WO2020248394A1 - 申请验证方法、装置、计算设备和计算机可读存储介质 - Google Patents

申请验证方法、装置、计算设备和计算机可读存储介质 Download PDF

Info

Publication number
WO2020248394A1
WO2020248394A1 PCT/CN2019/103621 CN2019103621W WO2020248394A1 WO 2020248394 A1 WO2020248394 A1 WO 2020248394A1 CN 2019103621 W CN2019103621 W CN 2019103621W WO 2020248394 A1 WO2020248394 A1 WO 2020248394A1
Authority
WO
WIPO (PCT)
Prior art keywords
application
information
target
data processing
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2019/103621
Other languages
English (en)
French (fr)
Inventor
秦勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2020248394A1 publication Critical patent/WO2020248394A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2455—Query execution
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q40/12—Accounting
    • G06Q40/125—Finance or payroll
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40—Document-oriented image-based pattern recognition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition

Definitions

  • This application relates to the field of image recognition technology, and in particular to an application verification method, device, computing device, and computer non-volatile readable storage medium based on Optical Character Recognition (OCR).
  • OCR Optical Character Recognition
  • the data processing device can usually process the data contained in the data processing application after receiving the data processing application input by the user, so as to realize the response of the data processing device to the data processing application input by the user.
  • the inventor of this application has discovered in practice that the user may have errors in the input data processing data contained in the application. If the data processing device directly processes the data in the data processing application, errors may occur. The answer to this results in lower accuracy of data processing.
  • the present application provides an application verification method, device, computing device, and computer non-volatile readable storage medium based on optical character recognition.
  • an application verification method based on optical character recognition including:
  • the application image is recognized by optical character recognition technology to obtain the application information contained in the application image, and the correctness of the application image is verified according to the application information;
  • the target data is obtained from the application information, and data processing is performed on the target data.
  • an application verification device based on optical character recognition including:
  • the first obtaining unit is configured to obtain target processing items, target item types, application images, and user personal information from the data processing application information when the data processing application information input by the user is detected;
  • a judging unit for judging whether the pre-stored processing items matching the target item type include the target processing item
  • the recognition unit is configured to, when the result of the judgment by the judgment unit is yes, recognize the application image by using optical character recognition technology to obtain the application information contained in the application image, and compare the application information according to the application information. The correctness of the application image is verified;
  • the second obtaining unit is configured to obtain target data from the application information and perform data processing on the target data when the correctness of the application image is verified.
  • a computing device including a memory and a processor, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the above-mentioned The steps of the optical character recognition application verification method.
  • a computer non-volatile readable storage medium storing computer readable instructions.
  • the computer readable instructions are executed by one or more processors, one or more processors execute the above The steps of the application verification method based on optical character recognition.
  • the above-mentioned application verification method, device, computing device, and computer non-volatile readable storage medium based on optical character recognition can be identified by optical character recognition technology after determining that the target item type in the data processing application information matches the target processing item
  • the application content in the application image can make the obtained application content more accurate, thereby making the verification of the correctness of the application image more accurate, thereby improving the accuracy of the verification of the correctness of the data processing application information.
  • the accuracy of data processing can be improved.
  • Fig. 1 is a schematic diagram showing a network scenario to which an application verification method based on optical character recognition is applicable according to an exemplary embodiment
  • Fig. 2 is a flow chart showing an application verification method based on optical character recognition according to an exemplary embodiment
  • Fig. 3 is a flow chart showing an application verification method based on optical character recognition according to another exemplary embodiment
  • Fig. 4 is a block diagram showing an application verification device based on optical character recognition according to an exemplary embodiment
  • Fig. 5 is a block diagram showing an application verification device based on optical character recognition according to another exemplary embodiment.
  • the implementation environment of this application can be portable mobile devices, such as smart phones, tablet computers, and desktop computers.
  • the images stored in the portable mobile device can be: images downloaded from the Internet; images received through a wireless connection or wired connection; images captured by its built-in camera.
  • Fig. 1 is a schematic diagram showing a device according to an exemplary embodiment.
  • the apparatus 100 may be the aforementioned portable mobile device.
  • the device 100 may include one or more of the following components: a processing component 102, a memory 104, a power supply component 106, a multimedia component 108, an audio component 110, a sensor component 114, and a communication component 116.
  • the processing component 102 generally controls the overall operations of the device 100, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
  • the processing component 102 may include one or more processors 118 to execute instructions to complete all or part of the steps of the following method.
  • the processing component 102 may include one or more modules to facilitate the interaction between the processing component 102 and other components.
  • the processing component 102 may include a multimedia module to facilitate the interaction between the multimedia component 108 and the processing component 102.
  • the memory 104 is configured to store various types of data to support operations in the device 100. Examples of these data include instructions for any application or method operating on the device 100.
  • the memory 104 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (Static Random Access Memory). Access Memory, SRAM for short), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read-Only Memory (EPROM) Red-Only Memory, PROM for short), Read-Only Memory (ROM for short), magnetic memory, flash memory, magnetic disk or optical disk.
  • SRAM static random access memory
  • EEPROM Electrically erasable programmable read-only memory
  • EPROM Erasable Programmable Read Only Memory
  • EPROM Programmable Read-Only Memory
  • PROM Read-Only Memory
  • ROM Read-Only Memory
  • the power supply component 106 provides power to various components of the device 100.
  • the power supply component 106 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 100.
  • the multimedia component 108 includes a screen that provides an output interface between the device 100 and the user.
  • the screen may include a liquid crystal display (Liquid Crystal Display, referred to as LCD) and touch panel. If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure related to the touch or slide operation.
  • the screen may also include an organic electroluminescence display (Organic Light Emitting Display, OLED for short).
  • the audio component 110 is configured to output and/or input audio signals.
  • the audio component 110 includes a microphone (Microphone, MIC for short).
  • the microphone is configured to receive an external audio signal.
  • the received audio signal can be further stored in the memory 104 or sent via the communication component 116.
  • the audio component 110 further includes a speaker for outputting audio signals.
  • the sensor component 114 includes one or more sensors for providing the device 100 with various aspects of state evaluation.
  • the sensor component 114 can detect the open/close state of the device 100 and the relative positioning of components.
  • the sensor component 114 can also detect the position change of the device 100 or a component of the device 100 and the temperature change of the device 100.
  • the sensor component 114 may also include a magnetic sensor, a pressure sensor or a temperature sensor.
  • the communication component 116 is configured to facilitate wired or wireless communication between the apparatus 100 and other devices.
  • the device 100 can access a wireless network based on a communication standard, such as WiFi (Wireless-Fidelity, wireless fidelity).
  • the communication component 116 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 116 further includes a near field communication (Near Field Communication, NFC for short) module for facilitating short-range communication.
  • NFC Near Field Communication
  • the NFC module can be based on radio frequency identification (Radio Frequency Identification, referred to as RFID) technology, infrared data association (Infrared Data Association, referred to as IrDA) technology, ultra-wideband (Ultra Wideband, referred to as UWB) technology, Bluetooth technology and other technologies.
  • RFID Radio Frequency Identification
  • IrDA Infrared Data Association
  • UWB ultra-wideband
  • Bluetooth Bluetooth technology
  • the apparatus 100 may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuits). Specific Integrated Circuit, referred to as ASIC), digital signal processor, digital signal processing equipment, programmable logic device, field programmable gate array, controller, microcontroller, microprocessor or other electronic components to implement the following method.
  • ASIC Application Specific Integrated Circuit
  • digital signal processor digital signal processing equipment
  • programmable logic device programmable logic device
  • field programmable gate array programmable gate array
  • controller microcontroller
  • microprocessor microprocessor or other electronic components to implement the following method.
  • Fig. 2 is a flow chart showing an application verification method based on optical character recognition according to an exemplary embodiment. As shown in Figure 2, this method includes the following steps.
  • Step 201 When the data processing application information input by the user is detected, obtain the target processing item, the target item type, the application image, and the user's personal information from the data processing application information.
  • the data processing application information can be reimbursement application information
  • the target processing item can be the reimbursement amount
  • the target item type can be reimbursement items
  • the application image can be an invoice image
  • the user's personal information can include account information
  • reimbursement The application information may include the amount of reimbursement applied for, reimbursement items, invoice images, account information, etc.
  • the invoice image can be the image of the invoice that needs to be provided for this reimbursement that the user has taken or scanned.
  • the account information can be the user's receiving account. After the reimbursement application is approved, the reimbursement money can be issued to the user's account based on the account information.
  • Step 202 Determine whether the pre-stored processing items that match the target item type include the target processing item, if yes, perform step 203 to step 204; if not, end this process.
  • the reimbursement application can be judged in advance Whether it complies with the enterprise's reimbursement regulations, if the reimbursement items do not match the reimbursement department, the reimbursement application can be rejected to avoid causing economic losses to the enterprise.
