WO2018184300A1 - 信息处理方法、信息处理装置及计算机可读存储介质 - Google Patents

信息处理方法、信息处理装置及计算机可读存储介质 Download PDF

Info

Publication number
WO2018184300A1
WO2018184300A1 PCT/CN2017/089320 CN2017089320W WO2018184300A1 WO 2018184300 A1 WO2018184300 A1 WO 2018184300A1 CN 2017089320 W CN2017089320 W CN 2017089320W WO 2018184300 A1 WO2018184300 A1 WO 2018184300A1
Authority
WO
WIPO (PCT)
Prior art keywords
case
score
information
information item
evaluation model
Prior art date
Application number
PCT/CN2017/089320
Other languages
English (en)
French (fr)
Inventor
彭舜东
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 WO2018184300A1 publication Critical patent/WO2018184300A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08Insurance

Definitions

  • the present invention relates to the field of information processing technologies, and in particular, to an information processing method, an information processing apparatus, and a computer readable storage medium.
  • the present invention provides an information processing method and an information processing apparatus, so that a related person can conduct a survey of a claim case more specifically.
  • a first aspect of the present invention provides an information processing method, where the information processing method includes:
  • a second aspect of the present invention provides an information processing apparatus, where the information processing apparatus includes:
  • a claim reason determining unit configured to determine a reason for claim settlement of the claim case to be processed
  • an obtaining unit configured to acquire a preset evaluation model corresponding to the reason for the claim application determined by the claim reason determining unit, wherein the foregoing evaluation model is based on a historical claim case of the same claim application reason Constructing, and the above evaluation model indicates a weighting coefficient of at least two information items, and the at least two information items are required fields for applying for a claim;
  • a calculating unit configured to calculate a score of the claim case based on a weight coefficient of each information item in the evaluation model acquired by the acquiring unit, and information recorded by a corresponding information item of the claim case;
  • the storage unit is configured to store the score of the claim case calculated by the calculating unit in association with the claim case.
  • a third aspect of the present invention provides another information processing apparatus, including a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor executes the computer program ⁇ Implement the following steps:
  • a fourth aspect of the present invention provides a computer readable storage medium, the computer program being executed by a processor, implementing the following steps:
  • the score of the claim case includes: [0026] converting the information entered in the corresponding information item of the claim case into a score of the corresponding information item;
  • the solution of the present invention constructs an evaluation model based on historical claims cases of the same claims application reason, and obtains an evaluation model corresponding to the reason for the claims application of the claim case for the claim case to be processed, and Calculating the score of the claim case based on the weight coefficient of each information item in the obtained evaluation model and the information entered in the corresponding information item of the claim case, and storing the score of the claim case in association with the claim case, thereby causing related personnel
  • the investigation of the claims case can be conducted in a targeted manner based on the score associated with the claim case, which can reduce the unnecessary waste of human resources to a certain extent.
  • FIG. 1 is a schematic flow chart of an embodiment of an information processing method provided by the present invention.
  • FIG. 2 is a schematic flow chart of another embodiment of an information processing method provided by the present invention.
  • FIG. 3 is a schematic structural diagram of an embodiment of an information processing apparatus according to the present invention.
  • FIG. 4 is a schematic structural diagram of another embodiment of an information processing apparatus according to the present invention.
  • FIG. 5 is a schematic structural diagram of still another embodiment of an information processing apparatus according to the present invention.
  • FIG. 6 is a schematic structural diagram of still another embodiment of an information processing apparatus according to the present invention.
  • An embodiment of the present invention describes an information processing method.
  • the information processing method in the embodiment of the present invention includes:
  • Step 101 Determine a reason for claim settlement of the claim case to be processed
  • the claim case to be processed refers to a claim case that has submitted an application but has not been investigated and investigated.
  • the method may include: determining a claim case currently submitted for review as a pending claims case. Further, it is also possible to impose a constraint on the payment condition, avoiding the handling of the claim case that does not meet the payment condition, and achieving the purpose of improving the processing efficiency and saving resources. Then, the claim case currently submitted for review is determined as a pending claim case, and specifically: the claim case currently submitted for review and meeting the preset payment condition is determined as a pending claim case.
  • the claim case currently submitted for review may be manually identified as a pending claim case, or the claim case currently submitted for review and meeting the preset claim condition may be manually identified as pending.
  • the claim case is not limited here.
  • the information processing method shown in FIG. 1 may be executed after the auxiliary entry is submitted, that is, after the auxiliary entry is submitted, the claim case submitted for review is determined as a pending claim case. And performing the information processing method shown in FIG. 1 for the claim case submitted for review; or, after the auxiliary entry is submitted, automatically detecting whether the claim case submitted for review meets the preset payment condition, and if yes, The claim case submitted for review is determined as the pending claims case, and the information processing method shown in Figure 1 is executed for the claim case submitted for review. If it is not met, the claim case submitted for review is not executed. The information processing method shown.
  • auxiliary entry submission refers to the action of submitting the review after the completion of the information required to complete the claim application.
  • the execution of the information processing method shown in FIG. 1 is triggered based on the asynchronous task table, and the process is as follows:
  • an asynchronous task is inserted into the preset asynchronous task table, and the asynchronous task is inserted. Used to trigger the execution of the information processing method shown in FIG. 1.
  • the claim case submitted for review may be stored as a pending claim case in a preset database, and then periodically or periodically, for the claim case to be processed stored in the database, Parallel or serial execution of the information processing method shown in FIG.
  • the claim case submitted for review and meeting the payment condition may be stored as a pending claim case in a preset database, and then periodically or periodically targeted to the database.
  • the pending claim case stored in parallel, or serially or serially executes the information processing method shown in FIG. 1; or, the claim case submitted for review may be stored in a preset database, and then periodically or periodically targeted to the database.
  • the reasons for the claim application include, but are not limited to, the following reasons: accidental death, disease death, major illness, accidental medical treatment, disease medical treatment.
  • the reason for the claim of the claim case may be determined based on the case information of the claim case to be processed.
  • Step 102 Obtain a preset evaluation model corresponding to the reason for the claim application.
  • the evaluation model is pre-built based on historical claim cases of the same claim application reason, and the evaluation model indicates weight coefficients of at least two information items, and the at least two information items are required fields of the claim settlement ⁇ .
  • the weighting coefficients of the at least two information items are constructed based on the historical claims case of the corresponding claim application reason, for example, may be determined based on the relationship between the investigation rate of the historical claims case and the corresponding information item based on the reason for the corresponding claim application.
  • the SAS system the statistical analysis system of SAS
  • the big data technology the historical claims cases of various claim application reasons can be analyzed and summarized, and the evaluation model corresponding to the reason of the claim application is summarized.
  • the at least two information items may be divided into four dimensions, and the information items included in each dimension may be referred to as follows:
  • the customer risk dimension may include, but is not limited to, the following information items: age, gender, occupation, whether there are past claims, and the like.
  • the salesperson risk dimension may include, but is not limited to, the following information items: whether the claim occurrence rate is abnormal, whether the disease occurrence rate is abnormal, whether it is a blacklist salesperson, or the like.
  • Policy risk dimension which may include but is not limited to the following information items: insurance coverage, risk insurance amount, insurance amount/premium, cost insurance grade/number of copies, and the like.
  • the accident risk dimension may include, but is not limited to, the following information items: the day of the report, the day of the accident, the date of the application for the settlement of the accident, the main disease category, the hospital for treatment, whether the insurance is different.
  • Step 103 Calculate a score of the claim case based on the obtained weight coefficient of each information item in the evaluation model and the information entered in the corresponding information item of the claim case;
  • the information entered in the corresponding information item of the claim case may be first converted into a score of the corresponding information item, and then based on the obtained weight coefficient and corresponding information of each information item in the evaluation model.
  • the score of the item calculates the score of the above claim case.
  • the score of the claim case may be calculated by using a weighted summation method.
  • Step 103 includes: converting information recorded by the corresponding information item of the claim case into a score of the corresponding information item; performing weighting calculation based on the weight coefficient of each information item in the evaluation model and the score of the corresponding information item of the claim case And, get the score of the above claims case.
  • XB represents the score obtained by weighted summation
  • A the coefficient represents the weight coefficient of the information item A
  • A the value represents the information item A
  • the A 2 coefficient represents the information item A 2
  • the weight coefficient, the A 2 value represents the score obtained by converting the information entered in the information item A 2
  • the A N coefficient represents the weight coefficient of the information item
  • N is a natural number greater than 2, indicating a preset fixed constant. In other embodiments, 1 ⁇ may also take 0.
  • the weight coefficient of each information item and the above claim based on the above evaluation model After the weighted summation of the scores of the corresponding information items of the case, the scores obtained by the weighted summation can also be subjected to logistic regression calculation. , the score obtained by the logistic regression is used as the score of the above claim case.
  • the score obtained by the weighted summation may be subjected to a logistic regression calculation based on the second formula, where the second formula is specifically: SCOR E ⁇ l/il+expi-l ⁇ XB)) , wherein SCORE i represents logistic regression
