+

WO2018166236A1 - 理赔账单识别方法、装置、设备及计算机可读存储介质 - Google Patents

理赔账单识别方法、装置、设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2018166236A1
WO2018166236A1 PCT/CN2017/112096 CN2017112096W WO2018166236A1 WO 2018166236 A1 WO2018166236 A1 WO 2018166236A1 CN 2017112096 W CN2017112096 W CN 2017112096W WO 2018166236 A1 WO2018166236 A1 WO 2018166236A1
Authority
WO
WIPO (PCT)
Prior art keywords
bill
field
field information
settled
comparison result
Prior art date
Application number
PCT/CN2017/112096
Other languages
English (en)
French (fr)
Inventor
蔡宁
米艺
方晓
仇一
薛燕
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2018166236A1 publication Critical patent/WO2018166236A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance

Definitions

  • the present application relates to the field of insurance technology, and in particular, to a claim bill identification method, apparatus, device, and computer readable storage medium.
  • Medical insurance is an insurance that compensates for the medical expenses incurred by the disease. It is a social insurance provided by the society or the enterprise to provide necessary medical services or material assistance when the employee is sick, injured or born. Such as China's public medical care, labor insurance and so on.
  • the traditional medical claim method is that after the user submits the claim statement, the auditor of the claim system manually manually enters the claim statement, and manually checks the authenticity of the claim statement for the claim operation. It can be seen that the existing claim method is cumbersome to operate, has many manual operations, and has a high error rate.
  • the main purpose of the present application is to provide a method, device, device and computer readable storage medium for identifying a claim bill, which aims to solve the technical problem of cumbersome operation and high error rate of the existing claim method.
  • the present application provides a method for identifying a claim bill, and the method for identifying a claim bill includes the steps of:
  • the bill to be settled is obtained, the bill to be settled is compared with the pre-deposit bill template, and the authenticity of the bill to be settled is confirmed according to the comparison result obtained by the comparison;
  • the auditor of the claim system is prompted to perform the claim operation according to the field information.
  • the present application further provides a claim bill identification device, where the claim bill identification device includes:
  • a comparison module configured to compare the to-be-resolved bill with the pre-deposit billing template when the bill to be settled is obtained, and confirm the authenticity of the bill to be settled according to the comparison result obtained by the comparison;
  • An identification module configured to identify each field in the to-be-resolved bill when the confirmation bill is confirmed to be a real bill according to the comparison result, and obtain field information corresponding to each field;
  • the prompting module is configured to prompt the auditor of the claim system to perform the claim operation according to the field information.
  • the present application further provides a claim bill identifying apparatus, the claim bill identifying apparatus including a memory, a processor, and a claim bill identifying program stored on the memory and operable on the processor
  • the processor is configured to invoke the claim bill identification program stored in the memory, and perform the following steps:
  • the bill to be settled is obtained, the bill to be settled is compared with the pre-deposit bill template, and the authenticity of the bill to be settled is confirmed according to the comparison result obtained by the comparison;
  • the auditor of the claim system is prompted to perform the claim operation according to the field information.
  • the present application further provides a computer readable storage medium, where the claim bill identification program is stored, and the claim bill identification program is executed by a processor to implement the above The steps of the claim form identification method.
  • the present application compares the to-be-recognized bill with the pre-deposit billing template when obtaining the bill to be settled, and confirms the authenticity of the bill to be settled according to the comparison result obtained by the comparison; when the claim is confirmed according to the comparison result
  • the bill is a real bill
  • each field in the bill to be settled is identified, and field information corresponding to each field is obtained; and the auditor of the claim system is prompted to perform the claim operation according to the field information.
  • FIG. 1 is a schematic flow chart of a preferred embodiment of a method for identifying a claim statement of the present application
  • FIG. 2 is a schematic diagram of a hardware environment of a method for identifying a claim statement of the present application
  • FIG. 3 is a schematic flowchart of identifying a field in the to-be-resolved bill when the to-be-recognized bill is a real bill according to the comparison result in the embodiment of the present application, and obtaining a recognition result;
  • FIG. 4 is a schematic diagram of functional modules of a preferred embodiment of the claim settlement identification device of the present application.
  • FIG. 5 is a schematic diagram of a functional module of an identification module in an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a device in a hardware operating environment according to an embodiment of the present application.
  • the application provides a method for identifying a claim bill.
  • FIG. 1 is a schematic flowchart of a preferred embodiment of a method for identifying a claim bill of the present application.
  • the claim bill identification method of the present application can be applied to a hardware environment composed of the server 102 and the terminal 104 as shown in FIG. 2.
  • the server 102 is connected to the terminal 104 through a network.
  • the network includes but is not limited to a wide area network, a metropolitan area network, or a local area network.
  • the terminal 104 is not limited to a PC, a mobile phone, a tablet, etc., and the server 102 includes but not Limited to single-way servers, multi-way servers, and distributed servers.
  • the claim bill identification method of the embodiment of the present application may be executed by the server 102, may be executed by the terminal 104, or may be jointly executed by the server 102 and the terminal 104.
  • the user sends the to-be-solved bill to the server 102 through the client in the terminal 104; after receiving the bill to be settled, the server 102 obtains the bill to be settled and the bill to be settled and the pre-deposit bill. Comparing the templates, confirming the authenticity of the claims bill according to the comparison result obtained by the comparison; when confirming that the claims bill is a real bill according to the comparison result, identifying the field information corresponding to each field in the bill to be settled, and obtaining the identification of the field information As a result, the auditor of the claim system is prompted to perform the claim operation according to the recognition result, and the result of the claim after the auditor performs the claim operation is sent to the terminal 104.
  • the method for identifying the claim bill includes:
  • Step S10 when the to-be-resolved bill is obtained, comparing the to-be-resolved bill with the pre-deposit billing template, and confirming the authenticity of the bill to be settled according to the comparison result obtained by the comparison;
  • the obtained bill to be settled is compared with the bill template pre-stored by the claim system, and the comparison result is obtained, and the authenticity of the bill to be settled is confirmed according to the comparison result.
  • the billing templates used in different regions may be different. Therefore, billing templates for different regions are pre-stored.
  • the medical bill template used in Guangdong is different from the medical bill template used in Hunan.
  • the to-be-repayed bill includes information on the fields of the hospital, the time of the visit, the cost item, and the amount of the fee.
  • the claim system may obtain the to-be-recognized bill by scanning the bill to be settled, or by the auditor of the claim system (worker) or the user of the claim bill uploading the image of the bill to be settled.
  • step S10 includes:
  • Step a when obtaining the bill to be settled, determining an area to which the bill to be settled belongs;
  • the visiting hospital corresponding to the claim bill is determined by the text recognition technology, and the area to be settled by the claim hospital is determined by the visiting hospital.
  • the character recognition technology used is OCR. (Optical Character Recognition, optical character recognition).
  • OCR Optical Character Recognition, optical character recognition
  • the area to be settled by the bill can be specific to the province, city and district according to the specific circumstances. Those skilled in the art can understand that in addition to OCR, other commonly used image text recognition technologies can be used to determine the hospital to be treated corresponding to the bill of claim.
  • Step b determining a pre-stored target bill template corresponding to the area to which the bill of claims is to be located;
  • Step c comparing the to-be-resolved bill with the pre-stored target bill template
  • the pre-existing target bill template corresponding to the area to which the claim bill belongs is determined, and the format of the claim settlement bill is compared with the pre-stored target bill template. That is, it is compared with the position of each field in the to-be-resolved bill and the location of each field of the pre-stored target bill template, and the number of fields. For example, whether the fields such as the time of the treatment, the expense item, and the amount of the expense in the to-be-received bill and the pre-existing target bill template are in the same position, and whether the same number of fields exist in the bill to be settled and the pre-stored target bill template.
  • Step d if the format of the to-be-resolved bill is consistent with the pre-stored target bill template, confirm that the bill to be settled is a real bill;
  • step e if the format of the to-be-resolved bill is inconsistent with the pre-stored target bill template, the to-be-recognized bill is confirmed as a false bill.
  • the bill to be settled is confirmed as a real bill; if the format of the bill to be settled is inconsistent with the pre-stored billing template, the bill to be settled is confirmed as a false bill.
  • the specific information of each field in the bill to be settled is not compared, for example, the specific time of the visit in the bill to be settled is not compared, but the bill to be settled is compared. Is there a field of visit time, and the location of the field at the time of the visit is consistent with the location of the field in the pre-existing target bill template.
  • the speed of confirming the authenticity of the bill to be settled is improved.
  • a corresponding identifier may be added to the bill to be settled to distinguish the authenticity of the bill to be settled. For example, when it is confirmed that the to-be-resolved bill is a real bill, the identifier 1 is added for the real bill to be settled; when the bill to be settled is confirmed to be a false bill, the identifier 0 is added for the false bill to be settled.
  • the prompt message may be sent to the terminal held by the bill-to-claims user, so that the user-requested bill to be presented as the claim request is identified as a false bill, wherein the prompt message may be sent by SMS , can also be sent by mail or other means.
  • Step S20 when it is confirmed that the to-be-resolved bill is a real bill according to the comparison result, identify each field in the to-be-resolved bill, and obtain field information corresponding to each field;
  • Step S30 prompting the auditor of the claim system to perform the claim operation according to the field information.
  • each field in the bill to be settled is identified, and field information corresponding to each field is obtained, specifically, specific field information corresponding to each field in the bill to be settled is identified.
  • the specific field information corresponding to the hospital field in the claim settlement bill is A hospital
  • the specific field information corresponding to the clinic time field is 11:00 on January 1, 2017, and the like.
  • step S30 includes:
  • Step f displaying the field information, and prompting the auditor to review the displayed field information
  • Step g when detecting a confirmation instruction for confirming the field information, prompting the auditor to perform a claim operation according to the field information.
  • the field information is displayed on the display interface of the claim system, and the auditor of the claim system is prompted to review the field information to improve the correctness of the identified field information.
  • a confirmation command for confirming the correctness of the field information is detected.