  • Step 203 Recognize the application image through optical character recognition technology to obtain the application information contained in the application image, and verify the correctness of the application image according to the application information.
  • verifying the correctness of the application image according to the application information can be to verify the authenticity of the invoice image according to the invoice information.
  • the optical character recognition technology can first identify the text information contained in the invoice image, and recognize The output text information is integrated to obtain the invoice information contained in the invoice image.
  • the invoice information can include information such as invoice code, invoice verification code, and invoice password, and the authenticity of the invoice can be verified by verifying the invoice code, invoice verification code, and invoice password.
  • the application image is recognized by optical character recognition technology, and the way to obtain the application information contained in the application image can be: each pixel in the application image can be set through image binarization to The application image is converted into a black and white application image (that is, the color of any pixel is white or black) through the binarization process, and then several connected areas in the black and white application image can be determined by the color of each pixel in the black and white application image. Recognize several connected areas through text detection, combine several connected areas to obtain several characters and/or symbols, and sort the detected characters according to semantics, so as to obtain applications corresponding to the recognized characters information.
  • the application image is recognized by optical character recognition technology to obtain the application information contained in the application image, and the correctness of the application image can be verified according to the application information.
  • the method may include the following steps: Character recognition technology recognizes the application image to obtain the text information contained in the application image; analyzes the text information through the deep learning algorithm to generate the application information contained in the application image, and the application information contains at least the application items and target data; through the inspection interface Send the application information to the inspection platform so that the inspection platform can verify the correctness of the application image based on the application information and feed back the inspection result; when the inspection result sent by the inspection platform is received, it will judge whether the correctness of the application image is passed according to the inspection result verification.
  • the implementation of this implementation mode can first segment each participle contained in the text information through the semantic analysis technology in the deep learning algorithm to obtain several participles contained in the text information, and then can identify the meaning of each participle , It can also identify several clauses contained in the text information according to the recognized symbols, that is, each clause can contain several word segmentation, in addition, it can also pass TF-IDF (Term Frequency-Inverse Document Frequency) Calculate the weight value of each participle in each clause to determine the weight value of each participle in each clause.
  • TF-IDF Term Frequency-Inverse Document Frequency
  • each participle and the meaning of the participle of the participle the meaning of each clause can be determined , And then determine the application information contained in the application image according to the meaning of each clause, which improves the credibility of the application image correctness verification.
  • Step 204 When the correctness of the application image is verified, the target data is obtained from the application information, and data processing is performed on the target data.
  • the target data may be the invoice amount.
  • the invoice amount in the invoice information may be determined as the amount of reimbursement that needs to be issued to the user.
  • the reimbursement application information input by the user may also include the user's account information, and reimbursement funds may be issued to the user's account based on the account information.
  • the target data is obtained from the application information
  • the method of data processing on the target data may include the following steps: when the correctness of the application image is verified , To detect whether the application items match the target processing items in the data processing application information and whether the target data matches the application data in the reimbursement application information; if the application items match the target processing items and the target data matches the application data, the application data is determined It is the target data and performs data processing on the target data.
  • the implementation of this implementation mode can compare the identified application information with the data processing application information provided by the user. Only when the application information is consistent with the data processing application information, the target data can be processed, ensuring The accuracy of data processing.
  • the accuracy of verifying the correctness of the data processing application information is improved, so that the accuracy of data processing can be improved.
  • the implementation of the method described in Figure 2 improves the credibility of the application for image correctness verification.
  • the implementation of the method described in Figure 2 ensures the accuracy of data processing.
  • Fig. 3 is a flowchart showing an application verification method based on optical character recognition according to another exemplary embodiment. As shown in Figure 3, this method includes the following steps.
  • Step 301 When the data processing application input by the user is detected, the application interface is output and the application prompt information is output in the application interface.
  • the application prompt information is used to prompt the user to input the data processing application information through the application interface and to prompt the user to correctly apply for the image Characteristic points.
  • the application interface may be a reimbursement application interface
  • the application prompt information may be reimbursement prompt information.
  • the reimbursement application interface may be displayed through the display output of the reimbursement device based on optical character recognition, and the reimbursement prompt information may be displayed in text. The output is displayed on the application interface.
  • the reimbursement prompt information can be output by voice through the speaker of the reimbursement device based on risk management and control.
  • the reimbursement prompt information can prompt the user to fill in the specifications of each item in the reimbursement application information, and can also prompt the user the correct feature points of the real invoice and the wrong feature points of the false invoice, so that the user can self-check before uploading the invoice image. This prevents users from uploading wrong invoices, thereby improving the pass rate of reimbursement applications.
  • Step 302 When it is detected that the completion instruction is triggered, obtain the data processing application information input by the user from the application interface.
  • implementing the above steps 301 to 302 can prompt the user to fill in the data processing application information, so that the data processing application information filled in by the user is more accurate, and the intelligence of the data processing process is further improved.
  • Step 303 When the data processing application information input by the user is detected, obtain the user's personal information from the data processing application information.
  • the user’s personal information may include the user’s name, age, position, department, serial number and other information. According to the user’s personal information, it can be determined whether the user is an employee of the company. If the user is not an employee of the company, The reimbursement application information entered by the user will not be accepted; if the user is an employee of the company, the reimbursement department corresponding to the user can be determined.
  • Step 304 Obtain a target credit value matching the personal information from a pre-built credit system.
  • the pre-built credit system can store information such as the credit value and behavior information of each employee of the enterprise, and every behavior performed by the employees of the enterprise can be stored in the credit system.
  • the credit system can be The behavior information is calculated to obtain the credit value of each user.
  • an employee's behavior involves credit-related operations, it can prejudge whether the user's credit value meets the requirements for performing the current operation. If it does not meet the requirements, the user can be prohibited from performing the operation .
  • Step 305 When it is detected that the target credit value is greater than the preset credit value, obtain the target processing item, the target item type, and the application image from the data processing application information.
  • step 306 it is determined whether the pre-stored processing items matching the target item type include the target processing item, if yes, execute step 308 to step 309; if not, execute step 307.
  • step 307 the data processing application information is rejected, and the rejection prompt information is output.
  • the rejection prompt information is used to prompt the user to change the correct application image or cancel the data processing application.
  • the implementation of the above step 307 can prompt the user that there is a problem with the application image, and allow the user to perform operations of replacing the application image or canceling the data processing application, so that the user can correct the data processing application information in time.
  • the following steps may be performed after step 307: obtain behavioral information matching personal information from the credit system; mark the application image as an incorrect application image, and add the incorrect application image to the behavior information Obtain current behavior information; calculate the user's current credit value based on the current behavior information, and store the current credit value in association with the user's personal information in the credit system.
  • the wrong application image provided by the user this time can be stored in the user’s behavior information in the credit system, and then the user’s credit value can be recalculated based on the wrong application image, which improves the credit system.
  • the timeliness of the user's credit value can be performed after step 307: obtain behavioral information matching personal information from the credit system; mark the application image as an incorrect application image, and add the incorrect application image to the behavior information Obtain current behavior information; calculate the user's current credit value based on the current behavior information, and store the current credit value in association with the user's personal information in the credit system.
  • step 308 the application image is recognized by optical character recognition technology to obtain the application information contained in the application image, and the correctness of the application image is verified according to the application information.
  • step 309 it is judged whether the correctness verification of the applied image is passed, if yes, go to step 310; if not, go to step 311 to step 312.
  • Step 310 Obtain target data from the application information, and perform data processing on the target data.
  • Step 311 Output prompt information for adding a display item, which is used to prompt the user to apply for adding the target processing item to the processing item matching the target item type.
  • Step 312 When it is detected that the application instruction is triggered, an item addition application is generated according to the target processing item and the target item type, and the item addition application is stored, so that the maintenance personnel can process the item addition application.
  • the above steps 311 to 312 are implemented. Since the processing items corresponding to the target item type may not be comprehensive enough during initialization, the user can apply for adding processing items to the target item type, thereby improving Accuracy of identification of processing item types.
