CN109409648A - Claims Resolution air control method, apparatus, computer equipment and storage medium - Google Patents
Claims Resolution air control method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109409648A CN109409648A CN201811052447.8A CN201811052447A CN109409648A CN 109409648 A CN109409648 A CN 109409648A CN 201811052447 A CN201811052447 A CN 201811052447A CN 109409648 A CN109409648 A CN 109409648A
- Authority
- CN
- China
- Prior art keywords
- probability distribution
- basic probability
- evaluation information
- wind control
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000011156 evaluation Methods 0.000 claims abstract description 94
- 230000004927 fusion Effects 0.000 claims abstract description 14
- 238000009826 distribution Methods 0.000 claims description 114
- 230000006870 function Effects 0.000 claims description 60
- 238000012545 processing Methods 0.000 claims description 27
- 238000010606 normalization Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 18
- 238000012937 correction Methods 0.000 claims description 12
- 238000012790 confirmation Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract 1
- 238000007405 data analysis Methods 0.000 abstract 1
- 238000005315 distribution function Methods 0.000 description 20
- 238000012954 risk control Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 239000003814 drug Substances 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000009916 joint effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention discloses a kind of Claims Resolution air control method, apparatus, computer equipment and storage mediums.The present invention applies the field in big data in conjunction with artificial intelligence, is the intelligent predicting based on big data analysis.The described method includes: obtaining the risks and assumptions of Claims Resolution case；The evaluation information of the risks and assumptions is determined according to preset vulnerability database；It is normalized to obtain basic probability assignment using the subordinating degree function that fuzzy theory obtains the evaluation information；And the basic probability assignment is carried out to obtain the air control conclusion of the risks and assumptions by fusion according to rule of combination.The air control accuracy of Claims Resolution case can be improved in method by implementing the embodiment of the present invention, improves the controllability of air control cost, improves insurance service quality.
Description
Technical Field
The invention relates to the technical field of insurance claim settlement wind control, in particular to a claim settlement wind control method and device, computer equipment and a storage medium.
Background
With the development of science and economy, insurance has become a very important guarantee mode in people's daily life. However, some people attempt to gain interest in cheating insurance funds by creating false accident artifacts, and insurance companies spend a great deal of manpower and material on identifying such fraudulent insurance claim cases. The existing insurance claim wind control measures are generally used for risk control of claim cases by setting rules by insurance experts, so that the existing insurance claim wind control measures have high requirements on professional knowledge capability, risk judgment capability and insurance claim experience of the insurance experts, and different insurance experts have different risk control on the same claim case. For an insurance company, the risk control made by an insurance expert can greatly influence the wind control cost, the low-precision risk control can cause the wind control cost to be uncontrollable, and the quality of insurance service is reduced.
Disclosure of Invention
The embodiment of the invention provides a method and a device for claim settlement wind control, computer equipment and a storage medium, and aims to improve the risk control accuracy of claim settlement cases.
In a first aspect, an embodiment of the present invention provides a method for claim settlement wind control, including: acquiring risk factors of a claim case, wherein the risk factors are claim information used for judging whether the claim case has fraud possibility; determining the evaluation information of the risk factors according to a preset risk database; obtaining a membership function of the evaluation information by using a fuzzy theory and carrying out normalization processing to obtain basic probability distribution; and fusing the basic probability distribution according to a combination rule so as to obtain a wind control conclusion of the risk factor.
In a second aspect, an embodiment of the present invention further provides a claim settlement wind control device, which includes: the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring risk factors of a claim settlement case, and the risk factors are claim settlement information used for judging whether the claim settlement case has fraud possibility; the determining unit is used for determining the evaluation information of the risk factors according to a preset risk database; the normalization unit is used for obtaining a membership function of the evaluation information by using a fuzzy theory and carrying out normalization processing so as to obtain basic probability distribution; and the fusion unit is used for fusing the basic probability distribution according to a combination rule so as to obtain a wind control conclusion of the risk factor.
In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the above method when executing the computer program.
In a fourth aspect, the present invention also provides a computer-readable storage medium, which stores a computer program, and the computer program can implement the above method when being executed by a processor.
The embodiment of the invention provides a claim settlement wind control method and device, computer equipment and a storage medium. Wherein the method comprises the following steps: acquiring risk factors of the claim cases; determining the evaluation information of the risk factors according to a preset risk database; obtaining a membership function of the evaluation information by using a fuzzy theory and carrying out normalization processing to obtain basic probability distribution; and fusing the basic probability distribution according to a combination rule to obtain a wind control conclusion of the risk factor. According to the embodiment of the invention, the basic probability distribution is fused through the combination rule, so that the wind control accuracy of each risk factor can be improved, the wind control accuracy of claim settlement cases is further improved, the controllability of wind control cost is improved, and the insurance service quality is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic application scenario diagram of a claim settlement wind control method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a claim settlement wind control method according to an embodiment of the present invention;
fig. 3 is a schematic sub-flow chart of a claim settlement wind control method according to an embodiment of the present invention;
fig. 4 is a schematic sub-flow chart of a claim settlement wind control method according to an embodiment of the present invention;
fig. 5 is a schematic sub-flow chart of a claim settlement wind control method according to an embodiment of the present invention;
fig. 6 is a schematic block diagram of a claim settlement wind control device provided in an embodiment of the present invention;
fig. 7 is a schematic block diagram of a normalization unit of the claim settlement wind control device provided in the embodiment of the present invention;
fig. 8 is a schematic block diagram of a fusion unit of the claim settlement wind control device provided in the embodiment of the present invention; and
FIG. 9 is a schematic block diagram of a computer device provided by an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic view of an application scenario of the claim settlement wind control method according to the embodiment of the present invention. Fig. 2 is a schematic flowchart of a claim settlement wind control method according to an embodiment of the present invention. The claim wind control method is applied to the terminal 10. The terminal 10 is connected to the server 20 to receive all information on the claim cases transmitted by the server 20. The claim settlement wind control method is suitable for insurance claim settlement cases which can be cases such as vehicle insurance, medical insurance, property insurance and the like.