  • SCORE i represents logistic regression
  • XB represents the score obtained by weighted summation.
  • the score of the claim case may be calculated by using a weighted averaging method.
  • Step 103 includes: converting information recorded by the corresponding information item of the claim case into a score of the corresponding information item; performing weighting calculation based on the weight coefficient of each information item in the evaluation model and the score of the corresponding information item of the claim case The average value is obtained from the above claims case.
  • XBP represents the score obtained by weighted summation
  • A the coefficient represents the weight of the information item
  • A the value represents the information item A, the score obtained by the information entered
  • the A 2 coefficient represents the weight of the information item A 2 Coefficient
  • a 2 value represents the score obtained by converting the information entered in information item A 2
  • a N coefficient represents the weight coefficient of the information item
  • N is a natural number greater than 2
  • 1 ⁇ 2 represents a preset fixed constant . In other embodiments, 1 ⁇ 2 may also take zero.
  • the weight coefficient of each information item and the above claim based on the above evaluation model After the weighted averaging of the scores of the corresponding information items of the case, the scores obtained by the weighted summation may be subjected to logistic regression calculation, and the scores obtained by the logistic regression calculation are used as the scores of the above claim cases.
  • SCORE 2 represents logic
  • XBP represents the score obtained by weighted averaging.
  • Step 104 Associate the score of the claim case with the claim case
  • step 104 the score of the claim case calculated in step 103 is stored in association with the claim case, so that the relevant person can conduct the investigation of the claim case in a targeted manner based on the score associated with the claim case.
  • the claim case is highlighted or the reminder information indicating the priority review is output, so that the relevant personnel can conduct the investigation of the claim case more specifically.
  • the types of the above reminder information include, but are not limited to, one or a combination of two or more of the following: Picture, text, voice.
  • the information processing method in the embodiment of the present invention may be implemented by an information processing device, and the information processing device may be integrated into a server, a personal computer, or other devices, which is not limited herein.
  • an evaluation model is constructed based on a historical claim case based on the same claim application reason, and an evaluation model corresponding to the reason for the claim of the claim case is obtained for the claim case to be processed. And calculating a score of the claim case based on the weight coefficient of each information item in the obtained evaluation model and the information entered in the corresponding information item of the claim case, and storing the score of the claim case in association with the claim case, thereby Relevant personnel can conduct targeted investigations of claims cases based on the scores associated with the claims cases, which can reduce unnecessary waste of human resources to a certain extent.
  • the embodiment of the present invention further detects the payment condition for the claim case currently submitted for review.
  • the information processing method in the embodiment of the present invention includes:
  • Step 201 Detect whether the current claim submitted for review meets the preset payment condition
  • the claim condition detection is performed on the claim case currently submitted for review, and when it is detected that the claim case submitted for review currently meets the preset payout condition, the process proceeds to step 202, otherwise, the step is entered.
  • Step 202 Determine a reason for claim settlement in the claim case
  • the reasons for the claim application include, but are not limited to, the following reasons: accidental death, disease death, major illness, accidental medical treatment, disease medical treatment.
  • the reason for the claim of the claim case may be determined based on the case information of the claim case.
  • Step 203 Obtain a preset evaluation model corresponding to the reason for the claim application.
  • the foregoing evaluation model is constructed in advance based on a historical claim case of the same claim application reason, and the evaluation model indicates a weighting coefficient of at least two information items, and the at least two information items are required fields of the claim settlement claim.
  • the weighting coefficients of the at least two information items are constructed based on the historical claims cases of the corresponding claim application reasons, for example, the investigation rate and correspondingness of the historical claims cases based on the reasons for the corresponding claims application
  • the relationship of the information items is determined. Specifically, based on the SAS system (SAS English Statistical Analysis System) and big data technology, the historical claims cases of various claim application reasons can be analyzed and summarized, and the evaluation model corresponding to the reason for the claim application is summarized.
  • the at least two information items may be divided into four dimensions, and the information items included in each dimension may be referred to as follows:
  • Customer risk dimension which may include, but is not limited to, the following information items: age, gender, occupation, whether there are past claims, and the like.
  • the salesperson risk dimension may include, but is not limited to, the following information items: whether the claim occurrence rate is abnormal, whether the disease occurrence rate is abnormal, whether it is a blacklist salesperson, or the like.
  • the policy risk dimension may include, but is not limited to, the following information items: insurance coverage, risk insurance amount, insurance amount/guarantee, cost insurance grade/number of copies, and the like.
  • the accident risk dimension may include, but is not limited to, the following information items: the day of the report, the day of the accident, the date of the application for the compensation, the main disease category, the hospital for treatment, and whether the insurance is different.
  • Step 204 Calculate a score of the claim case based on the obtained weight coefficient of each information item in the evaluation model and the information entered in the corresponding information item of the claim case;
  • the information entered in the corresponding information item of the claim case may be first converted into a score of the corresponding information item, and then based on the obtained weight coefficient and corresponding information of each information item in the evaluation model.
  • the score of the item calculates the score of the above claim case.
  • the score of the claim case may be calculated by using a weighted summation method.
  • Step 204 includes: converting the information entered in the corresponding information item of the claim case into a score of the corresponding information item. And obtaining a score of the claim case based on the weight coefficient of each information item in the evaluation model and the score of the corresponding information item of the above claim case.
  • XB represents the score obtained by weighted summation
  • A the coefficient represents the weight coefficient of the information item A
  • A the value represents the information item A
  • the A 2 coefficient represents the information item A 2
  • the weight coefficient, the A 2 value represents the score obtained by converting the information entered in the information item A 2
  • the A N coefficient represents the weight coefficient of the information item
  • N is a natural number greater than 2, indicating a preset fixed constant. In other embodiments, 1 ⁇ may also take 0.
  • the weight coefficient of each information item and the above claim based on the above evaluation model After the weighted summation of the scores of the corresponding information items of the case, the scores obtained by the weighted summation may be subjected to logistic regression calculation, and the scores obtained by the logistic regression calculation are used as the scores of the above claim cases.
  • the score obtained by the weighted summation may be subjected to a logistic regression calculation based on the second formula, where the second formula is specifically: SCOR E ⁇ l/il+expi-l ⁇ XB)) , wherein SCORE i represents logistic regression
  • SCORE i represents logistic regression
  • XB represents the score obtained by weighted summation.
  • the score of the claim case may be calculated by weighted averaging.
  • Step 204 includes: converting information recorded by the corresponding information item of the claim case into a score of the corresponding information item; performing weighting calculation based on the weight coefficient of each information item in the evaluation model and the score of the corresponding information item of the claim case The average value is obtained from the above claims case.
  • XBP represents the score obtained by weighted summation
  • A the coefficient represents the weight of the information item
  • A the value represents the information item A, the score obtained by the information entered
  • the A 2 coefficient represents the weight of the information item A 2 Coefficient
  • a 2 value represents the score obtained by converting the information entered in information item A 2
  • a N coefficient represents the weight coefficient of the information item
  • N is a natural number greater than 2
  • 1 ⁇ 2 represents a preset fixed constant . In other embodiments, 1 ⁇ 2 may also take zero.
  • the weight coefficient of each information item and the above claim based on the above evaluation model After the weights of the corresponding information items of the case are averaged, the weights can be summed.
  • the scores obtained are subjected to logistic regression calculation, and the scores obtained by the logistic regression are used as the scores of the above claim cases.
  • SCORE 2 represents logic
  • XBP represents the score obtained by weighted averaging.
  • Step 205 Store the score of the claim case in association with the claim case
  • step 205 the score of the claim case calculated in step 204 is stored in association with the claim case, so that the relevant person can carry out the investigation of the claim case in a targeted manner based on the score associated with the claim case.
  • the claim case is highlighted or the reminder information indicating the priority review is output, so that the relevant person can conduct the investigation of the claim case more specifically.
  • the types of the above reminder information include, but are not limited to, one or a combination of two or more of the following: picture, text, voice.
  • Step 206 End the current processing flow.
  • the information processing method in the embodiment of the present invention may be implemented by an information processing device, and the information processing device may be integrated into a server, a personal computer, or other devices, which is not limited herein.
  • an evaluation model is constructed based on a historical claim case based on the same claim application reason, and the claim case that is currently submitted for review and meets the preset payment condition is obtained by acquiring the preset claim case.
  • the evaluation model corresponding to the claim reason and based on the weight coefficient of each information item in the obtained evaluation model and the information entered in the corresponding information item of the claim case, the score of the claim case is calculated, and the score of the claim case is The claim case is stored in association, so that the relevant person can conduct a targeted investigation of the claim case based on the score associated with the claim case, which can reduce the unnecessary waste of human resources to a certain extent.
  • you can avoid The handling of claims cases that do not meet the payment conditions further improves information processing efficiency and saves resources.
  • the information processing apparatus 300 in the embodiment of the present invention includes:
  • a claim reason determining unit 301 configured to determine a reason for claim settlement of the claim case to be processed
  • the obtaining unit 302 is configured to acquire a preset evaluation model corresponding to the reason for the claim application determined by the claim reason determining unit, wherein the evaluation model is pre-built based on a historical claim case of the same claim application reason, and the evaluation model is Indicate a weighting coefficient of at least two information items, where the at least two information items are required fields for applying for a claim;
  • the calculating unit 303 is configured to calculate, according to the weight coefficient of each information item in the evaluation model acquired by the obtaining unit 302
  • the storage unit 304 is configured to store the score of the claim case calculated by the calculation unit 303 in association with the claim case.
  • the calculating unit 303 includes:
  • a score conversion unit 3031 configured to convert information recorded by the corresponding information item of the claim case into a score of the corresponding information item
  • the weighting and summing unit 3032 is configured to perform weighted summation based on the weight coefficient of each information item in the evaluation model acquired by the obtaining unit 302 and the score of the corresponding information item of the above-mentioned claim case converted by the score conversion unit 3031. , get the score of the above claims case.
  • the calculating unit 303 further includes: a logistic regression calculating unit 3033, configured to calculate the weighting and summing unit 3032.
  • the obtained score is subjected to logistic regression calculation; the calculation unit 303 is specifically configured to output the score calculated by the logistic regression calculation unit 3033 as the score of the above claim case.
  • the information processing apparatus in the embodiment of the present invention further includes: a case determining unit, configured to determine the claim case currently submitted for review as a pending claim case.
  • the case determining unit is specifically configured to: submit the current submission review and meet the preset payment condition
  • the claim case is determined as a pending claim case.
  • the information processing apparatus in the embodiment of the present invention may be specifically integrated into a server, a personal computer, or other devices, which is not limited herein.
  • the information processing apparatus in the embodiment of the present invention may be used to implement all the technical solutions in the foregoing method embodiments, and the functions of the various functional modules may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation thereof is implemented.
  • the process reference may be made to the related description in the foregoing embodiments, and the parts that are not detailed and mentioned in the embodiments of the present invention may be referred to the description of the foregoing method embodiments, and details are not described herein again.
  • an evaluation model is constructed based on a historical claim case based on the same claims application reason, and an evaluation model corresponding to the reason for the claims application of the claim case is obtained for the claim case to be processed. And calculating a score of the claim case based on the weight coefficient of each information item in the obtained evaluation model and the information entered in the corresponding information item of the claim case, and storing the score of the claim case in association with the claim case, thereby Relevant personnel can conduct targeted investigations of claims cases based on the scores associated with the claims cases, which can reduce unnecessary waste of human resources to a certain extent.
  • the information processing apparatus in the embodiment of the present invention includes: a memory 601, one or more processors 602 (only one is shown in FIG. 6). And a computer program stored on the memory 601 and operable on the processor.
  • the memory 601 is used to store software programs and modules
  • the processor 602 executes various functional applications and data processing by running software programs and units stored in the memory 601.
  • the processor 602 implements the following steps by running the above-described computer program stored in the memory 601:
  • an evaluation model corresponding to the reason for the claim application wherein the evaluation model is constructed in advance based on a historical claim case of the same claim application reason, and the evaluation model indicates a weight coefficient of at least two information items
  • the at least two information items are required fields for applying for claims;
  • the calculating the score of the claim case based on the weight coefficient of each information item in the evaluation model and the information entered in the corresponding information item of the claim case including:
  • the weighting coefficient of each information item in the evaluation model and the corresponding information item of the claim case The scores are weighted and summed to obtain the score of the claim case, and also includes:
  • the processor 602 performs The computer program is further configured to: before determining the reason for the claim application of the claim case to be processed, implementing the following steps: determining the claim case currently submitted for review as a pending claim case.
  • a claim case that is currently submitted for review and meets the preset payout condition is determined as a claim case to be processed.
  • the above information processing apparatus may further include: one or more input devices 603 (only one is shown in FIG. 6) and one or more output devices 604 (only shown in FIG. 6) One) .
  • the memory 60 1, the processor 602, the input device 603, and the output device 604 are connected by a bus 605.
  • the so-called processor 602 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (Digital Signal Processor) , DSP), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the input device 603 may include a keyboard, a touchpad, a fingerprint sensor (for collecting fingerprint information of the user and direction information of the fingerprint), a microphone, and the like, and the output device 604 may include a display, a speaker, and the like.
  • Memory 604 can include read only memory and random access memory and provides instructions and data to processor 401. Some or all of memory 604 may also include non-volatile random access memory. For example, the memory 404 can also store information of the device type.
  • the solution of the present invention constructs an evaluation model based on historical claims cases of the same claim application reason, and obtains an evaluation model corresponding to the reason for the claims application of the claim case for the claim case to be processed, and Calculating the score of the claim case based on the weight coefficient of each information item in the obtained evaluation model and the information entered in the corresponding information item of the claim case, and storing the score of the claim case in association with the claim case, thereby causing related personnel
  • the ability to conduct targeted investigations based on the scores associated with the claims case can reduce the unnecessary waste of human resources to a certain extent.
  • the present invention further provides a computer readable storage medium, which may be a computer readable storage medium included in the memory in the above embodiment; or may exist separately, not assembled into the terminal Computer readable storage medium.
  • the computer readable storage medium can be a non-transitory computer readable storage medium.
  • the computer readable storage medium described above stores one or more programs, which may be executed by one or more processors for use in
  • an evaluation model corresponding to the reason for the claim application wherein the evaluation model is constructed in advance based on a historical claim case of the same claim application reason, and the evaluation model indicates a weight coefficient of at least two information items
  • the at least two information items are required fields for applying for claims;
  • the calculating the score of the claim case based on the weight coefficient of each information item in the evaluation model and the information entered by the corresponding information item of the claim case including: [0130] converting information recorded by the corresponding information item of the claim case into a score of the corresponding information item;
  • the weighting coefficient of each information item in the evaluation model and the score of the corresponding information item of the claim case are weighted and summed, and the score of the claim case is obtained, and the method further includes:
  • a logistic regression calculation is performed on the score obtained by the weighted summation, and the score obtained by the logistic regression is used as the score of the claim case.
  • the computer program is executed by the processor, and is further configured to: perform the following steps before determining the reason for the claim of the claims file to be processed:
  • the claim case currently submitted for review is determined as a pending claim case, and the claim case that is currently submitted for review and meets the preset payment condition is determined as a pending claim case.
  • each functional unit and module described above is exemplified. In practical applications, the above functions may be assigned differently according to needs.
  • the functional unit and the module are completed, that is, the internal structure of the above device is divided into different functional units or modules to complete all or part of the functions described above.
  • Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit, and the integrated unit may be implemented by hardware.
  • Formal implementation can also be implemented in the form of software functional units.
  • the disclosed apparatus and method may be implemented in other ways.
  • the system embodiment described above is merely illustrative.
  • the division of the above module or unit is only a logical function division, and the actual implementation may have another division manner, for example, multiple units or components may be combined. Either can be integrated into another system, or some features can be ignored, or not executed.
  • the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in electrical, mechanical or other form.
  • the units described above as separate components may or may not be physically distributed, and the components displayed as the units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple networks. On the unit. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • the above-described integrated unit if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the present invention implements all or part of the processes in the foregoing embodiments, and may also be completed by a computer program to instruct related hardware.
  • the computer program may be stored in a computer readable storage medium, the computer program After being executed by the processor, the steps of the various method embodiments described above can be implemented.
  • the above computer program comprises computer program code
  • the computer program code may be in the form of source code, object code form, executable file or some intermediate form.
  • the computer readable medium may include: any entity or device capable of carrying the above computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a Read-Only Memory (ROM), a random Access memory (RAM, Random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • electrical carrier signals telecommunications signals
  • software distribution media software distribution media. It should be noted that the content contained in the above computer readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, computer readable storage The medium does not include electrical carrier signals and telecommunication signals.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种信息处理方法、信息处理装置及计算机可读存储介质,其中,上述信息处理方法包括:确定待处理的理赔案件的理赔申请原因;获取预设的与所述理赔申请原因对应的评估模型,其中,所述评估模型预先基于同一理赔申请原因的历史理赔案件构建,且所述评估模型指示至少两个信息项的权重系数,所述至少两个信息项为申请理赔时的必填项;基于获取到的所述评估模型中各信息项的权重系数,以及所述理赔案件的相应信息项所录入的信息,计算所述理赔案件的评分;将所述理赔案件的评分与所述理赔案件关联存储。本技术方案使得相关人员能更有针对性地进行理赔案件的调查。