  • the accuracy of verifying the correctness of the data processing application information is improved, so that the accuracy of data processing can be improved.
  • implementing the method described in Figure 3 improves the intelligence of the data processing flow.
  • implementing the method described in Figure 3 improves the efficiency of data processing.
  • the data processing application information can be corrected in time.
  • implementing the method described in Figure 3 improves the timeliness of the credit value of each user in the credit system.
  • the implementation of the method described in Figure 3 improves the accuracy of processing item type recognition.
  • the present application also provides an application verification device based on optical character recognition.
  • Fig. 4 is a block diagram showing an application verification device based on optical character recognition according to an exemplary embodiment.
  • the device includes: a first obtaining unit 401, which is used to obtain target processing items, target item types, application images, and user information from the data processing application information when the data processing application information input by the user is detected. Personal information.
  • the determining unit 402 is configured to determine whether the pre-stored processing items matching the target item type acquired by the first acquiring unit 401 include the target processing item.
  • the recognition unit 403 is configured to recognize the application image through optical character recognition technology when the judgment result of the judgment unit 402 is yes, obtain application information contained in the application image, and verify the correctness of the application image according to the application information.
  • the recognition unit 403 recognizes the application image through optical character recognition technology, obtains the application information contained in the application image, and verifies the correctness of the application image according to the application information.
  • the specific method may be: Recognize the application image through optical character recognition technology to obtain the text information contained in the application image;
  • the text information is analyzed through deep learning algorithms to generate the application information contained in the application image.
  • the application information contains at least the application items and target data; the application information is sent to the inspection platform through the inspection interface, so that the inspection platform can compare the application image according to the application information.
  • the correctness is checked and the result of the check is fed back; when the check result sent by the check platform is received, it is judged whether the correctness of the applied image has passed the verification according to the check result.
  • the implementation of this implementation mode can first segment each participle contained in the text information through the semantic analysis technology in the deep learning algorithm to obtain several participles contained in the text information, and then can identify the meaning of each participle .
  • the application information improves the credibility of the correctness verification of the application image.
  • the second obtaining unit 404 is configured to obtain the target data from the application information and perform data processing on the target data when the identification unit 403 passes the verification of the correctness of the application image.
  • the second acquiring unit 404 acquires target data from the application information, and performs data processing on the target data in a specific manner: when the correctness of the application image is verified, it detects whether the application items are consistent with The target processing items in the data processing application information match and whether the target data matches the application data in the reimbursement application information; if the application items match the target processing items and the target data matches the application data, the application data is determined as the target data, and Data processing of the target data.
  • the implementation of this implementation mode can compare the identified application information with the data processing application information provided by the user. Only when the application information is consistent with the data processing application information, the target data can be processed, ensuring The accuracy of data processing.
  • the accuracy of verifying the correctness of the data processing application information is improved, so that the accuracy of data processing can be improved.
  • the credibility of the application for image correctness verification is improved.
  • the accuracy of data processing is guaranteed.
  • Fig. 5 is a block diagram showing an application verification device based on optical character recognition according to another exemplary embodiment.
  • the application verification device based on optical character recognition shown in FIG. 5 is optimized by the application verification device based on optical character recognition shown in FIG. 4.
  • the application verification device based on optical character recognition shown in FIG. 4 is optimized by the application verification device based on optical character recognition shown in FIG. 4.
  • the 5 may further include: a first output unit 405, configured to detect when the first acquisition unit 401 When the data processing application information input by the user is reached, before the target processing item, target item type, application image, and user personal information are obtained from the data processing application, and when the data processing application input by the user is detected, the application interface is output and displayed, The application prompt information is output in the application interface, and the application prompt information is used to prompt the user to input data processing application information through the application interface and to prompt the user to correctly apply for the feature points of the image.
  • the third acquiring unit 406 is configured to acquire the data processing application information input by the user from the application interface when it is detected that the completion instruction is triggered.
  • the third acquiring unit 406 is triggered to start.
  • the user may be prompted to fill in the data processing application information, so that the data processing application information filled in by the user is more accurate, and the intelligence of the data processing process is further improved.
  • the first obtaining unit 401 of the optical character recognition-based application verification apparatus shown in FIG. 5 may include: a first obtaining subunit 4011 for processing application information when the data input by the user is detected When the user's personal information is obtained from the data processing application information; the second obtaining subunit 4012 is used to obtain the target credit value matching the personal information obtained by the first obtaining subunit 4011 from the pre-built credit system; third The obtaining subunit 4013 is configured to obtain the target processing item, the target item type, and the application image from the data processing application information when it is detected that the target credit value obtained by the second obtaining subunit 4012 is greater than the preset credit value.
  • the implementation of this embodiment can perform automatic data processing on users whose target credit value is greater than the preset credit value, which improves the efficiency of data processing.
  • the reimbursement device based on optical character recognition shown in FIG. 5 may further include:
  • the second output unit 407 is configured to reject the data processing application information when the judgment result of the judgment unit 402 is no, and output the rejection prompt information, which is used to prompt the user to change the correct application image or cancel the data processing application.
  • the implementation of this implementation manner can prompt the user that there is a problem with the application image, and allow the user to perform the operation of replacing the application image or canceling the data processing application, so that the user can correct the data processing application information in a timely manner.
  • the second output unit 407 can also be used to: obtain behavior information matching the personal information from the credit system; mark the application image as an incorrect application image, and add the incorrect application image to the behavior information
  • the current behavior information is obtained from the current behavior information; the current credit value of the user is calculated according to the current behavior information, and the current credit value and the user's personal information are associated and stored in the credit system.
  • the wrong application image provided by the user this time can be stored in the user’s behavior information in the credit system, and then the user’s credit value can be recalculated based on the wrong application image, which improves the credit value of the user.
  • the timeliness of the user's credit value can be used to: obtain behavior information matching the personal information from the credit system; mark the application image as an incorrect application image, and add the incorrect application image to the behavior information
  • the current behavior information is obtained from the current behavior information; the current credit value of the user is calculated according to the current behavior information, and the current credit value and the user's personal information are associated and stored in the credit
  • the application verification apparatus based on optical character recognition shown in FIG. 5 may further include:
  • the third output unit 408 is used for outputting the display item addition prompt information when the identification unit 403 fails to verify the correctness of the application image, and the item addition prompt information is used to prompt the user to propose adding the target processing item to match the target item type
  • the generating unit 409 is configured to generate a matter addition application according to the target processing matter and the target matter type acquired by the first acquiring unit 401 when it is detected that the application instruction is triggered, and store the matter addition application, In order to enable the maintenance personnel to process the item addition application.
  • the implementation of this embodiment because the processing items corresponding to the target item type may not be comprehensive enough at the time of initialization, the user can apply for adding processing items to the target item type, thereby improving the accuracy of processing item type identification .
  • the accuracy of verifying the correctness of the data processing application information is improved, so that the accuracy of data processing can be improved.
  • the intelligence of the data processing flow is improved.
  • the efficiency of data processing is improved.
  • the data processing application information can be corrected in time.
  • the timeliness of the credit value of each user in the credit system is improved.
  • the accuracy of processing item type recognition is improved.
  • a computing device which executes all or part of the steps of any one of the above-mentioned optical character recognition-based application verification methods.
  • the computing equipment includes:
  • At least one processor At least one processor
  • a memory communicatively connected with the at least one processor; wherein,
  • the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute as shown in any one of the above exemplary embodiments.
  • the application verification method based on optical character recognition.
  • the computing device may be the apparatus 100 shown in FIG. 1.
  • a computer non-volatile readable storage medium storing computer readable instructions.
  • the computer readable instructions are executed by one or more processors, the one or more processors execute The steps in the above embodiment of the application verification method based on optical character recognition.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Human Resources & Organizations (AREA)
  • Accounting & Taxation (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Technology Law (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • Multimedia (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Character Discrimination (AREA)
  • Character Input (AREA)