Fig. 2 is a schematic flow chart of a claim settlement wind control method according to an embodiment of the present invention. As shown in fig. 2, the method comprises the following steps S110-S150.
S110, obtaining risk factors of the claim cases, wherein the risk factors are claim information used for judging whether the claim cases have fraud possibility.
In one embodiment, the claim settlement case is an event that the insurance applicant has an insurance accident within the scope of application and asks the insurance company for insurance funds. For example, an event where an applicant has a vehicle accident and asks an insurance company for insurance coverage; or an event in which the applicant suddenly becomes ill and asks an insurance company for insurance funds. In processing the claim cases, the insurance company firstly collects all the claim information related to the claim cases. In the medical claims case, the claims information includes, for example, insurance policy, medical history, and medical invoice; the vehicle insurance claim case includes, for example, an insurance policy, a loss policy, a responsibility approval, and the like. After the claim information is obtained, acquiring risk factors for judging whether fraud exists in the claim case from the claim information, wherein in the medical claim case, the risk factors comprise diagnosis records in medical records, inspection items, medicine lists in medicine invoices and the like; in the case of vehicle insurance claims, the risk factors are, for example, the vehicle model in the insurance policy, the damaged parts in the damage policy, the time and place of the accident in the responsibility approval, and the like.
In one embodiment, as shown in FIG. 3, the step S110 may include steps S111-S112.
And S111, acquiring the claim settlement information in the claim settlement case from the server.
In one embodiment, the claim information is uploaded to the server by the applicant or insurance staff, e.g., the insurance staff uploads insurance policies, loss orders, and responsibility claims provided by the applicant to the server. And the terminal receives the claim settlement information of the vehicle insurance claim settlement case through the server.
And S112, extracting risk factors from the claim settlement information according to a preset risk database.
In an embodiment, since the claim information includes the claim information that can be used for judging whether fraud is possible and other claim information that is irrelevant to judging whether fraud is possible, the claim information that is used for judging whether fraud is possible needs to be extracted from the claim information as the risk factor. The risk database is a data set of risk factors preset by insurance experts, after the claim information is obtained, the risk factors in the risk database are matched with the claim information, and if the claim information has risk factors matched with the risk factors preset by the risk database, the risk factors in the claim information are extracted. For example, the insurance policy includes claim information such as name, age, household registration, vehicle model, vehicle age, etc. of the applicant, where the vehicle model and the vehicle age are risk factors preset in the risk database, and the claim information includes claim information of the vehicle model and the vehicle age, and then the vehicle model is the B brand in the claim information is extracted as one risk factor, and the vehicle age is 6 years as another risk factor.
And S120, determining the evaluation information of the risk factors according to a preset risk database.
In an embodiment, the preset risk database further includes a data set of a corresponding relationship between a risk factor preset by an insurance expert and the evaluation information. After the risk factor is obtained, the evaluation information corresponding to the risk factor is searched from the risk database so as to determine the evaluation information of the risk factor. In this embodiment, there are three types of evaluation information, namely, the presence of fraud, the absence of fraud, and the uncertainty of the presence or absence of fraud. For example, for the risk factor with the vehicle model of B, obtaining the fraud-free evaluation information according to a preset rule; obtaining the evaluation information of the fraud for the risk factors with the risk time being a little in the morning according to a preset rule; and obtaining the evaluation information which is uncertain whether the fraud exists according to the preset rule for the risk factor of which the insurance place is national road.
And S130, obtaining the membership function of the evaluation information by using a fuzzy theory, and performing normalization processing to obtain basic probability distribution.
In one embodiment, since the evaluation information is not a quantized value, but a fuzzy evaluation, such as the presence of fraud, the absence of fraud, and the uncertainty of the presence or absence of fraud, cannot satisfy the calculation condition, it is necessary to perform normalization processing on the evaluation information to obtain a quantized value.
In one embodiment, as shown in FIG. 4, the step S130 may include steps S131-S133.
S131, constructing a membership function of the evaluation information by using a fuzzy theory.
In one embodiment, fuzzy theory refers to theory that uses the basic concept of fuzzy sets or continuous membership functions. The membership function is a mathematical tool used to characterize fuzzy sets and, in order to describe the membership of an element to a fuzzy set on a subset, it will be used from the interval 0,1 due to the ambiguity of this relationship]The numerical value in (1) is described by replacing two values of 0 and 1, and represents the "true degree" of the element belonging to a fuzzy set. In this embodiment, let Θ be ═ θ1、θ2、θ3…θnTheta is a discourse domain and represents all possibilities of whether fraud exists in the evaluation information, theta is a fuzzy subset, and theta is a discourse domain and represents all possibilities of fraud in the evaluation informationnIs the nth fuzzy subset, and satisfies the following conditions: theta is equal to theta, P (theta) → [0,1 ]]P (theta) is called as a membership function of the evaluation information. Where the domain theta includes theta1、θ2、θ3Three fuzzy subsets, theta1For the presence of a fraudulent fuzzy subset, θ2For fuzzy subsets without fraud, θ3Is an ambiguous subset that is uncertain as to whether fraud is present. Then theta1、θ2、θ3The corresponding membership functions are respectively: p (theta)1)、P(θ2)、P(θ3). Wherein, the specific formula of the membership function is determined by an expert experience method. The expert experience method is a method for determining membership functions by giving processing equations of fuzzy information or corresponding weight coefficient values according to actual experience of experts. I.e. the membership function is set up by the insurance specialist according to certain rules.
And S132, obtaining the corresponding membership degree of the evaluation information through the membership degree function.