  • the output prompt message prompts the auditor to perform the claim operation according to the field information.
  • the modification instruction for modifying the field information may be detected before the confirmation instruction that the confirmation field information is correct is detected.
  • the modification instruction for modifying the field information is detected, the field information is modified according to the modification instruction. After the field information is successfully modified according to the modification instruction, a confirmation instruction for confirming the correctness of the field information is detected.
  • the auditor reviews the field information again to improve the correctness of the field information and reduce the error rate in the claim process.
  • the bill to be settled when the bill to be settled is obtained, the bill to be settled is compared with the pre-deposit bill template, and the authenticity of the bill to be settled is confirmed according to the comparison result obtained by the comparison; when the confirmation is confirmed according to the comparison result
  • the claim bill is a real bill
  • each field in the bill to be settled is identified, and field information corresponding to each field is obtained; and the auditor of the claim system is prompted to perform the claim operation according to the field information.
  • It realizes the automatic identification of the authenticity of the bills to be settled through various types of billing templates stored in advance, and automatically identifies the semantics of each field in the bills to be settled, and obtains the field information for the auditor of the claim system to execute the claim according to the field information.
  • the operation simplifies the operation process of the claim settlement, reduces the manual operation process in the claim process, and reduces the error rate in the claim process.
  • the second embodiment of the claim bill identification method differs from the first embodiment of the claim bill identification method in that, referring to FIG. 3, the step S20 includes:
  • Step S21 when it is confirmed that the to-be-resolved bill is a real bill according to the comparison result, acquiring a field voice corresponding to each field in the to-be-resolved bill;
  • the field voice corresponding to each field in the bill to be settled is obtained to obtain specific information of each field in the bill to be settled.
  • the voice recognition technology can be used to identify the field voice corresponding to each field entered by the user, thereby avoiding the need for the auditor or the user to manually enter the specific information corresponding to each field in the bill to be settled.
  • Step S22 comparing the field voice with a preset voice recognition character library to obtain a comparison result
  • Step S23 determining, according to the comparison result, a first character having the highest degree of similarity with the field voice in the voice recognition character library, and using the first character as field information corresponding to each field.
  • the obtained field voice is compared with the preset voice recognition character library to obtain a comparison result.
  • the speech recognition font library includes a hospital font library and a diagnostic code library. In the speech recognition font library, special medical terms can be identified through the hospital font library and the diagnostic code library to improve the success rate of field speech recognition.
  • the comparison result is obtained, the text with the highest similarity to the field speech in the speech recognition character library is determined according to the comparison result, and is recorded as the first character, and the first character is used as the field information corresponding to each field.
  • step S20 further includes:
  • Step h acquiring, in the speech recognition character library, a to-be-selected text corresponding to the field speech similarity corresponding to the preset similarity;
  • Step i outputting the to-be-selected text
  • Step j when detecting a selection instruction for selecting the to-be-selected text, determining, according to the selection instruction, a second text corresponding to the field voice in the to-be-selected text, and using the second text as each field Corresponding field information.
  • the text with the similarity of the field speech is greater than the preset similarity is obtained in the speech recognition character library, and the acquired text is recorded as the to-be-selected text.
  • the preset similarity can be set according to specific needs, for example, it can be set to 70%, or can be set to 80%.
  • the text to be selected is outputted in the display interface of the claim system, and a selection instruction for selecting the text to be selected is detected.
  • the selection instruction for selecting the text to be selected is detected, the text corresponding to the field voice in the to-be-selected text is determined according to the selection instruction, and is recorded as the second text, and the second text is used as the field information corresponding to each field.
  • a prompt message may be output to prompt the auditor to select the text to be selected.
  • the manner of outputting the prompt information includes but is not limited to the form of the prompt sound and the prompt light, and the prompting manner of the prompt light may be displaying a fixed color or blinking the prompt light.
  • the specific information corresponding to each field in the bill to be settled can also be obtained by the image text recognition technology, and the field information corresponding to each field is obtained.
  • the field voice corresponding to each field in the bill of claim is obtained, and the obtained field voice is compared with the preset voice recognition character library, and the specific information of each field in the current account to be settled is compared with the existing manual entry. It simplifies the operation process of claim settlement, reduces the manual operation process in the claim process, and reduces the error rate in the claim process.
  • the application further provides a claim bill identification device.
  • FIG. 4 is a schematic diagram of functional modules of a preferred embodiment of the claim settlement identification device of the present application.
  • the block diagram shown in FIG. 4 is merely an exemplary diagram of a preferred embodiment, and those skilled in the art can surround the module of the claim bill identification apparatus 100 shown in FIG.
  • the new module is easily added; the name of each module is a custom name, which is only used to assist in understanding the various program function blocks of the claim bill identification device 100, and is not used to limit the technical solution of the present application.
  • the core of the technical solution of the present application is The functions to be achieved by the modules that each define the name.
  • the claim bill identification device 100 includes:
  • the comparison module 10 is configured to compare the to-be-recognized bill with the pre-deposit billing template when the bill to be settled is obtained, and confirm the authenticity of the bill to be settled according to the comparison result obtained by the comparison;
  • the comparison module 10 compares the obtained bill to be settled with the bill template pre-stored by the claim system to obtain a comparison result, and confirms the authenticity of the bill to be settled according to the comparison result.
  • the billing templates used in different regions may be different. Therefore, billing templates for different regions are pre-stored.
  • the medical bill template used in Guangdong is different from the medical bill template used in Hunan.
  • the to-be-repayed bill includes information on the fields of the hospital, the time of the visit, the cost item, and the amount of the fee.
  • the claim system may obtain the to-be-recognized bill by scanning the bill to be settled, or by the auditor of the claim system (worker) or the user of the claim bill uploading the image of the bill to be settled.
  • comparison module 10 includes:
  • a first determining unit configured to determine an area to which the bill to be settled belongs when the bill to be settled is obtained
  • the first determining unit determines the hospital to be treated corresponding to the claim bill through the character recognition technology, and determines the area to which the bill to be settled belongs through the hospital.
  • the character recognition technology used is OCR. (Optical Character Recognition, optical character recognition).
  • OCR Optical Character Recognition, optical character recognition
  • the area to be settled by the bill can be specific to the province, city and district according to the specific circumstances. Those skilled in the art can understand that in addition to OCR, other commonly used image text recognition technologies can be used to determine the hospital to be treated corresponding to the bill of claim.
  • the first determining unit is further configured to determine a pre-stored target bill template corresponding to the area to which the to-be-required bill belongs;
  • a first comparing unit configured to compare the to-be-repayable bill with the pre-stored target billing template
  • the first determining unit determines a pre-stored target bill template corresponding to the region to which the bill to be settled belongs, and the first comparing unit compares the format of the bill to be settled with the pre-stored billing template. That is, it is compared with the position of each field in the to-be-resolved bill and the location of each field of the pre-stored target bill template, and the number of fields. For example, whether the fields such as the time of the treatment, the expense item, and the amount of the expense in the to-be-received bill and the pre-existing target bill template are in the same position, and whether the same number of fields exist in the bill to be settled and the pre-stored target bill template.
  • a confirmation unit configured to: if the format of the to-be-recognized bill is consistent with the pre-stored target bill template, confirm that the to-be-recognized bill is a real bill; if the format of the to-be-resolved bill is inconsistent with the pre-stored target bill template, Then, the claim settlement bill is confirmed as a false bill.
  • the confirmation unit confirms that the claim settlement bill is a real bill; if the format of the claim settlement bill is inconsistent with the pre-stored target bill template, the confirmation unit confirms that the claim settlement bill is a false bill. It can be understood that, in the process of comparing the to-be-solved bill with the pre-existing target bill template, the first comparison unit does not compare the specific information of each field in the bill to be settled, for example, does not compare the specific time of the visit in the bill to be settled, but only Compare the field of the visit time in the bill to be settled, and whether the location of the field at the time of the visit is consistent with the location of the field in the pre-existing target bill template.
  • the speed of confirming the authenticity of the bill to be settled is improved.
  • a corresponding identifier may be added to the bill to be settled to distinguish the authenticity of the bill to be settled. For example, when it is confirmed that the to-be-resolved bill is a real bill, the identifier 1 is added for the real bill to be settled; when the bill to be settled is confirmed to be a false bill, the identifier 0 is added for the false bill to be settled.
  • the prompt message may be sent to the terminal held by the bill-to-claims user, so that the user-requested bill to be presented as the claim request is identified as a false bill, wherein the prompt message may be sent by SMS , can also be sent by mail or other means.
  • the identifying module 20 is configured to: when the to-be-resolved bill is confirmed as a real bill according to the comparison result, identify each field in the to-be-resolved bill, and obtain field information corresponding to each field;
  • the prompting module 30 is configured to prompt the auditor of the claim system to perform the claim operation according to the field information.
  • the identification module 20 identifies each field in the bill to be settled, and obtains field information corresponding to each field. Specifically, the identification module 20 identifies a specific field corresponding to each field in the bill to be settled. information. For example, the specific field information corresponding to the hospital field in the claim settlement bill is A hospital, and the specific field information corresponding to the clinic time field is 11:00 on January 1, 2017, and the like. After obtaining the field information corresponding to each field, the prompting module 30 prompts the auditor of the claim system to perform the claim operation according to the obtained field information.
  • the prompting module 30 includes:
  • a display unit configured to display the field information
  • a prompting unit configured to prompt the auditing personnel to review the displayed field information; when detecting a confirmation instruction for confirming the field information, prompting the auditing personnel to perform a claim operation according to the field information.
