WO2019100601A1 - 风险理赔的评估方法及装置 - Google Patents

风险理赔的评估方法及装置 Download PDF

Info

Publication number
WO2019100601A1
WO2019100601A1 PCT/CN2018/075677 CN2018075677W WO2019100601A1 WO 2019100601 A1 WO2019100601 A1 WO 2019100601A1 CN 2018075677 W CN2018075677 W CN 2018075677W WO 2019100601 A1 WO2019100601 A1 WO 2019100601A1
Authority
WO
WIPO (PCT)
Prior art keywords
type
preset
evaluation
parameter
logical
Prior art date
Application number
PCT/CN2018/075677
Other languages
English (en)
French (fr)
Inventor
蔡宁
和婷
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 WO2019100601A1 publication Critical patent/WO2019100601A1/zh

Links

Images

Classifications

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

Definitions

  • the present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for evaluating risk claims.
  • the insurance industry's underwriting personnel need to approve the proofreading case in order to accurately make claims and reduce the risk of claims.
  • the insured personnel in the process of evaluating claims cases include the loss and the nuclear damage. After the damage is determined, the nuclear damage personnel will review the results of their work. If there is no doubt, they will agree to the result. If there is any objection, Will be returned to prevent fraud.
  • the present application provides a method and an apparatus for evaluating risk claims, and the main purpose thereof is to solve the problem that an existing nuclear damage personnel can easily miss some high-risk cases through manual review when conducting a review of a claim case. Bring some economic losses.
  • a method for evaluating risk claims including:
  • the parsing the logic information to be evaluated in the claim information and the historical policy information includes: extracting the claim information and the historical policy information, respectively, the number of times, the number of types, the type of the fee, and the type of the attribute Corresponding logical parameter; determining whether the value of the logical parameter corresponding to the number of times, the number of types, the type of the fee, and the type of the attribute are respectively greater than a preset upper limit value, and/or less than a preset a lower limit value; if less than the preset upper limit value, and/or greater than the preset lower limit value, the logic corresponding to the number of times, the number of types, the type of the fee, and the attribute type
  • the parameter configures the number of intervals, and the number of intervals is used to distinguish parameters corresponding to the preset preset evaluation logic formula.
  • the matching according to the logic parameter and the preset evaluation logic, and counting the evaluation result of the claim case corresponding to the logic parameter includes: calculating the logic of the number of times according to the preset evaluation logic formula by using different interval numbers
  • the evaluation score corresponding to the parameter, and the preset evaluation logic formula is Where i is the number of intervals, x is the value of the logical parameter of the order type; and the evaluation score corresponding to the logical parameter of the number type is calculated according to the preset evaluation logic formula by different interval numbers, and the preset evaluation logic formula is Where i is the interval number, y is the value of the logical parameter of the number type; and the evaluation score corresponding to the logical parameter of the fee type is calculated according to the preset evaluation logic formula with different interval numbers, and the preset evaluation logic formula is Where i is the interval number, z is the value of the logical parameter of the expense type; and the evaluation score corresponding to the logical parameter of the attribute type is calculated according to the preset evaluation logic formula by different interval numbers, and the preset evaluation
  • the method further includes: generating an interval weight vector corresponding to the claim case according to the different claim product information, wherein the weight value corresponding to the fee type in the interval weight vector is respectively greater than the number of times, the number type, and the attribute type. Corresponding weights.
  • the method further includes: performing the evaluation result and the preset claim amount Comparing; if the comparison result is that the evaluation result is greater than two-thirds of the preset claim amount, the claim case is determined as a risk claim case, and the warning information is sent.
  • an apparatus for evaluating risk claims includes: an obtaining unit for acquiring claim information and historical policy information of an insured in a claim case; and an analyzing unit for parsing the claim information and the a logical parameter to be evaluated in the history policy information, wherein the logic parameter is used to reflect the situation in which the insured participates in the medical item in the claim case; the statistical unit is configured to match the preset evaluation logic according to the logic parameter, and The evaluation result of the claim case corresponding to the logical parameter is counted, and the preset evaluation logic is used to reflect the relationship between different logical parameters and different evaluation scores.
  • the parsing unit includes: an extracting module, configured to extract logical parameters corresponding to the number of times, the number of types, the type of the fee, and the type of the attribute in the claim information and the historical policy information; the determining module is configured to: Determining whether the value of the logical parameter corresponding to the number of times, the number of types, the type of the fee, and the type of the attribute are respectively greater than a preset upper limit value, and/or less than a preset lower limit value; a module, configured to determine, by the determining module, that the value of the logical parameter corresponding to the number of times, the number of types, the type of the fee, and the type of the attribute are respectively less than a preset upper limit value, and/or greater than a preset
  • the lower limit value is the number of logical parameter configuration intervals corresponding to the number of times, the number of types, the type of the fee, and the attribute type, and the number of intervals is used to distinguish the corresponding preset evaluation logic formula Parameters.
  • the statistic unit includes: a calculation module, configured to calculate, according to the preset evaluation logic formula, an evaluation score corresponding to the logic parameter of the number of times in different interval numbers, where the preset evaluation logic formula is Where i is the number of intervals, x is the value of the logical parameter of the number of times; and the calculation module is further configured to calculate the evaluation score corresponding to the logical parameter of the number type according to the preset evaluation logic formula by using different interval numbers,
  • the preset evaluation logic formula is Where i is the interval number, y is the value of the logical parameter of the number type; and the calculation module is further configured to calculate the evaluation score corresponding to the logical parameter of the fee type by using different preset numbers according to the preset evaluation logic formula,
  • the preset evaluation logic formula is Where i is the number of intervals, z is the value of the logical parameter of the cost type; and the calculation module is further configured to calculate an evaluation score corresponding to the logical parameter of the attribute type by using different preset numbers according to the preset evaluation logic formula
  • the device further includes: a generating unit, configured to generate an interval weight vector corresponding to the claim case according to the different claim product information, wherein the weight value corresponding to the fee type in the interval weight vector is sequentially greater than the number of times, The weight corresponding to the type and attribute type.
  • a generating unit configured to generate an interval weight vector corresponding to the claim case according to the different claim product information, wherein the weight value corresponding to the fee type in the interval weight vector is sequentially greater than the number of times, The weight corresponding to the type and attribute type.
  • the apparatus further includes: a comparing unit, configured to compare the evaluation result with a preset claim amount; and a determining unit, configured to: if the comparison result is that the evaluation result is greater than three points of the preset claim amount Second, the claim case is determined as a risk claim case and an early warning message is sent.
  • a storage medium in which at least one executable instruction is stored, the executable instruction causing a processor to perform an operation corresponding to the evaluation method of the risk claim described above.
  • a server including: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface complete mutual communication through the communication bus
  • the memory is configured to store at least one executable instruction that causes the processor to perform an operation corresponding to the evaluation method of the risk claim described above.
  • the technical solution provided by the embodiment of the present application has at least the following advantages:
  • the present application provides a method and device for evaluating risk claims, first obtaining claim information and historical policy information of the insured in the claim case, and then parsing the claim information and the logical parameters to be evaluated in the historical policy information.
  • the logic parameter is used to reflect the situation in which the insured participates in the medical item in the claim case, and then matches the preset parameter according to the logical parameter, and collects the evaluation result of the claim case corresponding to the logical parameter, the pre-
  • the evaluation logic is used to reflect the relationship between different logical parameters and different evaluation scores. Compared with the existing nuclear damage personnel in the review of claim cases, all of them are manually reviewed, and it is easy to miss some high-risk cases.
  • the embodiment of the present application analyzes the claims related to the claims case.
  • FIG. 1 is a flowchart of a method for evaluating risk claims provided by an embodiment of the present application
  • FIG. 2 is a flowchart of another method for evaluating risk claims provided by an embodiment of the present application.
  • FIG. 3 is a block diagram of an apparatus for evaluating risk claims provided by an embodiment of the present application.
  • FIG. 4 is a block diagram of another apparatus for evaluating risk claims provided by an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of a server provided by an embodiment of the present application.
  • the embodiment of the present application provides a method for evaluating risk claims, as shown in FIG. 1 , the method includes:
  • the insured refers to a person who has the right to claim the insurance premium after the occurrence of the insured event according to the effective insurance contract
  • the claim case is a case arising from the insured person's insured item specified in the insured product.
  • the claim information includes all information generated by the insured in the claim case, such as the time when the insured product is accident insurance, the time of the accident, the cause of the accident, and a series of treatment information produced at the designated hospital after the accident occurred.
  • the information in the present application is not specifically limited.
  • the historical policy information is all information generated by the insured from the initiating time to the current time period regarding the insured product, such as the insured product, the standard premium of the insured product, the effective time of the insured, the expiration time, and the underwriting
  • the time and the application time if there is a claim case, the claim amount of the claim case, the cause of the claim case, and the like, the embodiment of the present application does not specifically limit.
  • the insured when the customer is insured, the insured is the person who delivers the premium.
  • the insured and the insured may be the same person, or may not be the same person. One insured may insure multiple people, that is, when the customer is insured.
  • An insured customer generates a policy corresponding to a policy number, in which the policy includes information for the insured to insure all insured persons, and each insured generates a sub-order corresponding to a sub-order number, for the embodiment of the present application
  • the policy information of the insured may be a separate policy information, or may be a sub-single information corresponding to the insured, which is not specifically limited in this embodiment.
  • the claim information will be saved, and finally the historical policy information will be obtained, and since each insured person corresponds to a policy number, the history policy information can be obtained through the policy number.
  • the logic parameter is used to reflect the situation in which the insured participates in the medical item in the claim case, because the meaning of the insurance company exists is to make risk claims for the customer, especially for the health insurance product, after the customer has a claim case, Generally, it is necessary to treat certain medical items, and the insurance company will pay for the expenses incurred by these medical items. However, the production of a large number of medical items may not be within the scope of claims for insurance products, and it is necessary to claim claims. And the policy information is evaluated by the insured in the medical project.
  • the logical parameter may include information such as the time, the number of times, the content, the fee, and the like of the insured person participating in the medical project, such as one month (this time + history all cases)