In one embodiment, after the membership function is determined, the evaluation information is input into the membership function to obtain the membership of the evaluation information. The membership degree is an output value of a membership function and represents a membership degree of evaluation information belonging to a certain fuzzy subset. For example, the evaluation information of the vehicle model B is input into the membership function to obtain P (theta)1)＝0.2、P(θ2)＝0.7、P(θ3) 0.1. Wherein, P (theta)1) 0.2 indicates that the evaluation information of the vehicle model B has fraud, and the membership of P (θ) is 0.22) 0.7, the membership degree of the evaluation information indicating that the vehicle model is the B brand is 0.7, P (θ)3) The membership degree of 0.1 indicating that the evaluation information of the vehicle model B is not certain whether or not fraud is present is 0.1.
And S133, distributing the membership degree as basic probability.
In one embodiment, the base is first constructedProbability distribution function, Basic Probability distribution function is used to distribute to each proposition trust degree, Basic Probability distribution (BPA) is the output value of Basic Probability distribution function to express trust degree to proposition. Let the recognition frame be Θ, Θ ═ θ1、θ2、θ3…θnThe recognition framework represents the set of all possible answers to the proposition, and theta represents one of the possible answers. For example, Θ is a set of evaluation information of risk factors in a claim case, which includes three possible kinds of θ1、θ2、θ3，θ1Indicating the presence of fraud, θ2Indicating the absence of fraud, θ3Indicating that it is uncertain whether fraud is present. Definition m:2Θ→[0,1]And the following conditions are satisfied:
therein, 2ΘA set which is formed by all subsets of a recognition framework theta is represented and is called a power set of theta, the formula (1) represents that the basic probability distribution of an empty set is 0, and the formula (2) represents 2ΘThe sum of the basic probability assignments for all of the above elements is 1. When the above conditions are satisfied, m is 2ΘThe above basic probability distribution function is a basic probability distribution in which m (θ) is θ, and represents the degree of confidence in the proposition θ.
And after the basic probability distribution function is constructed, assigning the obtained membership degree to the basic probability distribution function to obtain basic probability distribution.
P(θ)＝m(θ) (3)
For example, the membership degree of the vehicle model B is assigned to the basic probability distribution function to obtain the basic probability distribution of 0.2, and m (theta) is obtained through the formula (3)1)＝P(θ1)＝0.2，m(θ1) The confidence level that the vehicle model is B card fraud is 0.2; assigning membership grade of which the evaluation information of the vehicle model is B card is that no fraud exists to a baseThe basic probability distribution obtained by the probability distribution function is 0.7, and m (theta) is obtained by the formula (3)2)＝P(θ2)＝0.7，m(θ2) A confidence level of 0.7 indicating that fraud is not present for the vehicle model B; assigning membership grade of which the vehicle model is B card to a basic probability distribution function to obtain the basic probability distribution of 0.1, and obtaining m (theta) through a formula (3)3)＝P(θ3)＝0.1，m(θ3) The confidence level indicating that the vehicle model is B card and whether fraud is uncertain is 0.1.
And S140, fusing the basic probability distribution according to a combination rule to obtain a wind control conclusion of the risk factor.
In one embodiment, the composition rule is a composition rule that may represent a joint effect between evidence. In this embodiment, the basic probability distribution function is the evidence in the combination rule, and the basic probability distribution is expressed as the trust level of the evidence. For example, in a case of claims for insurance settlement, the risk factor is the type of the vehicle is brand B, the evaluation information is obtained according to the preset rules respectively set by the insurance experts 1 and 2, and the basic probability distribution m is obtained after normalization processing1(θ1)、m1(θ2)、m1(θ3) And m2(θ1)、m2(θ2)、m2(θ3)，m1(θ1) Representing the degree of confidence that insurance expert 1 has fraud on the type B of vehicle, m1(θ2) Representing the degree of confidence that insurance expert 1 does not have fraud on the type B of vehicle, m1(θ3) Representing the trust degree of the insurance expert 1 on whether the vehicle model B is uncertain or not to have fraud; m is2(θ1) M represents the confidence level that the insurance expert 2 has fraud on the vehicle model B2(θ2) M represents the degree of confidence that insurance expert 2 does not have fraud on the vehicle model B2(θ3) Representing the degree of confidence that the insurance expert 2 has that the vehicle model B is uncertain as to whether fraud is present. M is combined according to a combination rule1(θ1) Andm2(θ1) Performing fusion of m1(θ2) And m2(θ2) Performing fusion of m1(θ3) And m2(θ3) And performing fusion to obtain corresponding joint basic probability distribution, wherein the fusion refers to a process of inputting the two evidences into a combination rule as input to obtain the joint basic probability distribution. The maximum joint base probability assignment indicates the greatest confidence in the evidence, and thus the maximum joint base probability assignment is used as a wind-controlled conclusion of the risk factor, e.g., m1(θ2) And m2(θ2) And the fused joint basic probability is the maximum, and the wind control conclusion of the risk factor with the vehicle model number of B is that no fraud exists.
In one embodiment, as shown in FIG. 5, the step S140 may include steps S141-S143.
And S141, correcting the basic probability distribution through a correction factor.
In one embodiment, each evidence is of different importance due to the different knowledge abilities of each insurance expert, thereby giving the evidence different degrees of confidence and weight. And correcting the evidence by introducing a correction factor to obtain more accurate evidence.
Wherein, crw,iAs a correction factor, wiRepresents a weight, riRepresenting confidence and i representing the ith evidence. m isθ,iRepresenting the basic probability distribution before the correction,denotes the corrected basic probability distribution, and P (theta) denotesEquations (5) and (6) represent specific equations for modifying the basic probability distribution for a superset of θ. The weight and confidence level are both [0,1 ]]The weight is given in a value range according to the importance degree of the evidence, and the reliability is given in the value range according to the knowledge ability of the expert.
And S142, fusing the corrected basic probability distribution according to the combination rule to obtain combined basic probability distribution.
In one embodiment, the modified base probability distribution is substituted into the combination rule to obtain a joint base probability distribution.
Wherein,for joint fundamental probability distribution, equations (7) and (8) are combination rules.
And S143, taking the maximum joint basic probability distribution as a wind control conclusion of the risk factors.