Description

发明名称:信息处理方法、 信息处理装置及计算机可读存储介质 技术领域
[0001] 本发明涉及信息处理技术领域, 具体涉及一种信息处理方法、 信息处理装置及 计算机可读存储介质。
背景技术
[0002] 随着理赔业务量的不断上涨, 理赔申请量也随之增加。
[0003] 传统的理赔调査方案需要相关调査人员针对每一件理赔案件的理赔信息进行评 估审核, 理赔申请量的增加无疑给相关调査人员带来了很大地工作压力, 而针 对一些毫无意义的理赔案件的调査也会导致人力资源的不必要浪费。
技术问题
[0004] 本发明提供一种信息处理方法和信息处理装置, 使得相关人员能更有针对性地 进行理赔案件的调査。
问题的解决方案
技术解决方案
[0005] 本发明第一方面提供一种信息处理方法, 上述信息处理方法包括:
[0006] 确定待处理的理赔案件的理赔申请原因;
[0007] 获取预设的与上述理赔申请原因对应的评估模型, 其中, 上述评估模型预先基 于同一理赔申请原因的历史理赔案件构建, 且上述评估模型指示至少两个信息 项的权重系数, 上述至少两个信息项为申请理赔吋的必填项;
[0008] 基于获取到的上述评估模型中各信息项的权重系数, 以及上述理赔案件的相应 信息项所录入的信息, 计算上述理赔案件的评分;
[0009] 将上述理赔案件的评分与上述理赔案件关联存储。
[0010] 本发明第二方面提供一种信息处理装置, 上述信息处理装置包括:
[0011] 理赔原因确定单元, 用于确定待处理的理赔案件的理赔申请原因;
[0012] 获取单元, 用于获取预设的与上述理赔原因确定单元确定的理赔申请原因对应 的评估模型, 其中, 上述评估模型预先基于同一理赔申请原因的历史理赔案件 构建, 且上述评估模型指示至少两个信息项的权重系数, 上述至少两个信息项 为申请理赔吋的必填项;
[0013] 计算单元, 用于基于上述获取单元获取到的评估模型中各信息项的权重系数, 以及上述理赔案件的相应信息项所录入的信息, 计算上述理赔案件的评分;
[0014] 存储单元, 用于将上述计算单元计算得到的上述理赔案件的评分与上述理赔案 件关联存储。
[0015] 本发明第三方面提供另一种信息处理装置, 包括存储器, 处理器及存储在存储 器上并可在处理器上运行的计算机程序, 其特征在于, 所述处理器执行所述计 算机程序吋实现以下步骤:
[0016] 确定待处理的理赔案件的理赔申请原因;
[0017] 获取预设的与所述理赔申请原因对应的评估模型, 其中, 所述评估模型预先基 于同一理赔申请原因的历史理赔案件构建, 且所述评估模型指示至少两个信息 项的权重系数, 所述至少两个信息项为申请理赔吋的必填项;
[0018] 基于获取到的所述评估模型中各信息项的权重系数, 以及所述理赔案件的相应 信息项所录入的信息, 计算所述理赔案件的评分;
[0019] 将所述理赔案件的评分与所述理赔案件关联存储。
[0020] 本发明第四方面提供一种计算机可读存储介质, 该计算机程序被处理器执行吋 实现以下步骤:
[0021] 确定待处理的理赔案件的理赔申请原因;
[0022] 获取预设的与所述理赔申请原因对应的评估模型, 其中, 所述评估模型预先基 于同一理赔申请原因的历史理赔案件构建, 且所述评估模型指示至少两个信息 项的权重系数, 所述至少两个信息项为申请理赔吋的必填项;
[0023] 基于获取到的所述评估模型中各信息项的权重系数, 以及所述理赔案件的相应 信息项所录入的信息, 计算所述理赔案件的评分;
[0024] 将所述理赔案件的评分与所述理赔案件关联存储。
[0025] 基于本发明第四方面, 在第一种可能的实现方式中, 所述基于所述评估模型中 各信息项的权重系数, 以及所述理赔案件的相应信息项所录入的信息, 计算所 述理赔案件的评分, 包括: [0026] 将所述理赔案件的相应信息项所录入的信息转化为相应信息项的分值;
[0027] 基于所述评估模型中各信息项的权重系数和所述理赔案件的相应信息项的分值 进行加权求和, 得到所述理赔案件的评分。
发明的有益效果
有益效果
[0028] 由上可见, 本发明方案预先基于同一理赔申请原因的历史理赔案件构建评估模 型, 针对待处理的理赔案件, 通过获取预设的与该理赔案件的理赔申请原因对 应的评估模型, 并基于获取到的评估模型中各信息项的权重系数以及该理赔案 件的相应信息项所录入的信息, 计算该理赔案件的评分, 将该理赔案件的评分 与该理赔案件关联存储, 从而使得相关人员能够基于与该理赔案件关联的评分 有针对性地进行理赔案件的调査, 可在一定程度上减少人力资源的不必要浪费 对附图的简要说明
附图说明
[0029] 为了更清楚地说明本发明实施例或现有技术中的技术方案, 下面将对实施例或 现有技术描述中所需要使用的附图作简单地介绍, 显而易见地, 下面描述中的 附图仅仅是本发明的一些实施例, 对于本领域普通技术人员来讲, 在不付出创 造性劳动性的前提下, 还可以根据这些附图获得其他的附图。
[0030] 图 1为本发明提供的信息处理方法一个实施例流程示意图;
[0031] 图 2为本发明提供的信息处理方法另一个实施例流程示意图;
[0032] 图 3为本发明提供的信息处理装置一个实施例结构示意图;
[0033] 图 4为本发明提供的信息处理装置另一个实施例结构示意图;
[0034] 图 5为本发明提供的信息处理装置再一个实施例结构示意图;
[0035] 图 6为本发明提供的信息处理装置再一个实施例结构示意图。
本发明的实施方式
[0036] 为使得本发明的发明目的、 特征、 优点能够更加的明显和易懂, 下面将结合本 发明实施例中的附图, 对本发明实施例中的技术方案进行清楚、 完整地描述, 显然, 所描述的实施例仅仅是本发明一部分实施例, 而非全部实施例。 基于本 发明中的实施例, 本领域普通技术人员在没有做出创造性劳动前提下所获得的 所有其他实施例, 都属于本发明保护的范围。
[0037] 实施例一
[0038] 本发明实施例对一种信息处理方法进行描述, 请参阅图 1, 本发明实施例中的 信息处理方法包括:
[0039] 步骤 101、 确定待处理的理赔案件的理赔申请原因;
[0040] 本发明实施例中, 待处理的理赔案件是指已提交申请但未经调査审核的理赔案 件。 可选的, 步骤 101之前可包括: 将当前提交审核的理赔案件确定为待处理的 理赔案件。 进一步, 还可以进行赔付条件的约束, 避免对不符合赔付条件的理 赔案件的处理, 达到提高处理效率和节省资源的目的。 那么, 上述将当前提交 审核的理赔案件确定为待处理的理赔案件, 具体可为: 将当前提交审核且符合 预设的赔付条件的理赔案件确定为待处理的理赔案件。 当然, 在其它实现方式 中, 也可以由相关人员将当前提交审核的理赔案件手动标识为待处理的理赔案 件, 或者, 将当前提交审核且符合预设的赔付条件的理赔案件手动标识为待处 理的理赔案件, 此处不作限定。
[0041] 在一种应用场景中, 可以在辅助录入提交吋执行图 1所示的信息处理方法, 即 , 在辅助录入提交吋, 将本次提交审核的理赔案件确定为待处理的理赔案件, 并针对本次提交审核的理赔案件执行图 1所示的信息处理方法; 或者, 在辅助录 入提交吋, 自动检测本次提交审核的理赔案件是否符合预设的赔付条件, 若符 合, 则将本次提交审核的理赔案件确定为待处理的理赔案件, 并针对本次提交 审核的理赔案件执行图 1所示的信息处理方法, 若不符合, 则不针对本次提交审 核的理赔案件执行图 1所示的信息处理方法。 其中, 上述辅助录入提交是指完成 理赔申请所需信息的录入之后, 提交审核的动作。 具体地, 可以在辅助录入提 交吋, 基于异步任务表触发图 1所示的信息处理方法的执行, 其过程如下: 在辅 助录入提交吋, 向预设的异步任务表插入异步任务, 该异步任务用于触发图 1所 示的信息处理方法的执行。 [0042] 在另一种应用场景中, 可以将提交审核的理赔案件作为待处理的理赔案件存储 于预设的数据库中, 之后周期性或定期性针对该数据库中存储的待处理的理赔 案件, 并行或串行执行图 1所示的信息处理方法; 或者, 可以将提交审核且符合 赔付条件的理赔案件作为待处理的理赔案件存储于预设的数据库中, 之后周期 性或定期性针对该数据库中存储的待处理的理赔案件, 并行或串行执行图 1所示 的信息处理方法; 或者, 可以将提交审核的理赔案件存储于预设的数据库中, 之后周期性或定期性针对该数据库中存储的各个理赔案件, 检测各个理赔案件 是否符合预设的赔付条件, 将符合赔付条件的理赔案件作为待处理的理赔案件
, 之后针对待处理的理赔案件执行图 1所示的信息处理方法。
[0043] 在本发明实施例中, 理赔申请原因包括但不限于如下几种原因: 意外死亡、 疾 病死亡、 重大疾病、 意外医疗、 疾病医疗。 在步骤 101中, 可以基于待处理的理 赔案件的案件信息确定该理赔案件的理赔申请原因。
[0044] 步骤 102、 获取预设的与上述理赔申请原因对应的评估模型;
[0045] 其中, 上述评估模型预先基于同一理赔申请原因的历史理赔案件构建, 且上述 评估模型指示至少两个信息项的权重系数, 上述至少两个信息项为申请理赔吋 的必填项。 上述至少两个信息项的权重系数是基于相应理赔申请原因的历史理 赔案件构建, 例如, 可基于相应理赔申请原因的历史理赔案件的调査率和对应 信息项的关系确定。 具体地, 可以基于 SAS系统 (SAS的英文全文为 Statistics Analysis System) 和大数据技术对各种理赔申请原因的历史理赔案件进行分析整 理, 归纳出与理赔申请原因对应的评估模型。