  • the display unit displays the field information on the display interface of the claim system, and the prompting unit prompts the auditor of the claim system to review the field information to improve the correctness of the identified field information.
  • a confirmation command for confirming the correctness of the field information is detected.
  • the output prompt message prompts the auditor to perform the claim operation according to the field information.
  • the modification instruction for modifying the field information may be detected before the confirmation instruction that the confirmation field information is correct is detected.
  • the modification instruction for modifying the field information is detected, the field information is modified according to the modification instruction. After the field information is successfully modified according to the modification instruction, a confirmation instruction for confirming the correctness of the field information is detected.
  • the auditor reviews the field information again to improve the correctness of the field information and reduce the error rate in the claim process.
  • the bill to be settled when the bill to be settled is obtained, the bill to be settled is compared with the pre-deposit bill template, and the authenticity of the bill to be settled is confirmed according to the comparison result obtained by the comparison; when the confirmation is confirmed according to the comparison result
  • the claim bill is a real bill
  • each field in the bill to be settled is identified, and field information corresponding to each field is obtained; and the auditor of the claim system is prompted to perform the claim operation according to the field information.
  • It realizes the automatic identification of the authenticity of the bills to be settled through various types of billing templates stored in advance, and automatically identifies the semantics of each field in the bills to be settled, and obtains the field information for the auditor of the claim system to execute the claim according to the field information.
  • the operation simplifies the operation process of the claim settlement, reduces the manual operation process in the claim process, and reduces the error rate in the claim process.
  • the second embodiment of the claim bill identification device 100 differs from the first embodiment of the claim bill identification device 100 in that, referring to FIG. 5, the identification module 20 includes:
  • the obtaining unit 21 is configured to: when confirming that the to-be-resolved bill is a real bill according to the comparison result, acquiring a field voice corresponding to each field in the to-be-resolved bill;
  • the obtaining unit 21 acquires the field voice corresponding to each field in the bill to be settled, to obtain specific information of each field in the bill to be settled.
  • the voice recognition technology can be used to identify the field voice corresponding to each field entered by the user, thereby avoiding the need for the auditor or the user to manually input the corresponding fields in the bill to be settled. specific information.
  • a second comparing unit 22 configured to compare the field voice with a preset voice recognition character library to obtain a comparison result
  • the second determining unit 23 is configured to determine, according to the comparison result, a first character that has the highest degree of similarity with the field voice in the voice recognition character library, and use the first text as field information corresponding to each field.
  • the second comparing unit 22 compares the obtained field voice with the preset voice recognition character library to obtain a comparison result.
  • the speech recognition font library includes a hospital font library and a diagnostic code library. In the speech recognition font library, special medical terms can be identified through the hospital font library and the diagnostic code library to improve the success rate of field speech recognition.
  • the second determining unit 23 determines, according to the comparison result, the text with the highest degree of similarity to the field speech in the speech recognition character library, and records it as the first character, and uses the first character as the field information corresponding to each field.
  • the acquiring unit 21 is further configured to: in the voice recognition character library, acquire a to-be-selected character corresponding to the field voice similarity corresponding to the preset similarity;
  • the identification module 20 further includes: an output unit, configured to output the to-be-selected text;
  • the second determining unit 23 is further configured to: when detecting a selection instruction for selecting the to-be-selected text, determining, according to the selection instruction, a second text corresponding to the field voice in the to-be-selected text, The second text is used as the field information corresponding to each field.
  • the obtaining unit 21 acquires a character whose similarity with the field voice is greater than the preset similarity in the speech recognition character library, and records the acquired character as the to-be-selected character.
  • the preset similarity can be set according to specific needs, for example, it can be set to 70%, or can be set to 80%.
  • the output unit After determining the text to be selected, the output unit outputs the to-be-selected text in the display interface of the claims system, and detects a selection instruction for selecting the text to be selected.
  • the second determining unit 23 determines, according to the selection instruction, the text corresponding to the field voice in the character to be selected, and records it as the second text, and uses the second text as the field corresponding to each field. information.
  • a prompt message may be output to prompt the auditor to select the text to be selected.
  • the manner of outputting the prompt information includes but is not limited to the form of the prompt sound and the prompt light, and the prompting manner of the prompt light may be displaying a fixed color or blinking the prompt light.
  • the specific information corresponding to each field in the bill to be settled can also be obtained by the image text recognition technology, and the field information corresponding to each field is obtained.
  • the field voice corresponding to each field in the bill of claim is obtained, and the obtained field voice is compared with the preset voice recognition character library, and the specific information of each field in the current account to be settled is compared with the existing manual entry. It simplifies the operation process of claim settlement, reduces the manual operation process in the claim process, and reduces the error rate in the claim process.
  • FIG. 6 is a schematic structural diagram of a device in a hardware operating environment according to an embodiment of the present application.
  • the claim bill identification device in the embodiment of the present application may be a PC (personal Computer, personal computer), can also be a smartphone, tablet, e-book reader, MP3 (Moving Picture Experts Group Audio) Layer III, motion picture expert compresses standard audio layer 3) player, MP4 (Moving Picture Experts Group Audio Layer IV, the dynamic image expert compresses the standard audio layer 4) a portable terminal device having a display function such as a player or a portable computer.
  • PC personal Computer, personal computer
  • the claim bill identification device may include a processor 1001, such as a CPU, a user interface 1003, a memory 1005, and a communication bus 1002.
  • the communication bus 1002 is used to implement connection communication between these components.
  • the user interface 1003 can include a display, an input unit such as a keyboard, and the optional user interface 1003 can also include a standard wired interface, a wireless interface.
  • the memory 1005 may be a high speed RAM memory or a stable memory (non-volatile) Memory), such as disk storage.
  • the memory 1005 can also optionally be a storage device independent of the aforementioned processor 1001.
  • the claim bill identification device may further include a camera, RF (Radio) Frequency, RF) circuits, sensors, audio circuits, WiFi modules, and more.
  • RF Radio
  • RF Radio
  • FIG. 1 does not constitute a limitation to the terminal, and may include more or less components than those illustrated, or combine some components, or different component arrangements. .
  • an operating system and a claims bill identification program may be included in the memory 1005 as a computer storage medium.
  • the operating system is a program that manages and controls the claims bill to identify the hardware and software resources of the device, and supports the operation of the claims bill identification program and other software and/or programs.
  • the user interface 1003 is mainly used for detecting an operation instruction or the like, such as detecting a user's selection instruction.
  • the processor 1001 can be used to call the claims bill identification program stored in the memory 1005 and perform the following operations:
  • the bill to be settled is obtained, the bill to be settled is compared with the pre-deposit bill template, and the authenticity of the bill to be settled is confirmed according to the comparison result obtained by the comparison;
  • the auditor of the claim system is prompted to perform the claim operation according to the field information.
  • comparing the to-be-resolved bill with the pre-deposit billing template, and confirming the authenticity of the bill to be settled according to the comparison result obtained by the comparison includes:
  • the to-be-recognized bill is confirmed as a false bill.
  • the step of identifying each field in the to-be-resolved bill to obtain the field information corresponding to each field includes:
  • the to-be-recognized bill is a real bill according to the comparison result, acquiring a field voice corresponding to each field in the to-be-resolved bill;
  • the processor 1001 may further be configured to call the claim statement identification program stored in the memory 1005, and perform the following operations:
  • the selection instruction for selecting the to-be-selected text When the selection instruction for selecting the to-be-selected text is detected, determining, according to the selection instruction, a second text corresponding to the field voice in the to-be-selected text, and using the second text as a field corresponding to each field information.
  • step of prompting the auditor of the claim system to perform the claim operation according to the field information includes:
  • the auditor is prompted to perform a claim operation according to the field information.
  • the embodiment of the present application further provides a computer readable storage medium, where the claim bill identification program is stored, and the claim bill identification program is executed by the processor to implement the following steps:
  • the bill to be settled is obtained, the bill to be settled is compared with the pre-deposit bill template, and the authenticity of the bill to be settled is confirmed according to the comparison result obtained by the comparison;
  • the auditor of the claim system is prompted to perform the claim operation according to the field information.
  • comparing the to-be-resolved bill with the pre-deposit billing template, and confirming the authenticity of the bill to be settled according to the comparison result obtained by the comparison includes:
  • the to-be-recognized bill is confirmed as a false bill.
  • the step of identifying each field in the to-be-resolved bill to obtain the field information corresponding to each field includes:
  • the to-be-recognized bill is a real bill according to the comparison result, acquiring a field voice corresponding to each field in the to-be-resolved bill;
  • the claim bill identification program is executed by the processor to implement the following steps:
  • the selection instruction for selecting the to-be-selected text When the selection instruction for selecting the to-be-selected text is detected, determining, according to the selection instruction, a second text corresponding to the field voice in the to-be-selected text, and using the second text as a field corresponding to each field information.
  • step of prompting the auditor of the claim system to perform the claim operation according to the field information includes:
  • the auditor is prompted to perform a claim operation according to the field information.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better.
  • Implementation Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • General Business, Economics & Management (AREA)
  • Inspection Of Paper Currency And Valuable Securities (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请公开了一种理赔账单识别方法、装置、设备及计算机可读存储介质，该方法包括步骤：当获取到待理赔账单时，将待理赔账单与预存账单模板对比，根据对比所得的对比结果确认待理赔账单的真实性；当根据对比结果确认待理赔账单为真实账单时，识别待理赔账单中的各个字段，得到各个字段对应的字段信息；根据字段信息提示理赔系统的审核人员执行理赔操作。本申请实现了通过预先存储的各种类型账单模板，自动识别待理赔账单的真实性，并自动识别待理赔账单中的各个字段的语义，得到识别结果，以供理赔系统的审核人员根据识别结果执行理赔操作，简化了理赔的操作流程，以及减少了理赔过程中的人工操作环节，降低了理赔过程中的出错率。