In an embodiment, joint basic probability distribution is obtained according to a combination rule, wherein evaluation information corresponding to the maximum joint probability distribution is a final conclusion. For example, the basic probability assignments in table 1 are fused according to a combination rule.
Table 1:
deriving joint fundamental probability distributions from combinatorial rulesAndwhereinThat is to sayThe value of (a) is the largest,and the corresponding evaluation information indicates that the vehicle model is the B card and no fraud exists, so that the conclusion is that the vehicle model is the B card and no fraud exists.
Through the steps, different evidences are fused, and the problem that different insurance experts make different risk judgments on the same claim settlement case is solved. Each risk factor obtains a more accurate wind control conclusion through a claim settlement wind control method, so that a decision maker can carry out risk control on claim settlement cases according to all high-accuracy risk factors, and the risk control accuracy of the claim settlement cases is improved.
S150, obtaining a trust interval of the joint basic probability distribution according to the joint basic probability distribution by using an evidence theory so as to represent the confirmation degree of the evaluation information corresponding to the joint basic probability distribution.
In one embodiment, a trust function and a likelihood function of joint basic probability distribution are solved according to an evidence theory to obtain a trust interval. Evidence theory is a reasoning method with the ability to handle uncertain information. The trust function represents the trust degree of the evidence being true, and the likelihood function represents the trust degree of the evidence being not false, so that the trust interval composed of the trust function and the likelihood function can be used for representing the confirmation degree of the evidence.
Wherein Bel (theta) is a trust function, Pl (theta) is a likelihood function, and a trust interval [ Bel (theta), Pl (theta) is formed by Bel (theta) and Pl (theta)]. For example, joint fundamental probability distribution is calculated according to equations (9) and (10)Has a trust interval of 0.55,0.85]0.55 represents the confidence level that the fraud is not true for the vehicle model B, 0.85 represents the confidence level that the fraud is not false for the vehicle model B, 0.85-0.55-0.3 represents the confidence level that the fraud is not uncertain for the vehicle model B, and 1-0.85-0.15 represents the confidence level that the fraud is not false for the vehicle model B.
The embodiment of the invention discloses a claim settlement wind control method, which comprises the steps of obtaining risk factors of claim settlement cases; determining the evaluation information of the risk factors according to a preset risk database; obtaining a membership function of the evaluation information by using a fuzzy theory and carrying out normalization processing to obtain basic probability distribution; and fusing the basic probability distribution according to the combination rule to obtain a wind control conclusion of the risk factors, so that the wind control accuracy of each risk factor can be improved, the wind control accuracy of claim cases is further improved, the controllability of wind control cost is improved, and the insurance service quality is improved.
Fig. 6 is a schematic block diagram of a claim wind control device according to an embodiment of the present invention. As shown in fig. 6, the invention further provides a claim settlement wind control device 200 corresponding to the claim settlement wind control method. The claim wind control device comprises a unit for executing the claim wind control method, and the device can be configured in a desktop computer, a tablet computer, a portable computer, and the like. Specifically, referring to fig. 6, the claim wind control apparatus 200 includes an obtaining unit 210, a determining unit 220, a normalizing unit 230, and a fusing unit 240.
The obtaining unit 210 is configured to obtain a risk factor of a claim case, where the risk factor is claim information used for determining whether the claim case has a possibility of fraud.
In one embodiment, the claim settlement case is an event that the insurance applicant has an insurance accident within the scope of application and asks the insurance company for insurance funds. For example, an event where an applicant has a vehicle accident and asks an insurance company for insurance coverage; or an event in which the applicant suddenly becomes ill and asks an insurance company for insurance funds. In processing the claim cases, the insurance company firstly collects all the claim information related to the claim cases. In the medical claims case, the claims information includes, for example, insurance policy, medical history, and medical invoice; the vehicle insurance claim case includes, for example, an insurance policy, a loss policy, a responsibility approval, and the like. After the claim information is obtained, acquiring risk factors for judging whether fraud exists in the claim case from the claim information, wherein in the medical claim case, the risk factors comprise diagnosis records in medical records, inspection items, medicine lists in medicine invoices and the like; in the case of vehicle insurance claims, the risk factors are, for example, the vehicle model in the insurance policy, the damaged parts in the damage policy, the time and place of the accident in the responsibility approval, and the like.
The determining unit 220 is configured to determine the evaluation information of the risk factor according to a preset risk database.
In an embodiment, the preset risk database further includes a data set of a corresponding relationship between a risk factor preset by an insurance expert and the evaluation information. After the risk factor is obtained, the evaluation information corresponding to the risk factor is searched from the risk database so as to determine the evaluation information of the risk factor. In this embodiment, there are three types of evaluation information, namely, the presence of fraud, the absence of fraud, and the uncertainty of the presence or absence of fraud. For example, for the risk factor with the vehicle model of B, obtaining the fraud-free evaluation information according to a preset rule; obtaining the evaluation information of the fraud for the risk factors with the risk time being a little in the morning according to a preset rule; and obtaining the evaluation information which is uncertain whether the fraud exists according to the preset rule for the risk factor of which the insurance place is national road.
And the normalization unit 230 is configured to perform normalization processing on the membership function of the evaluation information obtained by using a fuzzy theory to obtain basic probability distribution.
In one embodiment, since the evaluation information is not a quantized value, but a fuzzy evaluation, such as the presence of fraud, the absence of fraud, and the uncertainty of the presence or absence of fraud, cannot satisfy the calculation condition, it is necessary to perform normalization processing on the evaluation information to obtain a quantized value.
In one embodiment, as shown in fig. 7, the normalization unit 230 includes sub-units: a building unit 231, a membership unit 232, and a basic probability distribution unit 233.
And the constructing unit 231 is used for constructing the membership function of the evaluation information by using a fuzzy theory.