  • the number of visits to the same disease within one state one visit: the same hospital on the same day
  • the number of hospitals visited within one month this state + all cases of history
  • the number of hospital visits within one month this + history of all cases
  • the time of the second outbreak is abnormal (from the time when my policy is effective), the time of this insurance Abnormal (from the end of my policy), this treatment is an overseas clinic (hospital property), the time of this outpatient visit, the history of all cases, the rules of mutual exclusion rules (the insured), physical therapy (cost type) fees ( With the hospital) public, physical therapy (cost type) costs (with the hospital) private, Chinese medicine treatment costs, Chinese medicine treatment times (number of visits: the same hospital on the same day), Chinese herbal medicine single cost, hospitalization expenses, inspection and inspection fees accounted for the total cost Proportion, whether to use medical insurance card
  • the corresponding logical parameters may be extracted through the storage identifiers of the various parameters in the claim information and the historical policy information, and then parsed. Specific data corresponding to these parameters, such as the amount of public outpatient applications (high-end) is 5,000 yuan.
  • the preset evaluation logic is configured to reflect a relationship between different logical parameters and different evaluation scores, wherein the evaluation score is a score for evaluating each logical parameter.
  • the data of each logical parameter may be divided into scores.
  • the logical parameter in order to determine the score according to the content of each range, for example, the logical parameter is the number of visits to the same disease within one month (this time + all cases of history) (one visit: the same hospital on the same day), the logical parameters parsed corresponding The data is 3 times, and the corresponding logical parameters have a score range of 2 points for 2 times, 3 points for 2 or 3 times, 4 points for 4 times, and 5 points for 5 times or more. The higher the score, the higher the risk of the claims case.
  • the logical parameters include not only the parameters of the order type but also the parameters of the number, cost, attribute, etc., the data of the logical parameters of each type corresponds to the range of division.
  • the evaluation results need to be counted according to the scores of all logical parameters, so that the staff can use the evaluation results to determine whether the current claim case is a dangerous claim case.
  • the scores obtained by each logical parameter need to be counted, and the average value can be calculated for the summation, and then the average value is judged whether the average value exceeds a specific risk value, and if it is exceeded, it is determined as a risk claim case, and is performed to the technician.
  • Early warning is the average value is judged whether the average value exceeds a specific risk value, and if it is exceeded, it is determined as a risk claim case, and is performed to the technician.
  • the application provides a method for evaluating risk claims, and the existing nuclear damage personnel are manually audited, and it is easy to miss some high-risk cases.
  • the embodiment of the present application passes the claims according to the claims.
  • the information and historical policy information analyzes the logical parameters related to the claim case, matches the logical parameters with the preset evaluation logic, obtains the evaluation result, and realizes the computer automatically calculates the evaluation result without manual operation, ensuring that each claim case is in accordance with a standard. Conduct an assessment to improve the efficiency of claims assessments.
  • the embodiment of the present application provides another method for evaluating risk claims, as shown in FIG. 2, the method includes:
  • step 201 Obtain the claim information and historical policy information of the insured in the claim case. This step is the same as the method of step 102 shown in FIG. 1, and details are not described herein again.
  • the number of types can include the number of visits to the same disease within one month (this time + all cases of history) (one visit: the same hospital on the same day), the number of Chinese medicine treatments (number of visits: same hospital on the same day), historical case E ( WeChat, APP) number of claims application, the number of types is less than one month (this + history of all cases) the number of hospitals, within one month (this + history of all cases) the number of treatments, this time out of the abnormal time ( The time from the effective date of my policy), the abnormal time of this insurance (from the end of my policy), the number of hospital stays (single), the underwriting option is MHD and the number of first-time insurance policies, the underwriting option is non-MHD policy and the first of the policy
  • the cost type is physical therapy (cost type) fee (with hospital) public, physical therapy (cost type) fee (with hospital) private, Chinese medicine treatment fee, Chinese herbal medicine single fee, historical case E-based claim application amount ( Accumulated), public outpatient application amount
  • the preset upper limit value and/or the lower limit value are preset values of the technician according to different types of logic parameters, for example, the number of types of logic parameters is within one month (this time + history all case states)
  • the preset upper limit of the number of hospitals to be treated is 8. When the number of hospitals in the insured's claims information is 10 in one month, it is greater than the preset upper limit. For the insured's hospital The data is obviously unreasonable and requires early warning to the underwriters who handle the claims.
  • the logical parameter configuration corresponding to the number of times, the number of types, the type of the fee, and the type of the attribute respectively The number of intervals.
  • the interval number is used to distinguish parameters corresponding to the preset preset evaluation logic formula. Since different types of logic parameters use the preset evaluation logic formula to evaluate the score, the data corresponding to each logical parameter needs to be replaced by a formula that can be matched. The calculated value, therefore, it is necessary to divide the number of intervals for each logical parameter.
  • the logical parameters of the number type, the number type, and the cost type can be divided into five interval numbers, wherein the number of times and the number type are insured.
  • the importance of judging the risk of claim in the claim case is the second most important.
  • the number of times and the number of each type are 1, 2, 3, 4, and 5.
  • the importance of determining the risk of claim in the insurance claim case is The most important, the cost type is 6, 7, 8, 9, and 10, respectively. It is not important to determine the importance of the claim risk in the insurance claim case for the attribute type, and the number of each type of the attribute type is 0.
  • the attribute type logic parameter is whether to use the medical insurance card (social security bill), the data is "yes and no", for "yes”
  • the number of intervals is 0, and the number of intervals for "No” is 2; the number of logical parameters of this type is abnormal for this time (from the time when the policy is effective), and the data are "more than 7 months, 5-6 months, Within 3-4 months, 1-2 months, and 1 month, the number of intervals of "more than 7 months” is 1, and so on.
  • the cost type logic parameter is the cost of traditional Chinese medicine treatment.
  • the data are respectively 0-300. 300-500, 500-700, 700-900, 900 or more", "0-300,” the interval number is divided into 6, and so on, and the embodiment of the present application is not specifically limited.
  • the logical parameters of different data are converted into parameters that can be replaced in the preset evaluation logic formula for formula operations.
  • the current risk claim evaluation method can be embedded into any insurance management system in the form of a calculation module to connect with the database storing the insurance customer information, and obtain data for calculation.
  • the number of intervals that need to be configured in the current step 204 may be pre-configured in the system cache.
  • the number of intervals of the logical parameter is determined according to the specific data of the logical parameter, and the specific program is compiled.
  • the embodiment is not specifically limited.
  • the logic parameter is reported to the display interface, and is not used as a parameter in the preset evaluation logic formula. Operation.
  • the preset evaluation logic formula calculates, according to the preset evaluation logic formula, an evaluation score corresponding to the logical parameter of the number of times in different interval numbers.
  • the preset evaluation logic formula is Where i is the number of intervals and x is the value of the logical parameter of the number type.
  • the logical parameter is the public hospitalization application amount (high end), and the cost of the customer 1 found in the database in the claim event and the historical policy information is 25,000 yuan, and the current logical parameter is determined according to the number of intervals corresponding to the type of the fee type.
  • the number of intervals is 8, and 25000 and 8 are brought into the preset evaluation logic formula to obtain an evaluation score of about 76.
  • the preset evaluation logic formula is stored in the calculation module in the form of program code, and when the calculation program is started, the operation is directly performed according to each logic parameter, and the evaluation scores of all the logic parameters are obtained.
  • the evaluation score corresponding to the logical parameter of the number type is calculated by different interval numbers according to the preset evaluation logic formula 205b along with the step 205a.
  • the preset evaluation logic formula is Where i is the number of intervals and y is the value of the logical parameter of the number type.
  • Step 205b is the same as the specific implementation method of step 205a, and will not be described again.
  • the evaluation score corresponding to the logical parameter of the fee type is calculated by different interval numbers according to the preset evaluation logic formula 205c along with the step 205a.
  • the preset evaluation logic formula is Where i is the interval number and z is the value of the logical parameter of the expense type.
  • Step 205c is the same as the specific implementation method of step 205a, and will not be described again.
  • the evaluation score corresponding to the logical parameter of the attribute type is calculated in different interval numbers according to the preset evaluation logic formula 205d along with the step 205a.
  • the preset evaluation logic formula is Where i is the number of intervals and l is the value of the logical parameter of the attribute type.
  • Step 205d is the same as the specific implementation method of step 205a, and will not be described again.
  • the estimation result of the evaluation score corresponding to the number of times, the number of types, the type of the fee, and the type of the attribute is obtained according to a preset interval weight vector.
  • the weight corresponding to the interval number is the weight corresponding to the number of interval types, a3 is the weight corresponding to the number of interval types, and a4 is the weight corresponding to the interval number of the attribute type, wherein the underwriting can be based on the claim case
  • the personnel determine the accuracy of the evaluation results of different interval numbers in the evaluation.
  • A1 in the weight vector is determined as the column vector, that is, a a1 can be a column vector, including the weights corresponding to the five interval numbers.
  • the specific value of the weight is the same as the size of the interval number, that is, the evaluation score of each logical parameter needs to be multiplied by the same weight as the interval corresponding to each logical parameter to obtain an evaluation result. No specific restrictions.
  • the general preset interval weight vector may be determined by the underwriting personnel of the insurance company according to the historical claim risk data, which is not specifically limited in the embodiment of the present application.
  • the statistical method is to multiply the evaluation score corresponding to each logical parameter and the interval weight vector to obtain an evaluation result for comparison.
  • the embodiment of the present application further includes: generating an interval weight vector corresponding to the claim case according to the different claim product information, wherein the weight value corresponding to the fee type in the interval weight vector is sequentially greater than the number of times, The weight corresponding to the type and attribute type.
  • the order of weights is a1>a2>a3>a4.
  • different insurance products have different claims effects in claims cases, such as the large claims insurance claims risk is much larger than the small insurance corresponding claims risk.
  • the other information may be determined according to the information corresponding to the claim product in the claim case or the historical policy information to determine the interval in the risk-free claim case.
  • the weight vector is used as a reference to directly generate the corresponding interval weight vector.
  • the preset evaluation logic formula is used as a form data for converting all types of data into a certain range, so as to facilitate The insurance company compares the amount of claims most concerned in the claims case to determine whether it is a risk claim case.
  • the preset claim amount is the maximum amount that should be paid in different claims products, which is not specifically limited in the embodiment of the present application.