[0046] 可选的, 上述至少两个信息项可以分为四个维度, 每个维度所包含的信息项可 参照如下:
[0047] 1.客户风险维度, 可包括但不限于如下信息项: 年齢, 性别, 职业, 是否有既 往理赔等。
[0048] 2.业务员风险维度, 可包括但不限于如下信息项: 理赔发生率是否异常, 疾病 发生率是否异常, 是否黑名单业务员等。
[0049] 3.保单风险维度, 可包括但不限于如下信息项: 投保吋间, 风险保额, 保额 /保 费, 费用险档次 /份数等。 [0050] 4.事故风险维度, 可包括但不限于如下信息项: 报案日距事故日吋间, 申请理 赔距事故日吋间, 主要疾病类别, 就诊医院, 是否异地出险等。
[0051] 需要说明的是, 上述信息项仅是示意, 而并非穷举, 在实际应用中, 可以根据 实际情况增刪信息项, 此处不作限定。 由于不同的评估模型为预先针对不同的 理赔申请原因构建, 因此, 不同评估模型可能不同, 当然, 也不排除因偶然因 素而出现相同的评估模型。
[0052] 步骤 103、 基于获取到的上述评估模型中各信息项的权重系数, 以及上述理赔 案件的相应信息项所录入的信息, 计算上述理赔案件的评分;
[0053] 本发明实施例中, 可先将上述理赔案件的相应信息项所录入的信息转化为相应 信息项的分值, 然后基于获取到的上述评估模型中各信息项的权重系数和相应 信息项的分值计算上述理赔案件的评分。
[0054] 可选的, 预先设定各信息项的可能值 (可能值也即可能录入的信息) 与分值之 间的对应关系, 或者设定各信息项的可能值所在的区间与分值之间的对应关系
, 以便基于该对应关系, 将上述理赔案件的相应信息项所录入的信息转化为相 应信息项的分值。
[0055] 在一种应用场景中, 可以采用加权求和的方式计算上述理赔案件的评分。 步骤 103包括: 将上述理赔案件的相应信息项所录入的信息转化为相应信息项的分值 ; 基于上述评估模型中各信息项的权重系数和上述理赔案件的相应信息项的分 值进行加权求和, 得到上述理赔案件的评分。 具体地, 步骤 103可以根据第一公 式计算上述理赔案件的评分, 上述第一公式为: 8= 1系数* 1值+ 2系数*八2 值 + .....八^系数^^ ^直+!^。 其中, XB表示加权求和得到的分数, A ,系数表示信 息项 A ,的权重系数, A ,值表示信息项 A ,所录入的信息转化得到的分值, A 2系 数表示信息项 A 2的权重系数, A 2值表示信息项 A 2所录入的信息转化得到的分值 , 以此类推, A N系数表示信息项 的权重系数, N为大于 2的自然数, 表示 预设的固定常量。 在其它实施例中, 1^也可以取0。 进一步, 为了将上述理赔案 件的评分约束在 0到 1的范围内, 以便于该评分后续能更好地被调用, 本应用场 景中, 在基于上述评估模型中各信息项的权重系数和上述理赔案件的相应信息 项的分值进行加权求和之后, 还可以对加权求和得到的分数进行逻辑回归计算 , 将逻辑回归计算得到的分数作为上述理赔案件的评分。 具体地, 可以基于第 二公式对加权求和得到的分数进行逻辑回归计算, 上述第二公式具体为: SCOR E ^l/il+expi-l^^XB)) , 其中, SCORE i表示逻辑回归计算得到的分数, XB表示 加权求和得到的分数。
[0056] 在另一种应用场景中, 可以采用加权求平均值的方式计算上述理赔案件的评分 。 步骤 103包括: 将上述理赔案件的相应信息项所录入的信息转化为相应信息项 的分值; 基于上述评估模型中各信息项的权重系数和上述理赔案件的相应信息 项的分值进行加权求平均值, 得到上述理赔案件的评分。 具体地, 步骤 103可以 根据第三公式计算上述理赔案件的评分, 上述第三公式为: XBP= 系数 值 +A 2系数 * 2值+ ..... ^系数* ^直) /N+L 2。 其中, XBP表示加权求和得到的 分数, A ,系数表示信息项 ,的权重系数, A ,值表示信息项 A ,所录入的信息转 化得到的分值, A 2系数表示信息项 A 2的权重系数, A 2值表示信息项 A 2所录入 的信息转化得到的分值, 以此类推, A N系数表示信息项 的权重系数, N为大 于 2的自然数, 1^ 2表示预设的固定常量。 在其它实施例中, 1^ 2也可以取 0。 进一 步, 为了将上述理赔案件的评分约束在 0到 1的范围内, 以便于该评分后续能更 好地被调用, 本应用场景中, 在基于上述评估模型中各信息项的权重系数和上 述理赔案件的相应信息项的分值进行加权求平均值之后, 还可以对加权求和得 到的分数进行逻辑回归计算, 将逻辑回归计算得到的分数作为上述理赔案件的 评分。 具体地, 可以基于第四公式对加权求和得到的分数进行逻辑回归计算, 上述第四公式具体为: SCORE 2=l/(l+exp(-l*XBP)), 其中, SCORE 2表示逻辑 回归计算得到的分数, XBP表示加权求平均值得到的分数。
[0057] 步骤 104、 将上述理赔案件的评分与上述理赔案件关联存储;
[0058] 在步骤 104中, 将步骤 103计算得到的上述理赔案件的评分与上述理赔案件关联 存储, 以便相关人员能够基于与该理赔案件关联的评分有针对性地进行理赔案 件的调査。
[0059] 可选的, 针对评分超过预先的评分阈值的理赔案件, 对该理赔案件进行加显处 理或输出指示优先审核的提醒信息, 以便相关人员可以更有针对性地进行理赔 案件的调査。 上述提醒信息的类型包括但不限于如下一种或两种以上的组合: 图片、 文字、 语音。
[0060] 需要说明的是, 本发明实施例中的信息处理方法可以由信息处理装置实现, 该 信息处理装置具体可以集成在服务器、 个人计算机或其它设备中, 此处不作限 定。
[0061] 由上可见, 本发明实施例中预先基于同一理赔申请原因的历史理赔案件构建评 估模型, 针对待处理的理赔案件, 通过获取预设的与该理赔案件的理赔申请原 因对应的评估模型, 并基于获取到的评估模型中各信息项的权重系数以及该理 赔案件的相应信息项所录入的信息, 计算该理赔案件的评分, 将该理赔案件的 评分与该理赔案件关联存储, 从而使得相关人员能够基于与该理赔案件关联的 评分有针对性地进行理赔案件的调査, 可在一定程度上减少人力资源的不必要 浪费。
[0062] 实施例二
[0063] 本发明实施例与实施例一的区别在于, 本发明实施例进一步对当前提交审核的 理赔案件进行赔付条件的检测。 具体地, 请参阅图 2, 本发明实施例中的信息处 理方法包括:
[0064] 步骤 201、 检测当前提交审核的理赔案件是否符合预设的赔付条件;
[0065] 本发明实施例中, 对当前提交审核的理赔案件进行赔付条件检测, 当检测到当 前提交审核的理赔案件符合预设的赔付条件吋, 进入步骤 202, 否则, 进入步骤
205。
[0066] 步骤 202、 确定上述理赔案件的理赔申请原因;
[0067] 本发明实施例中, 理赔申请原因包括但不限于如下几种原因: 意外死亡、 疾病 死亡、 重大疾病、 意外医疗、 疾病医疗。 在步骤 202中, 可以基于上述理赔案件 的案件信息确定该理赔案件的理赔申请原因。
[0068] 步骤 203、 获取预设的与上述理赔申请原因对应的评估模型;
[0069] 其中, 上述评估模型预先基于同一理赔申请原因的历史理赔案件构建, 且上述 评估模型指示至少两个信息项的权重系数, 上述至少两个信息项为申请理赔吋 的必填项。 上述至少两个信息项的权重系数是基于相应理赔申请原因的历史理 赔案件构建, 例如, 可基于相应理赔申请原因的历史理赔案件的调査率和对应 信息项的关系确定。 具体地, 可以基于 SAS系统 (SAS的英文全文为 Statistics Analysis System) 和大数据技术对各种理赔申请原因的历史理赔案件进行分析整 理, 归纳出与理赔申请原因对应的评估模型。
[0070] 可选的, 上述至少两个信息项可以分为四个维度, 每个维度所包含的信息项可 参照如下:
[0071] 1.客户风险维度, 可包括但不限于如下信息项: 年齢, 性别, 职业, 是否有既 往理赔等。
[0072] 2.业务员风险维度, 可包括但不限于如下信息项: 理赔发生率是否异常, 疾病 发生率是否异常, 是否黑名单业务员等。
[0073] 3.保单风险维度, 可包括但不限于如下信息项: 投保吋间, 风险保额, 保额 /保 费, 费用险档次 /份数等。
[0074] 4.事故风险维度, 可包括但不限于如下信息项: 报案日距事故日吋间, 申请理 赔距事故日吋间, 主要疾病类别, 就诊医院, 是否异地出险等。
[0075] 需要说明的是, 上述信息项仅是示意, 而并非穷举, 在实际应用中, 可以根据 实际情况增刪信息项, 此处不作限定。 由于不同的评估模型为预先针对不同的 理赔申请原因构建, 因此, 不同评估模型可能不同, 当然, 也不排除因偶然因 素而出现相同的评估模型。
[0076] 步骤 204、 基于获取到的上述评估模型中各信息项的权重系数, 以及上述理赔 案件的相应信息项所录入的信息, 计算上述理赔案件的评分;
[0077] 本发明实施例中, 可先将上述理赔案件的相应信息项所录入的信息转化为相应 信息项的分值, 然后基于获取到的上述评估模型中各信息项的权重系数和相应 信息项的分值计算上述理赔案件的评分。
[0078] 可选的, 预先设定各信息项的可能值 (可能值也即可能录入的信息) 与分值之 间的对应关系, 或者设定各信息项的可能值所在的区间与分值之间的对应关系
, 以便基于该对应关系, 将上述理赔案件的相应信息项所录入的信息转化为相 应信息项的分值。
[0079] 在一种应用场景中, 可以采用加权求和的方式计算上述理赔案件的评分。 步骤 204包括: 将上述理赔案件的相应信息项所录入的信息转化为相应信息项的分值 ; 基于上述评估模型中各信息项的权重系数和上述理赔案件的相应信息项的分 值进行加权求和, 得到上述理赔案件的评分。 具体地, 步骤 204可以根据第一公 式计算上述理赔案件的评分, 上述第一公式为: 8= 1系数* 1值+ 2系数*八2 值 + .....八^系数*八^直+!^。 其中, XB表示加权求和得到的分数, A ,系数表示信 息项 A ,的权重系数, A ,值表示信息项 A ,所录入的信息转化得到的分值, A 2系 数表示信息项 A 2的权重系数, A 2值表示信息项 A 2所录入的信息转化得到的分值 , 以此类推, A N系数表示信息项 的权重系数, N为大于 2的自然数, 表示 预设的固定常量。 在其它实施例中, 1^也可以取0。 进一步, 为了将上述理赔案 件的评分约束在 0到 1的范围内, 以便于该评分后续能更好地被调用, 本应用场 景中, 在基于上述评估模型中各信息项的权重系数和上述理赔案件的相应信息 项的分值进行加权求和之后, 还可以对加权求和得到的分数进行逻辑回归计算 , 将逻辑回归计算得到的分数作为上述理赔案件的评分。 具体地, 可以基于第 二公式对加权求和得到的分数进行逻辑回归计算, 上述第二公式具体为: SCOR E ^l/il+expi-l^^XB)) , 其中, SCORE i表示逻辑回归计算得到的分数, XB表示 加权求和得到的分数。
在另一种应用场景中, 可以采用加权求平均值的方式计算上述理赔案件的评分 。 步骤 204包括: 将上述理赔案件的相应信息项所录入的信息转化为相应信息项 的分值; 基于上述评估模型中各信息项的权重系数和上述理赔案件的相应信息 项的分值进行加权求平均值, 得到上述理赔案件的评分。 具体地, 步骤 204可以 根据第三公式计算上述理赔案件的评分, 上述第三公式为: XBP= ( ^系数^^ , 值 +A 2系数 * 2值+ ..... ^系数^^ ^直) /N+L 2。 其中, XBP表示加权求和得到的 分数, A ,系数表示信息项 ,的权重系数, A ,值表示信息项 A ,所录入的信息转 化得到的分值, A 2系数表示信息项 A 2的权重系数, A 2值表示信息项 A 2所录入 的信息转化得到的分值, 以此类推, A N系数表示信息项 的权重系数, N为大 于 2的自然数, 1^ 2表示预设的固定常量。 在其它实施例中, 1^ 2也可以取 0。 进一 步, 为了将上述理赔案件的评分约束在 0到 1的范围内, 以便于该评分后续能更 好地被调用, 本应用场景中, 在基于上述评估模型中各信息项的权重系数和上 述理赔案件的相应信息项的分值进行加权求平均值之后, 还可以对加权求和得 到的分数进行逻辑回归计算, 将逻辑回归计算得到的分数作为上述理赔案件的 评分。 具体地, 可以基于第四公式对加权求和得到的分数进行逻辑回归计算, 上述第四公式具体为: SCORE 2=l/(l+exp(-l*XBP)), 其中, SCORE 2表示逻辑 回归计算得到的分数, XBP表示加权求平均值得到的分数。
[0081] 步骤 205、 将上述理赔案件的评分与上述理赔案件关联存储;
[0082] 在步骤 205中, 将步骤 204计算得到的上述理赔案件的评分与上述理赔案件关联 存储, 以便相关人员能够基于与该理赔案件关联的评分有针对性地进行理赔案 件的调査。
[0083] 可选的, 针对评分超过预先的评分阈值的理赔案件, 对该理赔案件进行加显处 理或输出指示优先审核的提醒信息, 以便相关人员可以更有针对性地进行理赔 案件的调査。 上述提醒信息的类型包括但不限于如下一种或两种以上的组合: 图片、 文字、 语音。
[0084] 步骤 206、 结束本次处理流程。
[0085] 需要说明的是, 本发明实施例中是当检测当前提交审核的理赔案件不符合预设 的赔付条件或者步骤 205执行之后结束本次处理流程。 当然, 在其它实施例中, 当检测当前提交审核的理赔案件不符合预设的赔付条件, 也可以不结束本次处 理流程而执行其它预设的步骤。 同理, 在步骤 205执行之后也可以不结束本次处 理流程而执行其它预设的步骤, 此处不作限定。
[0086] 需要说明的是, 本发明实施例中的信息处理方法可以由信息处理装置实现, 该 信息处理装置具体可以集成在服务器、 个人计算机或其它设备中, 此处不作限 定。
[0087] 由上可见, 本发明实施例中预先基于同一理赔申请原因的历史理赔案件构建评 估模型, 针对当前提交审核且符合预设的赔付条件的理赔案件, 通过获取预设 的与该理赔案件的理赔申请原因对应的评估模型, 并基于获取到的评估模型中 各信息项的权重系数以及该理赔案件的相应信息项所录入的信息, 计算该理赔 案件的评分, 将该理赔案件的评分与该理赔案件关联存储, 从而使得相关人员 能够基于与该理赔案件关联的评分有针对性地进行理赔案件的调査, 可在一定 程度上减少人力资源的不必要浪费。 另外, 通过赔付条件的约束, 可以避免对 不符合赔付条件的理赔案件的处理, 进一步提高了信息处理效率, 节省了资源
[0088] 实施例三
[0089] 本发明实施例中对一种信息处理装置进行描述, 请参阅图 3, 本发明实施例中 的信息处理装置 300包括:
[0090] 理赔原因确定单元 301, 用于确定待处理的理赔案件的理赔申请原因;
[0091] 获取单元 302, 用于获取预设的与上述理赔原因确定单元确定的理赔申请原因 对应的评估模型, 其中, 上述评估模型预先基于同一理赔申请原因的历史理赔 案件构建, 且上述评估模型指示至少两个信息项的权重系数, 上述至少两个信 息项为申请理赔吋的必填项;
[0092] 计算单元 303, 用于基于获取单元 302获取到的评估模型中各信息项的权重系数
, 以及上述理赔案件的相应信息项所录入的信息, 计算上述理赔案件的评分; [0093] 存储单元 304, 用于将计算单元 303计算得到的上述理赔案件的评分与上述理赔 案件关联存储。
[0094] 可选的, 在图 3所示实施例的基础上, 如图 4所示的信息处理装置 400, 计算单 元 303包括:
[0095] 分值转化单元 3031, 用于将上述理赔案件的相应信息项所录入的信息转化为相 应信息项的分值;
[0096] 加权求和单元 3032, 用于基于获取单元 302获取到的评估模型中各信息项的权 重系数和分值转化单元 3031转化得到的上述理赔案件的相应信息项的分值进行 加权求和, 得到上述理赔案件的评分。
[0097] 可选的, 在图 4所示实施例的基础上, 如图 5所示的信息处理装置 500, 计算单 元 303还包括: 逻辑回归计算单元 3033, 用于对加权求和单元 3032计算得到的分 数进行逻辑回归计算; 计算单元 303具体用于将逻辑回归计算单元 3033计算得到 的分数作为上述理赔案件的评分输出。
[0098] 可选的, 本发明实施例中的信息处理装置还包括: 案件确定单元, 用于将当前 提交审核的理赔案件确定为待处理的理赔案件。
[0099] 进一步, 上述案件确定单元具体用于: 将当前提交审核且符合预设的赔付条件 的理赔案件确定为待处理的理赔案件。
[0100] 需要说明的是, 本发明实施例中的信息处理装置具体可以集成在服务器、 个人 计算机或其它设备中, 此处不作限定。
[0101] 应理解, 本发明实施例中的信息处理装置可以用于实现上述方法实施例中的全 部技术方案, 其各个功能模块的功能可以根据上述方法实施例中的方法具体实 现, 其具体实现过程可参照上述实施例中的相关描述, 并且, 在本发明实施例 中没有详述和提及的部分, 可以参见上述方法实施例的描述, 此处不再赘述。
[0102] 由上可见, 本发明实施例中预先基于同一理赔申请原因的历史理赔案件构建评 估模型, 针对待处理的理赔案件, 通过获取预设的与该理赔案件的理赔申请原 因对应的评估模型, 并基于获取到的评估模型中各信息项的权重系数以及该理 赔案件的相应信息项所录入的信息, 计算该理赔案件的评分, 将该理赔案件的 评分与该理赔案件关联存储, 从而使得相关人员能够基于与该理赔案件关联的 评分有针对性地进行理赔案件的调査, 可在一定程度上减少人力资源的不必要 浪费。
[0103] 实施例四
[0104] 本发明实施例提供另一种信息处理装置, 请参阅图 6, 本发明实施例中的信息 处理装置包括: 存储器 601, 一个或多个处理器 602 (图 6中仅示出一个) 及存储 在存储器 601上并可在处理器上运行的计算机程序。 其中: 存储器 601用于存储 软件程序以及模块, 处理器 602通过运行存储在存储器 601的软件程序以及单元 , 从而执行各种功能应用以及数据处理。 具体地, 处理器 602通过运行存储在存 储器 601的上述计算机程序吋实现以下步骤:
[0105] 确定待处理的理赔案件的理赔申请原因;
[0106] 获取预设的与所述理赔申请原因对应的评估模型, 其中, 所述评估模型预先基 于同一理赔申请原因的历史理赔案件构建, 且所述评估模型指示至少两个信息 项的权重系数, 所述至少两个信息项为申请理赔吋的必填项;
[0107] 基于获取到的所述评估模型中各信息项的权重系数, 以及所述理赔案件的相应 信息项所录入的信息, 计算所述理赔案件的评分;
[0108] 将所述理赔案件的评分与所述理赔案件关联存储。 [0109] 假设上述为第一种可能的实施方式, 则在第一种可能的实施方式作为基础而提 供的第二种可能的实施方式中,