In one embodiment, fuzzy theory refers to theory that uses the basic concept of fuzzy sets or continuous membership functions. The membership function is a mathematical tool used to characterize fuzzy sets and, in order to describe the membership of an element to a fuzzy set on a subset, it will be used from the interval 0,1 due to the ambiguity of this relationship]The numerical value in (1) is described by replacing two values of 0 and 1, and represents the "true degree" of the element belonging to a fuzzy set. In this embodiment, let Θ be ═ θ1、θ2、θ3…θnTheta is a discourse domain and represents all possibilities of whether fraud exists in the evaluation information, theta is a fuzzy subset, and theta is a discourse domain and represents all possibilities of fraud in the evaluation informationnIs the nth fuzzy subset, and satisfies the following conditions: theta is equal to theta, P (theta) → [0,1 ]]P (theta) is called as a membership function of the evaluation information. Where the domain theta includes theta1、θ2、θ3Three fuzzy subsets, theta1For the presence of a fraudulent fuzzy subset, θ2For fuzzy subsets without fraud, θ3Obfuscating to determine whether fraud is presentA subset. Then theta1、θ2、θ3The corresponding membership functions are respectively: p (theta)1)、P(θ2)、P(θ3). Wherein, the specific formula of the membership function is determined by an expert experience method. The expert experience method is a method for determining membership functions by giving processing equations of fuzzy information or corresponding weight coefficient values according to actual experience of experts. I.e. the membership function is set up by the insurance specialist according to certain rules.
And a membership unit 232, configured to obtain a membership corresponding to the evaluation information through the membership function.
In one embodiment, after the membership function is determined, the evaluation information is input into the membership function to obtain the membership of the evaluation information. The membership degree is an output value of a membership function and represents a membership degree of evaluation information belonging to a certain fuzzy subset. For example, the evaluation information of the vehicle model B is input into the membership function to obtain P (theta)1)＝0.2、P(θ2)＝0.7、P(θ3) 0.1. Wherein, P (theta)1) 0.2 indicates that the evaluation information of the vehicle model B has fraud, and the membership of P (θ) is 0.22) 0.7, the membership degree of the evaluation information indicating that the vehicle model is the B brand is 0.7, P (θ)3) The membership degree of 0.1 indicating that the evaluation information of the vehicle model B is not certain whether or not fraud is present is 0.1.
And a basic probability distribution unit 233, configured to distribute the membership degree as a basic probability.
In one embodiment, a Basic Probability distribution function is first constructed, where the Basic Probability distribution function is a function for distributing to each proposition confidence level, and Basic Probability distribution (BPA) is a function where an output value of the Basic Probability distribution function represents the confidence level for a proposition. Let the recognition frame be Θ, Θ ═ θ1、θ2、θ3…θnThe recognition framework represents the set of all possible answers to the proposition, and theta represents one of the possible answers. For example, the principle of thetaThe evaluation information set of the risk factors in the claims comprises three possible theta1、θ2、θ3，θ1Indicating the presence of fraud, θ2Indicating the absence of fraud, θ3Indicating that it is uncertain whether fraud is present. Definition m:2Θ→[0,1]And the following conditions are satisfied:
therein, 2ΘA set which is formed by all subsets of a recognition framework theta is represented and is called a power set of theta, the formula (1) represents that the basic probability distribution of an empty set is 0, and the formula (2) represents 2ΘThe sum of the basic probability assignments for all of the above elements is 1. When the above conditions are satisfied, m is 2ΘThe above basic probability distribution function is a basic probability distribution in which m (θ) is θ, and represents the degree of confidence in the proposition θ.
And after the basic probability distribution function is constructed, assigning the obtained membership degree to the basic probability distribution function to obtain basic probability distribution.
P(θ)＝m(θ) (3)
For example, the membership degree of the vehicle model B is assigned to the basic probability distribution function to obtain the basic probability distribution of 0.2, and m (theta) is obtained through the formula (3)1)＝P(θ1)＝0.2，m(θ1) The confidence level that the vehicle model is B card fraud is 0.2; assigning membership grade of which the vehicle model is B card to a basic probability distribution function to obtain the basic probability distribution of 0.7, and obtaining m (theta) through a formula (3)2)＝P(θ2)＝0.7，m(θ2) A confidence level of 0.7 indicating that fraud is not present for the vehicle model B; assigning membership grade of which the vehicle model is B card to a basic probability distribution function to obtain the basic probability distribution of 0.1, and obtaining m (theta) through a formula (3)3)＝P(θ3)＝0.1，m(θ3) Indicates the vehicle model asThe confidence level that card B is uncertain whether fraud is present is 0.1.
And a fusion unit 240, configured to fuse the basic probability distributions according to a combination rule, so as to obtain a wind control conclusion of the risk factor.
In one embodiment, the composition rule is a composition rule that may represent a joint effect between evidence. In this embodiment, the basic probability distribution function is the evidence in the combination rule, and the basic probability distribution is expressed as the trust level of the evidence. For example, in a case of claims for insurance settlement, the risk factor is the type of the vehicle is brand B, the evaluation information is obtained according to the preset rules respectively set by the insurance experts 1 and 2, and the basic probability distribution m is obtained after normalization processing1(θ1)、m1(θ2)、m1(θ3) And m2(θ1)、m2(θ2)、m2(θ3)，m1(θ1) Representing the degree of confidence that insurance expert 1 has fraud on the type B of vehicle, m1(θ2) Representing the degree of confidence that insurance expert 1 does not have fraud on the type B of vehicle, m1(θ3) Representing the trust degree of the insurance expert 1 on whether the vehicle model B is uncertain or not to have fraud; m is2(θ1) M represents the confidence level that the insurance expert 2 has fraud on the vehicle model B2(θ2) M represents the degree of confidence that insurance expert 2 does not have fraud on the vehicle model B2(θ3) Representing the degree of confidence that the insurance expert 2 has that the vehicle model B is uncertain as to whether fraud is present. M is combined according to a combination rule1(θ1) And m2(θ1) Performing fusion of m1(θ2) And m2(θ2) Performing fusion of m1(θ3) And m2(θ3) And performing fusion to obtain corresponding joint basic probability distribution, wherein the fusion refers to a process of inputting the two evidences into a combination rule as input to obtain the joint basic probability distribution. Maximum joint fundamental assignment probability represents confidence level of evidenceMaximum, and therefore maximum joint fundamental probability assignment as a wind-controlled conclusion of risk factors, e.g. m1(θ2) And m2(θ2) And the fused joint basic probability is the maximum, and the wind control conclusion of the risk factor with the vehicle model number of B is that no fraud exists.