  • the claim case is determined as a risk claim case, and the warning information is sent.
  • the calculated evaluation result In order to make the calculated evaluation result accurately determine whether it is a risk claim case, if it is greater than two-thirds of the setting, it can be accurately determined as a risk claim case, and an early warning is issued to the underwriting personnel, so that the underwriter can proceed to the next step.
  • the audit is not more than two-thirds of the preset claim amount, the current claim case is a normal claim case and will not be reviewed, so as to reduce the steps of human handling, thereby improving the efficiency of risk claim case evaluation.
  • the present application provides another method for evaluating risk claims.
  • the embodiment of the present application analyzes the logical parameters related to the claim case according to the claim information and the historical policy information, and sets the number of intervals of the logical parameters as parameters of the preset evaluation logic formula. Perform calculations to obtain the evaluation scores of each logical parameter, calculate the evaluation results by weight calculation, and compare with the preset claims amount to determine whether it is a risk claim case, and realize the computer automatically calculate the evaluation result without human intervention, ensuring each
  • the claim cases are evaluated according to a standard, and the data of all the logical parameters are converted into the amount by the preset evaluation logic formula, thereby realizing the purpose of comparing the different values in the claim case into the form of the amount, thereby improving The efficiency of claims assessment.
  • the embodiment of the present application provides an apparatus for evaluating risk claims.
  • the apparatus includes: an obtaining unit 31, an analyzing unit 32, and a statistics unit 33.
  • the obtaining unit 31 is configured to obtain the claim information and the historical policy information of the insured in the claim case; the obtaining unit 31 is configured to perform the function module for obtaining the claim information and the historical policy information of the insured in the claim case for the risk claim evaluation device.
  • the parsing unit 32 is configured to parse the claim information and the logical parameter to be evaluated in the historical policy information, where the logic parameter is used to reflect the situation in which the insured participates in the medical item in the claim case; the parsing unit 32 is The risk claim evaluation device performs a function module that parses the claim information and the logical parameter to be evaluated in the history policy information.
  • the statistic unit 33 is configured to perform matching on the logical parameter according to the preset evaluation logic, and collect the evaluation result of the claim case corresponding to the logical parameter, where the preset evaluation logic is used to reflect different logical parameters and different evaluation scores. Relationship between.
  • the statistic unit 33 performs, for the risk claim evaluation device, a function module that matches the preset parameter according to the logic parameter, and counts the evaluation result of the claim case corresponding to the logic parameter.
  • the application provides a risk claim evaluation device, and the existing nuclear damage personnel in the review of the claims case are manually audited, and it is easy to miss some high-risk cases.
  • the information and historical policy information analyzes the logical parameters related to the claim case, matches the logical parameters with the preset evaluation logic, obtains the evaluation result, and realizes the computer automatically calculates the evaluation result without manual operation, ensuring that each claim case is in accordance with a standard. Conduct an assessment to improve the efficiency of claims assessments.
  • the embodiment of the present application provides another apparatus for evaluating risk claims.
  • the apparatus includes: an obtaining unit 41, an analyzing unit 42, and a statistics unit 43.
  • the obtaining unit 41 is configured to obtain claim information and historical policy information of the insured in the claim case;
  • the parsing unit 42 is configured to parse the claim information and the logical parameter to be evaluated in the historical policy information, where the logical parameter is used In response to the situation in which the insured participates in the medical item in the claim case;
  • the statistical unit 43 is configured to match the preset parameter according to the logical parameter, and collect the evaluation result of the claim case corresponding to the logical parameter, Pre-set evaluation logic is used to reflect the relationship between different logic parameters and different evaluation scores.
  • the parsing unit 42 includes: an extracting module 4201, configured to extract logical parameters corresponding to the order type, the number type, the fee type, and the attribute type in the claim information and the historical policy information; the determining module 4202 And determining whether the value of the logical parameter corresponding to the number of times, the number of types, the type of the fee, and the type of the attribute are respectively greater than a preset upper limit value, and/or less than a preset lower limit.
  • a configuration module 4203 configured to determine, by the determining module 4202, that the value of the logical parameter corresponding to the number of times, the number of types, the type of the fee, and the type of the attribute are respectively less than a preset upper limit value, and And if the value is greater than the preset lower limit value, the number of the logical parameter corresponding to the number of times, the number of types, the type of the fee, and the type of the attribute are respectively configured, and the number of the interval is used to distinguish the replacement Set the parameters corresponding to the evaluation logic formula.
  • the statistic unit 43 includes: a calculation module 4301, configured to calculate, according to the preset evaluation logic formula, an evaluation score corresponding to the logical parameter of the number of times in different interval numbers, where the preset evaluation logic formula is Where i is the number of intervals, x is the value of the logical parameter of the number of times; and the calculating module 4301 is further configured to calculate the evaluation score corresponding to the logical parameter of the number type according to the preset evaluation logic formula by using different number of intervals, The preset evaluation logic formula is Where i is the number of intervals, y is the value of the logical parameter of the number type; and the calculating module 4301 is further configured to calculate the evaluation score corresponding to the logical parameter of the fee type by using different preset numbers according to the preset evaluation logic formula.
  • the preset evaluation logic formula is Where i is the number of intervals, z is the value of the logical parameter of the cost type; and the calculation module 4301 is further configured to calculate the evaluation score corresponding to the logical parameter of the attribute type by using the preset evaluation logic formula in different interval numbers,
  • the preset evaluation logic formula is Where i is the number of intervals, l is the value of the logical parameter of the attribute type, and the statistic module 4302 is configured to statistically obtain the type of the number, the type of the number, the type of the fee, and the location according to a preset interval weight vector. The evaluation result of the evaluation score corresponding to the attribute type.
  • the device further includes: a generating unit 44, configured to generate an interval weight vector corresponding to the claim case according to different claims product information, where the weight corresponding to the fee type in the interval weight vector is sequentially greater than the number of times, The weight of the number type and attribute type.
  • a generating unit 44 configured to generate an interval weight vector corresponding to the claim case according to different claims product information, where the weight corresponding to the fee type in the interval weight vector is sequentially greater than the number of times, The weight of the number type and attribute type.
  • the device further includes: a comparing unit 45, configured to compare the evaluation result with a preset claim amount; and a determining unit 46, configured to: if the comparison result is that the evaluation result is greater than the preset claim amount Two-thirds of the cases are identified as risk claims cases and sent early warning information.
  • the present application provides another risk claim evaluation device.
  • the embodiment of the present application analyzes the logical parameters related to the claim case according to the claim information and the historical policy information, and sets the logical parameter configuration interval number as the parameter of the preset evaluation logic formula. Perform calculations to obtain the evaluation scores of each logical parameter, calculate the evaluation results by weight calculation, and compare with the preset claims amount to determine whether it is a risk claim case, and realize the computer automatically calculate the evaluation result without human intervention, ensuring each The claim cases are evaluated according to a standard, and the data of all the logical parameters are converted into the amount by the preset evaluation logic formula, thereby realizing the purpose of comparing the different values in the claim case into the form of the amount, thereby improving The efficiency of claims assessment.
  • the embodiment of the present application further provides a computer readable storage medium, where the computer program is stored, and when the program is executed by the processor, the following steps are implemented: obtaining a claim case Claim information and historical policy information of the insurer; parsing the logic information to be evaluated in the claim information and the historical policy information, wherein the logic parameter is used to reflect the situation in which the insured participates in the medical item in the claim case; The logical parameters are matched with the preset evaluation logic, and the evaluation result of the claim case corresponding to the logical parameter is used, and the preset evaluation logic is used to reflect the relationship between different logical parameters and different evaluation scores.
  • the server may include a processor 51, a communications interface 52, a memory 53, and a communication bus 54.
  • the processor 51, the communication interface 52, and the memory 53 complete communication with each other via the communication bus 54.
  • the communication interface 54 is configured to communicate with network elements of other devices such as clients or other servers.
  • the processor 51 is configured to execute a program, and specifically may perform related steps in the testing method embodiment of the application.
  • the program can include program code, the program code including computer operating instructions.
  • the processor 51 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.
  • ASIC Application Specific Integrated Circuit
  • the one or more processors included in the terminal may be the same type of processor, such as one or more CPUs; or may be different types of processors, such as one or more CPUs and one or more ASICs.
  • the memory 53 is configured to store a program.
  • the memory 53 may include a high speed RAM memory and may also include a non-volatile memory such as at least one disk memory.
  • the program may be specifically configured to enable the processor 51 to: obtain the claim information and the history policy information of the insured in the claim case; and parse the claim information and the logical parameter to be evaluated in the historical policy information, the logic parameter
  • the method for responding to the insured person participating in the medical item in the claim case; matching the preset parameter according to the logic parameter, and counting the evaluation result of the claim case corresponding to the logic parameter, where the preset evaluation logic is used The relationship between different logical parameters and different evaluation scores.
  • modules in the devices of the embodiments can be adaptively changed and placed in one or more devices different from the embodiment.
  • the modules or units or components of the embodiments may be combined into one module or unit or component, and further they may be divided into a plurality of sub-modules or sub-units or sub-components.
  • any combination of the features disclosed in the specification, including the accompanying claims, the abstract and the drawings, and any methods so disclosed, or All processes or units of the device are combined.
  • Each feature disclosed in this specification (including the accompanying claims, the abstract and the drawings) may be replaced by alternative features that provide the same, equivalent or similar purpose.
  • the various component embodiments of the present application can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof.
  • a microprocessor or digital signal processor may be used in practice to implement some or all of the functionality of some or all of the components of the risk claim evaluation method and apparatus in accordance with embodiments of the present application.
  • the application can also be implemented as a device or device program (e.g., a computer program and a computer program product) for performing some or all of the methods described herein.
  • Such a program implementing the present application may be stored on a computer readable medium or may be in the form of one or more signals. Such signals may be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