Abstract

本申请揭示了一种申请验证方法、装置、计算设备和计算机非易失性可读存储介质。该方法包括当检测到用户输入的数据处理申请信息时，从数据处理申请信息中获取目标处理事项、目标事项类型、申请图像和用户的个人信息；判断预先存储的与目标事项类型匹配的处理事项中是否包含目标处理事项；如果包含，通过光学字符识别技术对申请图像进行识别，得到申请图像包含的申请信息，并根据申请信息对申请图像的正确性进行验证；当申请图像的正确性验证通过，从申请信息中获取目标数据，并对目标数据进行数据处理。此方法下，基于图像识别的图像提取中的OCR识别技术，可以提高对数据处理申请信息的正确性验证的准确率。综上，可以提升数据处理的准确率。

Description

申请验证方法、装置、计算设备和计算机可读存储介质 技术领域
本申请基于并要求2019年6月13日申请的、申请号为CN 201910510434.9、名称为“基于光学字符识别的申请验证方法、装置及电子设备”的中国专利申请的优先权，其全部内容在此并入作为参考。
本申请涉及图像识别技术领域，特别涉及一种基于光学字符识别（Optical Character Recognition，OCR）的申请验证方法、装置、计算设备和计算机非易失性可读存储介质。
 背景技术
目前，数据处理装置通常可以在接收到用户输入的数据处理申请之后，对数据处理申请中包含的数据进行处理，从而实现数据处理装置对用户输入的数据处理申请的响应。然而，本申请的发明人在实践中发现，用户在输入的数据处理申请中包含的数据时可能出现出入错误的情况，如果数据处理装置直接对数据处理申请中的数据进行处理，则可能得到错误的答案，从而导致数据处理的准确率较低。
 技术问题
为了解决相关技术中存在的数据处理的准确率较低的技术问题，本申请提供了一种基于光学字符识别的申请验证方法、装置、计算设备和计算机非易失性可读存储介质。
技术解决方案
第一方面，提供了一种基于光学字符识别的申请验证方法，包括：
当检测到用户输入的数据处理申请信息时，从所述数据处理申请信息中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息；
判断预先存储的与所述目标事项类型匹配的处理事项中是否包含所述目标处理事项；
如果包含，通过光学字符识别技术对所述申请图像进行识别，得到所述申请图像中包含的申请信息，并根据所述申请信息对所述申请图像的正确性进行验证；
当所述申请图像的正确性验证通过时，从所述申请信息中获取目标数据，并对所述目标数据进行数据处理。
第二方面，提供了一种基于光学字符识别的申请验证装置，包括：
第一获取单元，用于当检测到用户输入的数据处理申请信息时，从所述数据处理申请信息中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息；
判断单元，用于判断预先存储的与所述目标事项类型匹配的处理事项中是否包含所述目标处理事项；
识别单元，用于在所述判断单元判断的结果为是时，通过光学字符识别技术对所述申请图像进行识别，得到所述申请图像中包含的申请信息，并根据所述申请信息对所述申请图像的正确性进行验证；
第二获取单元，用于当所述申请图像的正确性验证通过时，从所述申请信息中获取目标数据，并对所述目标数据进行数据处理。
第三方面，提供了一种计算设备，包括存储器和处理器，所述存储器中存储有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述处理器执行上述基于光学字符识别的申请验证方法的步骤。
第四方面，提供了一种存储有计算机可读指令的计算机非易失性可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行上述基于光学字符识别的申请验证方法的步骤。
 有益效果
上述基于光学字符识别的申请验证方法、装置、计算设备和计算机非易失性可读存储介质，可以在确定数据处理申请信息中的目标事项类型与目标处理事项匹配之后，通过光学字符识别技术识别申请图像中的申请内容，以使得到的申请内容更加准确，进而使得对申请图像的正确性的验证也更加准确，从而提高了对数据处理申请信息的正确性验证的准确率。综上，可以提升数据处理的准确率。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性的，并不能限制本申请。
 附图说明
图1是根据一示例性实施例示出的一种基于光学字符识别的申请验证方法适用的网络场景的示意图；
图2是根据一示例性实施例示出的一种基于光学字符识别的申请验证方法的流程图；
图3是根据另一示例性实施例示出的一种基于光学字符识别的申请验证方法的流程图；
图4是根据一示例性实施例示出的一种基于光学字符识别的申请验证装置的框图；
图5是根据另一示例性实施例示出的一种基于光学字符识别的申请验证装置的框图。
 本发明的实施方式
这里将详细地对示例性实施例执行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。
本申请的实施环境可以是便携移动设备，例如智能手机、平板电脑、台式电脑。便携移动设备中所存储的图像可以是：从互联网下载的图像；通过无线连接或有线连接接收的图像；通过自身所内置摄像头拍摄得到的图像。
图1是根据一示例性实施例示出的一种装置的示意图。装置100可以是上述便携移动设备。如图1所示，装置100可以包括以下一个或多个组件：处理组件102，存储器104，电源组件106，多媒体组件108，音频组件110，传感器组件114以及通信组件116。
处理组件102通常控制装置100的整体操作，诸如与显示，电话呼叫，数据通信，相机操作以及记录操作相关联的操作等。处理组件102可以包括一个或多个处理器118来执行指令，以完成下述的方法的全部或部分步骤。此外，处理组件102可以包括一个或多个模块，用于便于处理组件102和其他组件之间的交互。例如，处理组件102可以包括多媒体模块，用于以方便多媒体组件108和处理组件102之间的交互。存储器104被配置为存储各种类型的数据以支持在装置100的操作。这些数据的示例包括用于在装置100上操作的任何应用程序或方法的指令。存储器104可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器（Static Random Access Memory，简称SRAM），电可擦除可编程只读存储器（Electrically Erasable Programmable Read-Only Memory，简称EEPROM），可擦除可编程只读存储器（Erasable Programmable Read Only Memory，简称EPROM），可编程只读存储器（Programmable Red-Only Memory，简称PROM），只读存储器（Read-Only Memory，简称ROM），磁存储器，快闪存储器，磁盘或光盘。存储器104中还存储有一个或多个模块，用于该一个或多个模块被配置成由该一个或多个处理器118执行，以完成如下所示方法中的全部或者部分步骤。电源组件106为装置100的各种组件提供电力。电源组件106可以包括电源管理系统，一个或多个电源，及其他与为装置100生成、管理和分配电力相关联的组件。多媒体组件108包括在所述装置100和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器（Liquid Crystal Display，简称LCD）和触摸面板。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。屏幕还可以包括有机电致发光显示器（Organic Light Emitting Display，简称OLED）。音频组件110被配置为输出和/或输入音频信号。例如，音频组件110包括一个麦克风（Microphone，简称MIC），当装置100处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器104或经由通信组件116发送。在一些实施例中，音频组件110还包括一个扬声器，用于输出音频信号。传感器组件114包括一个或多个传感器，用于为装置100提供各个方面的状态评估。例如，传感器组件114可以检测到装置100的打开/关闭状态，组件的相对定位，传感器组件114还可以检测装置100或装置100一个组件的位置改变以及装置100的温度变化。在一些实施例中，该传感器组件114还可以包括磁传感器，压力传感器或温度传感器。通信组件116被配置为便于装置100和其他设备之间有线或无线方式的通信。装置100可以接入基于通信标准的无线网络，如WiFi（Wireless-Fidelity，无线保真）。在一个示例性实施例中，通信组件116经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件116还包括近场通信（Near Field Communication，简称NFC）模块，用于以促进短程通信。例如，在NFC模块可基于射频识别（Radio Frequency Identification，简称RFID）技术，红外数据协会（Infrared Data Association，简称IrDA）技术，超宽带（Ultra Wideband，简称UWB）技术，蓝牙技术和其他技术来实现。