In one embodiment, as shown in fig. 8, the fusion unit 240 includes sub-units: a modification unit 241, a combination unit 242 and a conclusion unit 243.
A modifying unit 241, configured to modify the basic probability distribution by a modification factor.
In one embodiment, each evidence is of different importance due to the different knowledge abilities of each insurance expert, thereby giving the evidence different degrees of confidence and weight. And correcting the evidence by introducing a correction factor to obtain more accurate evidence.
Wherein, crw,iAs a correction factor, wiRepresents a weight, riRepresenting confidence and i representing the ith evidence. m isθ,iRepresenting the basic probability distribution before the correction,the modified base probability distribution is expressed, P (Θ) is expressed as a superset of θ, and expressions (5) and (6) are specific expressions for modifying the base probability distribution. The weight and confidence level are both [0,1 ]]The weight is given in a value range according to the importance degree of the evidence, and the credibility is given in the value range according to the knowledge ability of the expert.
And a combining unit 242, configured to fuse the modified basic probability distributions according to a combining rule to obtain a joint basic probability distribution.
In one embodiment, the modified base probability distribution is substituted into the combination rule to obtain a joint base probability distribution.
Wherein,for joint fundamental probability distribution, equations (7) and (8) are combination rules.
A conclusion unit 243 for assigning the maximum joint base probability as a wind-controlled conclusion of the risk factor.
In an embodiment, joint basic probability distribution is obtained according to a combination rule, wherein evaluation information corresponding to the maximum joint probability distribution is a final conclusion. For example, the basic probability assignments in table 1 are fused according to a combination rule.
Table 1:
deriving joint fundamental probability distributions from combinatorial rulesAndwhereinThat is to sayThe value of (a) is the largest,and the corresponding evaluation information indicates that the vehicle model is the B card, so that the conclusion is that the vehicle model is the B card and no fraud exists.
Through the steps, different evidences are fused, and the problem that different insurance experts make different risk judgments on the same claim settlement case is solved. Each risk factor obtains a more accurate wind control conclusion through a claim settlement wind control method, so that a decision maker can carry out risk control on claim settlement cases according to all high-accuracy risk factors, and the risk control accuracy of the claim settlement cases is improved.
The embodiment of the invention discloses a claim settlement wind control device, which is used for acquiring risk factors of claim settlement cases; determining the evaluation information of the risk factors according to a preset risk database; obtaining a membership function of the evaluation information by using a fuzzy theory and carrying out normalization processing to obtain basic probability distribution; and fusing the basic probability distribution according to a combination rule to obtain a wind control conclusion of the risk factors, so that the wind control accuracy of each risk factor can be improved, the wind control accuracy of claim cases is further improved, the controllability of wind control cost is improved, and the quality of insurance service is improved.
The claim wind control apparatus may be implemented in the form of a computer program that is executable on a computer device such as that shown in fig. 9.
Referring to fig. 9, fig. 9 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a terminal, and may be an electronic device with a communication function, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device.
Referring to fig. 9, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032, when executed, causes the processor 502 to perform a claims wind control method.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the execution of the computer program 5032 in the non-volatile storage medium 503, and when executed by the processor 502, the computer program 5032 causes the processor 502 to perform a claims management method.
The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the configuration shown in fig. 9 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation of the computer device 500 to which the present application may be applied, and that a particular computer device 500 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
Wherein the processor 502 is configured to run the computer program 5032 stored in the memory to implement the following steps: acquiring risk factors of the claim cases; determining the evaluation information of the risk factors according to a preset risk database; obtaining a membership function of the evaluation information by using a fuzzy theory and carrying out normalization processing to obtain basic probability distribution; and fusing the basic probability distribution according to a combination rule to obtain a wind control conclusion of the wind control factor.
In an embodiment, when the processor 502 implements the step of receiving the risk factor from the claim case, the following steps are specifically implemented: acquiring claim settlement information in the claim settlement case from a server; and extracting risk factors from the claim settlement information according to a preset risk database.
In an embodiment, when the processor 502 performs normalization processing on the membership function of the evaluation information obtained by using the fuzzy theory to obtain a basic probability distribution step, the following steps are further performed: constructing a membership function of the evaluation information by using a fuzzy theory; the evaluation information obtains the corresponding membership degree through the membership degree function; and taking the membership degree as basic probability distribution.
In an embodiment, when implementing the step of fusing the basic probability distributions according to the combination rule to obtain the wind control conclusion of the risk factor, the processor 502 further implements the following steps: correcting the basic probability distribution by a correction factor; fusing the corrected basic probability distribution according to a combination rule to obtain combined basic probability distribution; and taking the maximum joint basic probability distribution as a wind control conclusion of the risk factors.
In an embodiment, after implementing the step of fusing the basic probability distributions according to the combination rule to obtain the wind control conclusion of the risk factor, the processor 502 further implements the following steps: and obtaining a trust interval of the joint basic probability distribution by using an evidence theory according to the joint basic probability distribution to represent the confirmation degree of the evaluation information corresponding to the joint basic probability distribution.
It should be understood that, in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will be understood by those skilled in the art that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program instructing associated hardware. The computer program includes program instructions, and the computer program may be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program comprises program instructions. The program instructions, when executed by the processor, cause the processor to perform the steps of: acquiring risk factors of the claim cases; determining the evaluation information of the risk factors according to a preset risk database; obtaining a membership function of the evaluation information by using a fuzzy theory and carrying out normalization processing to obtain basic probability distribution; and fusing the basic probability distribution according to a combination rule so as to obtain a wind control conclusion of the risk factor.