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)
  • Medical Treatment And Welfare Office Work (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

一种风险理赔的评估方法及装置，涉及数据处理技术领域，主要目的在于解决现有的核损人员在进行理赔案件的审核时，通过人工审核，容易漏掉一些高风险案件，给保险公司带来一些经济损失的问题。一种风险理赔的评估方法，包括：获取理赔案件中被保险人的理赔信息及历史保单信息（101）；解析所述理赔信息及所述历史保单信息中待评估的逻辑参数（102），所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况；根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果（103），所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。上述方法用于风险理赔的评估。

Description

风险理赔的评估方法及装置
本申请要求与2017年11月22日提交中国专利局、申请号为201711171504.X、发明名称为“风险理赔的评估方法和装置”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
本申请涉及一种数据处理技术领域，特别是涉及一种风险理赔的评估方法及装置。
背景技术
在保险理赔案件发生后，保险行业的核保人员需要对理赔案件进行核准校对，以便准确进行理赔并降低理赔案件来带的理赔风险。其中，核保人员在对理赔案件进行评估过程中，包括了定损和核损，定损过后，核损人员对其的工作结果进行审核，如果没有疑义，会同意这个结果，如果有异议，就会被退回，以防出现骗保。
目前，现有的核损人员在进行理赔案件的审核时，都是通过人工审核，将被保人的投保信息与定损信息进行人工校对，但是对于人工校对审核来说，每个核损人员的认知标准与判断原则不同，效率不同，会导致结果不同，而对于保险理赔中的一些理赔项目的理赔范围，一些严格的核损人员会拒绝一些应该进行理赔的案件，一些宽松的核损人员会同意一些不应该进行理赔的案件，这就使得，容易漏掉一些高风险案件，给保险公司带来一些经济损失，若多人校对同一个理赔案件又会浪费较大的人力资源，因此，人工审核降低了理赔案件的评估效率。
发明内容
有鉴于此，本申请提供一种风险理赔的评估方法及装置，主要目的在于解决现有的核损人员在进行理赔案件的审核时，通过人工审核，容易漏掉一些高风险案件，对保险公司带来一些经济损失的问题。
依据本申请一个方面，提供了一种风险理赔的评估方法，包括：
获取理赔案件中被保险人的理赔信息及历史保单信息；解析所述理赔信息及 所述历史保单信息中待评估的逻辑参数，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况；根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。
进一步地，所述解析所述理赔信息及所述历史保单信息中待评估的逻辑参数包括：提取所述理赔信息及所述历史保单信息中与次数类型、个数类型、费用类型、属性类型分别对应的逻辑参数；判断所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数的数值是否分别大于预设的上限值、和/或小于预设的下限值；若小于预设的上限值、和/或大于预设的下限值，则为所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数配置区间数，所述区间数用于区分替换预置评估逻辑公式对应的参数。
进一步地，所述根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果包括：按照预置评估逻辑公式以不同区间数计算所述次数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000001
其中i为区间数，x为次数类的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述个数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000002
其中i为区间数，y为个数类型的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述费用类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000003
其中i为区间数，z为费用类型的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述属性类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000004
其中i为区间数，l为属性类型的逻辑参数的数值；按照预设的区间权值向量，统计得到所述次数类型、所述个数类型、所述费用类型、所述属性类型对应的评估分数的评估结果。
进一步地，所述方法还包括：根据不同理赔产品信息生成与理赔案件对应的区间权值向量，所述区间权值向量中费用类型对应的权值依次分别大于次数类 型、个数类型、属性类型对应的权值。
进一步地，所述根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果之后，所述方法还包括：将所述评估结果与预置理赔金额进行比较；若比较结果为所述评估结果大于所述预置理赔金额的三分之二，则将所述理赔案件确定为风险理赔案件，并发送预警信息。
依据本申请一个方面，提供了一种风险理赔的评估装置，包括：获取单元，用于获取理赔案件中被保险人的理赔信息及历史保单信息；解析单元，用于解析所述理赔信息及所述历史保单信息中待评估的逻辑参数，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况；统计单元，用于根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。
进一步地，所述解析单元包括：提取模块，用于提取所述理赔信息及所述历史保单信息中与次数类型、个数类型、费用类型、属性类型分别对应的逻辑参数；判断模块，用于判断所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数的数值是否分别大于预设的上限值、和/或小于预设的下限值；配置模块，用于若判断模块判断所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数的数值分别小于预设的上限值、和/或大于预设的下限值，则为所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数配置区间数，所述区间数用于区分替换预置评估逻辑公式对应的参数。
进一步地，所述统计单元包括：计算模块，用于按照预置评估逻辑公式以不同区间数计算所述次数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000005
其中i为区间数，x为次数类的逻辑参数的数值；以及所述计算模块，还用于按照预置评估逻辑公式以不同区间数计算所述个数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000006
其中i为区间数，y为个数类型的逻辑参数的数值；以及所述计算模块，还用于按照预置评估逻辑公式以不同区间数计算所述费用类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000007
其中i为区间数，z为费用类型的逻辑参数的数值；以及所述计算模块，还用于按照预置评估逻辑公式以不同区间数计算所述属性类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000008
其中i为区间数，l为属性类型的逻辑参数的数值；统计模块，用于按照预设的区间权值向量，统计得到所述次数类型、所述个数类型、所述费用类型、所述属性类型对应的评估分数的评估结果。
进一步地，所述装置还包括：生成单元，用于根据不同理赔产品信息生成与理赔案件对应的区间权值向量，所述区间权值向量中费用类型对应的权值依次分别大于次数类型、个数类型、属性类型对应的权值。
进一步地，所述装置还包括：比较单元，用于将所述评估结果与预置理赔金额进行比较；确定单元，用于若比较结果为所述评估结果大于所述预置理赔金额的三分之二，则将所述理赔案件确定为风险理赔案件，并发送预警信息。
根据本申请的又一方面，提供了一种存储介质，所述存储介质中存储有至少一可执行指令，所述可执行指令使处理器执行如上述风险理赔的评估方法对应的操作。
根据本申请的再一方面，提供了一种服务器，包括：处理器、存储器、通信接口和通信总线，所述处理器、所述存储器和所述通信接口通过所述通信总线完成相互间的通信；所述存储器用于存放至少一可执行指令，所述可执行指令使所述处理器执行上述风险理赔的评估方法对应的操作。
借由上述技术方案，本申请实施例提供的技术方案至少具有下列优点：
本申请提供了一种风险理赔的评估方法及装置，首先获取理赔案件中被保险人的理赔信息及历史保单信息，再解析所述理赔信息及所述历史保单信息中待评估的逻辑参数，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况，然后根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。与现有的核损人员在进行理赔案件的审核时，都是通过人工审核，容易漏掉一些高风险案件相比，本申请实施例通过根据理赔信息及历史保单信息解析出与理赔案件相关的逻辑参数，将逻辑参数与预置评估逻辑进行匹配，得到 评估结果，实现计算机自动计算评估结果，无需人为操作，确保了每个理赔案件按照一个标准进行评估，从而提高理赔案件评估的效率。
上述说明仅是本申请技术方案的概述，为了能够更清楚了解本申请的技术手段，而可依照说明书的内容予以实施，并且为了让本申请的上述和其它目的、特征和优点能够更明显易懂，以下特举本申请的具体实施方式。
附图说明
通过阅读下文优选实施方式的详细描述，各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出优选实施方式的目的，而并不认为是对本申请的限制。而且在整个附图中，用相同的参考符号表示相同的部件。在附图中：
图1示出了本申请实施例提供的一种风险理赔的评估方法流程图；
图2示出了本申请实施例提供的另一种风险理赔的评估方法流程图；
图3示出了本申请实施例提供的一种风险理赔的评估装置框图；
图4示出了本申请实施例提供的另一种风险理赔的评估装置框图；
图5示出了本申请实施例提供的一种服务器结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。
本申请实施例提供了一种风险理赔的评估方法，如图1所示，所述方法包括：
101、获取理赔案件中被保险人的理赔信息及历史保单信息。其中，所述被保险人是指根据生效的保险合同在保险事故发生后，享有保险金请求权的人，所述理赔案件为被保险人发生了投保产品中所规定的保险事项所产生的案件，所述理赔信息包括被保险人在理赔案件中所产生的所有信息，如投保产品为意外险，则发生意外的时间、发生意外的事由、发生意外后在定点医院所生产的一系列治疗信息等信息，本申请实施例不做具体限定。所述历史保单信息为被保险人从投保起始时间至当前时间段中关于投保产品所产生的所有信息，如投保产品、投保产品的标准保费、被投保人的生效时间、期满时间、承保时间、申请时间，若存 在理赔案件，还包括理赔案件的赔付金额、理赔案件产生的事由等，本申请实施例不做具体限定。需要说明的是，客户在进行投保时，投保人为交付保费的人，投保人与被保人可能一同一人，也可能不为同一人，一个投保人可以为多人进行投保，即在客户投保时，一个投保客户生成一个保单，对应一个保单号，在这个保单中包括投保人为所有被保人进行投保的信息，每个被保人生成一个分单，对应一个分单号，对于本申请实施例中，若被保险人的保单信息即可以为单独的保单信息，也可以为被保险人对应的分单信息，本申请实施例不做具体限定。另外，被保险人在产生理赔案件之后，理赔信息都会保存下来，最终得到历史保单信息，并且，由于每个被保险人都对应一个保单号，因此，可以通过保单号来获取到历史保单信息。
102、解析所述理赔信息及所述历史保单信息中待评估的逻辑参数。其中，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况，由于保险公司存在的意义就是为客户进行风险理赔，尤其是针对健康保险产品中，客户在发生理赔案件后，一般会需要进行一定的医疗项目的治疗，保险公司就会赔付这些医疗项目所产生的费用，但是大量的医疗项目的产生可能并非都是针对保险产品所应该理赔的范围内，就需要对理赔事件及保单信息中被保险人参与医疗项目的情况进行评估，因此，所述逻辑参数可以包括被保险人参与医疗项目的时间、次数、内容、费用等信息，如一个月(本次+历史所有案件状态)以内同一疾病就诊次数(一次就诊：同一天同一医院)、一个月以内(本次+历史所有案件状态)就诊医院数量、一个月以内(本次+历史所有案件状态)就诊疾病数量、本次出险时间异常(距本人保单生效时间)、本次出险时间异常(距本人保单结束时间)、本次治疗是境外就诊(医院属性)、本次门诊就诊时间、历史所有案件状态互斥规则筛处(该被保险人)、物理治疗(费用类型)费用(跟医院)公立、物理治疗(费用类型)费用(跟医院)私立、中医治疗费用、中医治疗次数(就诊次数：同一天同一医院)、中草药单次费用、住院费用中检查检验费占总费用的占比、是否使用医保卡(社保账单)、是否存在第三方支付(明确到账单中的字段)、历史案件E化(微信、APP)理赔申请次数、历史案件E化理赔申请金额(累计)、住院天数(单次)、公立门诊申请金额(高端)、私立门诊申请金额(高端)、公立住院申请金额(高端)、私立住院申请金额：(高端)、加保人员占首期人员占比、 退保人数占比首期投保人数、核保选项为MHD且保单首期投保人数、保单只有住院责任的团体(高端、人均保费)、核保选项为非MHD保单且保单的首期投保人数，本申请实施例不做具体限定。需要说明的是，由于这些逻辑参数对应的内容及数据均是存储在数据库中，解析这些逻辑参数时，可以通过理赔信息及历史保单信息中各个参数的存储标识来提取对应的逻辑参数，然后解析出这些参数对应的具体数据，如公立门诊申请金额(高端)为5000元等。
103、根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果。其中，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系，所述评估分数为为各个逻辑参数进行评价的分数，一般的，每个逻辑参数的数据都可以划分分数范围，以便根据各个范围内的内容来确定分数，例如，逻辑参数为一个月(本次+历史所有案件状态)以内同一疾病就诊次数(一次就诊：同一天同一医院)，解析出的逻辑参数对应的数据为3次，对应的逻辑参数的分数范围分别为1次为2分，2或3次为3分，4次为4分，5次以上为5分。分值越高说明理赔案件的风险越高，然而，由于逻辑参数中不仅包含次数类型的参数还包括个数、费用、属性等类型的参数，每个类型中逻辑参数的数据对应的划分范围都不同，因此需要根据所有逻辑参数的分值来统计评估结果，以便工作人员通过评估结果来确定当前理赔案件是否为危险理赔案件。需要说明的是，各个逻辑参数得到的分数后需要进行统计，可以为求和再计算平均值，然后判断这个平均值是否超过特定的风险值，若超过则确定为风险理赔案件，向技术人员进行预警。
本申请提供了一种风险理赔的评估方法，与现有的核损人员在进行理赔案件的审核时，都是通过人工审核，容易漏掉一些高风险案件相比，本申请实施例通过根据理赔信息及历史保单信息解析出与理赔案件相关的逻辑参数，将逻辑参数与预置评估逻辑进行匹配，得到评估结果，实现计算机自动计算评估结果，无需人为操作，确保了每个理赔案件按照一个标准进行评估，从而提高理赔案件评估的效率。
本申请实施例提供了另一种风险理赔的评估方法，如图2所示，所述方法包括：
201、获取理赔案件中被保险人的理赔信息及历史保单信息。本步骤与图1 所示的步骤102方法相同，在此不再赘述。
202、提取所述理赔信息及所述历史保单信息中与次数类型、个数类型、费用类型、属性类型分别对应的逻辑参数。对于本申请实施例，由于并不是所有的理赔事件及历史保单信息中都会包括所有的逻辑参数，并且，逻辑参数中的数据也并不都是具体的数值，如逻辑参数为是否使用医保卡(社保账单)，对应的数据为“是或否”，因此需要对逻辑参数进行划分类型，以便在根据逻辑参数评估分数时，准确的评分。例如，次数类型可以包括一个月(本次+历史所有案件状态)以内同一疾病就诊次数(一次就诊：同一天同一医院)、中医治疗次数(就诊次数：同一天同一医院)、历史案件E化(微信、APP)理赔申请次数，个数类型为一个月以内(本次+历史所有案件状态)就诊医院数量、一个月以内(本次+历史所有案件状态)就诊疾病数量、本次出险时间异常(距本人保单生效时间)、本次出险时间异常(距本人保单结束时间)、住院天数(单次)、核保选项为MHD且保单首期投保人数、核保选项为非MHD保单且保单的首期投保人数，费用类型为物理治疗(费用类型)费用(跟医院)公立、物理治疗(费用类型)费用(跟医院)私立、中医治疗费用、中草药单次费用、历史案件E化理赔申请金额(累计)、公立门诊申请金额(高端)、私立门诊申请金额(高端)、公立住院申请金额(高端)、私立住院申请金额：(高端)、保单只有住院责任的团体(高端、人均保费)，属性类型为本次治疗是境外就诊(医院属性)、本次门诊就诊时间、历史所有案件状态互斥规则筛处(该被保险人)、是否使用医保卡(社保账单)、是否存在第三方支付(明确到账单中的字段)、加保人员占首期人员占比、退保人数占比首期投保人数，本申请实施例不做具体限定。一般的，逻辑参数在数据库中以字段等形式进行存储，为了准确提取不同类型的逻辑参数，可以查找不同类型逻辑参数的存储标识，以便简化提取步骤。
203、判断所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数的数值是否分别大于预设的上限值、和/或小于预设的下限值。对于本申请实施例，为了避免逻辑参数中的数据出现严重的失真情况，需要设定一个上限值和/或下限值，以便确定当前逻辑参数的数据可以被用来对理赔风险进行评估，所述预设的上限值、和/或下限值为技术人员根据不同类型的逻辑参数预先设定的数值，如，个数类型的逻辑参数为一个月以内(本次+历史所有案 件状态)就诊医院数量的预设的上限值为8，当出现被保险人理赔信息中一个月内就诊医院数量的个数为10时，大于预设的上限值，对于被保险人的就诊医院数据明显是不合理的，需要向处理理赔案件的核保人员进行预警。
204、若小于预设的上限值、和/或大于预设的下限值，则为所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数配置区间数。其中，所述区间数用于区分替换预置评估逻辑公式对应的参数，由于不同类型的逻辑参数在利用预置评估逻辑公式评估分数时，每个逻辑参数对应的数据需要替换为公式中可以匹配计算的数值，因此，需要对每个逻辑参数进行划分区间数，优选的，次数类型、个数类型、费用类型的逻辑参数可以划分为5个区间数，其中，针对次数、个数类型在保险理赔案件中判断理赔风险的重要性为次重要，次数类型、个数类型每个区间数分别为1、2、3、4、5，针对费用类型在保险理赔案件中判断理赔风险的重要性为最重要，费用类型每个区间数分别为6、7、8、9、10，针对属性类型在保险理赔案件中判断理赔风险的重要性为不重要，则属性类型每个区间数分别为0、1、2、0、0，如，属性类型逻辑参数为是否使用医保卡(社保账单)，数据分别为“是和否”，对于“是”的区间数为0，对于“否”的区间数为2；个数类型逻辑参数为本次出险时间异常(距本人保单生效时间)，数据分别为“7个月以上、5-6个月、3-4个月、1-2个月、1个月以内”，“7个月以上”的区间数为1，依次类推，费用类型逻辑参数为中医治疗费用，数据分别为“0-300、300-500、500-700、700-900、900以上”，“0-300、”区间数分为6，依次类推，本申请实施例不做具体限定。通过为不同类型的逻辑参数分配区间数，将不同数据的逻辑参数转化为可以替换在预置评估逻辑公式中的参数，以便进行公式运算。需要说明的是，当前的风险理赔的评估方法可以以一个计算模块形式嵌入至任意一个保险管理***中，以便与存储有保险客户信息的数据库进行连接，获取数据来进行计算。另外，当前204步骤中需要配置的区间数可以预先配置在***缓存中，当接收到待评估的各个逻辑参数时，根据逻辑参数的具体数据来确定逻辑参数的区间数，具体的程序编译本申请实施例不做具体限定。对于本申请实施例，若大于预设的上限值、和/或小于预设的下限值，则将所述逻辑参数上报至显示界面，并不做为预设评估逻辑公式中的参数进行运算。
205a、按照预置评估逻辑公式以不同区间数计算所述次数类型的逻辑参数对 应的评估分数。其中，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000009
其中i为区间数，x为次数类型的逻辑参数的数值。例如，逻辑参数为公立住院申请金额(高端)，从数据库中查找到的客户1在理赔事件及历史保单信息中的费用为25000元，根据类型为费用类型对应的区间数，确定当前逻辑参数的区间数为8，将25000与8带入进行预置评估逻辑公式中得到评估分数约为76。为了提高理赔案件风险评估的准确性，需要对每个逻辑参数计算评估分数，以便根据综合了所有逻辑参数的评分来确定理赔案件的风险。需要说明的是，预置评估逻辑公式以程序代码形式存储在计算模块中，并在启动计算程序时，直接按照每个逻辑参数进行运算，得到所有逻辑参数的评估分数。
对于本申请实施例，与步骤205a并列的205b、按照预置评估逻辑公式以不同区间数计算所述个数类型的逻辑参数对应的评估分数。其中，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000010
其中i为区间数，y为个数类型的逻辑参数的数值。步骤205b与步骤205a具体的实施方法相同，不再进行赘述。
对于本申请实施例，与步骤205a并列的205c、按照预置评估逻辑公式以不同区间数计算所述费用类型的逻辑参数对应的评估分数。其中，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000011
其中i为区间数，z为费用类型的逻辑参数的数值。步骤205c与步骤205a具体的实施方法相同，不再进行赘述。
对于本申请实施例，与步骤205a并列的205d、按照预置评估逻辑公式以不同区间数计算所述属性类型的逻辑参数对应的评估分数。其中，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000012
其中i为区间数，l为属性类型的逻辑参数的数值。步骤205d与步骤205a具体的实施方法相同，不再进行赘述。
206、按照预设的区间权值向量，统计得到所述次数类型、所述个数类型、所述费用类型、所述属性类型对应的评估分数的评估结果。为了再次对评估效果进行提升，为每个类型的逻辑参数配置区间全职，所述预设的区间权值向量为一个向量，如，a＝[a1、a2、a3、a4]，a1为费用类型区间数对应的权值，a2为次 数类型区间数对应的权值，a3为个数类型区间数对应的权值，a4为属性类型区间数对应的权值，其中，可以根据理赔案件的核保人员对评估中不同区间数对评估结果的准确性影响，权值向量中的a1等确定为列向量，即，代表一个a1可以为1个列向量，包括了5个区间数分别对应的权值，优选的，权值的具体数值与区间数的大小数值相同，即各个逻辑参数的评估分数需要与与各个逻辑参数对应的区间数相同的权值相乘求和得到评估结果，本申请实施例不做具体限定。一般的预设的区间权值向量可以由保险公司的核保人员根据历史理赔风险数据进行确定的，本申请实施例不做具体限定。另外，统计的方式即为将各个逻辑参数对应的评估分数与区间权值向量进行相乘求和，得到一个评估结果，以便进行比较。
进一步地，步骤206之前，本申请实施例还包括：根据不同理赔产品信息生成与理赔案件对应的区间权值向量，所述区间权值向量中费用类型对应的权值依次分别大于次数类型、个数类型、属性类型对应的权值。其中，由于保险公司对于理赔案件风险评估的重点仍然以费用为主，因此，权值的大小顺序依次为a1>a2>a3>a4。另外，由于不同的保险产品在理赔案件中产生的理赔效果不同，如大额保险对应理赔风险比小额保险对应的理赔风险要大很多。一般的，当出现区间数匹配了，但是不符合a1>a2>a3>a4的情况时，可以根据理赔案件或历史保单信息中的理赔产品对应的信息获取其他以确定为无风险理赔案件中区间权值向量作为参照，直接生产对应的区间权值向量，本申请实施例不做具体限定，无需人为匹配，减少人工操作，节约成本。
207、将所述评估结果与预置理赔金额进行比较。需要说明的是，通过预置评估逻辑公式，可以将各个逻辑参数的数据直接以金额形式进行转化，即，预置评估逻辑公式作为将所有类型的数据转化为一定区间的金额形式数据，以便于保险公司对理赔案件中最为关注的理赔金额进行比较，从而确定是否为风险理赔案件。其中，预置理赔金额为不同理赔产品中最大应该赔付的金额，本申请实施例不做具体限定。
208、若比较结果为所述评估结果大于所述预置理赔金额的三分之二，则将所述理赔案件确定为风险理赔案件，并发送预警信息。为了使计算出的评估结果可以准确确定出是否为风险理赔案件，若大于三分之二的设定即可以准确确定为风险理赔案件，并向核保人员发出预警，以便核保人员进行下一步审核，若不大 于预置理赔金额的三分之二，则当前理赔案件为正常理赔案件，不再进行审核，以便减少人为处理的步骤，从而提高风险理赔案件评估的效率。
本申请提供了另一种风险理赔的评估方法，本申请实施例通过根据理赔信息及历史保单信息解析出与理赔案件相关的逻辑参数，将逻辑参数配置区间数后作为预置评估逻辑公式的参数进行运算，得到各个逻辑参数的评估分数，通过权值计算，统计出评估结果，与预置理赔金额比较，从而确定是否为风险理赔案件，实现计算机自动计算评估结果，无需人为操作，确保了每个理赔案件按照一个标准进行评估，并且，将所有的逻辑参数的数据通过预置评估逻辑公式以金额方式进行转化，实现了将理赔案件中的不同数值转换为金额形式来比较的目的，从而提高理赔案件评估的效率。
进一步的，作为对上述图1所示方法的实现，本申请实施例提供了一种风险理赔的评估装置，如图3所示，该装置包括：获取单元31、解析单元32、统计单元33。
获取单元31，用于获取理赔案件中被保险人的理赔信息及历史保单信息；所述获取单元31为风险理赔的评估装置执行获取理赔案件中被保险人的理赔信息及历史保单信息的功能模块。解析单元32，用于解析所述理赔信息及所述历史保单信息中待评估的逻辑参数，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况；所述解析单元32为风险理赔的评估装置执行解析所述理赔信息及所述历史保单信息中待评估的逻辑参数的功能模块。统计单元33，用于根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。所述统计单元33为风险理赔的评估装置执行根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果的功能模块。
本申请提供了一种风险理赔的评估装置，与现有的核损人员在进行理赔案件的审核时，都是通过人工审核，容易漏掉一些高风险案件相比，本申请实施例通过根据理赔信息及历史保单信息解析出与理赔案件相关的逻辑参数，将逻辑参数与预置评估逻辑进行匹配，得到评估结果，实现计算机自动计算评估结果，无需人为操作，确保了每个理赔案件按照一个标准进行评估，从而提高理赔案件评估 的效率。
进一步的，作为对上述图2所示方法的实现，本申请实施例提供了另一种风险理赔的评估装置，如图4所示，该装置包括：获取单元41、解析单元42、统计单元43、生成单元44、比较单元45、确定单元46。
获取单元41，用于获取理赔案件中被保险人的理赔信息及历史保单信息；解析单元42，用于解析所述理赔信息及所述历史保单信息中待评估的逻辑参数，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况；统计单元43，用于根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。
具体的，所述解析单元42包括：提取模块4201，用于提取所述理赔信息及所述历史保单信息中与次数类型、个数类型、费用类型、属性类型分别对应的逻辑参数；判断模块4202，用于判断所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数的数值是否分别大于预设的上限值、和/或小于预设的下限值；配置模块4203，用于若判断模块4202判断所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数的数值分别小于预设的上限值、和/或大于预设的下限值，则为所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数配置区间数，所述区间数用于区分替换预置评估逻辑公式对应的参数。
具体的，所述统计单元43包括：计算模块4301，用于用于按照预置评估逻辑公式以不同区间数计算所述次数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000013
其中i为区间数，x为次数类的逻辑参数的数值；以及所述计算模块4301，还用于按照预置评估逻辑公式以不同区间数计算所述个数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000014
其中i为区间数，y为个数类型的逻辑参数的数值；以及所述计算模块4301，还用于按照预置评估逻辑公式以不同区间数计算所述费用类型的逻辑参数对应的评估分数，所 述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000015
其中i为区间数，z为费用类型的逻辑参数的数值；以及所述计算模块4301，还用于按照预置评估逻辑公式以不同区间数计算所述属性类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
Figure PCTCN2018075677-appb-000016
其中i为区间数，l为属性类型的逻辑参数的数值；统计模块4302，用于按照预设的区间权值向量，统计得到所述次数类型、所述个数类型、所述费用类型、所述属性类型对应的评估分数的评估结果。
进一步地，所述装置还包括：生成单元44，用于根据不同理赔产品信息生成与理赔案件对应的区间权值向量，所述区间权值向量中费用类型对应的权值依次分别大于次数类型、个数类型、属性类型对应的权值。
进一步地，所述装置还包括：比较单元45，用于将所述评估结果与预置理赔金额进行比较；确定单元46，用于若比较结果为所述评估结果大于所述预置理赔金额的三分之二，则将所述理赔案件确定为风险理赔案件，并发送预警信息。
本申请提供了另一种风险理赔的评估装置，本申请实施例通过根据理赔信息及历史保单信息解析出与理赔案件相关的逻辑参数，将逻辑参数配置区间数后作为预置评估逻辑公式的参数进行运算，得到各个逻辑参数的评估分数，通过权值计算，统计出评估结果，与预置理赔金额比较，从而确定是否为风险理赔案件，实现计算机自动计算评估结果，无需人为操作，确保了每个理赔案件按照一个标准进行评估，并且，将所有的逻辑参数的数据通过预置评估逻辑公式以金额方式进行转化，实现了将理赔案件中的不同数值转换为金额形式来比较的目的，从而提高理赔案件评估的效率。
基于上述如图1所示方法，相应的，本申请实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现以下步骤：获取理赔案件中被保险人的理赔信息及历史保单信息；解析所述理赔信息及所述历史保单信息中待评估的逻辑参数，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况；根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。
如图5所示，该服务器可以包括：处理器(processor)51、通信接口(Communications Interface)52、存储器(memory)53、以及通信总线54。其中：处理器51、通信接口52、以及存储器53通过通信总线54完成相互间的通信。通信接口54，用于与其它设备比如客户端或其它服务器等的网元通信。处理器51，用于执行程序，具体可以执行上述应用程序的测试方法实施例中的相关步骤。具体地，程序可以包括程序代码，该程序代码包括计算机操作指令。处理器51可能是中央处理器CPU，或者是特定集成电路ASIC(Application Specific Integrated Circuit)，或者是被配置成实施本申请实施例的一个或多个集成电路。
终端包括的一个或多个处理器，可以是同一类型的处理器，如一个或多个CPU；也可以是不同类型的处理器，如一个或多个CPU以及一个或多个ASIC。存储器53，用于存放程序。存储器53可能包含高速RAM存储器，也可能还包括非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。程序具体可以用于使得处理器51执行以下操作：获取理赔案件中被保险人的理赔信息及历史保单信息；解析所述理赔信息及所述历史保单信息中待评估的逻辑参数，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况；根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。
在此提供的算法和显示不与任何特定计算机、虚拟***或者其它设备固有相关。各种通用***也可以与基于在此的示教一起使用。根据上面的描述，构造这类***所要求的结构是显而易见的。此外，本申请也不针对任何特定编程语言。应当明白，可以利用各种编程语言实现在此描述的本申请的内容，并且上面对特定语言所做的描述是为了披露本申请的最佳实施方式。在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本申请的实施例可以在没有这些具体细节的情况下实践。在一些实例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。
类似地，应当理解，为了精简本公开并帮助理解各个发明方面中的一个或多个，在上面对本申请的示例性实施例的描述中，本申请的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该公开的方法解释成 反映如下意图：即所要求保护的本申请要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说，如下面的权利要求书所反映的那样，发明方面在于少于前面公开的单个实施例的所有特征。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本申请的单独实施例。
本领域那些技术人员可以理解，可以对实施例中的设备中的模块进行自适应性地改变并且把它们设置在与该实施例不同的一个或多个设备中。可以把实施例中的模块或单元或组件组合成一个模块或单元或组件，以及此外可以把它们分成多个子模块或子单元或子组件。除了这样的特征和/或过程或者单元中的至少一些是相互排斥之外，可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组合意味着处于本申请的范围之内并且形成不同的实施例。例如，在下面的权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本申请的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本申请实施例的风险理赔的评估方法及装置中的一些或者全部部件的一些或者全部功能。本申请还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如，计算机程序和计算机程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
应该注意的是上述实施例对本申请进行说明而不是对本申请进行限制，并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。单词“包含”不排除存在未列在权利要求中的元件或步骤。位于元件之前的单词 “一”或“一个”不排除存在多个这样的元件。本申请可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。

Claims (20)

  1. 一种风险理赔的评估方法，其特征在于，包括：
    获取理赔案件中被保险人的理赔信息及历史保单信息；
    解析所述理赔信息及所述历史保单信息中待评估的逻辑参数，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况；
    根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。
  2. 根据权利要求1所述的方法，其特征在于，所述解析所述理赔信息及所述历史保单信息中待评估的逻辑参数包括：
    提取所述理赔信息及所述历史保单信息中与次数类型、个数类型、费用类型、属性类型分别对应的逻辑参数；判断所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数的数值是否分别大于预设的上限值、和/或小于预设的下限值；若小于预设的上限值、和/或大于预设的下限值，则为所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数配置区间数，所述区间数用于区分替换预置评估逻辑公式对应的参数。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果包括：
    按照预置评估逻辑公式以不同区间数计算所述次数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100001
    其中i为区间数，x为次数类的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述个数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100002
    其中i为区间数，y为个数类型的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述费用类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100003
    其中i为区间数，z为费用类型的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述属性类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100004
    其中i为区间数，l为属性类型的逻辑参数的数值；按照预设的区间权值向量，统计得到所述次数类型、所述个数类型、所述费用类型、所述属性类型对应的评估分数的评估结果。
  4. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    根据不同理赔产品信息生成与理赔案件对应的区间权值向量，所述区间权值向量中费用类型对应的权值依次分别大于次数类型、个数类型、属性类型对应的权值。
  5. 根据权利要求1所述的方法，其特征在于，所述根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果之后，所述方法还包括：
    将所述评估结果与预置理赔金额进行比较；若比较结果为所述评估结果大于所述预置理赔金额的三分之二，则将所述理赔案件确定为风险理赔案件，并发送预警信息。
  6. 一种风险理赔的评估装置，其特征在于，包括：获取单元，用于获取理赔案件中被保险人的理赔信息及历史保单信息；解析单元，用于解析所述理赔信息及所述历史保单信息中待评估的逻辑参数，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况；统计单元，用于根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。
  7. 根据权利要求6所述的装置，其特征在于，所述解析单元包括：提取模块，用于提取所述理赔信息及所述历史保单信息中与次数类型、个数类型、费用类型、属性类型分别对应的逻辑参数；判断模块，用于判断所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数的数值是否分别大于预设的上限值、和/或小于预设的下限值；配置模块，用于若判断模块判断所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数的数值分别小于预设的上限值、和/或大于预设的下限值，则为所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数配置区间数，所述区间数用于区分替换预置评估逻辑公式对应的参数。
  8. 根据权利要求7所述的装置，其特征在于，所述统计单元包括：计算模 块，用于按照预置评估逻辑公式以不同区间数计算所述次数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100005
    其中i为区间数，x为次数类的逻辑参数的数值；以及所述计算模块，还用于按照预置评估逻辑公式以不同区间数计算所述个数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100006
    其中i为区间数，y为个数类型的逻辑参数的数值；以及所述计算模块，还用于按照预置评估逻辑公式以不同区间数计算所述费用类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100007
    其中i为区间数，z为费用类型的逻辑参数的数值；以及所述计算模块，还用于按照预置评估逻辑公式以不同区间数计算所述属性类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100008
    其中i为区间数，l为属性类型的逻辑参数的数值；统计模块，用于按照预设的区间权值向量，统计得到所述次数类型、所述个数类型、所述费用类型、所述属性类型对应的评估分数的评估结果。
  9. 根据权利要求8所述的装置，其特征在于，所述装置还包括：生成单元，用于根据不同理赔产品信息生成与理赔案件对应的区间权值向量，所述区间权值向量中费用类型对应的权值依次分别大于次数类型、个数类型、属性类型对应的权值。
  10. 根据权利要求6所述的装置，其特征在于，所述装置还包括：比较单元，用于将所述评估结果与预置理赔金额进行比较；确定单元，用于若比较结果为所述评估结果大于所述预置理赔金额的三分之二，则将所述理赔案件确定为风险理赔案件，并发送预警信息。
  11. 一种存储介质，其上存储有计算机程序，其特征在于，所述程序被处理器执行时实现风险理赔的评估方法，包括：获取理赔案件中被保险人的理赔信息及历史保单信息；解析所述理赔信息及所述历史保单信息中待评估的逻辑参数，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况；根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。
  12. 根据权利要求11所述的存储介质，其特征在于，所述解析所述理赔信息及所述历史保单信息中待评估的逻辑参数包括：提取所述理赔信息及所述历史保单信息中与次数类型、个数类型、费用类型、属性类型分别对应的逻辑参数；判断所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数的数值是否分别大于预设的上限值、和/或小于预设的下限值；若小于预设的上限值、和/或大于预设的下限值，则为所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数配置区间数，所述区间数用于区分替换预置评估逻辑公式对应的参数。
  13. 根据权利要求12所述的存储介质，其特征在于，所述根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果包括：按照预置评估逻辑公式以不同区间数计算所述次数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100009
    其中i为区间数，x为次数类的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述个数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100010
    其中i为区间数，y为个数类型的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述费用类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100011
    其中i为区间数，z为费用类型的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述属性类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100012
    其中i为区间数，l为属性类型的逻辑参数的数值；按照预设的区间权值向量，统计得到所述次数类型、所述个数类型、所述费用类型、所述属性类型对应的评估分数的评估结果。
  14. 根据权利要求13所述的存储介质，其特征在于，所述方法还包括：根据不同理赔产品信息生成与理赔案件对应的区间权值向量，所述区间权值向量中费用类型对应的权值依次分别大于次数类型、个数类型、属性类型对应的权值。
  15. 根据权利要求11所述的存储介质，其特征在于，所述根据所述逻辑参 数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果之后，所述方法还包括：将所述评估结果与预置理赔金额进行比较；若比较结果为所述评估结果大于所述预置理赔金额的三分之二，则将所述理赔案件确定为风险理赔案件，并发送预警信息。
  16. 一种服务器，其特征在于，所述装置包括存储介质和处理器，所述存储介质，用于存储计算机程序；所述处理器，用于执行所述计算机程序以实现风险理赔的评估方法，包括：获取理赔案件中被保险人的理赔信息及历史保单信息；解析所述理赔信息及所述历史保单信息中待评估的逻辑参数，所述逻辑参数用于反应被保险人在理赔案件中参与医疗项目的情况；根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果，所述预置评估逻辑用于反应不同逻辑参数与不同评估分数之间的关系。
  17. 根据权利要求16所述的服务器，其特征在于，所述程序被处理器执行时实现所述解析所述理赔信息及所述历史保单信息中待评估的逻辑参数包括：提取所述理赔信息及所述历史保单信息中与次数类型、个数类型、费用类型、属性类型分别对应的逻辑参数；判断所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数的数值是否分别大于预设的上限值、和/或小于预设的下限值；若小于预设的上限值、和/或大于预设的下限值，则为所述次数类型、所述个数类型、所述费用类型、所述属性类型分别对应的逻辑参数配置区间数，所述区间数用于区分替换预置评估逻辑公式对应的参数。
  18. 根据权利要求17所述的服务器，其特征在于，所述程序被处理器执行时实现所述根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果包括：按照预置评估逻辑公式以不同区间数计算所述次数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100013
    其中i为区间数，x为次数类的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述个数类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100014
    其中i为区间数，y为个数类型的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述费用类型的逻辑参数对应的评估分数，所述预置 评估逻辑公式为
    Figure PCTCN2018075677-appb-100015
    其中i为区间数，z为费用类型的逻辑参数的数值；以及按照预置评估逻辑公式以不同区间数计算所述属性类型的逻辑参数对应的评估分数，所述预置评估逻辑公式为
    Figure PCTCN2018075677-appb-100016
    其中i为区间数，l为属性类型的逻辑参数的数值；按照预设的区间权值向量，统计得到所述次数类型、所述个数类型、所述费用类型、所述属性类型对应的评估分数的评估结果。
  19. 根据权利要求18所述的服务器，其特征在于，所述程序被处理器执行时实现所述方法还包括：根据不同理赔产品信息生成与理赔案件对应的区间权值向量，所述区间权值向量中费用类型对应的权值依次分别大于次数类型、个数类型、属性类型对应的权值。
  20. 根据权利要求16所述的服务器，其特征在于，所述程序被处理器执行时实现所述根据所述逻辑参数与预置评估逻辑进行匹配，并统计所述逻辑参数对应的理赔案件的评估结果之后，所述方法还包括：将所述评估结果与预置理赔金额进行比较；若比较结果为所述评估结果大于所述预置理赔金额的三分之二，则将所述理赔案件确定为风险理赔案件，并发送预警信息。
PCT/CN2018/075677 2017-11-22 2018-02-07 风险理赔的评估方法及装置 WO2019100601A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711171504.XA CN107871284A (zh) 2017-11-22 2017-11-22 风险理赔的评估方法及装置
CN201711171504.X 2017-11-22

Publications (1)

Publication Number Publication Date
WO2019100601A1 true WO2019100601A1 (zh) 2019-05-31

Family

ID=61754451

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/075677 WO2019100601A1 (zh) 2017-11-22 2018-02-07 风险理赔的评估方法及装置

Country Status (2)

Country Link
CN (1) CN107871284A (zh)
WO (1) WO2019100601A1 (zh)

Families Citing this family (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108399532A (zh) * 2018-04-12 2018-08-14 阿里巴巴集团控股有限公司 处理业务的可用资源的方法和装置
CN109542923B (zh) * 2018-05-28 2023-06-16 深圳平安医疗健康科技服务有限公司 核保方法、装置、计算机设备和存储介质
CN109522400B (zh) * 2018-05-28 2023-07-07 深圳平安医疗健康科技服务有限公司 核保方法、装置、计算机设备和存储介质
CN108876636B (zh) * 2018-06-19 2023-10-27 平安健康保险股份有限公司 理赔智能风控方法、***、计算机设备及存储介质
CN108898316A (zh) * 2018-07-02 2018-11-27 平安健康保险股份有限公司 理赔费用预警方法及***
CN109359802B (zh) * 2018-08-27 2023-10-31 平安健康保险股份有限公司 逆选择风险确定方法、***、计算机设备及存储介质
CN109146696A (zh) * 2018-09-03 2019-01-04 汇保医联信息科技有限公司 商业保险的风控核查方法、装置和电子设备
CN109360109A (zh) * 2018-09-26 2019-02-19 平安医疗健康管理股份有限公司 基于大数据分析和处理的智能理赔审核辅助方法和***
CN109272241A (zh) * 2018-09-29 2019-01-25 北京优全智汇信息技术有限公司 一种核赔方法和装置
CN109492095A (zh) * 2018-10-16 2019-03-19 平安健康保险股份有限公司 理赔数据处理方法、装置、计算机设备及存储介质
CN109636085A (zh) * 2018-10-24 2019-04-16 平安健康保险股份有限公司 基于数据处理的预授权自核方法及***
CN109544103A (zh) * 2018-10-30 2019-03-29 平安医疗健康管理股份有限公司 一种理赔模型的构建方法、装置、服务器及存储介质
CN109636626A (zh) * 2018-11-30 2019-04-16 平安医疗健康管理股份有限公司 免疫病报销准入方法、装置、设备及可读存储介质
CN109636644A (zh) * 2018-12-13 2019-04-16 平安医疗健康管理股份有限公司 医疗报销项目异常的监控方法、监控服务端及存储介质
CN109785161B (zh) * 2018-12-13 2024-07-09 深圳平安医疗健康科技服务有限公司 一种寿险核损数据处理方法、服务器及计算机可读介质
CN109636637A (zh) * 2018-12-13 2019-04-16 平安医疗健康管理股份有限公司 报销处理方法、装置、终端及计算机可读存储介质
CN109685670A (zh) * 2018-12-13 2019-04-26 平安医疗健康管理股份有限公司 社保违规检测方法、装置、设备及计算机可读存储介质
CN109685671A (zh) * 2018-12-13 2019-04-26 平安医疗健康管理股份有限公司 基于机器学习的就诊数据异常识别方法、设备及存储介质
CN109767343A (zh) * 2018-12-13 2019-05-17 平安医疗健康管理股份有限公司 意外险核损数据处理方法、服务器及计算机可读存储介质
CN109784644B (zh) * 2018-12-14 2024-03-15 平安科技（深圳）有限公司 案件分配方法、装置、计算机设备和存储介质
CN109784706A (zh) * 2019-01-03 2019-05-21 深圳壹账通智能科技有限公司 数值计算方法、装置、计算机设备和存储介质
CN109859059A (zh) * 2019-01-17 2019-06-07 深圳壹账通智能科技有限公司 保险理赔方法、装置、计算机设备及存储介质
CN110009515A (zh) * 2019-03-12 2019-07-12 中国平安财产保险股份有限公司 基于人脸识别的单据校验方法、装置、服务器及介质
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
CN110689441B (zh) * 2019-08-15 2023-06-27 平安健康保险股份有限公司 基于共性抽取的案件审核方法、装置、设备及存储介质
CN111008902B (zh) * 2019-11-25 2023-07-18 泰康保险集团股份有限公司 核保数据处理方法、装置、设备和介质
CN111738867A (zh) * 2020-04-17 2020-10-02 世纪保众(北京)网络科技有限公司 一种保险产品理赔宽松度可量化评估的方法和装置
CN112634064A (zh) * 2020-12-02 2021-04-09 北京健康之家科技有限公司 理赔智能审核方法及装置、***、存储介质
TWI819584B (zh) * 2022-04-28 2023-10-21 國泰人壽保險股份有限公司 保險理賠風險偵查方法與系統、電腦可讀取的記錄媒體

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106920066A (zh) * 2016-08-03 2017-07-04 阿里巴巴集团控股有限公司 信息处理方法和装置
CN106952162A (zh) * 2016-01-07 2017-07-14 平安科技（深圳）有限公司 洗钱风险等级计算方法及***
WO2017148160A1 (zh) * 2016-03-04 2017-09-08 深圳市前海安测信息技术有限公司 基于生物信息的健康保险风险评估***
CN107169869A (zh) * 2017-04-06 2017-09-15 平安科技（深圳）有限公司 信息处理方法和信息处理装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106952162A (zh) * 2016-01-07 2017-07-14 平安科技（深圳）有限公司 洗钱风险等级计算方法及***
WO2017148160A1 (zh) * 2016-03-04 2017-09-08 深圳市前海安测信息技术有限公司 基于生物信息的健康保险风险评估***
CN106920066A (zh) * 2016-08-03 2017-07-04 阿里巴巴集团控股有限公司 信息处理方法和装置
CN107169869A (zh) * 2017-04-06 2017-09-15 平安科技（深圳）有限公司 信息处理方法和信息处理装置

Also Published As

Publication number Publication date
CN107871284A (zh) 2018-04-03

Similar Documents

Publication Publication Date Title
WO2019100601A1 (zh) 风险理赔的评估方法及装置
JP6637135B2 (ja) 年配者コホートの慢性的重大疾患リスクについてリスク共有するための、患者データによりトリガされるプーリングシステム、及びその対応する方法
Mountain et al. Antiretroviral therapy uptake, attrition, adherence and outcomes among HIV-infected female sex workers: a systematic review and meta-analysis
CN109544364B (zh) 基于数据分析的违规行为检测方法、装置及终端
Hossain et al. Modelling coordination in hospital emergency departments through social network analysis
CN109615547A (zh) 异常购药的识别方法、装置、终端及计算机可读存储介质
JP2018060527A (ja) 情報処理装置、情報処理方法及びプログラム
WO2018184300A1 (zh) 信息处理方法、信息处理装置及计算机可读存储介质
CN112330466A (zh) 医保基金违规操作事件的在线监控方法及装置
US20080249788A1 (en) Method for developing an objective opinion
CN110490750B (zh) 数据识别的方法、***、电子设备及计算机存储介质
US10346921B2 (en) Parametric system for risk sharing of critical illness risks and corresponding method thereof
Diel et al. Enhanced cost-benefit analysis of strategies for LTBI screening and INH chemoprevention in Germany
CN113673870A (zh) 一种企业数据分析方法及相关组件
Berera et al. Antivirals in the 2009 pandemic–lessons and implications for future strategies
Wu et al. A simulation study of outpatient scheduling with multiple providers and a single device
CN109636647A (zh) 异常购药的识别方法、装置、终端及计算机可读存储介质
WO2020082809A1 (zh) 基于数据分析的医疗项目风控方法、装置、服务器及介质
Thorpe et al. Combating Medicare fraud: A struggling work in progress
Votruba et al. Medical adverse events and malpractice litigation in Arizona: By-the-numbers
Bartolomeo et al. A multistate model to evaluate COPD progression integrating drugs consumption data and hospital databases
Liu et al. Controlling HIV/AIDS in China: Health system challenges
Puteh et al. The Common Types of Health Insurance Fraud among Insured and Healthcare Provider
Zealand Serious injury outcome indicators–concepts and methods for 2000–11
WO2019019624A1 (zh) 控制撤单退款的方法、装置、计算机设备及存储介质

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: 18881158

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 01.10.2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18881158

Country of ref document: EP

Kind code of ref document: A1