在示例性实施例中，装置100可以被一个或多个应用专用集成电路（Application Specific Integrated Circuit，简称ASIC）、数字信号处理器、数字信号处理设备、可编程逻辑器件、现场可编程门阵列、控制器、微控制器、微处理器或其他电子元件实现，用于执行下述方法。
图2是根据一示例性实施例示出的一种基于光学字符识别的申请验证方法的流程图。如图2所示，此方法包括以下步骤。
步骤201，当检测到用户输入的数据处理申请信息时，从数据处理申请信息中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息。
本申请实施例中，数据处理申请信息可以为报销申请信息，目标处理事项可以为申请报销金额，目标事项类型可以为报销事项，申请图像可以为发票图像，用户的个人信息可以包含账户信息，报销申请信息可以包含申请报销金额、报销事项、发票图像以及账户信息等，发票图像可以为用户拍摄或扫描得到的本次报销需要提供的发票的图像。账户信息可以为用户的收款账户，当本次报销申请通过后，可以根据该账户信息向用户的账户发放报销金。
步骤202，判断预先存储的与目标事项类型匹配的处理事项中是否包含目标处理事项，如果是，执行步骤203~步骤204；如果否，结束本流程。
本申请实施例中，由于企业中不同的部门对应的部门职责不同，因此不同的部门可能会在不同的事项上花钱，通过判断报销事项是否与报销部门匹配，可以预先判断本次的报销申请是否符合企业的报销规定，如果报销事项与报销部门不匹配，可以将该报销申请驳回，从而避免给企业造成经济损失。
步骤203，通过光学字符识别技术对申请图像进行识别，得到申请图像中包含的申请信息，并根据申请信息对申请图像的正确性进行验证。
本申请实施例中，根据申请信息对申请图像的正确性进行验证可以为根据发票信息对发票图像的真实性进行验证，光学字符识别技术可以先识别出发票图像中包含的文字信息，并将识别出的文字信息进行整合，得到发票图像中包含的发票信息。发票信息可以包含发票代码、发票校验码、发票密码等信息，进而可以通过对发票代码、发票校验码以及发票密码等信息的验证来实现对发票真实性的验证。
本申请实施例中，通过光学字符识别技术对申请图像进行识别，得到申请图像中包含的申请信息的方式可以为：可以通过图像二值化将申请图像中的每个像素点都进行设置，以使申请图像经过二值化过程成为黑白申请图像（即任意一个像素的颜色为白色或黑色），进而可以通过黑白申请图像中的各个像素的颜色确定黑白申请图像中的若干个连通区域，之后可以通过文本检测对若干个连通区域进行识别，将若干个连通区域进行组合，以得到若干个文字和/或符号，还可以对检测出的文字按照语义进行排序，从而得到识别出的文字对应的申请信息。
作为一种可选的实施方式，通过光学字符识别技术对申请图像进行识别，得到申请图像中包含的申请信息，并根据申请信息对申请图像的正确性进行验证的方式可以包含以下步骤：通过光学字符识别技术对申请图像进行识别，得到申请图像中包含的文字信息；通过深度学习算法对文字信息进行分析，生成申请图像中包含的申请信息，申请信息至少包含申请事项和目标数据；通过查验接口向查验平台发送申请信息，以使查验平台根据申请信息对申请图像的正确性进行查验，并反馈查验结果；当接收到查验平台发送的查验结果时，根据查验结果判断申请图像的正确性是否通过验证。
其中，实施这种实施方式，可以通过深度学习算法中的语义分析技术先对文字信息中包含的各个分词进行分割，以得到文字信息中包含的若干个分词，进而可以识别得到各个分词的分词含义，还可以根据识别到的符号识别出文字信息中包含的若干个子句，即每个子句中可以包含若干个分词，此外，还可以通过TF-IDF（Term Frequency–Inverse Document Frequency）对各个子句中的每个分词的权重值进行计算，以确定各个子句中每个分词的权重值，之后，根据各个分词以及该分词的分词含义，可以确定各个子句的含义，进而根据各个子句的含义确定出申请图像中包含的申请信息，提高了申请图像正确性验证的可信度。
步骤204，当申请图像的正确性验证通过时，从申请信息中获取目标数据，并对目标数据进行数据处理。
本申请实施例中，目标数据可以为发票金额，在发票图像的真实性验证通过之后，可以将发票信息中的发票金额确定为需要向用户发放的报销款项的金额。此外，用户输入的报销申请信息中也可以包含用户的账户信息，可以根据该账户信息向用户的账户发放报销金。
作为一种可选的实施方式，当申请图像的正确性验证通过时，从申请信息中获取目标数据，并对目标数据进行数据处理的方式可以包含以下步骤：当申请图像的正确性验证通过时，检测申请事项是否与数据处理申请信息中的目标处理事项匹配以及目标数据是否与报销申请信息中的申请数据匹配；如果申请事项与目标处理事项匹配以及目标数据与申请数据匹配，将申请数据确定为目标数据，并对目标数据进行数据处理。其中，实施这种实施方式，可以根据识别出的申请信息与用户提供的数据处理申请信息进行对比，只有在申请信息与数据处理申请信息一致的情况下才可以对目标数据进行数据处理，保证了数据处理的准确性。
在图2所描述的方法中，提高了对数据处理申请信息的正确性验证的准确率，从而可以提升数据处理的准确率。此外，实施图2所描述的方法，提高了申请图像正确性验证的可信度。此外，实施图2所描述的方法，保证了数据处理的准确性。
图3是根据另一示例性实施例示出的一种基于光学字符识别的申请验证方法的流程图。如图3所示，此方法包括以下步骤。
步骤301，当检测到用户输入的数据处理申请时，输出显示申请界面，并在申请界面中输出申请提示信息，申请提示信息用于提示用户通过申请界面输入数据处理申请信息以及提示用户正确申请图像的特征点。
本申请实施例中，申请界面可以为报销申请界面，申请提示信息可以为报销提示信息，报销申请界面可以通过基于光学字符识别的报销装置的显示器输出显示，报销提示信息可以通过文字的方式在报销申请界面上显示输出，此外，还可以通过基于风险管控的报销装置的扬声器将报销提示信息通过声音的方式的输出。报销提示信息可以向用户提示报销申请信息中的每一项的填写规范，还可以向用户提示真实的发票的正确特征点以及虚假发票的错误特征点，以使用户可以在上传发票图像之前进行自检，避免了用户出现上传错误发票的情况，从而提高了报销申请的通过率。
步骤302，当检测到完成指令被触发时，从申请界面获取用户输入的数据处理申请信息。
本申请实施例中，实施上述的步骤301~步骤302，可以提示用户填写数据处理申请信息，以使用户填写的数据处理申请信息更加准确，进一步提升了数据处理流程的智能化。
步骤303，当检测到用户输入的数据处理申请信息时，从数据处理申请信息中获取用户的个人信息。
本申请实施例中，用户的个人信息可以包含用户的姓名、年龄、职位、部门、编号等信息，根据用户的个人信息可以确定该用户是否为企业的员工，如果该用户不为企业的员工，则该用户输入的报销申请信息不予受理；如果该用户为企业的员工，则可以确定该用户对应的报销部门。
步骤304，从预先构建的信用体系中获取与个人信息匹配的目标信用值。
本申请实施例中，预先构建的信用体系中可以存储企业每个员工的信用值和行为信息等信息，企业的员工执行的每一个行为都可以被存储至信用体系中，信用体系可以根据记录的行为信息计算得到各个用户的信用值，当员工的行为涉及到与信用有关的操作时，均可以预先判断该用户的信用值是否符合执行当前操作的要求，如果不符合要求可以禁止用户执行该操作。
步骤305，当检测出目标信用值大于预设信用值时，从数据处理申请信息中获取目标处理事项、目标事项类型以及申请图像。
本申请实施例中，实施上述的步骤303~步骤305，可以对目标信用值大于预设信用值的用户施行自动的数据处理，提高了数据处理的效率。
步骤306，判断预先存储的与目标事项类型匹配的处理事项中是否包含目标处理事项，如果是，执行步骤308~步骤309；如果否，执行步骤307。
步骤307，将数据处理申请信息进行驳回，并输出驳回提示信息，驳回提示信息用于提示用户更换正确申请图像或撤销数据处理申请。
本申请实施例中，实施上述的步骤307，可以提示用户的申请图像存在问题，可以让用户执行更换申请图像或撤销数据处理申请的操作，以使用户可以及时的对数据处理申请信息进行更正。
作为一种可选的实施方式，步骤307之后还可以执行以下步骤：从信用体系中获取与个人信息匹配的行为信息；将申请图像标记为错误申请图像，并将错误申请图像添加至行为信息中得到当前行为信息；根据当前行为信息计算得到用户的当前信用值，并将当前信用值与用户的个人信息关联存储至信用体系中。其中，实施这种实施方式，可以将用户本次提供的错误申请图像存储至信用体系中的用户的行为信息中，进而根据该错误申请图像重新计算得到用户的信用值，提高了信用系统中各个用户的信用值的时效性。
步骤308，通过光学字符识别技术对申请图像进行识别，得到申请图像中包含的申请信息，并根据申请信息对申请图像的正确性进行验证。
步骤309，判断申请图像的正确性验证是否通过，如果是，执行步骤310；如果否，执行步骤311~步骤312。
步骤310，从申请信息中获取目标数据，并对目标数据进行数据处理。
步骤311，输出显示事项添加提示信息，事项添加提示信息用于提示用户提出将目标处理事项添加至与目标事项类型匹配的处理事项中的申请。
步骤312，当检测到申请指令被触发时，根据目标处理事项和目标事项类型生成事项添加申请，并将事项添加申请进行存储，以使维护人员对事项添加申请进行处理。
本申请实施例中，实施上述的步骤311~步骤312，由于在初始化时可能存在目标事项类型对应的处理事项不够全面的情况，因此用户可以提出向目标事项类型添加处理事项的申请，从而提高了处理事项类型识别的准确性。
在图3所描述的方法中，提高了对数据处理申请信息的正确性验证的准确率，从而可以提升数据处理的准确率。此外，实施图3所描述的方法，提升了数据处理流程的智能化。此外，实施图3所描述的方法，提高了数据处理的效率。此外，实施图3所描述的方法，可以及时的对数据处理申请信息进行更正。此外，实施图3所描述的方法，提高了信用系统中各个用户的信用值的时效性。此外，实施图3所描述的方法，提高了处理事项类型识别的准确性。
在一个实施例中，本申请还提供了一种基于光学字符识别的申请验证装置，以下是本申请的装置实施例。图4是根据一示例性实施例示出的一种基于光学字符识别的申请验证装置的框图。如图4所示，该装置包括：第一获取单元401，用于当检测到用户输入的数据处理申请信息时，从数据处理申请信息中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息。判断单元402，用于判断预先存储的与第一获取单元401获取的目标事项类型匹配的处理事项中是否包含目标处理事项。识别单元403，用于在判断单元402判断的结果为是时，通过光学字符识别技术对申请图像进行识别，得到申请图像中包含的申请信息，并根据申请信息对申请图像的正确性进行验证。
作为一种可选的实施方式，识别单元403通过光学字符识别技术对申请图像进行识别，得到申请图像中包含的申请信息，并根据申请信息对申请图像的正确性进行验证的方式具体可以为：通过光学字符识别技术对申请图像进行识别，得到申请图像中包含的文字信息；
通过深度学习算法对文字信息进行分析，生成申请图像中包含的申请信息，申请信息至少包含申请事项和目标数据；通过查验接口向查验平台发送申请信息，以使查验平台根据申请信息对申请图像的正确性进行查验，并反馈查验结果；当接收到查验平台发送的查验结果时，根据查验结果判断申请图像的正确性是否通过验证。
其中，实施这种实施方式，可以通过深度学习算法中的语义分析技术先对文字信息中包含的各个分词进行分割，以得到文字信息中包含的若干个分词，进而可以识别得到各个分词的分词含义，还可以根据识别到的符号识别出文字信息中包含的若干个子句，即每个子句中可以包含若干个分词，此外，还可以通过TF-IDF对各个子句中的每个分词的权重值进行计算，以确定各个子句中每个分词的权重值，之后，根据各个分词以及该分词的分词含义，可以确定各个子句的含义，进而根据各个子句的含义确定出申请图像中包含的申请信息，提高了申请图像正确性验证的可信度。
第二获取单元404，用于当识别单元403对申请图像的正确性验证通过时，从申请信息中获取目标数据，并对目标数据进行数据处理。
作为一种可选的实施方式，第二获取单元404从申请信息中获取目标数据，并对目标数据进行数据处理的方式具体可以为：当申请图像的正确性验证通过时，检测申请事项是否与数据处理申请信息中的目标处理事项匹配以及目标数据是否与报销申请信息中的申请数据匹配；如果申请事项与目标处理事项匹配以及目标数据与申请数据匹配，将申请数据确定为目标数据，并对目标数据进行数据处理。其中，实施这种实施方式，可以根据识别出的申请信息与用户提供的数据处理申请信息进行对比，只有在申请信息与数据处理申请信息一致的情况下才可以对目标数据进行数据处理，保证了数据处理的准确性。
可见，在图4所描述的装置中，提高了对数据处理申请信息的正确性验证的准确率，从而可以提升数据处理的准确率。此外，在图4所描述的装置中，提高了申请图像正确性验证的可信度。此外，在图4所描述的装置中，保证了数据处理的准确性。
图5是根据另一示例性实施例示出的一种基于光学字符识别的申请验证装置的框图。其中，图5所示的基于光学字符识别的申请验证装置是由图4所示的基于光学字符识别的申请验证装置进行优化得到的。与图4所示的基于光学字符识别的申请验证装置相比，图5所示的基于光学字符识别的申请验证装置还可以包括：第一输出单元405，用于在第一获取单元401当检测到用户输入的数据处理申请信息时，从数据处理申请中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息之前，以及当检测到用户输入的数据处理申请时，输出显示申请界面，并在申请界面中输出申请提示信息，申请提示信息用于提示用户通过申请界面输入数据处理申请信息以及提示用户正确申请图像的特征点。第三获取单元406，用于当检测到完成指令被触发时，从申请界面获取用户输入的数据处理申请信息。
本申请实施例中，具体的，第一输出单元405在申请界面中输出申请提示信息之后，触发第三获取单元406启动。
本申请实施例中，可以提示用户填写数据处理申请信息，以使用户填写的数据处理申请信息更加准确，进一步提升了数据处理流程的智能化。
作为一种可选的实施方式，图5所示的基于光学字符识别的申请验证装置的第一获取单元401可以包括：第一获取子单元4011，用于当检测到用户输入的数据处理申请信息时，从数据处理申请信息中获取用户的个人信息；第二获取子单元4012，用于从预先构建的信用体系中获取与第一获取子单元4011获取的个人信息匹配的目标信用值；第三获取子单元4013，用于当检测出第二获取子单元4012获取的目标信用值大于预设信用值时，从数据处理申请信息中获取目标处理事项、目标事项类型以及申请图像。其中，实施这种实施方式，可以对目标信用值大于预设信用值的用户施行自动的数据处理，提高了数据处理的效率。
作为一种可选的实施方式，图5所示的基于光学字符识别的报销装置还可以包括：
第二输出单元407，用于在判断单元402判断的结果为否时，将数据处理申请信息进行驳回，并输出驳回提示信息，驳回提示信息用于提示用户更换正确申请图像或撤销数据处理申请。其中，实施这种实施方式，可以提示用户的申请图像存在问题，可以让用户执行更换申请图像或撤销数据处理申请的操作，以使用户可以及时的对数据处理申请信息进行更正。
作为一种可选的实施方式，第二输出单元407还可以用于：从信用体系中获取与个人信息匹配的行为信息；将申请图像标记为错误申请图像，并将错误申请图像添加至行为信息中得到当前行为信息；根据当前行为信息计算得到用户的当前信用值，并将当前信用值与用户的个人信息关联存储至信用体系中。其中，实施这种实施方式，可以将用户本次提供的错误申请图像存储至信用体系中的用户的行为信息中，进而根据该错误申请图像重新计算得到用户的信用值，提高了信用系统中各个用户的信用值的时效性。
作为一种可选的实施方式，图5所示的基于光学字符识别的申请验证装置还可以包括：
第三输出单元408，用于当识别单元403对申请图像的正确性验证未通过时，输出显示事项添加提示信息，事项添加提示信息用于提示用户提出将目标处理事项添加至与目标事项类型匹配的处理事项中的申请；生成单元409，用于当检测到申请指令被触发时，根据第一获取单元401获取的目标处理事项和目标事项类型生成事项添加申请，并将事项添加申请进行存储，以使维护人员对事项添加申请进行处理。其中，实施这种实施方式，由于在初始化时可能存在目标事项类型对应的处理事项不够全面的情况，因此用户可以提出向目标事项类型添加处理事项的申请，从而提高了处理事项类型识别的准确性。
可见，在图5所描述的装置中，提高了对数据处理申请信息的正确性验证的准确率，从而可以提升数据处理的准确率。此外，在图5所描述的装置中，提升了数据处理流程的智能化。此外，在图5所描述的装置中，提高了数据处理的效率。此外，在图5所描述的装置中，可以及时的对数据处理申请信息进行更正。此外，在图5所描述的装置中，提高了信用系统中各个用户的信用值的时效性。此外，在图5所描述的装置中，提高了处理事项类型识别的准确性。
在一个实施例中，提出了一种计算设备，执行上述任一所示的基于光学字符识别的申请验证方法的全部或者部分步骤。该计算设备包括：
至少一个处理器；以及
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如上述任一个示例性实施例所示出的基于光学字符识别的申请验证方法。
该计算设备可以是图1所示装置100。
在一个实施例中，提出了一种存储有计算机可读指令的计算机非易失性可读存储介质，该计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行上述基于光学字符识别的申请验证方法实施例中的步骤。
应当理解的是，本申请并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围执行各种修改和改变。本申请的范围仅由所附的权利要求来限制。