In an embodiment, when the processor executes the program instructions to implement the step of receiving the risk factor from the claim case, the processor specifically implements the following steps: acquiring claim settlement information in the claim settlement case from a server; and extracting risk factors from the claim settlement information according to a preset risk database.
In an embodiment, when the processor executes the program instruction to perform normalization processing on the membership function of the evaluation information obtained by using the fuzzy theory to obtain the basic probability distribution step, the following steps are specifically implemented: constructing a membership function of the evaluation information by using a fuzzy theory; the evaluation information obtains the corresponding membership degree through the membership degree function; and taking the membership degree as basic probability distribution.
In an embodiment, when the processor executes the program instructions to implement the step of fusing the basic probability distributions according to the combination rule to obtain the wind control conclusion of the risk factor, the following steps are specifically implemented: correcting the basic probability distribution by a correction factor; fusing the corrected basic probability distribution according to a combination rule to obtain combined basic probability distribution; and taking the maximum joint basic probability distribution as a wind control conclusion of the risk factors.
In an embodiment, after the step of fusing the basic probability distributions according to the combination rule to obtain the wind control conclusion of the risk factor is implemented by the processor by executing the program instructions, the following steps are further implemented: and obtaining a trust interval of the joint basic probability distribution by using an evidence theory according to the joint basic probability distribution to represent the confirmation degree of the evaluation information corresponding to the joint basic probability distribution.
The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, which can store various computer readable storage media.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be merged, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The 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 storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for claim settlement wind control, comprising:
acquiring risk factors of a claim case, wherein the risk factors are claim information used for judging whether the claim case has fraud possibility;
determining the evaluation information of the risk factors according to a preset risk database, wherein the risk database is preset with the corresponding relationship between the risk factors and the evaluation information;
obtaining a membership function of the evaluation information by using a fuzzy theory and carrying out normalization processing to obtain basic probability distribution; and
and fusing the basic probability distribution according to a combination rule so as to obtain a wind control conclusion of the risk factor.
2. The claim wind control method according to claim 1, wherein the obtaining risk factors for claim cases comprises:
acquiring claim settlement information in the claim settlement case from a server;
and extracting risk factors from the claim settlement information according to a preset risk database.
3. The claim wind control method according to claim 1, wherein the normalizing the membership function of the evaluation information obtained by using a fuzzy theory to obtain the basic probability distribution comprises:
constructing a membership function of the evaluation information by using a fuzzy theory;
the evaluation information obtains the corresponding membership degree through the membership degree function;
and taking the membership degree as basic probability distribution.
4. The claim wind control method according to claim 1, wherein the fusing the basic probability distributions according to a combination rule to reach a wind control conclusion of the risk factor comprises:
correcting the basic probability distribution by a correction factor;
fusing the corrected basic probability distribution according to a combination rule to obtain combined basic probability distribution;
and taking the maximum joint basic probability distribution as a wind control conclusion of the risk factors.
5. The claim wind control method of claim 4, further comprising:
and obtaining a trust interval of the joint basic probability distribution by using an evidence theory according to the joint basic probability distribution to represent the confirmation degree of the evaluation information corresponding to the joint basic probability distribution.
6. A claim settlement wind control device, comprising:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring risk factors of a claim settlement case, and the risk factors are claim settlement information used for judging whether the claim settlement case has fraud possibility;
the determining unit is used for determining the evaluation information of the risk factors according to a preset risk database, wherein the risk database is preset with the corresponding relation between the risk factors and the evaluation information;
the normalization unit is used for obtaining a membership function of the evaluation information by using a fuzzy theory and carrying out normalization processing so as to obtain basic probability distribution; and
and the fusion unit is used for fusing the basic probability distribution according to a combination rule so as to obtain a wind control conclusion of the risk factor.
7. The claim wind control device of claim 6, comprising:
the construction unit is used for constructing a membership function of the evaluation information by using a fuzzy theory;
the membership degree unit is used for obtaining the corresponding membership degree of the evaluation information through the membership degree function;
and the basic probability distribution unit is used for taking the membership degree as basic probability distribution.
8. The claim wind control device of claim 6, comprising:
a correction unit for correcting the basic probability distribution by a correction factor;
the combination unit is used for fusing the corrected basic probability distribution according to the combination rule to obtain combined basic probability distribution;
and the conclusion unit is used for taking the maximum joint basic probability as the wind control conclusion of the risk factors.
9. A computer arrangement, characterized in that the computer arrangement comprises a memory having stored thereon a computer program and a processor implementing the method according to any of claims 1-5 when executing the computer program.