Description

理赔账单识别方法、装置、设备及计算机可读存储介质
本申请要求于2017年3月13日提交中国专利局、申请号为201710149822.X、发明名称为“理赔账单识别方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在申请中。
技术领域
本申请涉及保险技术领域，尤其涉及一种理赔账单识别方法、装置、设备及计算机可读存储介质。
背景技术
医疗保险是为补偿疾病所带来得医疗费用的一种保险，是职工生病、负伤、生育时，由社会或企业提供必要的医疗服务或物质帮助的社会保险。如中国的公费医疗、劳保医疗等。
传统的医疗理赔方法，是当用户提交理赔账单后，由理赔系统的审核人员人工手动录入该理赔账单，人工审核该理赔账单的真实性以进行理赔操作。由此可知，现有理赔方法操作繁琐，人工操作环节多，出错率高。
发明内容
本申请的主要目的在于提供一种理赔账单识别方法、装置、设备及计算机可读存储介质，旨在解决现有的理赔方法操作繁琐，出错率高的技术问题。
为实现上述目的，本申请提供一种理赔账单识别方法，所述理赔账单识别方法包括步骤：
当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；
当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；
根据所述字段信息提示理赔系统的审核人员执行理赔操作。
此外，为实现上述目的，本申请还提供一种理赔账单识别装置，所述理赔账单识别装置包括：
对比模块，用于当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；
识别模块，用于当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；
提示模块，用于根据所述字段信息提示理赔系统的审核人员执行理赔操作。
此外，为实现上述目的，本申请还提供一种理赔账单识别设备，所述理赔账单识别设备包括存储器、处理器和存储在所述存储器上并可在所述处理器上运行的理赔账单识别程序，所述处理器用于调用所述存储器中存储的理赔账单识别程序，执行以下步骤：
当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；
当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；
根据所述字段信息提示理赔系统的审核人员执行理赔操作。
此外，为实现上述目的，本申请还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有理赔账单识别程序，所述理赔账单识别程序被处理器执行时实现如上所述的理赔账单识别方法的步骤。
本申请通过当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；根据所述字段信息提示理赔系统的审核人员执行理赔操作。实现了通过预先存储的各种类型账单模板，自动识别待理赔账单的真实性，并自动识别待理赔账单中的各个字段的语义，得到各个字段对应的字段信息，以供理赔系统的审核人员根据字段信息执行理赔操作，简化了理赔的操作流程，以及减少了理赔过程中的人工操作环节，降低了理赔过程中的出错率。
附图说明
图1为本申请理赔账单识别方法较佳实施例的流程示意图；
图2为本申请理赔账单识别方法的硬件环境示意图；
图3为本申请实施例中当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到识别结果的一种流程示意图；
图4为本申请理赔账单识别装置较佳实施例的功能模块示意图；
图5为本申请实施例中识别模块的一种功能模块示意图；
图6是本申请实施例方案涉及的硬件运行环境的设备结构示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请提供一种理赔账单识别方法。
参照图1，图1为本申请理赔账单识别方法较佳实施例的流程示意图。
在本实施例中，提供了理赔账单识别方法的实施例，需要说明的是，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
本申请的理赔账单识别方法可以应用于如图2所示的由服务器102和终端104所构成的硬件环境中。如图2所示，服务器102通过网络与终端104进行连接，上述网络包括但不限于：广域网、城域网或局域网，终端104并不限定于PC、手机、平板电脑等，服务器102包括但不限于单路服务器、多路服务器和分布式服务器。本申请实施例的理赔账单识别方法可以由服务器102来执行，也可以由终端104来执行，还可以是由服务器102和终端104共同执行。例如，在一些实施例中，用户通过终端104中的客户端将待理赔账单发送给服务器102；服务器102在接收到待理赔账单后，即获取到待理赔账单后，将待理赔账单与预存账单模板对比，根据对比所得的对比结果确认待理赔账单的真实性；当根据对比结果确认所述待理赔账单为真实账单时，识别待理赔账单中的各个字段对应的字段信息，得到字段信息的识别结果；根据识别结果提示理赔系统的审核人员执行理赔操作，并将审核人员执行理赔操作后的理赔结果发送给终端104。
所述理赔账单识别方法包括：
步骤S10，当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；
当获取到待理赔账单时，将所获取的待理赔账单与理赔系统预先存储的账单模板进行对比，得到对比结果，并根据对比结果确认待理赔账单的真实性。需要说明的是，不同地区所用的账单模板可能不一样，因此，会预先存储不同地区的账单模板。如广东地区所用的医疗账单模板和湖南地区所用的医疗账单模板是不一样的。待理赔账单中包括就诊医院、就诊时间、费用项目、以及费用金额等字段的信息。在本实施例中，理赔系统可通过扫描待理赔账单，也可以由理赔系统的审核人员（工作人员）或者待理赔账单的用户上传该待理赔账单的图像等方式获取该待理赔账单。
进一步地，所述步骤S10包括：
步骤a，当获取到待理赔账单时，确定所述待理赔账单所属地区；
当获取到待理赔账单时，通过文字识别技术确定待理赔账单对应的就诊医院，通过就诊医院确定待理赔账单所属地区。在本实施例中，所采用的文字识别技术为OCR （Optical Character Recognition，光学字符识别）。待理赔账单所属地区可根据具体情况具体到省、市和区等。本领域技术人员可以理解的是，除了OCR，还可以采用其它常用的图像文字识别技术来确定待理赔账单对应的就诊医院。
步骤b，确定与所述待理赔账单所属地区对应的预存目标账单模板；
步骤c，将所述待理赔账单与所述预存目标账单模板进行对比；
当确定待理赔账单所属地区时，确定与待理赔账单所属地区对应的预存目标账单模板，将待理赔账单的格式与预存目标账单模板进行对比。即对比待理赔账单中各个字段与预存目标账单模板的各个字段所在位置，以及字段数量等是否一致。如对比待理赔账单和预存目标账单模板中就诊时间、费用项目和费用金额等字段是否在同一个位置，对比待理赔账单和预存目标账单模板中是否都存在相同数量的字段等。
步骤d，若所述待理赔账单的格式和所述预存目标账单模板一致，则确认所述待理赔账单为真实账单；
步骤e，若所述待理赔账单的格式和所述预存目标账单模板不一致，则确认所述待理赔账单为虚假账单。
若待理赔账单的格式和预存目标账单模板一致，则确认待理赔账单为真实账单；若待理赔账单的格式和预存目标账单模板不一致，则确认待理赔账单为虚假账单。可以理解的是，在将待理赔账单与预存目标账单模板进行对比过程中，并不对比待理赔账单中各个字段的具体信息，如不对比待理赔账单中就诊的具体时间，只是对比待理赔账单中是否存在就诊时间这个字段，以及就诊时间这个字段所在位置与预存目标账单模板中就诊时间这个字段所在位置是否一致等。
本实施例通过先确认待理赔账单所属地区，然后确定与待理赔账单所属地区对应的预存目标账单模板，将待理赔账单与预存目标账单模板进行对比，提高了确认待理赔账单真实性的速度。
进一步地，当确认待理赔账单的真实性后，可为待理赔账单添加对应的标识，以区分待理赔账单的真实性。如当确认待理赔账单为真实账单时，为真实的待理赔账单添加标识1；当确认待理赔账单为虚假账单时，为虚假的待理赔账单添加标识0。
进一步地，当确认待理赔账单为虚假账单时，可发送提示消息给待理赔账单用户所持的终端，以提示提出理赔请求的用户待理赔账单被识别为虚假账单，其中，提示消息可以短信方式发送，也可以以邮件等方式发送。
步骤S20，当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；
步骤S30，根据所述字段信息提示理赔系统的审核人员执行理赔操作。
当根据对比结果确认待理赔账单为真实账单时，识别待理赔账单中的各个字段，得到各个字段对应的字段信息，具体地，识别待理赔账单中各个字段对应的具体字段信息。如待理赔账单中就诊医院字段对应的具体字段信息为A医院，就诊时间字段对应的具体字段信息为2017年1月1日11:00等等。当得到各个字段对应的字段信息后，根据所得的字段信息提示理赔系统的审核人员执行理赔操作。
进一步地，所述步骤S30包括：
步骤f，显示所述字段信息，并提示所述审核人员审核所显示的所述字段信息；
步骤g，当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
进一步地，当得到字段信息后，在理赔系统的显示界面显示该字段信息，提示理赔系统的审核人员审核该字段信息，以提高所识别的字段信息的正确性。当显示字段信息后，侦测确认字段信息正确性的确认指令。当侦测到确认字段信息正确的确认指令时，输出提示信息提示审核人员根据字段信息执行理赔操作。可以理解的是，在侦测到确认字段信息正确的确认指令之前，可能会侦测到修改字段信息的修改指令。当侦测到修改字段信息的修改指令时，根据修改指令修改字段信息。当根据修改指令成功修改字段信息后，侦测确认字段信息正确性的确认指令。
本实施例通过在得到字段信息之后，由审核人员再次审核字段信息，以提高字段信息的正确性，降低理赔过程中的出错率。
本实施例通过当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；根据所述字段信息提示理赔系统的审核人员执行理赔操作。实现了通过预先存储的各种类型账单模板，自动识别待理赔账单的真实性，并自动识别待理赔账单中的各个字段的语义，得到字段信息，以供理赔系统的审核人员根据字段信息执行理赔操作，简化了理赔的操作流程，以及减少了理赔过程中的人工操作环节，降低了理赔过程中的出错率。
进一步地，提出本申请理赔账单识别方法第二实施例。
所述理赔账单识别方法第二实施例与所述理赔账单识别方法第一实施例的区别在于，参照图3，所述步骤S20包括：
步骤S21，当根据所述对比结果确认所述待理赔账单为真实账单时，获取所述待理赔账单中各个字段对应的字段语音；
当根据对比结果确认待理赔账单为真实账单时，获取待理赔账单中各个字段对应的字段语音，以获取待理赔账单中各个字段的具体信息。在获取待理赔账单中各个字段对应的字段语音过程中，可以通过语音识别技术识别用户录入的各个字段对应的字段语音，避免需要审核人员或者用户手动录入待理赔账单中各个字段对应的具体信息。
步骤S22，将所述字段语音与预置的语音识别文字库进行对比，得到对比结果；
步骤S23，根据所述对比结果确定所述语音识别文字库中与所述字段语音相似度最大的第一文字，将所述第一文字作为各个字段对应的字段信息。
当获取到待理赔账单中各个字段对应的字段语音后，将所获取的字段语音与预置的语音识别文字库进行对比，得到对比结果。需要说明的是，语音识别文字库包括了医院文字库，以及诊断代码库。在语音识别文字库中，通过医院文字库和诊断代码库可以识别出专用的医疗用语，以提高字段语音识别的成功率。在得到对比结果后，根据对比结果确定语音识别文字库中与字段语音相似度最大的文字，记为第一文字，将第一文字作为各个字段对应的字段信息。
进一步地，所述步骤S20还包括：
步骤h，在所述语音识别文字库中获取与所述字段语音相似度大于预设相似度对应的待选择文字；
步骤i，输出所述待选择文字；
步骤j，当侦测到选择所述待选择文字的选择指令时，根据所述选择指令确定所述待选择文字中与所述字段语音对应的第二文字，将所述第二文字作为各个字段对应的字段信息。
进一步地，在得到对比结果后，在语音识别文字库中获取与字段语音相似度大于预设相似度的文字，将所获取的文字记为待选择文字。需要说明的是，预设相似度可根据具体需要而设置，如可设置为70%，也可以设置为80%等。
当确定待选择文字后，在理赔系统的显示界面中输出待选择文字，并侦测选择待选择文字的选择指令。当侦测到选择待选择文字的选择指令时，根据选择指令确定待选择文字中与字段语音对应的文字，记为第二文字，并将第二文字作为各个字段对应的字段信息。
进一步地，在输出待选择文字后，可输出提示信息提示审核人员选择待选择文字。输出提示信息方式包括但不限于提示音和提示灯的形式，提示灯的提示方式可为显示固定颜色，或者闪烁提示灯。
进一步地，在确认待理赔账单为真实账单时，也可通过图像文字识别技术得到待理赔账单中各个字段对应的具体信息，得到各个字段对应的字段信息。
本实施例通过获取待理赔账单中各个字段对应的字段语音，将所获取的字段语音与预置的语音识别文字库进行对比，相比现有的人工录入待理赔账单中各个字段的具体信息，简化了理赔的操作流程，以及减少了理赔过程中的人工操作环节，降低了理赔过程中的出错率。
本申请进一步提供一种理赔账单识别装置。
参照图4，图4为本申请理赔账单识别装置的较佳实施例的功能模块示意图。
需要强调的是，对本领域的技术人员来说，图4所示模块图仅仅是一个较佳实施例的示例图，本领域的技术人员围绕图4所示的理赔账单识别装置100的模块，可轻易进行新的模块的补充；各模块的名称是自定义名称，仅用于辅助理解该理赔账单识别装置100的各个程序功能块，不用于限定本申请的技术方案，本申请技术方案的核心是，各自定义名称的模块所要达成的功能。
在本实施例中，所述理赔账单识别装置100包括：
对比模块10，用于当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；
当获取到待理赔账单时，对比模块10将所获取的待理赔账单与理赔系统预先存储的账单模板进行对比，得到对比结果，并根据对比结果确认待理赔账单的真实性。需要说明的是，不同地区所用的账单模板可能不一样，因此，会预先存储不同地区的账单模板。如广东地区所用的医疗账单模板和湖南地区所用的医疗账单模板是不一样的。待理赔账单中包括就诊医院、就诊时间、费用项目、以及费用金额等字段的信息。在本实施例中，理赔系统可通过扫描待理赔账单，也可以由理赔系统的审核人员（工作人员）或者待理赔账单的用户上传该待理赔账单的图像等方式获取该待理赔账单。
进一步地，所述对比模块10包括：
第一确定单元，用于当获取到待理赔账单时，确定所述待理赔账单所属地区；
当获取到待理赔账单时，第一确定单元通过文字识别技术确定待理赔账单对应的就诊医院，通过就诊医院确定待理赔账单所属地区。在本实施例中，所采用的文字识别技术为OCR （Optical Character Recognition，光学字符识别）。待理赔账单所属地区可根据具体情况具体到省、市和区等。本领域技术人员可以理解的是，除了OCR，还可以采用其它常用的图像文字识别技术来确定待理赔账单对应的就诊医院。
第一确定单元还用于确定与所述待理赔账单所属地区对应的预存目标账单模板；
第一对比单元，用于将所述待理赔账单与所述预存目标账单模板进行对比；
当确定待理赔账单所属地区时，第一确定单元确定与待理赔账单所属地区对应的预存目标账单模板，第一对比单元将待理赔账单的格式与预存目标账单模板进行对比。即对比待理赔账单中各个字段与预存目标账单模板的各个字段所在位置，以及字段数量等是否一致。如对比待理赔账单和预存目标账单模板中就诊时间、费用项目和费用金额等字段是否在同一个位置，对比待理赔账单和预存目标账单模板中是否都存在相同数量的字段等。
确认单元，用于若所述待理赔账单的格式和所述预存目标账单模板一致，则确认所述待理赔账单为真实账单；若所述待理赔账单的格式和所述预存目标账单模板不一致，则确认所述待理赔账单为虚假账单。
若待理赔账单的格式和预存目标账单模板一致，确认单元则确认待理赔账单为真实账单；若待理赔账单的格式和预存目标账单模板不一致，确认单元则确认待理赔账单为虚假账单。可以理解的是，在第一对比单元将待理赔账单与预存目标账单模板进行对比过程中，并不对比待理赔账单中各个字段的具体信息，如不对比待理赔账单中就诊的具体时间，只是对比待理赔账单中是否存在就诊时间这个字段，以及就诊时间这个字段所在位置与预存目标账单模板中就诊时间这个字段所在位置是否一致等。
本实施例通过先确认待理赔账单所属地区，然后确定与待理赔账单所属地区对应的预存目标账单模板，将待理赔账单与预存目标账单模板进行对比，提高了确认待理赔账单真实性的速度。
进一步地，当确认待理赔账单的真实性后，可为待理赔账单添加对应的标识，以区分待理赔账单的真实性。如当确认待理赔账单为真实账单时，为真实的待理赔账单添加标识1；当确认待理赔账单为虚假账单时，为虚假的待理赔账单添加标识0。
进一步地，当确认待理赔账单为虚假账单时，可发送提示消息给待理赔账单用户所持的终端，以提示提出理赔请求的用户待理赔账单被识别为虚假账单，其中，提示消息可以短信方式发送，也可以以邮件等方式发送。
识别模块20，用于当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；
提示模块30，用于根据所述字段信息提示理赔系统的审核人员执行理赔操作。
当根据对比结果确认待理赔账单为真实账单时，识别模块20识别待理赔账单中的各个字段，得到各个字段对应的字段信息，具体地，识别模块20识别待理赔账单中各个字段对应的具体字段信息。如待理赔账单中就诊医院字段对应的具体字段信息为A医院，就诊时间字段对应的具体字段信息为2017年1月1日11:00等等。当得到各个字段对应的字段信息后，提示模块30根据所得的字段信息提示理赔系统的审核人员执行理赔操作。
进一步地，所述提示模块30包括：
显示单元，用于显示所述字段信息；
提示单元，用于提示所述审核人员审核所显示的所述字段信息；当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
进一步地，当得到字段信息后，显示单元在理赔系统的显示界面显示该字段信息，提示单元提示理赔系统的审核人员审核该字段信息，以提高所识别的字段信息的正确性。当显示字段信息后，侦测确认字段信息正确性的确认指令。当侦测到确认字段信息正确的确认指令时，输出提示信息提示审核人员根据字段信息执行理赔操作。可以理解的是，在侦测到确认字段信息正确的确认指令之前，可能会侦测到修改字段信息的修改指令。当侦测到修改字段信息的修改指令时，根据修改指令修改字段信息。当根据修改指令成功修改字段信息后，侦测确认字段信息正确性的确认指令。
本实施例通过在得到字段信息之后，由审核人员再次审核字段信息，以提高字段信息的正确性，降低理赔过程中的出错率。
本实施例通过当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；根据所述字段信息提示理赔系统的审核人员执行理赔操作。实现了通过预先存储的各种类型账单模板，自动识别待理赔账单的真实性，并自动识别待理赔账单中的各个字段的语义，得到字段信息，以供理赔系统的审核人员根据字段信息执行理赔操作，简化了理赔的操作流程，以及减少了理赔过程中的人工操作环节，降低了理赔过程中的出错率。
进一步地，提出本申请理赔账单识别装置100第二实施例。
所述理赔账单识别装置100第二实施例与所述理赔账单识别装置100第一实施例的区别在于，参照图5，所述识别模块20包括：
获取单元21，用于当根据所述对比结果确认所述待理赔账单为真实账单时，获取所述待理赔账单中各个字段对应的字段语音；
当根据对比结果确认待理赔账单为真实账单时，获取单元21获取待理赔账单中各个字段对应的字段语音，以获取待理赔账单中各个字段的具体信息。在获取单元21获取待理赔账单中各个字段对应的字段语音过程中，可以通过语音识别技术识别用户录入的各个字段对应的字段语音，避免需要审核人员或者用户手动录入待理赔账单中各个字段对应的具体信息。
第二对比单元22，用于将所述字段语音与预置的语音识别文字库进行对比，得到对比结果；
第二确定单元23，用于根据所述对比结果确定所述语音识别文字库中与所述字段语音相似度最大的第一文字，将所述第一文字作为各个字段对应的字段信息。
当获取到待理赔账单中各个字段对应的字段语音后，第二对比单元22将所获取的字段语音与预置的语音识别文字库进行对比，得到对比结果。需要说明的是，语音识别文字库包括了医院文字库，以及诊断代码库。在语音识别文字库中，通过医院文字库和诊断代码库可以识别出专用的医疗用语，以提高字段语音识别的成功率。在得到对比结果后，第二确定单元23根据对比结果确定语音识别文字库中与字段语音相似度最大的文字，记为第一文字，将第一文字作为各个字段对应的字段信息。
进一步地，所述获取单元21还用于在所述语音识别文字库中获取与所述字段语音相似度大于预设相似度对应的待选择文字；
所述识别模块20还包括：输出单元，用于输出所述待选择文字；
所述第二确定单元23还用于当侦测到选择所述待选择文字的选择指令时，根据所述选择指令确定所述待选择文字中与所述字段语音对应的第二文字，将所述第二文字作为各个字段对应的字段信息。
进一步地，在得到对比结果后，获取单元21在语音识别文字库中获取与字段语音相似度大于预设相似度的文字，将所获取的文字记为待选择文字。需要说明的是，预设相似度可根据具体需要而设置，如可设置为70%，也可以设置为80%等。
当确定待选择文字后，输出单元在理赔系统的显示界面中输出待选择文字，并侦测选择待选择文字的选择指令。当侦测到选择待选择文字的选择指令时，第二确定单元23根据选择指令确定待选择文字中与字段语音对应的文字，记为第二文字，并将第二文字作为各个字段对应的字段信息。
进一步地，在输出待选择文字后，可输出提示信息提示审核人员选择待选择文字。输出提示信息方式包括但不限于提示音和提示灯的形式，提示灯的提示方式可为显示固定颜色，或者闪烁提示灯。
进一步地，在确认待理赔账单为真实账单时，也可通过图像文字识别技术得到待理赔账单中各个字段对应的具体信息，得到各个字段对应的字段信息。
本实施例通过获取待理赔账单中各个字段对应的字段语音，将所获取的字段语音与预置的语音识别文字库进行对比，相比现有的人工录入待理赔账单中各个字段的具体信息，简化了理赔的操作流程，以及减少了理赔过程中的人工操作环节，降低了理赔过程中的出错率。
如图6所示，图6是本申请实施例方案涉及的硬件运行环境的设备结构示意图。
本申请实施例理赔账单识别设备可以是PC（personal computer，个人计算机），也可以是智能手机、平板电脑、电子书阅读器、MP3（Moving Picture Experts Group Audio Layer III，动态影像专家压缩标准音频层面3）播放器、MP4（Moving Picture Experts Group Audio Layer IV，动态影像专家压缩标准音频层面4）播放器、便携计算机等具有显示功能的可移动式终端设备。
如图1所示，该理赔账单识别设备可以包括：处理器1001，例如CPU，用户接口1003，存储器1005，通信总线1002。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏（Display）、输入单元比如键盘（Keyboard），可选用户接口1003还可以包括标准的有线接口、无线接口。存储器1005可以是高速RAM存储器，也可以是稳定的存储器（non-volatile memory），例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
可选地，理赔账单识别设备还可以包括摄像头、RF（Radio Frequency，射频）电路，传感器、音频电路、WiFi模块等等。
本领域技术人员可以理解，图1中示出的理赔账单识别设备结构并不构成对终端的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
如图1所示，作为一种计算机存储介质的存储器1005中可以包括操作系统以及理赔账单识别程序。其中，操作系统是管理和控制理赔账单识别设备硬件和软件资源的程序，支持理赔账单识别程序以及其它软件和/或程序的运行。
在图1所示的理赔账单识别设备中，用户接口1003主要用于侦测操作指令等，如侦测用户的选择指令。而处理器1001可以用于调用存储器1005中存储的理赔账单识别程序，并执行以下操作：
当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；
当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；
根据所述字段信息提示理赔系统的审核人员执行理赔操作。
进一步地，所述当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性的步骤包括：
当获取到待理赔账单时，确定所述待理赔账单所属地区；
确定与所述待理赔账单所属地区对应的预存目标账单模板；
将所述待理赔账单与所述预存目标账单模板进行对比；
若所述待理赔账单的格式和所述预存目标账单模板一致，则确认所述待理赔账单为真实账单；
若所述待理赔账单的格式和所述预存目标账单模板不一致，则确认所述待理赔账单为虚假账单。
进一步地，所述当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息的步骤包括：
当根据所述对比结果确认所述待理赔账单为真实账单时，获取所述待理赔账单中各个字段对应的字段语音；
将所述字段语音与预置的语音识别文字库进行对比，得到对比结果；
根据所述对比结果确定所述语音识别文字库中与所述字段语音相似度最大的第一文字，将所述第一文字作为各个字段对应的字段信息。
进一步地，所述将所述字段语音与预置的语音识别文字库进行对比，得到对比结果的步骤之后，处理器1001还可以用于调用存储器1005中存储的理赔账单识别程序，执行以下操作：
在所述语音识别文字库中获取与所述字段语音相似度大于预设相似度对应的待选择文字；
输出所述待选择文字；
当侦测到选择所述待选择文字的选择指令时，根据所述选择指令确定所述待选择文字中与所述字段语音对应的第二文字，将所述第二文字作为各个字段对应的字段信息。
进一步地，所述根据所述字段信息提示理赔系统的审核人员执行理赔操作的步骤包括：
显示所述字段信息，并提示所述审核人员审核所显示的所述字段信息；
当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
本申请理赔账单识别设备具体实施方式与上述理赔账单识别方法各实施例基本相同，在此不再赘述。
此外，本申请实施例还提出一种计算机可读存储介质，所述计算机可读存储介质上存储有理赔账单识别程序，所述理赔账单识别程序被处理器执行时实现如下步骤：
当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；
当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；
根据所述字段信息提示理赔系统的审核人员执行理赔操作。
进一步地，所述当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性的步骤包括：
当获取到待理赔账单时，确定所述待理赔账单所属地区；
确定与所述待理赔账单所属地区对应的预存目标账单模板；
将所述待理赔账单与所述预存目标账单模板进行对比；
若所述待理赔账单的格式和所述预存目标账单模板一致，则确认所述待理赔账单为真实账单；
若所述待理赔账单的格式和所述预存目标账单模板不一致，则确认所述待理赔账单为虚假账单。
进一步地，所述当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息的步骤包括：
当根据所述对比结果确认所述待理赔账单为真实账单时，获取所述待理赔账单中各个字段对应的字段语音；
将所述字段语音与预置的语音识别文字库进行对比，得到对比结果；
根据所述对比结果确定所述语音识别文字库中与所述字段语音相似度最大的第一文字，将所述第一文字作为各个字段对应的字段信息。
进一步地，所述将所述字段语音与预置的语音识别文字库进行对比，得到对比结果的步骤之后，所述理赔账单识别程序被处理器执行时实现如下步骤:
在所述语音识别文字库中获取与所述字段语音相似度大于预设相似度对应的待选择文字；
输出所述待选择文字；
当侦测到选择所述待选择文字的选择指令时，根据所述选择指令确定所述待选择文字中与所述字段语音对应的第二文字，将所述第二文字作为各个字段对应的字段信息。
进一步地，所述根据所述字段信息提示理赔系统的审核人员执行理赔操作的步骤包括：
显示所述字段信息，并提示所述审核人员审核所显示的所述字段信息；
当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
本申请计算机可读存储介质具体实施方式与上述理赔账单识别方法各实施例基本相同，在此不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质（如ROM/RAM、磁碟、光盘）中，包括若干指令用以使得一台终端设备（可以是手机，计算机，服务器，空调器，或者网络设备等）执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种理赔账单识别方法，其特征在于，所述理赔账单识别方法包括以下步骤：
    当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；
    当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；
    根据所述字段信息提示理赔系统的审核人员执行理赔操作。
  2. 如权利要求1所述的理赔账单识别方法，其特征在于，所述当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性的步骤包括：
    当获取到待理赔账单时，确定所述待理赔账单所属地区；
    确定与所述待理赔账单所属地区对应的预存目标账单模板；
    将所述待理赔账单与所述预存目标账单模板进行对比；
    若所述待理赔账单的格式和所述预存目标账单模板一致，则确认所述待理赔账单为真实账单；
    若所述待理赔账单的格式和所述预存目标账单模板不一致，则确认所述待理赔账单为虚假账单。
  3. 如权利要求1所述的理赔账单识别方法，其特征在于，所述当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息的步骤包括：
    当根据所述对比结果确认所述待理赔账单为真实账单时，获取所述待理赔账单中各个字段对应的字段语音；
    将所述字段语音与预置的语音识别文字库进行对比，得到对比结果；
    根据所述对比结果确定所述语音识别文字库中与所述字段语音相似度最大的第一文字，将所述第一文字作为各个字段对应的字段信息。
  4. 如权利要求3所述的理赔账单识别方法，其特征在于，所述将所述字段语音与预置的语音识别文字库进行对比，得到对比结果的步骤之后，还包括：
    在所述语音识别文字库中获取与所述字段语音相似度大于预设相似度对应的待选择文字；
    输出所述待选择文字；
    当侦测到选择所述待选择文字的选择指令时，根据所述选择指令确定所述待选择文字中与所述字段语音对应的第二文字，将所述第二文字作为各个字段对应的字段信息。
  5. 如权利要求1所述的理赔账单识别方法，其特征在于，所述根据所述字段信息提示理赔系统的审核人员执行理赔操作的步骤包括：
    显示所述字段信息，并提示所述审核人员审核所显示的所述字段信息；
    当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
  6. 如权利要求2所述的理赔账单识别方法，其特征在于，所述根据所述字段信息提示理赔系统的审核人员执行理赔操作的步骤包括：
    显示所述字段信息，并提示所述审核人员审核所显示的所述字段信息；
    当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
  7. 如权利要求3所述的理赔账单识别方法，其特征在于，所述根据所述字段信息提示理赔系统的审核人员执行理赔操作的步骤包括：
    显示所述字段信息，并提示所述审核人员审核所显示的所述字段信息；
    当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
  8. 如权利要求4所述的理赔账单识别方法，其特征在于，所述根据所述字段信息提示理赔系统的审核人员执行理赔操作的步骤包括：
    显示所述字段信息，并提示所述审核人员审核所显示的所述字段信息；
    当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
  9. 一种理赔账单识别装置，其特征在于，所述理赔账单识别装置包括：
    对比模块，用于当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；
    识别模块，用于当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；
    提示模块，用于根据所述字段信息提示理赔系统的审核人员执行理赔操作。
  10. 如权利要求9所述的理赔账单识别装置，其特征在于，所述对比模块包括：
    第一确定单元，用于当获取到待理赔账单时，确定所述待理赔账单所属地区；确定与所述待理赔账单所属地区对应的预存目标账单模板；
    第一对比单元，用于将所述待理赔账单与所述预存目标账单模板进行对比；
    确认单元，用于若所述待理赔账单的格式和所述预存目标账单模板一致，则确认所述待理赔账单为真实账单；若所述待理赔账单的格式和所述预存目标账单模板不一致，则确认所述待理赔账单为虚假账单。
  11. 如权利要求9所述的理赔账单识别装置，其特征在于，所述识别模块包括：
    获取单元，用于当根据所述对比结果确认所述待理赔账单为真实账单时，获取所述待理赔账单中各个字段对应的字段语音；
    第二对比单元，用于将所述字段语音与预置的语音识别文字库进行对比，得到对比结果；
    第二确定单元，用于根据所述对比结果确定所述语音识别文字库中与所述字段语音相似度最大的第一文字，将所述第一文字作为各个字段对应的字段信息。
  12. 如权利要求11所述的理赔账单识别装置，其特征在于，所述获取单元还用于在所述语音识别文字库中获取与所述字段语音相似度大于预设相似度对应的待选择文字；
    所述识别模块还包括：输出单元，用于输出所述待选择文字；
    所述第二确定单元还用于当侦测到选择所述待选择文字的选择指令时，根据所述选择指令确定所述待选择文字中与所述字段语音对应的第二文字，将所述第二文字作为各个字段对应的字段信息。
  13. 如权利要求9所述的理赔账单识别装置，其特征在于，所述提示模块包括：
    显示单元，用于显示所述字段信息；
    提示单元，用于提示所述审核人员审核所显示的所述字段信息；当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
  14. 如权利要求10所述的理赔账单识别装置，其特征在于，所述提示模块包括：
    显示单元，用于显示所述字段信息；
    提示单元，用于提示所述审核人员审核所显示的所述字段信息；当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
  15. 如权利要求11所述的理赔账单识别装置，其特征在于，所述提示模块包括：
    显示单元，用于显示所述字段信息；
    提示单元，用于提示所述审核人员审核所显示的所述字段信息；当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
  16. 如权利要求12所述的理赔账单识别装置，其特征在于，所述提示模块包括：
    显示单元，用于显示所述字段信息；
    提示单元，用于提示所述审核人员审核所显示的所述字段信息；当侦测到确认所述字段信息的确认指令时，提示所述审核人员根据所述字段信息执行理赔操作。
  17. 一种理赔账单识别设备，其特征在于，所述理赔账单识别设备包括存储器、处理器和存储在所述存储器上并可在所述处理器上运行的理赔账单识别程序，所述处理器用于调用所述存储器中存储的理赔账单识别程序，执行以下步骤：
    当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性；
    当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息；
    根据所述字段信息提示理赔系统的审核人员执行理赔操作。
  18. 如权利要求17所述的理赔账单识别设备，其特征在于，所述当获取到待理赔账单时，将所述待理赔账单与预存账单模板对比，根据对比所得的对比结果确认所述待理赔账单的真实性的步骤包括：
    当获取到待理赔账单时，确定所述待理赔账单所属地区；
    确定与所述待理赔账单所属地区对应的预存目标账单模板；
    将所述待理赔账单与所述预存目标账单模板进行对比；
    若所述待理赔账单的格式和所述预存目标账单模板一致，则确认所述待理赔账单为真实账单；
    若所述待理赔账单的格式和所述预存目标账单模板不一致，则确认所述待理赔账单为虚假账单。
  19. 如权利要求17所述的理赔账单识别设备，其特征在于，所述当根据所述对比结果确认所述待理赔账单为真实账单时，识别所述待理赔账单中的各个字段，得到各个字段对应的字段信息的步骤包括：
    当根据所述对比结果确认所述待理赔账单为真实账单时，获取所述待理赔账单中各个字段对应的字段语音；
    将所述字段语音与预置的语音识别文字库进行对比，得到对比结果；
    根据所述对比结果确定所述语音识别文字库中与所述字段语音相似度最大的第一文字，将所述第一文字作为各个字段对应的字段信息。
  20. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有理赔账单识别程序，所述理赔账单识别程序被处理器执行时实现如权利要求1所述的理赔账单识别方法的步骤。
PCT/CN2017/112096 2017-03-13 2017-11-21 理赔账单识别方法、装置、设备及计算机可读存储介质 WO2018166236A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710149822.XA CN107689006B (zh) 2017-03-13 2017-03-13 理赔账单识别方法和装置
CN201710149822.X 2017-03-13

Publications (1)

Publication Number Publication Date
WO2018166236A1 true WO2018166236A1 (zh) 2018-09-20

Family

ID=61152349

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/112096 WO2018166236A1 (zh) 2017-03-13 2017-11-21 理赔账单识别方法、装置、设备及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN107689006B (zh)
WO (1) WO2018166236A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110728142A (zh) * 2019-09-09 2020-01-24 上海凯京信达科技集团有限公司 一种流水文件识别方法、装置及计算机存储介质、电子设备

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110659970A (zh) * 2018-06-12 2020-01-07 百度在线网络技术（北京）有限公司 基于语音识别的账务信息处理方法、装置和电子设备
CN109785163B (zh) * 2018-12-13 2024-11-08 深圳平安医疗健康科技服务有限公司 一种理赔请求处理方法、服务器及计算机可读存储介质
CN109615536A (zh) * 2018-12-13 2019-04-12 平安医疗健康管理股份有限公司 基于ocr技术的保险理赔方法、装置、设备及可读存储介质
CN109710568A (zh) * 2018-12-18 2019-05-03 深圳壹账通智能科技有限公司 理赔文件格式标准化处理的方法、装置、介质及电子设备
CN110163603A (zh) * 2019-04-18 2019-08-23 平安城市建设科技(深圳)有限公司 信息验证方法、装置、设备及可读存储介质
CN110689322A (zh) * 2019-09-27 2020-01-14 成都知识视觉科技有限公司 一种适用于保险理赔流程的人工智能辅助核赔系统
CN111753817B (zh) * 2020-06-28 2024-01-26 国网数字科技控股有限公司 信息处理的方法及装置、电子设备及计算机可读存储介质
CN113610649A (zh) * 2021-08-10 2021-11-05 平安国际智慧城市科技股份有限公司 基于图像识别的审核方法、装置、设备及存储介质
CN114626950A (zh) * 2022-03-22 2022-06-14 深圳壹账通智能科技有限公司 保险理赔信息的录入方法、装置、计算机设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102054168A (zh) * 2010-12-23 2011-05-11 武汉大学苏州研究院 一种有价票据圆形印鉴识别方法
CN103729656A (zh) * 2014-01-22 2014-04-16 河北远东通信系统工程有限公司 印鉴印痕的鉴别方法及鉴别系统
CN104732231A (zh) * 2015-04-13 2015-06-24 广州广电运通金融电子股份有限公司 一种有价票据的识别方法
CN105095842A (zh) * 2014-05-22 2015-11-25 阿里巴巴集团控股有限公司 一种单据的信息识别的方法和装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101447017B (zh) * 2008-11-27 2010-12-08 浙江工业大学 一种基于版面分析的选票快速识别统计方法及系统
CN102737242A (zh) * 2012-06-12 2012-10-17 丰豪盈彩（北京）科技有限公司 应用于移动终端的票据自动识别方法和系统
US20150286860A1 (en) * 2014-04-02 2015-10-08 Le Moustache Club S.L. Method and Device for Generating Data from a Printed Document
CN105046553A (zh) * 2015-07-09 2015-11-11 胡昭 基于手机的云智能发票识别查验系统及方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102054168A (zh) * 2010-12-23 2011-05-11 武汉大学苏州研究院 一种有价票据圆形印鉴识别方法
CN103729656A (zh) * 2014-01-22 2014-04-16 河北远东通信系统工程有限公司 印鉴印痕的鉴别方法及鉴别系统
CN105095842A (zh) * 2014-05-22 2015-11-25 阿里巴巴集团控股有限公司 一种单据的信息识别的方法和装置
CN104732231A (zh) * 2015-04-13 2015-06-24 广州广电运通金融电子股份有限公司 一种有价票据的识别方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110728142A (zh) * 2019-09-09 2020-01-24 上海凯京信达科技集团有限公司 一种流水文件识别方法、装置及计算机存储介质、电子设备
CN110728142B (zh) * 2019-09-09 2023-12-22 上海斑马来拉物流科技有限公司 一种流水文件识别方法、装置及计算机存储介质、电子设备

Also Published As

Publication number Publication date
CN107689006B (zh) 2020-02-14
CN107689006A (zh) 2018-02-13

Similar Documents

Publication Publication Date Title
WO2018166236A1 (zh) 理赔账单识别方法、装置、设备及计算机可读存储介质
WO2019051899A1 (zh) 终端控制方法、装置及存储介质
WO2019051890A1 (zh) 终端控制方法、装置及计算机可读存储介质
WO2016082267A1 (zh) 语音识别方法和系统
WO2018233367A1 (zh) 立案方法、装置、终端和计算机可读存储介质
WO2019019378A1 (zh) 业务处理方法、装置、适配器及计算机可读存储介质
WO2019019374A1 (zh) 智能语音设备控制家电的方法、装置及系统
WO2018120457A1 (zh) 数据处理方法、装置、设备及计算机可读存储介质
WO2019231252A1 (en) Electronic device for authenticating user and operating method thereof
WO2016018004A1 (en) Method, apparatus, and system for providing translated content
WO2018227887A1 (zh) 视频广告投放、生成方法、装置、服务器及可读存储介质
WO2019085103A1 (zh) 培训管理方法、装置、计算机设备及存储介质
WO2018082482A1 (zh) 一种网络共享方法、接入网络方法及系统
WO2019019376A1 (zh) 业务流程管理方法、装置、设备及计算机可读存储介质
WO2019019340A1 (zh) 应用程序页面打开方法、装置、终端及可读存储介质
WO2019051895A1 (zh) 终端控制方法、装置及存储介质
WO2017201899A1 (zh) 连接蓝牙设备的方法及装置
WO2019114269A1 (zh) 一种节目续播方法、电视设备及计算机可读存储介质
WO2019051866A1 (zh) 权益信息管理方法、装置、设备及计算机可读存储介质
WO2018149191A1 (zh) 保单核保的方法、装置、设备及计算机可读存储介质
WO2018120459A1 (zh) 验证图像真伪的方法、装置、设备、存储介质及服务端
WO2019051934A1 (zh) 业务人员考核方法、考核平台和计算机可读存储介质
WO2019062194A1 (zh) 家电设备及其控制方法、系统及计算机可读存储介质
WO2018233221A1 (zh) 多窗口声音输出方法、电视机以及计算机可读存储介质
WO2018036153A1 (zh) 提醒消息的展示方法、装置、设备及计算机可读存储介质

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: 17900425

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 09/12/2019)

122 Ep: pct application non-entry in european phase

Ref document number: 17900425

Country of ref document: EP

Kind code of ref document: A1

点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载