Claims (20)

  1. 一种基于光学字符识别的申请验证方法，其中，所述方法包括：
    当检测到用户输入的数据处理申请信息时，从所述数据处理申请信息中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息；
    判断预先存储的与所述目标事项类型匹配的处理事项中是否包含所述目标处理事项；
    如果包含，通过光学字符识别技术对所述申请图像进行识别，得到所述申请图像中包含的申请信息，并根据所述申请信息对所述申请图像的正确性进行验证；
    当所述申请图像的正确性验证通过时，从所述申请信息中获取目标数据，并对所述目标数据进行数据处理。
  2. 根据权利要求1所述的方法，其中，所述当检测到用户输入的数据处理申请信息时，从所述数据处理申请中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息之前，所述方法还包括：
    当检测到用户输入的数据处理申请时，输出显示申请界面，并在所述申请界面中输出申请提示信息，所述申请提示信息用于提示用户通过所述申请界面输入数据处理申请信息以及提示用户正确申请图像的特征点；
    当检测到完成指令被触发时，从所述申请界面获取用户输入的所述数据处理申请信息；
    所述当检测到用户输入的数据处理申请信息时，从所述数据处理申请中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息，包括：
    当检测到用户输入的数据处理申请信息时，从所述数据处理申请信息中获取用户的个人信息；
    从预先构建的信用体系中获取与所述个人信息匹配的目标信用值；
    当检测出所述目标信用值大于预设信用值时，从所述数据处理申请信息中获取目标处理事项、目标事项类型以及申请图像。
  3. 根据权利要求2所述的方法，其中，当所述申请图像的正确性验证未通过时，所述方法还包括：
    将所述数据处理申请信息进行驳回，并输出驳回提示信息，所述驳回提示信息用于提示用户更换正确申请图像或撤销所述数据处理申请。
  4. 根据权利要求3所述的方法，其中，所述将所述数据处理申请信息进行驳回，并输出驳回提示信息之后，所述方法还包括：
    从所述信用体系中获取与所述个人信息匹配的行为信息；
    将所述申请图像标记为错误申请图像，并将所述错误申请图像添加至所述行为信息中得到当前行为信息；
    根据所述当前行为信息计算得到用户的当前信用值，并将所述当前信用值与用户的所述个人信息关联存储至所述信用体系中。
  5. 根据权利要求4所述的方法，其中，在判断出预先存储的与所述目标事项类型匹配的处理事项中未包含所述目标处理事项之后，所述方法还包括：
    输出显示事项添加提示信息，所述事项添加提示信息用于提示用户提出将所述目标处理事项添加至与所述目标事项类型匹配的处理事项中的申请；
    当检测到申请指令被触发时，根据所述目标处理事项和所述目标事项类型生成事项添加申请，并将所述事项添加申请进行存储，以使维护人员对所述事项添加申请进行处理。
  6. 根据权利要求1~5任一项所述的方法，其中，所述通过光学字符识别技术对所述申请图像进行识别，得到所述申请图像中包含的申请信息，并根据所述申请信息对所述申请图像的正确性进行验证，包括：
    通过光学字符识别技术对所述申请图像进行识别，得到所述申请图像中包含的文字信息；
    通过深度学习算法对所述文字信息进行分析，生成所述申请图像中包含的申请信息，所述申请信息至少包含申请事项和目标数据；
    通过查验接口向查验平台发送所述申请信息，以使所述查验平台根据所述申请信息对所述申请图像的正确性进行查验，并反馈查验结果；
    当接收到所述查验平台发送的所述查验结果时，根据所述查验结果判断所述申请图像的正确性是否通过验证。
  7. 根据权利要求6所述的方法，其中，所述当所述申请图像的正确性验证通过时，从所述申请信息中获取目标数据，并对所述目标数据进行数据处理，包括：
    当所述申请图像的正确性验证通过时，检测所述申请事项是否与所述数据处理申请信息中的目标处理事项匹配以及所述目标数据是否与所述报销申请信息中的申请数据匹配；
    如果所述申请事项与所述目标处理事项匹配以及所述目标数据与所述申请数据匹配，将所述申请数据确定为目标数据，并对所述目标数据进行数据处理。
  8. 一种基于光学字符识别的申请验证装置，其中，所述装置包括：
    第一获取单元，用于当检测到用户输入的数据处理申请信息时，从所述数据处理申请信息中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息；
    判断单元，用于判断预先存储的与所述目标事项类型匹配的处理事项中是否包含所述目标处理事项；
    识别单元，用于在所述判断单元判断的结果为是时，通过光学字符识别技术对所述申请图像进行识别，得到所述申请图像中包含的申请信息，并根据所述申请信息对所述申请图像的正确性进行验证；
    第二获取单元，用于当所述申请图像的正确性验证通过时，从所述申请信息中获取目标数据，并对所述目标数据进行数据处理。
  9. 根据权利要求8所述的装置，其中，所述装置还包括：
    第一输出单元，用于在第一获取单元当检测到用户输入的数据处理申请信息时，从所述数据处理申请中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息之前，以及当检测到用户输入的数据处理申请时，输出显示申请界面，并在所述申请界面中输出申请提示信息，所述申请提示信息用于提示用户通过所述申请界面输入数据处理申请信息以及提示用户正确申请图像的特征点；
    第三获取单元，用于当检测到完成指令被触发时，从所述申请界面获取用户输入的所述数据处理申请信息；
    所述第一获取单元包括：
    第一获取子单元，用于当检测到用户输入的数据处理申请信息时，从所述数据处理申请信息中获取用户的个人信息；
    第二获取子单元，用于从预先构建的信用体系中获取与所述个人信息匹配的目标信用值；
    第三获取子单元，用于当检测出所述目标信用值大于预设信用值时，从所述数据处理申请信息中获取目标处理事项、目标事项类型以及申请图像。
  10. 根据权利要求9所述的装置，其中，所述装置还包括：
    第二输出单元，用于在识别单元对所述申请图像的正确性验证未通过时，将所述数据处理申请信息进行驳回，并输出驳回提示信息，所述驳回提示信息用于提示用户更换正确申请图像或撤销所述数据处理申请。
  11. 一种计算设备，包括存储器和处理器，所述存储器中存储有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述处理器执行:
    当检测到用户输入的数据处理申请信息时，从所述数据处理申请信息中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息；
    判断预先存储的与所述目标事项类型匹配的处理事项中是否包含所述目标处理事项；
    如果包含，通过光学字符识别技术对所述申请图像进行识别，得到所述申请图像中包含的申请信息，并根据所述申请信息对所述申请图像的正确性进行验证；
    当所述申请图像的正确性验证通过时，从所述申请信息中获取目标数据，并对所述目标数据进行数据处理。
  12. 根据权利要求11所述的计算设备，其中，所述当检测到用户输入的数据处理申请信息时，从所述数据处理申请中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息之前，所述计算机可读指令被所述处理器执行时，使得所述处理器还执行:
    当检测到用户输入的数据处理申请时，输出显示申请界面，并在所述申请界面中输出申请提示信息，所述申请提示信息用于提示用户通过所述申请界面输入数据处理申请信息以及提示用户正确申请图像的特征点；
    当检测到完成指令被触发时，从所述申请界面获取用户输入的所述数据处理申请信息；
    所述当检测到用户输入的数据处理申请信息时，从所述数据处理申请中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息，包括：
    当检测到用户输入的数据处理申请信息时，从所述数据处理申请信息中获取用户的个人信息；
    从预先构建的信用体系中获取与所述个人信息匹配的目标信用值；
    当检测出所述目标信用值大于预设信用值时，从所述数据处理申请信息中获取目标处理事项、目标事项类型以及申请图像。
  13. 根据权利要求12所述的计算设备，其中，当所述申请图像的正确性验证未通过时，所述计算机可读指令被所述处理器执行时，使得所述处理器还执行:
    将所述数据处理申请信息进行驳回，并输出驳回提示信息，所述驳回提示信息用于提示用户更换正确申请图像或撤销所述数据处理申请。
  14. 根据权利要求13所述的计算设备，其中，所述将所述数据处理申请信息进行驳回，并输出驳回提示信息之后，所述计算机可读指令被所述处理器执行时，使得所述处理器还执行:
    从所述信用体系中获取与所述个人信息匹配的行为信息；
    将所述申请图像标记为错误申请图像，并将所述错误申请图像添加至所述行为信息中得到当前行为信息；
    根据所述当前行为信息计算得到用户的当前信用值，并将所述当前信用值与用户的所述个人信息关联存储至所述信用体系中。
  15. 根据权利要求14所述的计算设备，其中，在判断出预先存储的与所述目标事项类型匹配的处理事项中未包含所述目标处理事项之后，所述计算机可读指令被所述处理器执行时，使得所述处理器还执行:
    输出显示事项添加提示信息，所述事项添加提示信息用于提示用户提出将所述目标处理事项添加至与所述目标事项类型匹配的处理事项中的申请；
    当检测到申请指令被触发时，根据所述目标处理事项和所述目标事项类型生成事项添加申请，并将所述事项添加申请进行存储，以使维护人员对所述事项添加申请进行处理。
  16. 根据权利要求11~15任一项所述的计算设备，其特征在于，所述通过光学字符识别技术对所述申请图像进行识别，得到所述申请图像中包含的申请信息，并根据所述申请信息对所述申请图像的正确性进行验证，包括：
    通过光学字符识别技术对所述申请图像进行识别，得到所述申请图像中包含的文字信息；
    通过深度学习算法对所述文字信息进行分析，生成所述申请图像中包含的申请信息，所述申请信息至少包含申请事项和目标数据；
    通过查验接口向查验平台发送所述申请信息，以使所述查验平台根据所述申请信息对所述申请图像的正确性进行查验，并反馈查验结果；
    当接收到所述查验平台发送的所述查验结果时，根据所述查验结果判断所述申请图像的正确性是否通过验证。
  17. 根据权利要求16所述的计算设备，其中，所述当所述申请图像的正确性验证通过时，从所述申请信息中获取目标数据，并对所述目标数据进行数据处理，包括：
    当所述申请图像的正确性验证通过时，检测所述申请事项是否与所述数据处理申请信息中的目标处理事项匹配以及所述目标数据是否与所述报销申请信息中的申请数据匹配；
    如果所述申请事项与所述目标处理事项匹配以及所述目标数据与所述申请数据匹配，将所述申请数据确定为目标数据，并对所述目标数据进行数据处理。
  18. 一种存储有计算机可读指令的计算机非易失性可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行：
    当检测到用户输入的数据处理申请信息时，从所述数据处理申请信息中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息；
    判断预先存储的与所述目标事项类型匹配的处理事项中是否包含所述目标处理事项；
    如果包含，通过光学字符识别技术对所述申请图像进行识别，得到所述申请图像中包含的申请信息，并根据所述申请信息对所述申请图像的正确性进行验证；
    当所述申请图像的正确性验证通过时，从所述申请信息中获取目标数据，并对所述目标数据进行数据处理。
  19. 根据权利要求18所述的计算机非易失性可读存储介质，其中，所述当检测到用户输入的数据处理申请信息时，从所述数据处理申请中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息之前，所述计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器还执行：
    当检测到用户输入的数据处理申请时，输出显示申请界面，并在所述申请界面中输出申请提示信息，所述申请提示信息用于提示用户通过所述申请界面输入数据处理申请信息以及提示用户正确申请图像的特征点；
    当检测到完成指令被触发时，从所述申请界面获取用户输入的所述数据处理申请信息；
    所述当检测到用户输入的数据处理申请信息时，从所述数据处理申请中获取目标处理事项、目标事项类型、申请图像以及用户的个人信息，包括：
    当检测到用户输入的数据处理申请信息时，从所述数据处理申请信息中获取用户的个人信息；
    从预先构建的信用体系中获取与所述个人信息匹配的目标信用值；
    当检测出所述目标信用值大于预设信用值时，从所述数据处理申请信息中获取目标处理事项、目标事项类型以及申请图像。
  20. 根据权利要求19所述的计算机非易失性可读存储介质，其中，当所述申请图像的正确性验证未通过时，所述计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器还执行：
    将所述数据处理申请信息进行驳回，并输出驳回提示信息，所述驳回提示信息用于提示用户更换正确申请图像或撤销所述数据处理申请。
PCT/CN2019/103621 2019-06-13 2019-08-30 申请验证方法、装置、计算设备和计算机可读存储介质 Ceased WO2020248394A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910510434.9A CN110378217B (zh) 2019-06-13 2019-06-13 基于光学字符识别的申请验证方法、装置及电子设备
CN201910510434.9 2019-06-13

Publications (1)

Publication Number Publication Date
WO2020248394A1 true WO2020248394A1 (zh) 2020-12-17

Family

ID=68250257

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/103621 Ceased WO2020248394A1 (zh) 2019-06-13 2019-08-30 申请验证方法、装置、计算设备和计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN110378217B (zh)
WO (1) WO2020248394A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111311197A (zh) * 2020-03-05 2020-06-19 中国工商银行股份有限公司 差旅数据处理方法及装置
CN116543140A (zh) * 2022-01-26 2023-08-04 北京嘀嘀无限科技发展有限公司 信息验证方法和信息验证装置
CN115099919A (zh) * 2022-06-28 2022-09-23 平安银行股份有限公司 询证函管理方法、装置、存储介质及计算机设备

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104915808A (zh) * 2015-07-10 2015-09-16 丰镇市农村信用联社股份有限公司 电子印章管理实现方法及系统
CN107705087A (zh) * 2017-09-06 2018-02-16 深圳市恒创智达信息技术有限公司 员工入离职远程管理系统及方法
CN109308657A (zh) * 2018-08-02 2019-02-05 平安科技（深圳）有限公司 单证报销结算方法、装置、计算机设备及存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6527410B2 (ja) * 2015-07-06 2019-06-05 株式会社日立システムズ 文字認識装置、文字認識方法、及びプログラム
CN108460683A (zh) * 2017-02-20 2018-08-28 平安科技（深圳）有限公司 报销自助申请方法及装置
CN108229524A (zh) * 2017-05-25 2018-06-29 北京航空航天大学 一种基于遥感图像的烟囱和冷凝塔检测方法
CN109190629A (zh) * 2018-08-28 2019-01-11 传化智联股份有限公司 一种电子运单生成方法及装置
CN109472918A (zh) * 2018-10-12 2019-03-15 深圳壹账通智能科技有限公司 发票验证方法、融资审核方法、装置、设备及介质
CN109741517A (zh) * 2018-12-26 2019-05-10 大象慧云信息技术有限公司 一种发票查验方法、装置和系统

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104915808A (zh) * 2015-07-10 2015-09-16 丰镇市农村信用联社股份有限公司 电子印章管理实现方法及系统
CN107705087A (zh) * 2017-09-06 2018-02-16 深圳市恒创智达信息技术有限公司 员工入离职远程管理系统及方法
CN109308657A (zh) * 2018-08-02 2019-02-05 平安科技（深圳）有限公司 单证报销结算方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
CN110378217B (zh) 2024-09-20
CN110378217A (zh) 2019-10-25

Similar Documents

Publication Publication Date Title
US11170248B2 (en) Video capture in data capture scenario
US11853406B2 (en) System for verifying the identity of a user
US20210152550A1 (en) Machine learning for document authentication
US11488419B2 (en) Identity and liveness verification
US9582484B2 (en) Methods and systems for filling forms
US10380237B2 (en) Smart optical input/output (I/O) extension for context-dependent workflows
AU2020204204A1 (en) Automated vending machine with customer and identification authentication
CN110348703B (zh) 基于用户行为画像的数据处理方法、装置及电子设备
WO2020248394A1 (zh) 申请验证方法、装置、计算设备和计算机可读存储介质
US20150032605A1 (en) Systems and methods for digital check conversion
CN110162463A (zh) 基于自动化测试工具的软件测试方法、装置及电子设备
CN109800784B (zh) 基于神经网络的合同核对方法及装置
US20240005688A1 (en) Document authentication using multi-tier machine learning models
US20170076368A1 (en) Method and Device for Processing Card Application Data
CN110378377B (zh) 基于样本处理的数据处理方法、装置及电子设备
US12555401B2 (en) Auto-document detection and capture
US9213970B1 (en) Processing of co-mingled paper correspondence
US20240144713A1 (en) Methods and systems for determining the authenticity of an identity document
US20250378365A1 (en) Systems and methods for user classification using machine learning
US20240112487A1 (en) Systems and methods for automated paperwork
CN120656198A (zh) 信息检测方法、装置、设备及存储介质
CN114564941A (zh) 选项选择状态的判断方法、装置、设备及可读存储介质
CN121585433A (zh) 身份认证方法、装置、设备、介质和程序产品
CN116486121A (zh) 图像验证方法、装置、介质及设备

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: 19932330

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: 19932330

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19932330

Country of ref document: EP

Kind code of ref document: A1