10. A storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, may implement the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811052447.8A CN109409648A (en) | 2018-09-10 | 2018-09-10 | Claims Resolution air control method, apparatus, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811052447.8A CN109409648A (en) | 2018-09-10 | 2018-09-10 | Claims Resolution air control method, apparatus, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109409648A true CN109409648A (en) | 2019-03-01 |
Family
ID=65464610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811052447.8A Pending CN109409648A (en) | 2018-09-10 | 2018-09-10 | Claims Resolution air control method, apparatus, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109409648A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348669A (en) * | 2019-05-23 | 2019-10-18 | 中国平安财产保险股份有限公司 | Intelligent rules generation method, device, computer equipment and storage medium |
| CN110610431A (en) * | 2019-08-15 | 2019-12-24 | 中国平安人寿保险股份有限公司 | Intelligent claim settlement method and intelligent claim settlement system based on big data |
| CN112561713A (en) * | 2020-12-15 | 2021-03-26 | 中国人寿保险股份有限公司 | Method and device for anti-fraud recognition of claim settlement in insurance industry |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104125217A (en) * | 2014-06-30 | 2014-10-29 | 复旦大学 | Cloud data center real-time risk assessment method based on mainframe log analysis |
| CN105868912A (en) * | 2016-04-06 | 2016-08-17 | 清华大学 | Power transformer state evaluate method and apparatus based on data fusion |
| CN106022480A (en) * | 2016-05-13 | 2016-10-12 | 北京工业大学 | Robot functional module granularity division evaluating method based on D-S evidence theory |
| CN107240024A (en) * | 2017-05-22 | 2017-10-10 | 中国平安人寿保险股份有限公司 | The anti-fraud recognition methods of settlement of insurance claim and device |
| CN107871285A (en) * | 2017-12-06 | 2018-04-03 | 和金在线（北京）科技有限公司 | A kind of health insurance pays for the method for detecting and system of fraud and abuse |
| CN108256720A (en) * | 2017-11-07 | 2018-07-06 | 中国平安财产保险股份有限公司 | A kind of settlement of insurance claim methods of risk assessment and terminal device |
-
2018
- 2018-09-10 CN CN201811052447.8A patent/CN109409648A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104125217A (en) * | 2014-06-30 | 2014-10-29 | 复旦大学 | Cloud data center real-time risk assessment method based on mainframe log analysis |
| CN105868912A (en) * | 2016-04-06 | 2016-08-17 | 清华大学 | Power transformer state evaluate method and apparatus based on data fusion |
| CN106022480A (en) * | 2016-05-13 | 2016-10-12 | 北京工业大学 | Robot functional module granularity division evaluating method based on D-S evidence theory |
| CN107240024A (en) * | 2017-05-22 | 2017-10-10 | 中国平安人寿保险股份有限公司 | The anti-fraud recognition methods of settlement of insurance claim and device |
| CN108256720A (en) * | 2017-11-07 | 2018-07-06 | 中国平安财产保险股份有限公司 | A kind of settlement of insurance claim methods of risk assessment and terminal device |
| CN107871285A (en) * | 2017-12-06 | 2018-04-03 | 和金在线（北京）科技有限公司 | A kind of health insurance pays for the method for detecting and system of fraud and abuse |
Non-Patent Citations (3)
| Title |
|---|
| 梁静国 等: "基于证据理论的风险投资项目风险评价", 科技进步与对策, no. 12, 31 December 2005 (2005-12-31), pages 104 - 107 * |
| 闫丽颖 等: "基于改进D-S证据理论的工程项目风险评价模型", 建筑技术开发, vol. 40, no. 10, 31 October 2013 (2013-10-31), pages 69 - 72 * |
| 韩芬: "多传感器信息融合目标识别系统设计", 电子制作, no. 16, 31 August 2013 (2013-08-31), pages 125 - 126 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348669A (en) * | 2019-05-23 | 2019-10-18 | 中国平安财产保险股份有限公司 | Intelligent rules generation method, device, computer equipment and storage medium |
| CN110348669B (en) * | 2019-05-23 | 2023-08-22 | 中国平安财产保险股份有限公司 | Intelligent rule generation method, intelligent rule generation device, computer equipment and storage medium |
| CN110610431A (en) * | 2019-08-15 | 2019-12-24 | 中国平安人寿保险股份有限公司 | Intelligent claim settlement method and intelligent claim settlement system based on big data |
| CN110610431B (en) * | 2019-08-15 | 2023-10-27 | 中国平安人寿保险股份有限公司 | Intelligent claim settlement method and intelligent claim settlement system based on big data |
| CN112561713A (en) * | 2020-12-15 | 2021-03-26 | 中国人寿保险股份有限公司 | Method and device for anti-fraud recognition of claim settlement in insurance industry |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Evidential reasoning rule for MADM with both weights and reliabilities in group decision making | |
| Wan et al. | Additive consistent interval-valued Atanassov intuitionistic fuzzy preference relation and likelihood comparison algorithm based group decision making | |
| Liu et al. | A novel approach for failure mode and effects analysis using combination weighting and fuzzy VIKOR method | |
| Yazdani et al. | Improved decision model for evaluating risks in construction projects | |
| Gajzler et al. | Evaluation of planned construction projects using fuzzy logic | |
| CN109409648A (en) | Claims Resolution air control method, apparatus, computer equipment and storage medium | |
| Tavakkoli-Moghaddam et al. | A fuzzy comprehensive approach for risk identification and prioritization simultaneously in EPC projects | |
| CN112668822B (en) | Scientific and technological achievement transformation platform sharing system, method, storage medium and mobile phone APP | |
| CN110991999A (en) | Method and device for improving law enforcement amount cutting efficiency, computer equipment and storage medium | |
| CN112200684B (en) | Method, system and storage medium for detecting medical insurance fraud | |
| CN111582394B (en) | Group assessment method, device, equipment and medium | |
| Mahoney et al. | AI fairness | |
| CN117391583B (en) | Purchasing data management method and platform | |
| Ng | Evidential reasoning-based Fuzzy AHP approach for the evaluation of design alternatives’ environmental performances | |
| Qu et al. | A discourse of multi-criteria decision making (MCDM) approaches | |
| CN111192133A (en) | Method and device for generating risk model after user loan and electronic equipment | |
| WO2023043937A1 (en) | Model-based analysis of intellectual property collateral | |
| CN114219596B (en) | Data processing method and related equipment based on decision tree model | |
| Šuster et al. | Analysis of predictive performance and reliability of classifiers for quality assessment of medical evidence revealed important variation by medical area | |
| Goeva et al. | Optimization-based calibration of simulation input models | |
| CN113627997A (en) | Data processing method and device, electronic equipment and storage medium | |
| Li et al. | Propensity score‐based methods for causal inference and external data leveraging in regulatory settings: From basic ideas to implementation | |
| CN113469826A (en) | Information processing method, device, equipment and storage medium | |
| CN117495482A (en) | Secondhand mobile phone sales recommendation method and system based on user portrait | |
| Wei et al. | Combination of empirical study with qualitative simulation for optimization problem in mobile banking adoption |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |