponds to the target object, and the feature image includes image data and photographing information, and the photographing information includes the photographing time and the photographing location of the image data;

[0032] An acquisition module, configured to acquire the payment time and the payment location of the target order;

[0033] A calculation module, configured to calculate a first duration and a first distance, where the first duration indicates the time difference between the payment time and the photographing time, and the first distance indicates the distance difference between the payment location and the photographing location;

[0034] A processing module, configured to, if the first duration is less than a first preset duration and the first distance is greater than a preset distance, approve the appeal request.

[0035] In a possible implementation method, it further includes:

[0036] A quality verification module, configured to, if the quality of the feature image does not meet a preset condition, call the photographing device again to collect the feature image.

[0037] In a possible implementation method, the collection module is specifically configured to call the photographing device to perform image collection to obtain a to-be-detected image; perform a live detection based on the to-be-detected image; and determine the to-be-detected image that passes the live detection as the feature image.

[0038] In a possible implementation method, the feature image indicates the biological information of the target object, and the biological information includes at least one of palmprint features, fingerprint features, face features, and pupil features.

[0039] In a possible implementation method, the processing module is further configured to, if the first duration is not less than the first preset duration and / or the first distance is not greater than the preset distance, compare the feature image with first pre-stored information to obtain a first similarity, where the first pre-stored information corresponds to the pre-stored biological information of the target object; compare the feature image with second pre-stored information to obtain a second similarity, where the second pre-stored information corresponds to the biological information for creating the target order; and if the first similarity is greater than a second preset value and the second similarity is less than a third preset value, approve the appeal request.

[0040] In a possible implementation method, the processing module is specifically configured to obtain a first similarity if the first duration is less than a first preset duration and the first distance is greater than a preset distance; and approve the appeal request if the first similarity is greater than a fourth preset value, where the fourth preset value is less than the second preset value.

[0041] In a possible implementation method, the shooting information further includes device information of the target terminal; and further includes:

[0042] The device verification module is configured to determine that the target terminal is the common terminal device of the target object according to the device information.

[0043] In a possible implementation method, before calculating the first duration and the first distance, it further includes:

[0044] Calculate a second duration between the shooting time and the current time;

[0045] If the second duration is greater than a second preset duration, the shooting device is called again to collect the feature image.

[0046] The third aspect of this application provides a computer device, including:

[0047] A memory, a transceiver, a processor, and a bus system;

[0048] Wherein, the memory is used to store programs;

[0049] The processor is configured to execute the programs in the memory, including executing the methods in the above aspects;

[0050] The bus system is used to connect the memory and the processor to enable communication between the memory and the processor.

[0051] The fourth aspect of this application provides a computer-readable storage medium, in which instructions are stored. When the instructions run on a computer, the computer is enabled to execute the methods in the above aspects.

[0052] The fifth aspect of this application provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above aspects.

[0053] It can be seen from the above technical solutions that the embodiments of this application have the following advantages:

[0054] This application provides an appeal handling method and related devices. By responding to an appeal request for a target order sent by a target object, the photographing device of the target terminal is called to collect the feature image of the target object. The target terminal corresponds to the target object. The feature image includes image data and photographing information. The photographing information includes the photographing time and the photographing location of the image data; obtain the payment time and the payment location of the target order; calculate the first duration and the first distance. The first duration indicates the time difference between the payment time and the photographing time, and the first distance indicates the distance difference between the payment location and the photographing location; if the first duration is less than the first preset duration and the first distance is greater than the preset distance, the appeal request is approved. The method provided by the embodiments of this application, after obtaining the user's appeal request, collects the feature image of the user by calling the photographing device of the user terminal, determines the photographing time and the photographing location of the image based on the photographing information carried in the image, and compares the photographing information with the order time and the order location when creating the payment order. If it is determined according to the time difference and the distance difference that the user cannot move this distance within this time range, it is determined that there is a misidentification situation, so the user's appeal request is approved. The appeal verification process of this method only needs to use time and location parameters, omitting the step of biometric information comparison, improving the appeal efficiency of the order, and ensuring the user experience. Description of the Drawings

[0055] Figure 1a It is a schematic diagram of the device structure of the palm brushing payment device;

[0056] Figure 1b It is the code of a kind of EXIF information;

[0057] Figure 2 It is the application environment diagram of the appeal handling method in the embodiments of this application;

[0058] Figure 3 It is the method flowchart of the appeal handling method provided by the embodiments of this application;

[0059] Figure 4 It is a schematic diagram of the bill details interface of an electronic payment;

[0060] Figure 5 It is the processing interface of the appeal handling method provided by the embodiments of this application on the terminal device;

[0061] Figure 6 It is the method flowchart of the appeal handling method provided by the embodiments of this application;

[0062] Figure 7 It is the structure diagram of the appeal handling method based on palm brushing payment provided by the embodiments of this application;

[0063] Figure 8 It is a schematic diagram of an embodiment of the appeal handling device in the embodiments of this application;

[0064] Figure 9 It is a schematic diagram of a server structure provided by an embodiment of the present application. Specific implementation manners

[0065] The embodiment of the present application provides an appeal processing method and related device, which determines whether to agree to the user's appeal request based on the shooting information and order information of the collected image, so as to improve the compensation efficiency for misidentification.

[0066] The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of the present application are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "corresponding to" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these process, method, product or device.

[0067] Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science, which attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making.

[0068] Artificial intelligence technology is an interdisciplinary subject, involving a wide range of fields, including both hardware-level technologies and software-level technologies. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0069] Computer Vision Technology (CV) Computer vision is a science that studies how to enable machines to "see". More specifically, it refers to using cameras and computers to replace human eyes for tasks such as object recognition and measurement in machine vision, and further performing graphic processing to make the computer-processed images more suitable for human eyes to observe or for transmission to instruments for detection. As a scientific discipline, computer vision researches related theories and technologies, attempting to build artificial intelligence systems that can obtain information from images or multi-dimensional data. Computer vision technology usually includes technologies such as image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, 3D object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, etc., and also includes common biometric recognition technologies such as face recognition and fingerprint recognition.

[0070] Machine Learning (ML) is an interdisciplinary field that involves multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers can simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve their own performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its applications cover all fields of artificial intelligence. Machine learning and deep learning usually include technologies such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and rote learning.

[0071] With the research and progress of artificial intelligence technology, artificial intelligence technology has been studied and applied in multiple fields, such as common intelligent payment, smart home, smart wearable devices, virtual assistants, smart speakers, smart marketing, driverless, autonomous driving, drones, robots, smart healthcare, smart customer service, etc. It is believed that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important role.

[0072] The solution provided in the embodiments of this application involves computer vision technology and machine learning technology. It uses computer software and hardware tools to identify the biometric features of users, including palmprint features, fingerprint features, face features, pupil features, etc., and compares them with a set of identity features pre-stored in a database to verify the identity of the users.

[0073] With the rapid development of network technology, electronic payment has become a common payment method in current life. Combined with the increasing progress of current artificial intelligence (AI) technology, the payment method has gradually evolved from paperless to a more intelligent biometric payment, such as face swiping payment, fingerprint payment, palm swiping payment, etc.

[0074] Taking palm-sweeping payment as an example, please refer to Figure 1a , Figure 1a which is a schematic diagram of the device structure of the palm-sweeping payment device. Users can pre-enter palmprint information through a corresponding terminal device (such as a smartphone), and the server matches and stores the palmprint information and the user's personal information; when making a payment, the user places their palm on the scanning area of the device shown in Figure 1a for scanning; the device pairs the scanned palmprint with the palmprint pre-entered by the user to verify the user's identity; once the user's identity verification is successful, the payment platform will connect to the user's payment account and perform corresponding deduction operations on the payment account.

[0075] However, with the implementation of such biometric payment methods, it is inevitable that there will be some misidentifications. For example, user A makes a palm-sweeping payment, but the deduction account is the account of user B. In the current technology, for the appeal problem of misidentified orders generated based on this type of payment method, it usually requires strict review and verification, including: verifying the identity information of the appealing user; verifying and comparing biometric information, including comparing and verifying the biometric information of the appealing user with the biometric information collected when creating the payment order; analyzing the order information, including viewing the detailed information of the order, transaction time, transaction amount, etc., to confirm whether there is a misidentification. It can be understood that this process usually takes a long time, which is also a concern for users when using this type of payment method. Therefore, how to provide an appeal processing method to improve the appeal efficiency of orders and thus improve the user experience is a technical problem that those skilled in the art urgently need to solve.

[0076] The Exchangeable Image File Format (EXIF) is a data specifically set for digital camera photos and can record the attribute information and shooting data of digital photos. EXIF information is a series of shooting information collected by a digital camera during the shooting process. This type of shooting information is placed within image file formats such as JPEG / TIFF and mainly includes various pieces of information related to the photography conditions at that time, such as the aperture, shutter speed, white balance, ISO (sensitivity), focal length, date and time, etc. of the photography, as well as information such as the camera brand model, color coding, the sound recorded during shooting, and the Global Positioning System (GPS). As Figure 1b , Figure 1b is a code for a type of EXIF information.

[0077] This code is used to view the GPS metadata of the picture file img.jpg using the Exiftool command-line tool. Exiftool is an open-source software that can read and edit the metadata of image, video, and audio files.

[0078] The output of this code shows the GPS location information of img.jpg, including:

[0079] GPS Latitude Ref: This is an identifier indicating whether the latitude is relative to the Northern Hemisphere or the Southern Hemisphere. Here, "North" is shown, indicating that the latitude is north latitude.

[0080] GPS Longitude Ref: This is an identifier indicating whether the longitude is relative to the Eastern Hemisphere or the Western Hemisphere. Here, "East" is shown, indicating that the longitude is east longitude.

[0081] GPS Altitude Ref: This is a reference indicating the altitude relative to sea level. Here, "Above Sea Level" is shown, indicating that the altitude is the height relative to sea level.

[0082] GPS Time Stamp: This is the time when the photo was taken, in the format of hours:minutes:seconds. Here, "06:46:22" is shown, which means 6:46:22 am.

[0083] GPS Processing Method: This is a field describing the way of GPS data processing. Here, "ASCII" is shown, indicating that the processing method is ASCII encoding.

[0084] GPSDate Stamp: This is the date when the photo was taken, in the format of year:month:day. Here, "2020:01:28" is shown, which means January 28, 2020.

[0085] GPS Altitude: This is the altitude when the photo was taken, in meters. Here, "172.2m Above Sea Level" is shown, which means an altitude of 172.2 meters.

[0086] GPSDate / Time: This is the complete date and time when the photo was taken, in the format of year:month:day hours:minutes:seconds. Here, "2020:01:28 06:46:22Z" is shown, which means 6:46:22 am on January 28, 2020 (Coordinated Universal Time).

[0087] GPS Latitude: This is the latitude when the photo was taken, in the format of degrees:minutes:seconds. "31deg 34'54.76"N" indicates that the latitude is 31 degrees 34 minutes 54.76 seconds north latitude.

[0088] GPS Longitude: This is the longitude at which the photo was taken, in the format of degrees:minutes:seconds. "74deg 18'9.62""E" indicates that the longitude is 74 degrees 18 minutes 9.62 seconds east longitude.

[0089] GPS Position: This is the complete geographical location when the photo was taken. "31deg 34'54.76""N,74deg 18'9.62""E" indicates that the geographical location is 31 degrees 34 minutes 54.76 seconds north latitude and 74 degrees 18 minutes 9.62 seconds east longitude.

[0090] Since the EXIF file is metadata embedded in the photo and the EXIF encodings of different camera manufacturers have their own encoding styles, the EXIF file is not easily tampered with. Based on this, the embodiments of this application provide an appeal handling method and its related device. In the biometric payment scenario, when a user submits an appeal request for a payment order, by comparing and analyzing the shooting information carried by the user's feature image and the payment information of the payment order, it is determined whether there is a misidentification situation for the order. If there is a misidentification, the user's appeal request is approved and a refund operation is performed, improving the order appeal efficiency and compensation efficiency.

[0091] For ease of understanding, please refer to Figure 2 , Figure 2 which is the application environment diagram of the appeal handling method in the embodiments of this application. As Figure 2 shown, the appeal handling method in the embodiments of this application is applied to an electronic payment system. The electronic payment system includes: a server and a terminal device; among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server can be directly or indirectly connected through wired or wireless communication methods, and this application does not make any restrictions in this regard.

[0092] This method is applied to the payment scenario based on biometric recognition. When a user discovers an order with unauthorized consumption in their account, they can upload an appeal request through a preset channel. After the server obtains the appeal request for the order initiated by the user through the terminal device, it invokes the imaging device of the terminal device to collect the feature image of the user. The feature image includes image data and shooting information, and the shooting information includes the shooting time and shooting location corresponding to the image data. The server compares the payment time and payment location of the order with the shooting time and shooting location. If the duration between the payment time and the shooting time is close, and the distance between the payment location and the shooting location is far, it can be considered that the order was not created by this user, that is, it is determined that there is a misidentification situation. Therefore, the server agrees to the user's appeal request to perform a refund operation for the user.

[0093] Next, the appeal handling method in this application will be introduced from the perspective of the server. Please refer to Figure 3 , Figure 3 which is the flowchart of the appeal handling method provided by the embodiment of this application, including:

[0094] 301. In response to an appeal request for a target order sent by a target object, invoke the imaging device of the target terminal to collect the feature image of the target object. The target terminal corresponds to the target object. The feature image includes image data and shooting information, and the shooting information includes the shooting time and shooting location of the image data.

[0095] It can be understood that payment scenarios using payment methods such as palm brushing payment and face brushing payment all belong to payment scenarios based on biometric information (palm prints, faces, etc.). In payment scenarios based on biometric information, when the actual consumer performs biometric recognition operations such as palm brushing or face brushing on the biometric information recognition device offline, if the recognition ability of the recognition device is insufficient, there may be a misidentification phenomenon, that is, the recognition device recognizes the biometric information of the actual consumer as another user and deducts fees from the account of the other user. Usually, the deduction message of the deducted user will be pushed to the user's terminal device in the form of a message push. When the user receives the deduction message but has not actually consumed, they can file an appeal through the appeal channel.

[0096] As Figure 4 shown, Figure 4It is a schematic diagram of the bill details interface for electronic payment. When the deducted user receives the message push of the deduction through the mobile terminal and clicks on the push content, the bill details are displayed, including the consumption place (XX Shopping Mall), the consumption amount (365.70 yuan), the consumption status (transaction successful), and other payment information, such as the payment time, payment method, product description, etc. In addition, the bill details interface also includes after-sales information, such as "Contact Merchant" for contacting the product provider; "View Transaction History" for querying the historical transaction data with this merchant; "Apply for Electronic Receipt" for querying and printing the payment voucher; and "Appeal" for the deducted user to appeal for a refund for this order. When the deducted user discovers that they are unaware of this consumption, they can click on the "Appeal" option to initiate an appeal request. The deducted user is the target object in the embodiment of this application, and this order is the target order in the embodiment of this application.

[0097] After responding to the appeal request initiated by the target object, it is necessary to obtain the feature image of the target object, which is used to indicate the features of the target object. It can be understood that when performing this operation, it is necessary to ensure that the object using the target terminal currently is the target object to prevent other users from selecting and uploading pictures through the target terminal. To achieve real-time photo capture, when the user initiates an appeal request, it is necessary to call the shooting device of the target terminal (such as a mobile terminal) for image capture to ensure that the provided photos are real and real-time, rather than randomly selected or forged photos by the user.

[0098] The feature image refers to the photo taken by the target object through the target terminal. Since the shooting device of the target terminal belongs to a digital camera, this feature image not only includes image data but also can include shooting information. Usually, this shooting information is usually a piece of code attached to the image data in the form of EXIF information. The picture with the EXIF code can be browsed like a normal picture, but this piece of code can be parsed to obtain the shooting information. In the embodiment of this application, the shooting information used includes the shooting time and the shooting location.

[0099] Please refer to Figure 5 , Figure 5 This is the processing interface of the appeal handling method provided by the embodiment of this application on the terminal device. When the appeal handling method provided by the embodiment of this application is applied to the palm-sweeping payment scenario, the interfaces successively displayed by the terminal device to the appealing user include: the message push page, the palm-sweeping service management page, and the shooting page.

[0100] The message push page is used to display the order and amount information provided by the payment system to the payee when a payment order occurs, as well as the management of palm-swipe services. Among them, the order and payment information is used to display the order type and amount, such as: "Palm-swipe payment: 365.70 yuan". The palm-swipe service management is used to display the order details in response to the click operation of the payee, such as the "View Details" or "Close" button. For example: After user A performs palm-swipe recognition on an offline palm-swipe device, due to the insufficient ability of the algorithm to handle large-scale recognition, misrecognition occurs. At this time, the backend deducts the payment for user B. Meanwhile, the order and deduction information, etc., will be pushed to the mobile phone of user B in the form of a message push.

[0101] The palm-swipe service management page is used to display the order details and the channel for appealing against mis-swipe. Among them, the order details include the GPS (or location information) when the order occurs, such as: "XX Shopping Mall". In response to the click operation of the payee on the "XX Shopping Mall", the location of the shopping mall will be displayed on the map interface. The mis-swipe appeal is used for the payee to submit an appeal request, such as Figure 4 the "Appeal" button in. For example: After receiving the palm-swipe payment message push, user B clicks on the service management entry to further view the order details information. User B can click on the mis-swipe handling entry below to file an appeal against mis-swipe.

[0102] The shooting page is used to obtain the characteristic image of the payee. Specifically, in response to the click operation of the payee on the mis-swipe appeal button, the shooting device of the terminal device is called. For example: After user B files an appeal against mis-swipe, it jumps to the camera for shooting, and the collected image is uploaded to the backend together with the order for identification. It can be understood that preferably, only the images directly shot by the shooting device are supported in this embodiment, and local image selection is not supported. The reason is to prevent users from making malicious refunds through mis-swipe appeals.

[0103] 302, obtain the payment time and payment location of the target order.

[0104] It can be understood that to process the appeal request for the target order, it is necessary to obtain the order information of the target order. This order information includes the payment time and payment location. Among them, the payment time can be the creation time of the order or the time when the payment is completed. Preferably, it is the time when the payment of the order is completed. This time represents the time when the system verifies the biometric information of the purchaser and performs the deduction operation on the payment account, such as Figure 4 shown as "Payment time: 2023-11-30 11:03:13". The payment location can be represented as the location of the shopping venue or the location of the biometric device. For example Figure 4 "XX Shopping Mall" in. The payment location can also be determined based on the location of the biometric device. For example Figure 1aThe middle brush palm payment device can be equipped with a GPS positioning function. While performing the deduction operation, it uploads the current positioning information to the server.

[0105] 303. Calculate the first duration and the first distance. The first duration indicates the time difference between the payment time and the shooting time, and the first distance indicates the distance difference between the payment location and the shooting location.

[0106] It can be understood that after obtaining the payment time, shooting time, payment location, and shooting location, the position deviation between the current position of the target user and the generation position of the target order, and the time deviation between the current time of the target user and the generation time of the target order can be calculated.

[0107] 304. If the first duration is less than the first preset duration and the first distance is greater than the preset distance, then agree to the appeal request.

[0108] It can be understood that the first preset duration is the duration threshold, and the first preset distance is the distance threshold. If the time deviation between the current time of the target user and the generation time of the target order is small, while the position deviation between the current position of the target user and the generation position of the target order is large, that is, for the target user, the generation time of this order was not long ago, yet the completion position of this order is far from the current position, and the target user cannot move a long distance in a short time, which means that the target order is not the consumption order of the target object, and there is a misidentification situation for this order. Therefore, agree to this appeal request.

[0109] It can be understood that the longer the time, the longer the distance that can be moved. Therefore, according to different duration thresholds, different distance thresholds can be formulated. For example: if the first preset duration is 5 minutes, then the corresponding first preset distance can be set to 10 kilometers; if the first preset duration is 1 hour, the corresponding first preset distance can be set to 200 kilometers. The specific duration threshold and distance threshold can be determined according to the actual experimental results after the product is launched. This application does not limit this.

[0110] The embodiment of this application provides an appeal processing method. After obtaining the user's appeal request, it collects the user's feature image by calling the shooting device of the user terminal, determines the shooting time and shooting location of the image based on the shooting information carried in the image, compares the shooting information with the order time and order location when creating the payment order. If it is determined according to the time difference and distance difference that the user cannot move this distance within this time range, it is judged that there is a misidentification situation, and therefore the user's appeal request is agreed. The appeal verification process of this method only needs to use time and position parameters, omitting the step of biometric information comparison, improving the order appeal efficiency and compensation efficiency, and ensuring the user experience.

[0111] In the Figure 3 corresponding embodiment of the appeal handling method provided in the embodiment of the present application, please refer to Figure 6 , Figure 6 which is the flowchart of the appeal handling method provided by the embodiment of the present application, including:

[0112] 601. In response to an appeal request for a target order sent by a target object, call the shooting device of the target terminal to collect a feature image of the target object. The target terminal corresponds to the target object. The feature image includes image data and shooting information. The shooting information includes the shooting time, shooting location of the image data, and device information of the terminal device.

[0113] It can be understood that step 601 is similar to step 301 in the Figure 3 corresponding embodiment above.

[0114] As Figure 1b shown, the code in Figure 1b can be used to indicate the shooting information of the feature image. Among them, the 5th, 7th, and 9th lines all refer to the shooting time of the feature image. The shooting time is represented by "06:46:22", indicating that the shooting time is 6:46:22 in the morning, and "2020:01:28" represents January 28, 2020; the 10th to 12th lines refer to the shooting location of the feature image. "31deg 34'54.76"N,74deg 18'9.62"E" indicates that the geographical location is 31 degrees 34 minutes 54.76 seconds north latitude and 74 degrees 18 minutes 9.62 seconds east longitude. It can be understood that the above information is obtained through the GPS information of the terminal device. In addition, there is also the device information of the terminal device, which can be directly obtained from the terminal device.

[0115] In a possible implementation method, the feature image indicates the biometric information of the target object, and the biometric information includes at least one of palm print features, fingerprint features, face features, and pupil features.

[0116] It can be understood that after the target object sends an appeal request, the corresponding terminal device switches to the shooting interface and instructs the target object to perform a shooting operation on the specified biometric information. For example: perform feature extraction on the picture taken by the target object to determine whether the picture belongs to the feature image including the specified biometric information. Commonly used feature extraction methods include Local Binary Pattern (LBP), Histogram of Oriented Gradient (HOG), etc.

[0117] In the fields of biometrics and computer vision, feature extraction is one of the key steps for extracting meaningful features from the image of the target object.

[0118] Assume that the feature image indicates the facial information of the target object. First, the picture of the target object can be preprocessed, including grayscale conversion, size normalization, etc., for subsequent feature extraction. Then, the local texture features around each pixel point in the picture can be calculated using the LBP algorithm to generate an LBP feature descriptor, which contains the texture information of the image. The HOG algorithm can also be used to calculate the gradient intensity and direction in different directions of the image to form a HOG feature descriptor containing shape information. In addition, when the biological information is palmprint features, the feature image is specifically a palm image. After the server obtains the captured picture, it extracts the features of the picture and uses classification and discrimination algorithms to classify and discriminate the picture based on the extracted features to determine whether the picture is a palm image. Commonly used classification and discrimination algorithms include support vector machines, decision trees, neural networks, etc.: First, the server uses a feature extraction algorithm to extract the features related to the palm from the picture. These features may include the shape, texture, color, and size of the palm. For example, the local binary pattern (LBP) can be used to extract the texture features of the palm, or an edge detection algorithm can be used to extract the shape features of the palm. Next, the server uses classification and discrimination algorithms to classify and discriminate the picture based on the extracted features. Commonly used classification and discrimination algorithms include support vector machines (SVM), decision trees, and neural networks, etc. According to the output of the classification and discrimination algorithm, the server can determine whether the picture is a palm image. If the classification result is "palm image", the corresponding information is output; otherwise, "non-palm image" is output.

[0119] In a possible implementation method, it further includes: if the quality of the feature image does not meet the preset conditions, the shooting device is called again to collect the feature image.

[0120] In this embodiment, after obtaining the feature image, it is also necessary to evaluate whether the feature image meets the quality requirements according to a series of preset quality coefficient indicators of the current feature image. These indicators may include but are not limited to: feature image size, angle, image contrast, image brightness, and clarity, etc. Among them, the feature image size is used to ensure that the size of the feature image is appropriate, neither too large nor too small, to meet the needs of subsequent processing and analysis; the angle is used to check whether the angle of the feature image meets the requirements. For example, in face recognition, it is necessary to ensure that the face is facing the camera directly, rather than tilted or in profile; the image contrast is used to reflect the light and dark degree of the image. If the contrast is too low, details may be difficult to distinguish; if the contrast is too high, overexposed or underexposed areas may appear; brightness is an important factor affecting the visual effect of the image. If the brightness is insufficient, the image may appear dim; if the brightness is too high, overexposure may occur; clarity is used to reflect the degree of detail of the image. If the image is blurred, features may not be accurately extracted.

[0121] For the acquired feature images, they can be classified into high-quality and low-quality categories based on the above quality coefficient indicators, or classified according to other preset quality levels.

[0122] For example, an image that meets all the preset quality coefficient indicators is defined as a high-quality feature image, indicating that the feature image has a moderate size, correct angle, appropriate contrast, appropriate brightness, and high clarity; an image that does not meet some of the quality coefficient indicators is defined as a low-quality image, which may have problems such as inappropriate size, tilted angle, low contrast, insufficient brightness, or blurriness.

[0123] If the quality classification result of the feature image belongs to the high-quality category, then continue to execute the subsequent steps; if it belongs to the low-quality category, then return to step 601 and re-call the imaging device to acquire the feature image.

[0124] In addition, in addition to the high-low quality classification, multiple quality levels can also be set according to actual needs, such as "very good", "good", "average", and "poor", etc. Each level has a corresponding quality coefficient indicator range, and the classification examples are as follows:

[0125] Quality level 1 (very good): Meets all the preset quality coefficient indicators and has a very high image quality. These images can be directly used for high-precision recognition tasks.

[0126] Quality level 2 (good): Meets most of the preset quality coefficient indicators, but some indicators are slightly lower than the best values. These images may need to be subjected to some simple enhancement processing and then used for general recognition tasks.

[0127] Quality level 3 (average): Only some of the preset quality coefficient indicators are met, and further preprocessing or re-acquisition may be required.

[0128] Quality level 4 (poor): Most of the preset quality coefficient indicators are not met, and re-acquisition is required.

[0129] In this embodiment, by verifying the quality of the feature image, the server can obtain a clear and effective feature image, so as to more accurately verify the identity of the target user based on the feature image in the subsequent steps.

[0130] In a possible implementation method, in step 601, calling the imaging device of the target terminal to acquire the feature image of the target object specifically includes:

[0131] a1. Call the imaging device to perform image acquisition to obtain the image to be measured;

[0132] a2. Perform live detection based on the image to be measured;

[0133] a3. The to-be-detected image that passes the liveness detection is determined as the feature image.

[0134] In this embodiment, the effectiveness of the feature image is ensured through the liveness detection step.

[0135] First, call the imaging device to collect an image. For example, if the current payment method is palm vein recognition-based palm brushing payment, then this step specifically involves calling the imaging device to collect the palm image of the target user, and this palm image is the to-be-detected image.

[0136] Then, perform liveness detection on the to-be-detected image. Liveness detection is to determine whether the to-be-detected image contains real human parts rather than photos, videos, or other non-living contents. For example, in palm brushing payment, it is necessary to extract the features required for liveness detection from the palm image, including texture analysis of the palm texture in the palm image and obtaining depth information in the palm image based on deep learning. It can be understood that a classifier can be trained in advance using a preset palm image as training data, and the trained classifier is used to classify the palm image into two categories: real living palm and simulated fake palm. Commonly used classifiers include support vector machines (SVM), Random Forest, etc.

[0137] Finally, the to-be-detected image that passes the liveness detection is determined as the feature image. This feature image can be the palm image in the above example or the image of other body parts, such as face image, pupil image, fingerprint image, etc. This feature image can be used for subsequent identity recognition or verification.

[0138] Furthermore, in this embodiment, the shooting information also includes the device information of the terminal device. This device information refers to the identity (identity document, ID) information of the terminal device, including information such as identification code, serial number, and number for device identification of this terminal device. For example, the international mobile equipment identity (IMEI) of a mobile phone.

[0139] After determining the device information, it further includes:

[0140] 602. Determine that the target terminal is the common terminal device of the target object according to the device information.

[0141] It can be understood that applications with payment functions usually need to ensure the security of users' accounts. A relatively common method is to verify the device information of the corresponding terminal device when the user uses the payment function, so as to determine whether the user's payment environment is secure. For example, when a user attempts to use the payment function, the application will obtain the device information of the currently used terminal device and compare the device information obtained this time with the device information obtained historically. If the two are consistent, it means that the currently used terminal device is the user's usual device, thereby reducing the risk of account theft to a certain extent.

[0142] In this embodiment, by comparing the device information in the feature image with the device information obtained historically, it can be determined whether the target terminal is the target object's usual terminal device, thereby reducing the probability of malicious appeals by the target object. It can be understood that since the device information is extracted from the feature image, and the feature image is the current image captured by calling the imaging device, verifying based on this device information can ensure that the device information has not been tampered with. In short, in this embodiment, before performing the subsequent steps, it is necessary to determine that the target terminal is the target object's usual terminal device according to the device information. If the target terminal is not the target object's usual terminal device, the method of verifying and comparing based on biometric information in conventional technologies can be used to determine the appeal result, and this application does not limit this.

[0143] 603. Calculate the second duration between the shooting time and the current time;

[0144] 604. Determine whether the second duration is less than the second preset duration.

[0145] In this embodiment, the current time refers to the current time of the system. To prevent the target object from uploading other local pictures for malicious appeals, the time difference between the shooting time and the current time can be calculated. If the time difference is small, the possibility that the target object has tampered with the feature image is reduced. It can be understood that the speed at which the feature image is uploaded to the server depends on the current network speed. Usually, the transmission of picture data can be completed within a few seconds. Considering the normal network transmission speed and the running speed of the terminal device, the second duration can be specifically set to 1 minute.

[0146] If the second duration is greater than the second preset duration, return to step 601 and re-call the imaging device to collect the feature image.

[0147] In this embodiment, if the second duration is long, it means that the shooting time of the feature image is relatively long from the current time, which also means that the feature image is not an image just captured, and the feature image may have been tampered with and it is difficult to ensure its authenticity. At this time, it is necessary to return to step 601 and call the imaging device of the terminal device to re-collect the feature image.

[0148] If the second duration is less than the second preset duration, continue to execute other steps.

[0149] 605. Obtain the payment time and payment location of the target order.

[0150] In this embodiment, step 605 is similar to step 302 in the corresponding Figure 3 embodiment above. For related descriptions, please refer to the above text and will not be elaborated here.

[0151] 606. Calculate a first duration and a first distance. The first duration indicates the time difference between the payment time and the shooting time, and the first distance indicates the distance difference between the payment location and the shooting location.

[0152] In this embodiment, step 606 is similar to step 303 in the corresponding Figure 3 embodiment above. For related descriptions, please refer to the above text and will not be elaborated here.

[0153] 607. Determine whether the first duration is less than the first preset duration and the first distance is greater than the preset distance.

[0154] If so, it means that the first duration is less than the first preset duration and the first distance is greater than the preset distance. At this time, execute step 608 to approve the appeal request.

[0155] It can be understood that the first preset duration is the duration threshold, and the first preset distance is the distance threshold. If the time deviation between the current time of the target user and the generation time of the target order is small, while the position deviation between the current position of the target user and the generation position of the target order is large, that is, for the target user, the generation time of this order was not long ago, yet the completion position of this order is far from the current position, and the target user cannot move a long distance in a short time, which means that the target order is not the consumption order of this target object, and there is a misidentification situation for this order. Therefore, approve this appeal request.

[0156] If not, it means that the first duration is not less than the first preset duration and / or the first distance is not greater than the preset distance. At this time, execute step 609 and step 610:

[0157] 609. Compare the feature image with the first pre-stored information to obtain a first similarity. The first pre-stored information corresponds to the biological information pre-stored for the target object;

[0158] 610. Compare the feature image with the second pre-stored information to obtain a second similarity. The second pre-stored information corresponds to the biological information for creating the target order.

[0159] It can be understood that if the first duration is greater than the first preset duration, it indicates that the time deviation between the current time of the target user and the generation time of the target order is relatively large, and the target user can move a long distance within a long time. Therefore, time and distance cannot be used as judgment factors. Similarly, if the first distance is less than the preset distance, it means that the position deviation between the current position of the user and the generation position of the target order is relatively small, and the target user can move a short distance within a short time. Similarly, time and distance cannot be used as judgment factors.

[0160] In this embodiment, the pre-stored information refers to the information pre-stored in the system or device, which can be the user's basic information, identity information, biological information, etc. Among them, the first pre-stored information corresponds to the biological information pre-stored for the target object. For example, when a user needs to activate the palm-sweeping payment function, the payment system will require the user to perform palmprint recognition through a specific palmprint acquisition device and store it. The first pre-stored information indicates the biological information that the target user has previously recognized and uploaded through the biological information acquisition device. The second pre-stored information corresponds to the biological information at the time of creating the target order. For example, when a user needs to use the palm-sweeping payment function, the payment system verifies whether the palmprint information uploaded by the user during payment matches the pre-stored palmprint information to confirm the user's identity and authorization; if the match is successful, the user can perform the payment operation. The second pre-stored information indicates the biological information uploaded when paying the target order.

[0161] Compare the feature image with the first pre-stored information to determine whether the feature image belongs to the target object; compare the feature image with the second pre-stored information to determine whether the biological information corresponding to the creation of the target order belongs to the target object.

[0162] The comparison method based on biological information can specifically adopt a feature matching algorithm, including feature extraction of the feature image and the first / second pre-stored information, and determining the similarity between features based on the feature matching algorithm. Commonly used feature matching algorithms include the nearest neighbor (NN) algorithm based on distance measurement, the similarity measurement algorithm based on random forest (Random Forest, RF), etc.

[0163] 611. If the first similarity is greater than the second preset value and the second similarity is less than the third preset value, then agree to the appeal request.

[0164] In this embodiment, it is determined whether two pieces of biological information match according to the magnitude of the similarity. Specifically, an identification threshold is set. If the similarity exceeds the threshold, it is considered that the two pieces of biological information match; otherwise, it is considered that they do not match. It can be understood that the greater the first similarity, the greater the possibility that the feature image belongs to the target object. Given a second preset value, if the first similarity exceeds the second preset value, it indicates that the feature image belongs to the target object. The smaller the second similarity, the smaller the possibility that the biological information corresponding to the creation of the target order belongs to the target object. Given a third preset value, if the second similarity is less than the third preset value, it indicates that the biological information corresponding to the creation of the target order does not belong to the target object.

[0165] In the case where it is determined that the feature image belongs to the target object and the biological information corresponding to the creation of the target order does not belong to the target object, it can be determined that there is a misidentification situation for the target order. Therefore, the appeal request is approved.

[0166] Certainly, if the first similarity is not greater than the second preset value and / or the second similarity is less than the third preset value, the appeal request can be rejected, or further verification operations (such as manual verification, etc.) can be performed. This application does not limit this.

[0167] In the above situation, in a possible implementation method of the embodiment of this application, step 608 specifically includes:

[0168] 6081. Obtain the first similarity;

[0169] 6082. If the first similarity is greater than the fourth preset value, approve the appeal request, where the fourth preset value is less than the second preset value.

[0170] In this embodiment, in order to ensure the accuracy of appeal compensation, the similarity is also calculated when the first duration is less than the first preset duration and the first distance is greater than the preset distance. That is, step 6081 corresponds to the above step 609. The difference between 6082 and step 611 is that when the duration and distance conditions are met, the preset value of the first similarity only needs to be greater than the fourth preset value.

[0171] In this embodiment, the fourth preset value is less than the second preset value, indicating that when the duration and distance conditions are met, the similarity requirement between the feature image and the pre-stored biological information of the target object is smaller. That is to say, when the duration and distance conditions are met, a certain tolerance or error range for the similarity between two images or pieces of biological information is allowed.

[0172] For example, under normal circumstances, in order to ensure the accuracy of biometric identification, the similarity between the feature image and the pre-stored biometric information of the target object needs to meet more than 95% to be recognized as the same. However, when the duration and distance conditions are met, the requirement for similarity can be appropriately relaxed, that is, the threshold can be set to 90% or lower.

[0173] In summary, when the duration and distance conditions are met, a greater difference between the two comparison objects can be tolerated. Then, in practical applications, an algorithm that is relatively less accurate but has higher computational efficiency can be selected, so that while ensuring the accuracy of identification, the appeal efficiency can also be improved.

[0174] In this embodiment, after the server obtains the appeal request sent by the target object, it calls the shooting device of the corresponding target terminal to collect the feature image of the target object. Based on the shooting information carried in the feature image, it is also necessary to confirm that the target terminal is the common terminal device of the target object. At the same time, it is necessary to ensure that the feature image meets the quality requirements and that the feature image is an image that has passed the live detection, so as to facilitate further verification based on the feature image. After obtaining the feature image, when the first duration is not less than the first preset duration and / or the first distance is not greater than the preset distance, the feature image is compared with the first pre-stored information and the second pre-stored information respectively to determine whether there is a misidentification situation for the target order. If so, the appeal request is approved. In addition, when the first duration is less than the first preset duration and the first distance is greater than the preset distance, an information comparison operation can also be performed. However, when the duration and distance conditions are met, the information comparison algorithm used can be relatively less accurate, so as to improve the comparison efficiency, so that while ensuring the accuracy of identification, the appeal efficiency can also be improved.

[0175] For the sake of easy understanding, the following will be combined with Figure 7 introduce an appeal handling method based on palm brushing payment. Figure 7 This is the structural diagram of the appeal handling method based on palm brushing payment provided by the embodiment of the present application, which is applied to an application software that provides payment services, and this payment software can provide the function of palm brushing payment.

[0176] This application software includes a payment back-end service 7100, a mobile phone end 7200, and a palm brushing module 7300.

[0177] The payment backend service 7100 refers to the server-side part of the application software, including the palm-sweeping payment recognition service 7101, payment service 7102, basic service 7103, message push service 7104, biometric information comparison service 7105, mis-sweeping compensation identification service 7106, refund service 7107, etc. Among them, the basic service 7103 is used to provide other payment functions or additional functions, such as password payment function, code-scanning payment function, chat function, etc., which will not be elaborated here; the palm-sweeping payment recognition service 7101 is used to provide the palmprint recognition function, receive palmprint information and compare and verify it; the payment service 7102 is used to match the corresponding payment account to perform the payment operation based on the verification result of the palmprint information; the message push service 7104 is used to send the order after the payment operation to the terminal device corresponding to the paying user in the form of message push; the biometric information comparison service 7105 is used to compare the palmprint information of the paying user with the pre-stored palmprint information; the mis-sweeping compensation identification service 7106 is used to identify whether there is mis-identification based on the time difference and distance difference between the order information and the appeal information, or the comparison result of the palmprint information, where the appeal information includes the shooting time and shooting location of the captured image after the paying user submits an appeal request; the refund service 7107 is used to perform a refund operation to the paying user when the identification result shows that there is mis-identification.

[0178] The mobile terminal 7200 is the terminal device corresponding to the paying user, including a camera 7201 and application software 7202, and the application software 7202 can provide payment functions. The application software 7202 includes an instant messaging (IM) module, and the IM module is used to send message notifications, and the above order information is displayed to the paying user in the form of message notifications; the application software 7202 also includes a palm-sweeping service module, and the palm-sweeping service module includes an order association function and a photographing function, where the order association function is used to provide order information based on palm-sweeping payment, and the photographing function is used to call the camera 7201 to take pictures.

[0179] The palm-sweeping module 7300 refers to a module with palmprint recognition and authentication functions, and the palm-sweeping module 7300 can be used to support the palm-sweeping payment recognition service in the payment backend service 7100. The palm-sweeping module 7300 includes a 3D camera 7301, a palm-sweeping module 7302, and a positioning module 7303. Among them, the 3D camera 7301 is a camera that can obtain three-dimensional space information, such as a shooting device equipped with an infrared sensor, which can capture the depth information of an object through sensors and algorithms, and can realize the function of detecting the quality of the captured image and the function of detecting a live body; the palm-sweeping module 7302 includes a palm-sweeping recognition function, and based on the 3D camera, it can realize the function of detecting the quality of the captured image and the function of detecting a live body; the positioning module 7303 can be used to provide a positioning function, and the positioning function can be realized based on wireless communication (WiFi) and GPS.

[0180] The appeal processing device in the present application will be described in detail below. Please refer to Figure 8 . Figure 8 FIG. is a schematic diagram of an embodiment of the appeal processing device 800 in an embodiment of the present application. The appeal processing device 800 includes:

[0181] An acquisition module 801, configured to, in response to an appeal request for a target order sent by a target object, call a photographing device of a target terminal to acquire a feature image of the target object. The target terminal corresponds to the target object. The feature image includes image data and photographing information. The photographing information includes the photographing time and the photographing location of the image data;

[0182] An obtaining module 802, configured to obtain the payment time and the payment location of the target order;

[0183] A calculation module 803, configured to calculate a first duration and a first distance. The first duration indicates the time difference between the payment time and the photographing time, and the first distance indicates the distance difference between the payment location and the photographing location;

[0184] A processing module 804, configured to, if the first duration is less than a first preset duration and the first distance is greater than a preset distance, approve the appeal request.

[0185] In this embodiment, after receiving the user's appeal request, the feature image of the user is acquired by calling the photographing device of the user terminal. The photographing time and the photographing location of the image are determined based on the photographing information carried in the image. The photographing information is compared with the order time and the order location when creating the payment order. If it is determined according to the time difference and the distance difference that the user cannot move this distance within this time range, it is determined that there is a misidentification situation, so the user's appeal request is approved. The appeal verification process of this method only needs to use time and location parameters, omitting the step of biometric information comparison, improving the appeal efficiency of misidentification, and ensuring the user experience.

[0186] In a possible implementation method, it further includes:

[0187] A quality verification module, configured to, if the quality of the feature image does not meet the preset conditions, call the photographing device again to acquire the feature image.

[0188] In this embodiment, after acquiring the feature image, it is also necessary to determine whether the current feature image meets the quality requirements. By verifying the quality of the feature image, the server can obtain a clear and effective feature image, so as to more accurately verify the identity of the target user based on the feature image in the subsequent steps.

[0189] In a possible implementation method, the acquisition module 801 is specifically configured to call a photographing device to acquire an image to be measured, perform a live detection based on the image to be measured, and determine the image to be measured that passes the live detection as a feature image.

[0190] In this embodiment, the validity of the feature image is ensured through the step of live detection.

[0191] In a possible implementation method, the feature image indicates the biological information of the target object, and the biological information includes at least one of palmprint features, fingerprint features, face features, and pupil features.

[0192] In a possible implementation method, the processing module 804 is further configured to, if the first duration is not less than the first preset duration and / or the first distance is not greater than the preset distance, compare the feature image with the first pre-stored information to obtain a first similarity, where the first pre-stored information corresponds to the pre-stored biological information of the target object; compare the feature image with the second pre-stored information to obtain a second similarity, where the second pre-stored information corresponds to the biological information for creating the target order; and if the first similarity is greater than the second preset value and the second similarity is less than the third preset value, then agree to the appeal request.

[0193] In this embodiment, if the first duration and / or the first distance do not meet the requirements, then time and distance cannot be used as judgment factors, so the biological information is used to determine whether there is a misidentification situation for the target order.

[0194] In a possible implementation method, the processing module 804 is specifically configured to, if the first duration is less than the first preset duration and the first distance is greater than the preset distance, obtain the first similarity; and if the first similarity is greater than the fourth preset value, then agree to the appeal request, where the fourth preset value is less than the second preset value.

[0195] In this embodiment, when the duration and distance conditions are met, a greater difference between the two comparison objects can be tolerated. Then, in practical applications, an algorithm that is relatively less accurate but has higher computational efficiency can be selected, so as to improve the appeal efficiency while ensuring the recognition accuracy.

[0196] In a possible implementation method, the shooting information further includes the device information of the target terminal; it further includes:

[0197] The device verification module is configured to determine that the target terminal is the common terminal device of the target object according to the device information.

[0198] In this embodiment, by determining that the target terminal is the common terminal device of the target object, the probability of malicious appeal by the target object is reduced.

[0199] In a possible implementation method, before calculating the first duration and the first distance, it further includes:

[0200] Calculating a second duration between the shooting time and the current time;

[0201] If the second duration is greater than a second preset duration, the shooting device is called again to collect a feature image.

[0202] In this embodiment, in order to prevent the target object from uploading other local pictures for malicious appeals, the time difference between the shooting time and the current time can be calculated. If the time difference is small, the possibility that the target object tampers with the feature image is reduced.

[0203] Figure 9 FIG. 13 is a schematic structural diagram of a server provided by an embodiment of the present application. The server 300 may vary greatly due to different configurations or performances, and may include one or more central processing units (CPUs) 322 (for example, one or more processors) and a memory 332, and one or more storage media 330 (for example, one or more mass storage devices) for storing application programs 342 or data 344. Among them, the memory 332 and the storage media 330 may be transient storage or persistent storage. The program stored in the storage media 330 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Further, the central processor 322 may be configured to communicate with the storage media 330 and execute a series of instruction operations in the storage media 330 on the server 300.

[0204] The server 300 may further include one or more power supplies 326, one or more wired or wireless network interfaces 350, one or more input / output interfaces 358, and / or one or more operating systems 341, such as Windows Server TM , Mac OS X TM , Unix TM , Linux TM , FreeBSD TM and so on.

[0205] In the above embodiment, the steps executed by the server may be based on the Figure 9 server structure shown.

[0206] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0207] It is understandable that in the specific embodiments of the present application, data related to order information, biological information, shooting information, etc. is involved. When the above embodiments of the present application are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0208] In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of an overall module or unit that includes the functions of that module or unit.

[0209] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in an electrical, mechanical, or other form.

[0210] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0211] In addition, the functional units in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0212] When an integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0213] The above, the above embodiments are only used to illustrate the technical solutions of this application, rather than to limit it; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of various embodiments of this application.

Claims

1. A complaint handling method, characterized in that, Including: In response to an appeal request for a target order sent by a target object, the photographing device of a target terminal is called to collect a feature image of the target object. The target terminal corresponds to the target object. The feature image includes image data and photographing information. The photographing information includes the photographing time and the photographing position of the image data; Obtain the payment time and payment position of the target order; Calculate a first duration and a first distance. The first duration indicates the time difference between the payment time and the photographing time, and the first distance indicates the distance difference between the payment position and the photographing position; If the first duration is less than a first preset duration and the first distance is greater than a preset distance, then agree to the appeal request.

2. The method according to claim 1, wherein Before calculating the first duration and the first distance, it further includes: If the quality of the feature image does not meet the preset conditions, then call the photographing device again to collect the feature image.

3. The method according to claim 1, characterized in that The calling the photographing device of the target terminal to collect the feature image of the target object includes: Call the photographing device to perform image collection to obtain a to-be-detected image; Perform a live detection based on the to-be-detected image; Determine the to-be-detected image that passes the live detection as the feature image.

4. The method according to claim 3, wherein After calculating the first duration and the first distance, it further includes: If the first duration is not less than the first preset duration and / or the first distance is not greater than the preset distance, then: Compare the feature image with first pre-stored information to obtain a first similarity. The first pre-stored information corresponds to the biological information pre-stored for the target object; Compare the feature image with second pre-stored information to obtain a second similarity. The second pre-stored information corresponds to the biological information for creating the target order; If the first similarity is greater than a second preset value and the second similarity is less than a third preset value, then agree to the appeal request.

5. The method according to claim 4, wherein The if the first duration is less than the first preset duration and the first distance is greater than the preset distance, then agree to the appeal request, includes: If the first duration is less than the first preset duration and the first distance is greater than the preset distance, then: Obtain the first similarity; If the first similarity is greater than a fourth preset value, then agree to the appeal request, where the fourth preset value is less than the second preset value.

6. The method according to claim 1, characterized in that, The photographing information further includes the device information of the target terminal; after calling the photographing device of the target terminal to collect the feature image of the target object, it further includes: Determine that the target terminal is the common terminal device of the target object according to the device information.

7. The method according to claim 1, wherein Before calculating the first duration and the first distance, it further includes: Calculate a second duration between the photographing time and the current time; If the second duration is greater than a second preset duration, then call the photographing device again to collect the feature image.

8. An appeal handling device, characterized in that, Including: An acquisition module, configured to, in response to an appeal request for a target order sent by a target object, call the photographing device of a target terminal to collect a feature image of the target object. The target terminal corresponds to the target object. The feature image includes image data and photographing information. The photographing information includes the photographing time and the photographing position of the image data; An acquisition module, configured to acquire the payment time and payment location of the target order; A calculation module, configured to calculate a first duration and a first distance, where the first duration indicates the time difference between the payment time and the shooting time, and the first distance indicates the distance difference between the payment location and the shooting location; A processing module, configured to approve the appeal request if the first duration is less than a first preset duration and the first distance is greater than a preset distance.

9. A computer device, characterized in that, Comprising: A memory, a transceiver, a processor, and a bus system; Wherein, the memory is used for storing programs; The processor is configured to execute the programs in the memory, including executing the appeal processing method according to any one of claims 1 to 7; The bus system is used for connecting the memory and the processor, so that the memory and the processor can communicate with each other.

10. A computer-readable storage medium, characterized in that, Comprising instructions, which when running on a computer, cause the computer to execute the appeal processing method according to any one of claims 1 to 7.

Images