[0110] 所述基于所述评估模型中各信息项的权重系数, 以及所述理赔案件的相应信息 项所录入的信息, 计算所述理赔案件的评分, 包括:
[0111] 将所述理赔案件的相应信息项所录入的信息转化为相应信息项的分值;
[0112] 基于所述评估模型中各信息项的权重系数和所述理赔案件的相应信息项的分值 进行加权求和, 得到所述理赔案件的评分。
[0113] 在上述第二种可能的实现方式作为基础而提供的第三种可能的实施方式中, 所 述基于所述评估模型中各信息项的权重系数和所述理赔案件的相应信息项的分 值进行加权求和, 得到所述理赔案件的评分, 还包括:
[0114] 对所述加权求和得到的分数进行逻辑回归计算, 将逻辑回归计算得到的分数作 为所述理赔案件的评分。
[0115] 在上述第一种可能的实现方式, 或者上述第二种可能的实现方式, 或者上述第 三种可能的实现方式作为基础而提供的第四种可能的实施方式中, 处理器 602执 行所述计算机程序吋还用于在确定待处理的理赔案件的理赔申请原因之前, 实 现如下步骤: 将当前提交审核的理赔案件确定为待处理的理赔案件。
[0116] 在上述第四种可能的实现方式作为基础而提供的第五种可能的实施方式中, 所 述将当前提交审核的理赔案件确定为待处理的理赔案件, 为:
[0117] 将当前提交审核且符合预设的赔付条件的理赔案件确定为待处理的理赔案件。
[0118] 进一步, 如图 6所示, 上述信息处理装置还可包括: 一个或多个输入设备 603 ( 图 6中仅示出一个) 和一个或多个输出设备 604 (图 6中仅示出一个) 。 存储器 60 1、 处理器 602、 输入设备 603和输出设备 604通过总线 605连接。
[0119] 应当理解, 在本发明实施例中, 所称处理器 602可以是中央处理单元 (Central Processing Unit, CPU) , 该处理器还可以是其他通用处理器、 数字信号处理器 (Digital Signal Processor, DSP)、 专用集成电路 (Application Specific Integrated Circuit, ASIC)、 现成可编程门阵列(Field-Programmable Gate Array, FPGA)或 者其他可编程逻辑器件、 分立门或者晶体管逻辑器件、 分立硬件组件等。 通用 处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。 [0120] 输入设备 603可以包括键盘、 触控板、 指纹采传感器 (用于采集用户的指纹信 息和指纹的方向信息) 、 麦克风等, 输出设备 604可以包括显示器、 扬声器等。
[0121] 存储器 604可以包括只读存储器和随机存取存储器, 并向处理器 401提供指令和 数据。 存储器 604的一部分或全部还可以包括非易失性随机存取存储器。 例如, 存储器 404还可以存储设备类型的信息。
[0122] 由上可见, 本发明方案预先基于同一理赔申请原因的历史理赔案件构建评估模 型, 针对待处理的理赔案件, 通过获取预设的与该理赔案件的理赔申请原因对 应的评估模型, 并基于获取到的评估模型中各信息项的权重系数以及该理赔案 件的相应信息项所录入的信息, 计算该理赔案件的评分, 将该理赔案件的评分 与该理赔案件关联存储, 从而使得相关人员能够基于与该理赔案件关联的评分 有针对性地进行理赔案件的调査, 可在一定程度上减少人力资源的不必要浪费
[0123] 实施例五
[0124] 本发明还提供了一种计算机可读存储介质, 该计算机可读存储介质可以是上述 实施例中的存储器中所包含的计算机可读存储介质; 也可以是单独存在, 未装 配入终端中的计算机可读存储介质。 具体地, 该计算机可读存储介质可以为非 暂态计算机可读存储介质。 上述计算机可读存储介质存储有一个或者一个以上 程序, 所述一个或者一个以上程序可被一个或者一个以上的处理器执行以用于
[0125] 确定待处理的理赔案件的理赔申请原因;
[0126] 获取预设的与所述理赔申请原因对应的评估模型, 其中, 所述评估模型预先基 于同一理赔申请原因的历史理赔案件构建, 且所述评估模型指示至少两个信息 项的权重系数, 所述至少两个信息项为申请理赔吋的必填项;
[0127] 基于获取到的所述评估模型中各信息项的权重系数, 以及所述理赔案件的相应 信息项所录入的信息, 计算所述理赔案件的评分;
[0128] 将所述理赔案件的评分与所述理赔案件关联存储。
[0129] 可选的, 所述基于所述评估模型中各信息项的权重系数, 以及所述理赔案件的 相应信息项所录入的信息, 计算所述理赔案件的评分, 包括: [0130] 将所述理赔案件的相应信息项所录入的信息转化为相应信息项的分值;
[0131] 基于所述评估模型中各信息项的权重系数和所述理赔案件的相应信息项的分值 进行加权求和, 得到所述理赔案件的评分。
[0132] 可选的, 所述基于所述评估模型中各信息项的权重系数和所述理赔案件的相应 信息项的分值进行加权求和, 得到所述理赔案件的评分, 还包括:
[0133] 对所述加权求和得到的分数进行逻辑回归计算, 将逻辑回归计算得到的分数作 为所述理赔案件的评分。
[0134] 可选的, 所述计算机程序被处理器执行吋, 还用于在所述确定待处理的理赔案 件的理赔申请原因之前实现如下步骤:
[0135] 将当前提交审核的理赔案件确定为待处理的理赔案件。
[0136] 可选的, 所述将当前提交审核的理赔案件确定为待处理的理赔案件, 为: 将当 前提交审核且符合预设的赔付条件的理赔案件确定为待处理的理赔案件。
[0137] 所属领域的技术人员可以清楚地了解到, 为了描述的方便和简洁, 仅以上述各 功能单元、 模块的划分进行举例说明, 实际应用中, 可以根据需要而将上述功 能分配由不同的功能单元、 模块完成, 即将上述装置的内部结构划分成不同的 功能单元或模块, 以完成以上描述的全部或者部分功能。 实施例中的各功能单 元、 模块可以集成在一个处理单元中, 也可以是各个单元单独物理存在, 也可 以两个或两个以上单元集成在一个单元中, 上述集成的单元既可以采用硬件的 形式实现, 也可以采用软件功能单元的形式实现。 另外, 各功能单元、 模块的 具体名称也只是为了便于相互区分, 并不用于限制本申请的保护范围。 上述系 统中单元、 模块的具体工作过程, 可以参考前述方法实施例中的对应过程, 在 此不再赘述。
[0138] 在上述实施例中, 对各个实施例的描述都各有侧重, 某个实施例中没有详述或 记载的部分, 可以参见其它实施例的相关描述。
[0139] 本领域普通技术人员可以意识到, 结合本文中所公幵的实施例描述的各示例的 单元及算法步骤, 能够以电子硬件、 或者计算机软件和电子硬件的结合来实现 。 这些功能究竟以硬件还是软件方式来执行, 取决于技术方案的特定应用和设 计约束条件。 专业技术人员可以对每个特定的应用来使用不同方法来实现所描 述的功能, 但是这种实现不应认为超出本发明的范围。
[0140] 在本发明所提供的实施例中, 应该理解到, 所揭露的装置和方法, 可以通过其 它的方式实现。 例如, 以上所描述的系统实施例仅仅是示意性的, 例如, 上述 模块或单元的划分, 仅仅为一种逻辑功能划分, 实际实现吋可以有另外的划分 方式, 例如多个单元或组件可以结合或者可以集成到另一个系统, 或一些特征 可以忽略, 或不执行。 另一点, 所显示或讨论的相互之间的耦合或直接耦合或 通讯连接可以是通过一些接口, 装置或单元的间接耦合或通讯连接, 可以是电 性, 机械或其它的形式。
[0141] 上述作为分离部件说明的单元可以是或者也可以不是物理上分幵的, 作为单元 显示的部件可以是或者也可以不是物理单元, 即可以位于一个地方, 或者也可 以分布到多个网络单元上。 可以根据实际的需要选择其中的部分或者全部单元 来实现本实施例方案的目的。
[0142] 上述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用 吋, 可以存储在一个计算机可读取存储介质中。 基于这样的理解, 本发明实现 上述实施例方法中的全部或部分流程, 也可以通过计算机程序来指令相关的硬 件来完成, 上述的计算机程序可存储于一计算机可读存储介质中, 该计算机程 序在被处理器执行吋, 可实现上述各个方法实施例的步骤。 其中, 上述计算机 程序包括计算机程序代码, 上述计算机程序代码可以为源代码形式、 对象代码 形式、 可执行文件或某些中间形式等。 上述计算机可读介质可以包括: 能够携 带上述计算机程序代码的任何实体或装置、 记录介质、 U盘、 移动硬盘、 磁碟、 光盘、 计算机存储器、 只读存储器 (ROM, Read-Only Memory) 、 随机存取存 储器 (RAM, Random Access Memory) 、 电载波信号、 电信信号以及软件分发 介质等。 需要说明的是, 上述计算机可读存储介质包含的内容可以根据司法管 辖区内立法和专利实践的要求进行适当的增减, 例如在某些司法管辖区, 根据 立法和专利实践, 计算机可读存储介质不包括是电载波信号和电信信号。
[0143] 以上上述实施例仅用以说明本发明的技术方案, 而非对其限制; 尽管参照前述 实施例对本发明进行了详细的说明, 本领域的普通技术人员应当理解: 其依然 可以对前述各实施例所记载的技术方案进行修改, 或者对其中部分技术特征进 行等同替换; 而这些修改或者替换, 并不使相应技术方案的本质脱离本发明各 实施例技术方案的精神和范围, 均应包含在本发明的保护范围之内。

Claims

权利要求书
[权利要求 1] 一种信息处理方法, 其特征在于, 所述信息处理方法包括:
确定待处理的理赔案件的理赔申请原因;
获取预设的与所述理赔申请原因对应的评估模型, 其中, 所述评估模 型预先基于同一理赔申请原因的历史理赔案件构建, 且所述评估模型 指示至少两个信息项的权重系数, 所述至少两个信息项为申请理赔吋 的必填项;
基于获取到的所述评估模型中各信息项的权重系数, 以及所述理赔案 件的相应信息项所录入的信息, 计算所述理赔案件的评分; 将所述理赔案件的评分与所述理赔案件关联存储。
[权利要求 2] 根据权利要求 1所述的信息处理方法, 其特征在于, 所述基于所述评 估模型中各信息项的权重系数, 以及所述理赔案件的相应信息项所录 入的信息, 计算所述理赔案件的评分, 包括:
将所述理赔案件的相应信息项所录入的信息转化为相应信息项的分值 基于所述评估模型中各信息项的权重系数和所述理赔案件的相应信息 项的分值进行加权求和, 得到所述理赔案件的评分。
[权利要求 3] 根据权利要求 2所述的信息处理方法, 其特征在于, 所述基于所述评 估模型中各信息项的权重系数和所述理赔案件的相应信息项的分值进 行加权求和, 得到所述理赔案件的评分, 还包括: 对所述加权求和得到的分数进行逻辑回归计算, 将逻辑回归计算得到 的分数作为所述理赔案件的评分。
[权利要求 4] 根据权利要求 1至 3任一项所述的信息处理方法, 其特征在于, 所述确 定待处理的理赔案件的理赔申请原因, 之前包括: 将当前提交审核的理赔案件确定为待处理的理赔案件。
[权利要求 5] 根据权利要求 4所述的信息处理方法, 其特征在于, 所述将当前提交 审核的理赔案件确定为待处理的理赔案件, 为: 将当前提交审核且符合预设的赔付条件的理赔案件确定为待处理的理 赔案件。
[权利要求 6] —种信息处理装置, 其特征在于, 所述信息处理装置包括:
理赔原因确定单元, 用于确定待处理的理赔案件的理赔申请原因; 获取单元, 用于获取预设的与所述理赔原因确定单元确定的理赔申请 原因对应的评估模型, 其中, 所述评估模型预先基于同一理赔申请原 因的历史理赔案件构建, 且所述评估模型指示至少两个信息项的权重 系数, 所述至少两个信息项为申请理赔吋的必填项;
计算单元, 用于基于所述获取单元获取到的评估模型中各信息项的权 重系数, 以及所述理赔案件的相应信息项所录入的信息, 计算所述理 赔案件的评分;
存储单元, 用于将所述计算单元计算得到的所述理赔案件的评分与所 述理赔案件关联存储。
[权利要求 7] 根据权利要求 6所述的信息处理装置, 其特征在于,
所述计算单元包括:
分值转化单元, 用于将所述理赔案件的相应信息项所录入的信息转化 为相应信息项的分值;
加权求和单元, 用于基于所述获取单元获取到的评估模型中各信息项 的权重系数和所述分值转化单元转化得到的所述理赔案件的相应信息 项的分值进行加权求和, 得到所述理赔案件的评分。
[权利要求 8] 根据权利要求 7所述的信息处理装置, 其特征在于,
所述计算单元还包括: 逻辑回归计算单元, 用于对所述加权求和单元 计算得到的分数进行逻辑回归计算;
所述计算单元具体用于将所述逻辑回归计算单元计算得到的分数作为 所述理赔案件的评分输出。
[权利要求 9] 根据权利要求 6至 8任一项所述的信息处理装置, 其特征在于, 所述信 息处理装置还包括:
案件确定单元, 用于将当前提交审核的理赔案件确定为待处理的理赔 案件。 根据权利要求 9所述的信息处理装置, 其特征在于, 所述案件确定单 元具体用于: 将当前提交审核且符合预设的赔付条件的理赔案件确定 为待处理的理赔案件。
一种信息处理装置, 包括存储器, 处理器及存储在存储器上并可在处 理器上运行的计算机程序, 其特征在于, 所述处理器执行所述计算机 程序吋实现以下步骤: 确定待处理的理赔案件的理赔申请原因;
获取预设的与所述理赔申请原因对应的评估模型, 其中, 所述评估模 型预先基于同一理赔申请原因的历史理赔案件构建, 且所述评估模型 指示至少两个信息项的权重系数, 所述至少两个信息项为申请理赔吋 的必填项;
基于获取到的所述评估模型中各信息项的权重系数, 以及所述理赔案 件的相应信息项所录入的信息, 计算所述理赔案件的评分; 将所述理赔案件的评分与所述理赔案件关联存储。
根据权利要求 11所述的信息处理装置, 其特征在于, 所述基于所述评 估模型中各信息项的权重系数, 以及所述理赔案件的相应信息项所录 入的信息, 计算所述理赔案件的评分, 包括:
将所述理赔案件的相应信息项所录入的信息转化为相应信息项的分值
基于所述评估模型中各信息项的权重系数和所述理赔案件的相应信息 项的分值进行加权求和, 得到所述理赔案件的评分。
根据权利要求 12所述的信息处理装置, 其特征在于, 所述基于所述评 估模型中各信息项的权重系数和所述理赔案件的相应信息项的分值进 行加权求和, 得到所述理赔案件的评分, 还包括:
对所述加权求和得到的分数进行逻辑回归计算, 将逻辑回归计算得到 的分数作为所述理赔案件的评分。
根据权利要求 11至 13任一项所述的信息处理装置, 其特征在于, 所述 处理器执行所述计算机程序吋还用于在确定待处理的理赔案件的理赔 申请原因之前, 实现如下步骤: 将当前提交审核的理赔案件确定为待 处理的理赔案件。
[权利要求 15] 根据权利要求 14所述的信息处理装置, 其特征在于, 所述将当前提交 审核的理赔案件确定为待处理的理赔案件, 为: 将当前提交审核且符合预设的赔付条件的理赔案件确定为待处理的理 赔案件。
[权利要求 16] —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计算机 程序, 其特征在于, 所述计算机程序被处理器执行吋实现以下步骤: 确定待处理的理赔案件的理赔申请原因;
获取预设的与所述理赔申请原因对应的评估模型, 其中, 所述评估模 型预先基于同一理赔申请原因的历史理赔案件构建, 且所述评估模型 指示至少两个信息项的权重系数, 所述至少两个信息项为申请理赔吋 的必填项;
基于获取到的所述评估模型中各信息项的权重系数, 以及所述理赔案 件的相应信息项所录入的信息, 计算所述理赔案件的评分; 将所述理赔案件的评分与所述理赔案件关联存储。
[权利要求 17] 根据权利要求 16所述的计算机可读存储介质, 其特征在于, 所述基于 所述评估模型中各信息项的权重系数, 以及所述理赔案件的相应信息 项所录入的信息, 计算所述理赔案件的评分, 包括:
将所述理赔案件的相应信息项所录入的信息转化为相应信息项的分值 基于所述评估模型中各信息项的权重系数和所述理赔案件的相应信息 项的分值进行加权求和, 得到所述理赔案件的评分。
[权利要求 18] 根据权利要求 17所述的计算机可读存储介质, 其特征在于, 所述基于 所述评估模型中各信息项的权重系数和所述理赔案件的相应信息项的 分值进行加权求和, 得到所述理赔案件的评分, 还包括:
对所述加权求和得到的分数进行逻辑回归计算, 将逻辑回归计算得到 的分数作为所述理赔案件的评分。 [权利要求 19] 根据权利要求 16至 18任一项所述的计算机可读存储介质, 其特征在于 , 所述计算机程序被处理器执行吋, 还用于在所述确定待处理的理赔 案件的理赔申请原因之前实现如下步骤:
将当前提交审核的理赔案件确定为待处理的理赔案件。
[权利要求 20] 根据权利要求 19所述的计算机可读存储介质, 其特征在于, 所述将当 前提交审核的理赔案件确定为待处理的理赔案件, 为:
将当前提交审核且符合预设的赔付条件的理赔案件确定为待处理的理 赔案件。
PCT/CN2017/089320 2017-04-06 2017-06-21 信息处理方法、信息处理装置及计算机可读存储介质 WO2018184300A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710221784.4 2017-04-06
CN201710221784.4A CN107169869A (zh) 2017-04-06 2017-04-06 信息处理方法和信息处理装置

Publications (1)

Publication Number Publication Date
WO2018184300A1 true WO2018184300A1 (zh) 2018-10-11

Family

ID=59849810

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/089320 WO2018184300A1 (zh) 2017-04-06 2017-06-21 信息处理方法、信息处理装置及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN107169869A (zh)
WO (1) WO2018184300A1 (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107871284A (zh) * 2017-11-22 2018-04-03 平安科技(深圳)有限公司 风险理赔的评估方法及装置
CN111445261A (zh) * 2018-12-29 2020-07-24 达丰(上海)电脑有限公司 客户理赔案件的处理方法、系统、电子终端、及存储介质
CN116720829A (zh) * 2019-04-10 2023-09-08 创新先进技术有限公司 审核组成员评估方法及装置
CN110246046B (zh) * 2019-04-24 2023-01-10 创新先进技术有限公司 健康告知案例维护系统、方法以及装置
CN110675268A (zh) * 2019-08-14 2020-01-10 中国平安财产保险股份有限公司 风险客户的识别方法、装置和服务器
CN111144738A (zh) * 2019-12-24 2020-05-12 太平金融科技服务(上海)有限公司 信息处理方法、装置、计算机设备和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015017155A1 (en) * 2013-08-02 2015-02-05 Transamerica Corporation Categorizing life insurance applicants to determine suitable life insurance products
CN105374211A (zh) * 2015-12-09 2016-03-02 敏驰信息科技(上海)有限公司 基于多源数据计算驾驶风险与辅助车险定价的系统及方法
CN105488046A (zh) * 2014-09-16 2016-04-13 钛马信息网络技术有限公司 基于车辆保险业务的大数据分析系统
CN105678622A (zh) * 2016-01-07 2016-06-15 平安科技(深圳)有限公司 车险理赔照片的分析方法及系统
CN106204282A (zh) * 2015-05-04 2016-12-07 腾讯科技(深圳)有限公司 一种数据处理方法及装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102332143A (zh) * 2011-07-22 2012-01-25 大连亿创天地科技发展有限公司 一种在线保险理赔核实赔付方法及系统
CN106022924A (zh) * 2016-05-13 2016-10-12 中国建设银行股份有限公司 一种适用于客户风险评估的信息处理方法和系统
CN106296389A (zh) * 2016-07-28 2017-01-04 联动优势科技有限公司 一种用户信用度的评估方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015017155A1 (en) * 2013-08-02 2015-02-05 Transamerica Corporation Categorizing life insurance applicants to determine suitable life insurance products
CN105488046A (zh) * 2014-09-16 2016-04-13 钛马信息网络技术有限公司 基于车辆保险业务的大数据分析系统
CN106204282A (zh) * 2015-05-04 2016-12-07 腾讯科技(深圳)有限公司 一种数据处理方法及装置
CN105374211A (zh) * 2015-12-09 2016-03-02 敏驰信息科技(上海)有限公司 基于多源数据计算驾驶风险与辅助车险定价的系统及方法
CN105678622A (zh) * 2016-01-07 2016-06-15 平安科技(深圳)有限公司 车险理赔照片的分析方法及系统

Also Published As

Publication number Publication date
CN107169869A (zh) 2017-09-15

Similar Documents

Publication Publication Date Title
WO2018184300A1 (zh) 信息处理方法、信息处理装置及计算机可读存储介质
CN108615119B (zh) 一种异常用户的识别方法及设备
CN107679995B (zh) 电子装置、保险案件理赔审核方法及计算机可读存储介质
TW202020791A (zh) 理賠業務處理方法及裝置
CN109460944B (zh) 基于大数据的核保方法、装置、设备及可读存储介质
US20190311395A1 (en) Estimating click-through rate
CN109635029B (zh) 基于标签指标体系的数据处理方法、装置、设备及介质
TW202004636A (zh) 保險服務優化方法、系統及電腦程式產品
CA2913647C (en) Method of re-identification risk measurement and suppression on a longitudinal dataset
WO2019232892A1 (zh) 预测投保风险概率的方法、装置、计算机设备和存储介质
Li et al. Marginal modeling of cluster-period means and intraclass correlations in stepped wedge designs with binary outcomes
CN111489290A (zh) 一种人脸图像超分辨重建方法、装置及终端设备
JP2016099915A (ja) 与信審査用サーバと与信審査用システム及び与信審査用プログラム
WO2020000715A1 (zh) 基于指数特征提取的股指预测方法、服务器及存储介质
WO2019232821A1 (zh) 风控数据处理方法、装置、计算机设备及存储介质
Qiu et al. Estimating disease burden using Internet data
Guma et al. Risk factors for death among COVID-19 Patients admitted to isolation Units in Gedaref state, Eastern Sudan: a retrospective cohort study
Wilson et al. Quality of neurologic care in the United States: initial report from the Axon Registry
Shi et al. A forward and backward stagewise algorithm for nonconvex loss functions with adaptive lasso
CN110265127B (zh) 病种费用测算方法、装置及终端设备
US20150199781A1 (en) Patent Valuation System
CN109035033B (zh) 一种减保业务的信息处理方法及终端
CN109033161B (zh) 一种数据处理方法、服务器及计算机可读介质
WO2019214086A1 (zh) 访问规划方法、装置、终端设备及介质
Curran et al. Herpes zoster related healthcare burden and costs in immunocompromised (IC) and IC-free populations in England: an observational retrospective database analysis

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: 17904567

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 14.01.2020)

122 Ep: pct application non-entry in european phase

Ref document number: 17904567

Country of ref document: EP

Kind code of ref document: A1