CN108256720A - A kind of settlement of insurance claim methods of risk assessment and terminal device - Google Patents
A kind of settlement of insurance claim methods of risk assessment and terminal device Download PDFInfo
- Publication number
- CN108256720A CN108256720A CN201711084960.0A CN201711084960A CN108256720A CN 108256720 A CN108256720 A CN 108256720A CN 201711084960 A CN201711084960 A CN 201711084960A CN 108256720 A CN108256720 A CN 108256720A
- Authority
- CN
- China
- Prior art keywords
- insurance
- settlement
- sample
- network model
- neural network
- 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
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)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention belongs to field of computer technology more particularly to a kind of settlement of insurance claim methods of risk assessment and terminal device.The method obtains the event type of target settlement of insurance claim event first, then it according to the event type determines that the target settlement of insurance claim event is carried out assessing required assessment dimension, and it obtains the target settlement of insurance claim event and surveys information in determining each assessment dimension, finally determine preset neural network model corresponding with the event type, and the information of surveying is handled using the neural network model, obtain the risk assessment value of the target settlement of insurance claim event.Due to substituting manual evaluation using neural network model, avoid the interference of human factor, acquired results are more objective, and the neural network model be the authentic specimen of a large amount of particular event type is trained using machine learning algorithm and take into account it is multiple assessment dimensions on the accuracys rate surveyed information, substantially increase assessment result.
Description
Technical field
The invention belongs to field of computer technology more particularly to a kind of settlement of insurance claim methods of risk assessment and terminal device.
Background technology
With the continuous social and economic development, there is a growing awareness that the importance of insurance.Insurer is based on contract about
Fixed, to insurer's premium payment, the loss caused by the risk that the possibility of contract engagement occurs for the insurer undertakes reparation
Insurance money.Therefore, the insurer is particularly important for the risk assessment of insurance business.
It is of the prior art when carrying out settlement of insurance claim risk assessment, typically by business personnel according to the past experience of oneself
Manual evaluation is carried out for specific scene, relies primarily on the judgement of business personnel individual, subjectivity is extremely strong, the assessment finally obtained
As a result often accuracy rate is relatively low.
Invention content
In view of this, an embodiment of the present invention provides a kind of settlement of insurance claim methods of risk assessment and terminal device, to solve
It is artificial to carry out the problem of subjectivity during the assessment of settlement of insurance claim equivalent risk is extremely strong and accuracy rate is relatively low.
The first aspect of the embodiment of the present invention provides a kind of settlement of insurance claim methods of risk assessment, can include：
Obtain the event type of target settlement of insurance claim event；
According to the event type determine that the target settlement of insurance claim event is carried out to assess required assessment dimension, it is described
The number for assessing dimension is two or more；
It obtains the target settlement of insurance claim event and surveys information in determining each assessment dimension；
Determine preset neural network model corresponding with the event type, the neural network model be by using
Machine learning algorithm is to specifying the settlement of insurance claim sample corresponding with the event type in settlement of insurance claim sample database to be trained
It obtains, the settlement of insurance claim sample is chosen, and the sample of the settlement of insurance claim sample from history settlement of insurance claim record
Number is more than preset first threshold, and in the training process, the input of the neural network model is the settlement of insurance claim sample
Survey information, the risk assessment value of the output of the neural network model for the settlement of insurance claim sample；
The information of surveying is handled using the neural network model, obtains the target settlement of insurance claim event
Risk assessment value.
The second aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer-readable instruction, and the computer-readable instruction realizes following steps when being executed by processor：
Obtain the event type of target settlement of insurance claim event；
According to the event type determine that the target settlement of insurance claim event is carried out to assess required assessment dimension, it is described
The number for assessing dimension is two or more；
It obtains the target settlement of insurance claim event and surveys information in determining each assessment dimension；
Determine preset neural network model corresponding with the event type, the neural network model be by using
Machine learning algorithm is to specifying the settlement of insurance claim sample corresponding with the event type in settlement of insurance claim sample database to be trained
It obtains, the settlement of insurance claim sample is chosen, and the sample of the settlement of insurance claim sample from history settlement of insurance claim record
Number is more than preset first threshold, and in the training process, the input of the neural network model is the settlement of insurance claim sample
Survey information, the risk assessment value of the output of the neural network model for the settlement of insurance claim sample；
The information of surveying is handled using the neural network model, obtains the target settlement of insurance claim event
Risk assessment value.
The third aspect of the embodiment of the present invention provides a kind of settlement of insurance claim risk assessment terminal device, including memory,
Processor and it is stored in the computer-readable instruction that can be run in the memory and on the processor, the processor
Following steps are realized when performing the computer-readable instruction：
Obtain the event type of target settlement of insurance claim event；
According to the event type determine that the target settlement of insurance claim event is carried out to assess required assessment dimension, it is described
The number for assessing dimension is two or more；
It obtains the target settlement of insurance claim event and surveys information in determining each assessment dimension；
Determine preset neural network model corresponding with the event type, the neural network model be by using
Machine learning algorithm is to specifying the settlement of insurance claim sample corresponding with the event type in settlement of insurance claim sample database to be trained
It obtains, the settlement of insurance claim sample is chosen, and the sample of the settlement of insurance claim sample from history settlement of insurance claim record
Number is more than preset first threshold, and in the training process, the input of the neural network model is the settlement of insurance claim sample
Survey information, the risk assessment value of the output of the neural network model for the settlement of insurance claim sample；
The information of surveying is handled using the neural network model, obtains the target settlement of insurance claim event
Risk assessment value.
Existing advantageous effect is the embodiment of the present invention compared with prior art：The embodiment of the present invention obtains target guarantor first
The event type of danger Claims Resolution event, then determines to carry out assessment institute to the target settlement of insurance claim event according to the event type
The assessment dimension needed, and obtain the target settlement of insurance claim event and survey information in determining each assessment dimension, finally
It determines preset neural network model corresponding with the event type, and letter is surveyed to described using the neural network model
Breath is handled, and obtains the risk assessment value of the target settlement of insurance claim event.It is artificial due to being substituted using neural network model
Assessment, avoids the interference of human factor, and acquired results are more objective, and the neural network model is to use machine learning
It is that algorithm trains the authentic specimen of a large amount of particular event type and take into account it is multiple assessment dimensions on survey letter
Breath, consideration is more comprehensive, stronger to the specific aim of particular event type, substantially increases the accuracy rate of assessment result.
Description of the drawings
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description be only the present invention some
Embodiment, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is a kind of one embodiment flow chart of settlement of insurance claim methods of risk assessment in the embodiment of the present invention；
Fig. 2 is a kind of step S105 of settlement of insurance claim methods of risk assessment in the embodiment of the present invention under an application scenarios
Schematic flow diagram；
Fig. 3 is the schematic flow diagram for carrying out sample training in the embodiment of the present invention to neural network model；
Fig. 4 is the schematic flow diagram that the whole degree of deviation is calculated in the embodiment of the present invention；
Fig. 5 is a kind of one embodiment structure chart of settlement of insurance claim risk assessment device in the embodiment of the present invention；
Fig. 6 is a kind of schematic block diagram of settlement of insurance claim risk assessment terminal device in the embodiment of the present invention.
Specific embodiment
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment is clearly and completely described the technical solution in the embodiment of the present invention, it is clear that disclosed below
Embodiment be only part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
All other embodiment that those of ordinary skill is obtained without making creative work, belongs to protection of the present invention
Range.
Referring to Fig. 1, a kind of one embodiment of settlement of insurance claim methods of risk assessment can include in the embodiment of the present invention：
Step S101, the event type of target settlement of insurance claim event is obtained.
One and only one corresponding event type of each settlement of insurance claim event, the event class of settlement of insurance claim event
Type includes but not limited to vehicle insurance, life insurance, engineering danger etc..The event type of settlement of insurance claim event is determined simultaneously in the stage of insuring
Remain unchanged, if for example, client insures for a certain architectural engineering, the stage of insuring the settlement of insurance claim event event type i.e.
For engineering danger, in the Claims Resolution stage, can also be settled a claim with the event type of engineering danger.
Step S102, it according to the event type determines that the target settlement of insurance claim event is carried out assessing required assessment
Dimension.
The number of the assessment dimension is two or more.By taking engineering danger as an example, assessment dimension can include：Whether is had
Whether one scene, insurer provide material in time, whether data is more than theoretical maximum heap with the presence or absence of fraud, report damage material quantity
Put quantity, report damage material quantity whether be more than corresponding engineering residual engineering workload, whether provide be in danger before photo, material book whether
It loses, whether material is that subcontractor owns, whether stack place reasonable etc..
Step S103, it obtains the target settlement of insurance claim event and surveys information in determining each assessment dimension.
Usually, when settlement of insurance claim event occurs, need the personnel of surveying according to determining each assessment dimension to the guarantor
Dangerous Claims Resolution event carries out dam site investigation and phone is surveyed, so as to obtain surveying information.Specifically, personnel are surveyed firstly the need of determining
Which event type is currently processed settlement of insurance claim event belong to, then obtain it is corresponding with the event type survey guide table,
It surveys in guide table at this and lists the content surveyed in each assessment dimension in detail, survey personnel according to looking into
It surveys guide table to complete after surveying, relevant information of surveying is summarized, these information will be used as progress settlement of insurance claim risk comment
The foundation estimated.
Step S104, preset neural network model corresponding with the event type is determined.
The neural network model be by using machine learning algorithm to specify settlement of insurance claim sample database in it is described
The corresponding settlement of insurance claim sample of event type is trained, in the training process, the input of the neural network model
For the information of surveying of the settlement of insurance claim sample, the output of the neural network model is commented for the risk of the settlement of insurance claim sample
Valuation.
The settlement of insurance claim sample is chosen, and the sample of the settlement of insurance claim sample from history settlement of insurance claim record
Number is more than preset first threshold, and the first threshold can be configured according to actual conditions, in order to ensure training result
Accuracy rate, generally require increase number of samples as much as possible, for example, the first threshold can be set as to 10000,
20000th, 50000 etc., the present embodiment is not specifically limited this.
Preferably, in the present embodiment, for each event type, unique neural network model is corresponding to it,
For example, for vehicle insurance, there can be neural network model 1 to be corresponding to it, for life insurance, there can be the neural network model 2 right therewith
Should, for engineering danger, there can be neural network model 3 to be corresponding to it.As a result of multiple nerves corresponding with event type
Network model rather than only use an identical neural network model so that the present embodiment is to the specific aim of particular event type
It is stronger, accuracy rate higher.
Step S105, the information of surveying is handled using the neural network model, obtains the target insurance
The risk assessment value of Claims Resolution event.
Specifically, step S105 can include step as shown in Figure 2：
Step S201, the information of surveying is identified as the neural network mould according to determining each assessment dimension
The input layer data of type.
Neural network model in the present embodiment can include input layer, hidden layer and output layer.The input layer is used for
Input data is received from outside, including more than two input layers, the hidden layer is used to handle data, including
More than two hidden layer nodes, the output layer is for exporting handling result, including an output node layer.
The input layer is corresponded with the assessment dimension.For example, if a certain event type shares 3 assessment dimensions
Degree respectively assesses dimension 1, assessment dimension 2 and assessment dimension 3, then the input layer of corresponding neural network model
Number also should be 3, respectively input layer 1, input layer 2 and input layer 3, wherein, input layer 1 is with commenting
Estimate dimension 1 to correspond to, input layer 2 is corresponding with assessment dimension 2, and input layer 3 is corresponding with assessment dimension 3.
Preferably, the information of surveying can be converted to numeric form, then by the numeric form to survey information true
It is set to the input layer data of the neural network model, by taking engineering danger as an example, whether is more than theory in report damage material quantity
In this dimension of maximum stacking quantity, if survey information is more than theoretical maximum stacking quantity for report damage material quantity, by its turn
Numerical value 1 is changed to, quantity is stacked if surveying information and being less than or equal to theoretical maximum for report damage material quantity, is converted into numerical value
0。
Step S202, in the hidden layer node of the neural network model respectively using fuzzy Gauss membership function to institute
It states input layer data to be handled, obtains hidden layer node data.
In the present embodiment, the hidden layer node data can be obtained by following calculation formula：
Wherein：
I is the label of input layer, and value range is [1, n], and n is the number of input layer；
J is the label of hidden layer node, and value range is [1, h], and h is the number of hidden layer node；
Φj(x) the hidden layer node data for j-th of hidden layer node；
Gij(xi) i-th of fuzzy Gauss membership function for j-th hidden layer node；
X be input layer data, xiInput layer data for i-th of input layer therein；
μijThe mathematic expectaion of i-th of fuzzy Gauss membership function for j-th of hidden layer node；
σijThe standard deviation of i-th of fuzzy Gauss membership function for j-th of hidden layer node.
Preferably, the hidden layer node data can also be normalized, to reduce the hidden layer node
The difference of data specifically, can obtain maximum value and minimum value in the hidden layer node data, then according to most
The hidden layer node data are normalized in big value and the minimum value, obtain normalized node in hidden layer
According to.
For example, the hidden layer node data can be normalized by the following formula：
Wherein：
Ψj(x) the normalized hidden layer node data for j-th of hidden layer node；
Φmax(x) it is Φj(x) maximum value in；
Φmin(x) it is Φj(x) minimum value in.
Step S203, summation is weighted to the hidden layer node data respectively using preset weights, obtained described
The risk assessment value of target settlement of insurance claim event.
For the hidden layer node data not being normalized, the meter of the risk assessment value of the target settlement of insurance claim event
Calculating formula can be：
For normalized hidden layer node data, the calculation formula of the risk assessment value of the target settlement of insurance claim event
Can be：
Wherein：
ωjFor weights corresponding with the hidden layer node data of j-th of hidden layer node；
R (x) is the risk assessment value of output layer node data namely the target settlement of insurance claim event.
Preferably, before each step for carrying out insurance risk assessment shown in FIG. 1, pair as shown in Figure 3 can be included
The neural network model carries out default step：
Step S301, calculate using the neural network model in the settlement of insurance claim sample database with the event class
Whole degree of deviation when the corresponding settlement of insurance claim sample of type is assessed.
The entirety degree of deviation is the whole extent of deviation between the risk assessment value and desired value that assessment obtains, described whole
The calculating of the body degree of deviation can specifically include step as shown in Figure 4：
Step S3011, chosen from the settlement of insurance claim sample database one it is not yet choosing with the event type pair
The settlement of insurance claim sample answered is as current sample.
The selection sequence of sample can be random or carried out according to preset sequence, for example, in advance can be with
To settlement of insurance claim sample into line label, then chosen successively according to the sequence of label from small to large.
Step S3012, the information of surveying of the current sample is handled using the neural network model, obtains institute
State the first risk assessment value of current sample.
The step that the specific steps of step S3012 are corresponding with Fig. 2 is similar, specifically can refer in step S201 to step S203
Description, details are not described herein for this implementation.
Step S3013, by the difference of the first risk assessment value and the second risk assessment value square be determined as it is described
The sample bias degree of current sample.
Risk assessment value of the second risk assessment value for the current sample in history settlement of insurance claim record.
The calculation formula of the sample bias degree of the current sample can be：
Ek=(R'k-Rk)2
Wherein：
K is the label of current sample, and value range is [1, p], and p is the total number of the settlement of insurance claim sample；
EkSample bias degree for current sample；
RkThe first risk assessment value for current sample；
R'kThe second risk assessment value for current sample.
Step S3014, judge in the settlement of insurance claim sample database with the presence or absence of not yet choosing with the event type
Corresponding settlement of insurance claim sample.
If there is the settlement of insurance claim sample corresponding with the event type not yet chosen in the settlement of insurance claim sample database
This, then return and perform step S3011 and subsequent step；
If the settlement of insurance claim sample standard deviation corresponding with the event type in the settlement of insurance claim sample database was selected,
Perform step S3015.
Step S3015, the sum of sample bias degree of the settlement of insurance claim sample being selected is determined as the entirety
The degree of deviation.
It is described entirety the degree of deviation calculation formula can be：
Wherein, E is the whole degree of deviation.
Step S302, judge whether the whole degree of deviation is more than preset second threshold.
If the entirety degree of deviation is more than the second threshold, step S303 is performed, is then back to and performs step S301,
Until the whole degree of deviation is less than or equal to the second threshold；
If the entirety degree of deviation is less than or equal to the second threshold, step S304 is performed.
Step S303, the parameter of the neural network model is adjusted.
In the present embodiment, the parameter that can be adjusted includes：μij、σijAnd/or ωj。
With to μijFor being adjusted, the formula being adjusted to it can be：
μ′ij=μij+kΔμ
Wherein：
μ′ijFor the value after adjustment；
Δ μ is adjusting step, can be pre-set according to actual conditions；
K is regulation coefficient, and value can be arbitrary integer.
With to σijFor being adjusted, the formula being adjusted to it can be：
σ′ij=σij+kΔσ
Wherein：
σ′ijFor the value after adjustment；
Δ σ is adjusting step, can be pre-set according to actual conditions.
With to ωjFor being adjusted, the formula being adjusted to it can be：
ω'j=ωj+kΔω
Wherein：
ω'jFor the value after adjustment；
Δ ω is adjusting step, can be pre-set according to actual conditions.
It is especially noted that in practical parameter tuning process, it can be just for any one parameter therein
It is adjusted, can also be adjusted for any two parameter therein, adjustment can also be carried out at the same time to these parameters, this
Embodiment is not especially limited this.
Step S304, the neural network model is determined as neural network model corresponding with the event type.
The neural network model determined have passed through a large amount of sample training, and its whole degree of deviation be maintained at one compared with
In small range, handled using the neural network model surveying information, you can obtain one of settlement of insurance claim event compared with
Accurate risk assessment value.
In conclusion the embodiment of the present invention obtains the event type of target settlement of insurance claim event first, then according to
Event type determines that the target settlement of insurance claim event is carried out assessing required assessment dimension, and obtains the target insurance reason
Compensation event surveys information in determining each assessment dimension, finally determines preset nerve corresponding with the event type
Network model, and the information of surveying is handled using the neural network model, obtain the target settlement of insurance claim thing
The risk assessment value of part.Due to substituting manual evaluation using neural network model, the interference of human factor, acquired results are avoided
It is more objective, and the neural network model is the authentic specimen using machine learning algorithm to a large amount of particular event type
It trains obtaining and takes into account multiple information of surveying assessed in dimensions, consideration is more comprehensive, to the needle of particular event type
It is stronger to property, substantially increase the accuracy rate of assessment result.
It should be understood that the size of the serial number of each step is not meant to the priority of execution sequence, each process in above-described embodiment
Execution sequence should determine that the implementation process without coping with the embodiment of the present invention forms any limit with its function and internal logic
It is fixed.
Corresponding to a kind of settlement of insurance claim methods of risk assessment described in foregoing embodiments, Fig. 5 shows the embodiment of the present invention
A kind of one embodiment structure chart of the settlement of insurance claim risk assessment device provided.
A kind of settlement of insurance claim risk assessment device in the present embodiment can include：
Event type acquisition module 501, for obtaining the event type of target settlement of insurance claim event；
Assess dimension determining module 502, for according to the event type determine to the target settlement of insurance claim event into
Assessment dimension needed for row assessment, the number of the assessment dimension is two or more；
Data obtaining module 503 is surveyed, for obtaining the target settlement of insurance claim event in determining each assessment dimension
On survey information；
Neural network model determining module 504, for determining preset neural network mould corresponding with the event type
Type, the neural network model be by using machine learning algorithm to specify settlement of insurance claim sample database in the event class
The corresponding settlement of insurance claim sample of type is trained, and the settlement of insurance claim sample is chosen from history settlement of insurance claim record
, and the number of samples of the settlement of insurance claim sample is more than preset first threshold, in the training process, the neural network mould
Survey information of the input of type for the settlement of insurance claim sample, the output of the neural network model is the settlement of insurance claim sample
Risk assessment value；
Message processing module 505 is surveyed, for being handled using the neural network model the information of surveying, is obtained
To the risk assessment value of the target settlement of insurance claim event.
Further, the message processing module 505 of surveying can include：
Input layer data determination unit, for according to determining each assessment dimension by it is described survey information difference it is true
It is set to the input layer data of the neural network model, the input layer is corresponded with the assessment dimension；
Input layer data processing unit is fuzzy for being used respectively in the hidden layer node of the neural network model
Gauss membership function handles the input layer data, obtains hidden layer node data；
Weighted sum unit, for being weighted summation to the hidden layer node data respectively using preset weights,
Obtain the risk assessment value of the target settlement of insurance claim event.
Further, the message processing module 505 of surveying can also include：
Hidden layer node data acquiring unit, for obtaining maximum value and minimum value in the hidden layer node data；
Normalized unit, for being carried out according to the maximum value and the minimum value to the hidden layer node data
Normalized obtains normalized hidden layer node data.
Further, the settlement of insurance claim risk assessment device can also include：
Whole degree of deviation computing module, for calculating using the neural network model in the settlement of insurance claim sample database
The whole degree of deviation of the settlement of insurance claim sample corresponding with event type when being assessed, the entirety degree of deviation is assessment
Whole extent of deviation between obtained risk assessment value and desired value；
Whole degree of deviation judgment module, for judging whether the whole degree of deviation is more than preset second threshold；
Parameter adjustment module, if being more than the second threshold for the whole degree of deviation, to the neural network mould
The parameter of type is adjusted, and is returned and performed described calculate using the neural network model in the settlement of insurance claim sample database
The whole degree of deviation of the settlement of insurance claim sample corresponding with event type when being assessed the step of, until the entirety is inclined
Margin is less than or equal to the second threshold；
Neural network model determining module, will if being less than or equal to the second threshold for the whole degree of deviation
The neural network model is determined as neural network model corresponding with the event type.
Further, the whole degree of deviation computing module can include：
Current sample selection unit, for chosen from the settlement of insurance claim sample database one it is not yet choosing with it is described
The corresponding settlement of insurance claim sample of event type is as current sample；
Information process unit is surveyed, for being carried out using the neural network model to the information of surveying of the current sample
Processing, obtains the first risk assessment value of the current sample；
Sample bias degree determination unit, for putting down the difference of the first risk assessment value and the second risk assessment value
Side is determined as the sample bias degree of the current sample, and the second risk assessment value is protected for the current sample in the history
Risk assessment value in danger Claims Resolution record；
Settlement of insurance claim sample judging unit, for judging to whether there is what is not yet chosen in the settlement of insurance claim sample database
Settlement of insurance claim sample corresponding with the event type；
First processing units, if not yet choosing with the event type for existing in the settlement of insurance claim sample database
Corresponding settlement of insurance claim sample, then return execution it is described chosen from the settlement of insurance claim sample database one it is not yet choosing with
The step of corresponding settlement of insurance claim sample of the event type is as current sample and subsequent step；
Second processing unit, if for the settlement of insurance claim corresponding with the event type in the settlement of insurance claim sample database
Sample standard deviation was selected, then it is inclined the sum of sample bias degree of the settlement of insurance claim sample being selected to be determined as the entirety
Margin.
Fig. 6 shows a kind of schematic block diagram of settlement of insurance claim risk assessment terminal device provided in an embodiment of the present invention, is
Convenient for explanation, illustrate only and the relevant part of the embodiment of the present invention.
In the present embodiment, the settlement of insurance claim risk assessment terminal device 6 can be desktop PC, notebook,
The computing devices such as palm PC and cloud server.The settlement of insurance claim risk assessment terminal device 6 may include：Processor 60 is deposited
Reservoir 61 and the computer-readable instruction 62 that can be run in the memory 61 and on the processor 60 is stored in, such as
Perform the computer-readable instruction of above-mentioned settlement of insurance claim methods of risk assessment.The processor 60 performs described computer-readable
The step in above-mentioned each settlement of insurance claim methods of risk assessment embodiment, such as step S101 shown in FIG. 1 are realized when instructing 62
To S105.Alternatively, the processor 60 realizes each mould in above-mentioned each device embodiment when performing the computer-readable instruction 62
The function of block/unit, such as the function of module 501 to 505 shown in Fig. 5.
Illustratively, the computer-readable instruction 62 can be divided into one or more module/units, one
Or multiple module/units are stored in the memory 61, and are performed by the processor 60, to complete the present invention.Institute
It can be the series of computation machine readable instruction section that can complete specific function to state one or more module/units, the instruction segment
For describing implementation procedure of the computer-readable instruction 62 in the settlement of insurance claim risk assessment terminal device 6.
The processor 60 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
The memory 61 can be the internal storage unit of the settlement of insurance claim risk assessment terminal device 6, such as protect
The hard disk or memory of danger Claims Resolution risk assessment terminal device 6.The memory 61 can also be the settlement of insurance claim risk assessment
The plug-in type hard disk being equipped on the External memory equipment of terminal device 6, such as the settlement of insurance claim risk assessment terminal device 6,
Intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash
Card) etc..Further, the memory 61 can also both include the inside of the settlement of insurance claim risk assessment terminal device 6
Storage unit also includes External memory equipment.The memory 61 is used to store the computer-readable instruction and the insurance
The other instruction and datas settled a claim needed for risk assessment terminal device 6.The memory 61 can be also used for temporarily storing
Data through exporting or will export.
Each functional unit in each embodiment of the present invention can be integrated in a processing unit or each
Unit is individually physically present, can also two or more units integrate in a unit.Above-mentioned integrated unit both may be used
It realizes, can also be realized in the form of SFU software functional unit in the form of using hardware.
If the integrated unit is realized in the form of SFU software functional unit and is independent product sale or uses
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme of the present invention is substantially
The part to contribute in other words to the prior art or all or part of the technical solution can be in the form of software products
Embody, which is stored in a storage medium, including several computer-readable instructions use so that
One computer equipment (can be personal computer, server or the network equipment etc.) performs each embodiment institute of the present invention
State all or part of step of method.And aforementioned storage medium includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with
Store the medium of computer-readable instruction.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to aforementioned reality
Example is applied the present invention is described in detail, it will be understood by those of ordinary skill in the art that：It still can be to aforementioned each
Technical solution recorded in embodiment modifies or carries out equivalent replacement to which part technical characteristic；And these are changed
Or it replaces, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of settlement of insurance claim methods of risk assessment, which is characterized in that including：
Obtain the event type of target settlement of insurance claim event；
According to the event type determine that the target settlement of insurance claim event is carried out assessing required assessment dimension, the assessment
The number of dimension is two or more；
It obtains the target settlement of insurance claim event and surveys information in determining each assessment dimension；
Determine preset neural network model corresponding with the event type, the neural network model is by using machine
Learning algorithm is to specifying the settlement of insurance claim sample corresponding with the event type in settlement of insurance claim sample database to be trained to obtain
, the settlement of insurance claim sample is chosen, and the number of samples of the settlement of insurance claim sample from history settlement of insurance claim record
More than preset first threshold, in the training process, input the looking into for the settlement of insurance claim sample of the neural network model
Information is surveyed, the output of the neural network model is the risk assessment value of the settlement of insurance claim sample；
The information of surveying is handled using the neural network model, obtains the risk of the target settlement of insurance claim event
Assessed value.
2. settlement of insurance claim methods of risk assessment according to claim 1, which is characterized in that described to use the neural network
Model handles the information of surveying, and the risk assessment value for obtaining the target settlement of insurance claim event includes：
According to determining each assessment dimension by the input layer section surveyed information and be identified as the neural network model
Point data, the input layer are corresponded with the assessment dimension；
Fuzzy Gauss membership function is used respectively to the input layer in the hidden layer node of the neural network model
Data are handled, and obtain hidden layer node data；
Summation is weighted to the hidden layer node data respectively using preset weights, obtains the target settlement of insurance claim thing
The risk assessment value of part.
3. settlement of insurance claim methods of risk assessment according to claim 2, which is characterized in that distinguish using preset weights
Before being weighted summation to the hidden layer node data, further include：
Obtain the maximum value and minimum value in the hidden layer node data；
The hidden layer node data are normalized according to the maximum value and the minimum value, are obtained normalized
Hidden layer node data.
4. settlement of insurance claim methods of risk assessment according to any one of claim 1 to 3, which is characterized in that the nerve
The default process of network model includes：
It calculates using the neural network model to the insurance corresponding with the event type in the settlement of insurance claim sample database
The whole degree of deviation of Claims Resolution sample when being assessed, the entirety degree of deviation be the risk assessment value that assessment obtains and desired value it
Between whole extent of deviation；
Judge whether the whole degree of deviation is more than preset second threshold；
If the entirety degree of deviation is more than the second threshold, the parameter of the neural network model is adjusted, and returns
It is calculated described in receipt row using the neural network model to corresponding with the event type in the settlement of insurance claim sample database
The whole degree of deviation of settlement of insurance claim sample when being assessed the step of, until the whole degree of deviation is less than or equal to described the
Two threshold values；
If the entirety degree of deviation is less than or equal to the second threshold, the neural network model is determined as and the thing
The corresponding neural network model of part type.
5. settlement of insurance claim methods of risk assessment according to claim 4, which is characterized in that described calculate uses the nerve
When network model assesses the settlement of insurance claim sample corresponding with the event type in the settlement of insurance claim sample database
The whole degree of deviation includes：
A settlement of insurance claim sample corresponding with the event type not yet choosing is chosen from the settlement of insurance claim sample database
This is as current sample；
The information of surveying of the current sample is handled using the neural network model, obtains the of the current sample
One risk assessment value；
By the sample for square being determined as the current sample of the difference of the first risk assessment value and the second risk assessment value
The degree of deviation, risk assessment value of the second risk assessment value for the current sample in history settlement of insurance claim record；
Judge in the settlement of insurance claim sample database with the presence or absence of the settlement of insurance claim corresponding with the event type not yet chosen
Sample；
If there is the settlement of insurance claim sample corresponding with the event type not yet chosen in the settlement of insurance claim sample database,
It returns and performs one guarantor corresponding with the event type not yet choosing of selection from the settlement of insurance claim sample database
The step of danger Claims Resolution sample is as current sample and subsequent step；
It, will be by if the settlement of insurance claim sample standard deviation corresponding with the event type in the settlement of insurance claim sample database was selected
The sum of sample bias degree of the settlement of insurance claim sample chosen is determined as the whole degree of deviation.
6. a kind of computer readable storage medium, the computer-readable recording medium storage has computer-readable instruction, special
Sign is, the insurance reason as described in any one of claim 1 to 5 is realized when the computer-readable instruction is executed by processor
The step of paying for methods of risk assessment.
7. a kind of settlement of insurance claim risk assessment terminal device including memory, processor and is stored in the memory simultaneously
The computer-readable instruction that can be run on the processor, which is characterized in that the processor performs described computer-readable
Following steps are realized during instruction：
Obtain the event type of target settlement of insurance claim event；
According to the event type determine that the target settlement of insurance claim event is carried out assessing required assessment dimension, the assessment
The number of dimension is two or more；
It obtains the target settlement of insurance claim event and surveys information in determining each assessment dimension；
Determine preset neural network model corresponding with the event type, the neural network model is by using machine
Learning algorithm is to specifying the settlement of insurance claim sample corresponding with the event type in settlement of insurance claim sample database to be trained to obtain
, the settlement of insurance claim sample is chosen, and the number of samples of the settlement of insurance claim sample from history settlement of insurance claim record
More than preset first threshold, in the training process, input the looking into for the settlement of insurance claim sample of the neural network model
Information is surveyed, the output of the neural network model is the risk assessment value of the settlement of insurance claim sample；
The information of surveying is handled using the neural network model, obtains the risk of the target settlement of insurance claim event
Assessed value.
8. settlement of insurance claim risk assessment terminal device according to claim 7, which is characterized in that described to use the nerve
Network model handles the information of surveying, and the risk assessment value for obtaining the target settlement of insurance claim event includes：
According to determining each assessment dimension by the input layer section surveyed information and be identified as the neural network model
Point data, the input layer are corresponded with the assessment dimension；
Fuzzy Gauss membership function is used respectively to the input layer in the hidden layer node of the neural network model
Data are handled, and obtain hidden layer node data；
Summation is weighted to the hidden layer node data respectively using preset weights, obtains the target settlement of insurance claim thing
The risk assessment value of part.
9. the settlement of insurance claim risk assessment terminal device according to any one of claim 7 to 8, which is characterized in that described
The default process of neural network model includes：
It calculates using the neural network model to the insurance corresponding with the event type in the settlement of insurance claim sample database
The whole degree of deviation of Claims Resolution sample when being assessed, the entirety degree of deviation be the risk assessment value that assessment obtains and desired value it
Between whole extent of deviation；
Judge whether the whole degree of deviation is more than preset second threshold；
If the entirety degree of deviation is more than the second threshold, the parameter of the neural network model is adjusted, and returns
It is calculated described in receipt row using the neural network model to corresponding with the event type in the settlement of insurance claim sample database
The whole degree of deviation of settlement of insurance claim sample when being assessed the step of, until the whole degree of deviation is less than or equal to described the
Two threshold values；
If the entirety degree of deviation is less than or equal to the second threshold, the neural network model is determined as and the thing
The corresponding neural network model of part type.
10. settlement of insurance claim risk assessment terminal device according to claim 9, which is characterized in that described calculate uses institute
Neural network model is stated to comment the settlement of insurance claim sample corresponding with the event type in the settlement of insurance claim sample database
Whole degree of deviation when estimating includes：
A settlement of insurance claim sample corresponding with the event type not yet choosing is chosen from the settlement of insurance claim sample database
This is as current sample；
The information of surveying of the current sample is handled using the neural network model, obtains the of the current sample
One risk assessment value；
By the sample for square being determined as the current sample of the difference of the first risk assessment value and the second risk assessment value
The degree of deviation, risk assessment value of the second risk assessment value for the current sample in history settlement of insurance claim record；
Judge in the settlement of insurance claim sample database with the presence or absence of the settlement of insurance claim corresponding with the event type not yet chosen
Sample；
If there is the settlement of insurance claim sample corresponding with the event type not yet chosen in the settlement of insurance claim sample database,
It returns and performs one guarantor corresponding with the event type not yet choosing of selection from the settlement of insurance claim sample database
The step of danger Claims Resolution sample is as current sample and subsequent step；
It, will be by if the settlement of insurance claim sample standard deviation corresponding with the event type in the settlement of insurance claim sample database was selected
The sum of sample bias degree of the settlement of insurance claim sample chosen is determined as the whole degree of deviation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711084960.0A CN108256720A (en) | 2017-11-07 | 2017-11-07 | A kind of settlement of insurance claim methods of risk assessment and terminal device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711084960.0A CN108256720A (en) | 2017-11-07 | 2017-11-07 | A kind of settlement of insurance claim methods of risk assessment and terminal device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108256720A true CN108256720A (en) | 2018-07-06 |
Family
ID=62721523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711084960.0A Pending CN108256720A (en) | 2017-11-07 | 2017-11-07 | A kind of settlement of insurance claim methods of risk assessment and terminal device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108256720A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360581A (en) * | 2018-10-12 | 2019-02-19 | 平安科技（深圳）有限公司 | Sound enhancement method, readable storage medium storing program for executing and terminal device neural network based |
| CN109409648A (en) * | 2018-09-10 | 2019-03-01 | 平安科技（深圳）有限公司 | Claims Resolution air control method, apparatus, computer equipment and storage medium |
| CN109492095A (en) * | 2018-10-16 | 2019-03-19 | 平安健康保险股份有限公司 | Claims Resolution data processing method, device, computer equipment and storage medium |
| CN109785117A (en) * | 2018-12-14 | 2019-05-21 | 平安科技（深圳）有限公司 | Air control method, computer readable storage medium and server neural network based |
| CN109859059A (en) * | 2019-01-17 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Settlement of insurance claim method, apparatus, computer equipment and storage medium |
| CN110059924A (en) * | 2019-03-13 | 2019-07-26 | 平安城市建设科技(深圳)有限公司 | Checking method, device, equipment and the computer readable storage medium of contract terms |
| CN110136010A (en) * | 2019-04-18 | 2019-08-16 | 中国平安财产保险股份有限公司 | The method, apparatus and computer equipment of risk case are judged based on neural network |
| CN110163407A (en) * | 2019-04-02 | 2019-08-23 | 阿里巴巴集团控股有限公司 | The optimization method and device of quantization strategy |
| CN110223182A (en) * | 2019-04-29 | 2019-09-10 | 上海暖哇科技有限公司 | A kind of Claims Resolution air control method, apparatus and computer readable storage medium |
| CN110322357A (en) * | 2019-05-30 | 2019-10-11 | 深圳壹账通智能科技有限公司 | Anomaly assessment method, apparatus, computer equipment and the medium of data |
| CN110472162A (en) * | 2019-08-20 | 2019-11-19 | 深圳前海微众银行股份有限公司 | Appraisal procedure, system, terminal and readable storage medium storing program for executing |
| WO2020073510A1 (en) * | 2018-10-11 | 2020-04-16 | 平安科技（深圳）有限公司 | Neural network-based vehicle damage determination method, server and medium |
| CN111222994A (en) * | 2018-11-23 | 2020-06-02 | 泰康保险集团股份有限公司 | Client risk assessment method, device, medium and electronic equipment |
| CN111260487A (en) * | 2020-01-20 | 2020-06-09 | 北京中科泽达科技有限公司 | Risk control method and device for vehicle insurance claim settlement |
| CN112634064A (en) * | 2020-12-02 | 2021-04-09 | 北京健康之家科技有限公司 | Intelligent claims auditing method, device and system and storage medium |
| CN113469826A (en) * | 2021-07-22 | 2021-10-01 | 阳光人寿保险股份有限公司 | Information processing method, device, equipment and storage medium |
| US20230005067A1 (en) * | 2021-07-02 | 2023-01-05 | Optum Services (Ireland) Limited | Generating risk determination machine learning frameworks using per-horizon historical claim sets |
| CN116342300A (en) * | 2023-05-26 | 2023-06-27 | 凯泰铭科技（北京）有限公司 | Method, device and equipment for analyzing characteristics of insurance claim settlement personnel |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090287512A1 (en) * | 2003-04-30 | 2009-11-19 | Genworth Financial,Inc | System And Process For Dominance Classification For Insurance Underwriting Suitable For Use By An Automated System |
| CN106570759A (en) * | 2016-11-09 | 2017-04-19 | 中国平安财产保险股份有限公司 | Intelligent risk scoring method and system for loss assessment of auto insurance case |
| CN106600417A (en) * | 2016-11-09 | 2017-04-26 | 前海企保科技（深圳）有限公司 | Underwriting method and device of property insurance policies |
| CN106971343A (en) * | 2016-01-13 | 2017-07-21 | 平安科技（深圳）有限公司 | The risk analysis method and system of insurance data |
| CN107292528A (en) * | 2017-06-30 | 2017-10-24 | 阿里巴巴集团控股有限公司 | Vehicle insurance Risk Forecast Method, device and server |
-
2017
- 2017-11-07 CN CN201711084960.0A patent/CN108256720A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090287512A1 (en) * | 2003-04-30 | 2009-11-19 | Genworth Financial,Inc | System And Process For Dominance Classification For Insurance Underwriting Suitable For Use By An Automated System |
| CN106971343A (en) * | 2016-01-13 | 2017-07-21 | 平安科技（深圳）有限公司 | The risk analysis method and system of insurance data |
| CN106570759A (en) * | 2016-11-09 | 2017-04-19 | 中国平安财产保险股份有限公司 | Intelligent risk scoring method and system for loss assessment of auto insurance case |
| CN106600417A (en) * | 2016-11-09 | 2017-04-26 | 前海企保科技（深圳）有限公司 | Underwriting method and device of property insurance policies |
| CN107292528A (en) * | 2017-06-30 | 2017-10-24 | 阿里巴巴集团控股有限公司 | Vehicle insurance Risk Forecast Method, device and server |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109409648A (en) * | 2018-09-10 | 2019-03-01 | 平安科技（深圳）有限公司 | Claims Resolution air control method, apparatus, computer equipment and storage medium |
| WO2020073510A1 (en) * | 2018-10-11 | 2020-04-16 | 平安科技（深圳）有限公司 | Neural network-based vehicle damage determination method, server and medium |
| CN109360581A (en) * | 2018-10-12 | 2019-02-19 | 平安科技（深圳）有限公司 | Sound enhancement method, readable storage medium storing program for executing and terminal device neural network based |
| CN109492095A (en) * | 2018-10-16 | 2019-03-19 | 平安健康保险股份有限公司 | Claims Resolution data processing method, device, computer equipment and storage medium |
| CN111222994A (en) * | 2018-11-23 | 2020-06-02 | 泰康保险集团股份有限公司 | Client risk assessment method, device, medium and electronic equipment |
| CN109785117A (en) * | 2018-12-14 | 2019-05-21 | 平安科技（深圳）有限公司 | Air control method, computer readable storage medium and server neural network based |
| CN109859059A (en) * | 2019-01-17 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Settlement of insurance claim method, apparatus, computer equipment and storage medium |
| CN110059924A (en) * | 2019-03-13 | 2019-07-26 | 平安城市建设科技(深圳)有限公司 | Checking method, device, equipment and the computer readable storage medium of contract terms |
| CN110163407B (en) * | 2019-04-02 | 2023-01-17 | 创新先进技术有限公司 | Quantization strategy optimization method and device |
| CN110163407A (en) * | 2019-04-02 | 2019-08-23 | 阿里巴巴集团控股有限公司 | The optimization method and device of quantization strategy |
| CN110136010A (en) * | 2019-04-18 | 2019-08-16 | 中国平安财产保险股份有限公司 | The method, apparatus and computer equipment of risk case are judged based on neural network |
| CN110223182A (en) * | 2019-04-29 | 2019-09-10 | 上海暖哇科技有限公司 | A kind of Claims Resolution air control method, apparatus and computer readable storage medium |
| CN110322357A (en) * | 2019-05-30 | 2019-10-11 | 深圳壹账通智能科技有限公司 | Anomaly assessment method, apparatus, computer equipment and the medium of data |
| CN110472162A (en) * | 2019-08-20 | 2019-11-19 | 深圳前海微众银行股份有限公司 | Appraisal procedure, system, terminal and readable storage medium storing program for executing |
| CN110472162B (en) * | 2019-08-20 | 2024-03-08 | 深圳前海微众银行股份有限公司 | Evaluation method, system, terminal and readable storage medium |
| CN111260487A (en) * | 2020-01-20 | 2020-06-09 | 北京中科泽达科技有限公司 | Risk control method and device for vehicle insurance claim settlement |
| CN112634064A (en) * | 2020-12-02 | 2021-04-09 | 北京健康之家科技有限公司 | Intelligent claims auditing method, device and system and storage medium |
| US20230005067A1 (en) * | 2021-07-02 | 2023-01-05 | Optum Services (Ireland) Limited | Generating risk determination machine learning frameworks using per-horizon historical claim sets |
| US11955244B2 (en) * | 2021-07-02 | 2024-04-09 | Optum Services (Ireland) Limited | Generating risk determination machine learning frameworks using per-horizon historical claim sets |
| CN113469826A (en) * | 2021-07-22 | 2021-10-01 | 阳光人寿保险股份有限公司 | Information processing method, device, equipment and storage medium |
| CN113469826B (en) * | 2021-07-22 | 2022-12-09 | 阳光人寿保险股份有限公司 | Information processing method, device, equipment and storage medium |
| CN116342300A (en) * | 2023-05-26 | 2023-06-27 | 凯泰铭科技（北京）有限公司 | Method, device and equipment for analyzing characteristics of insurance claim settlement personnel |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108256720A (en) | A kind of settlement of insurance claim methods of risk assessment and terminal device | |
| Rayan | Financial leverage and firm value | |
| Overesch et al. | The effects of company taxation in EU accession countries on German FDI 1 | |
| CN109785117A (en) | Air control method, computer readable storage medium and server neural network based | |
| CN105303445A (en) | Agricultural investment and financing platform risk evaluation apparatus and system | |
| CN110796539A (en) | Credit investigation evaluation method and device | |
| Hashemi et al. | Compromise ranking approach with bootstrap confidence intervals for risk assessment in port management projects | |
| EP3961507A1 (en) | Optimal policy learning and recommendation for distribution task using deep reinforcement learning model | |
| CN109840676A (en) | Air control method, apparatus, computer equipment and storage medium based on big data | |
| de Castro et al. | Expected utility or prospect theory: Which better fits agent-based modeling of markets? | |
| CN110599351A (en) | Investment data processing method and device | |
| Wang et al. | Applying TOPSIS method to evaluate the business operation performance of Vietnam listing securities companies | |
| CN112702410A (en) | Evaluation system and method based on block chain network and related equipment | |
| CN108241675A (en) | Data processing method and device | |
| Razali et al. | Identification of Risk Factors in Business Valuation | |
| Long et al. | Equilibrium Time‐Consistent Strategy for Corporate International Investment Problem with Mean‐Variance Criterion | |
| Nursimulu et al. | Excessive volatility is also a feature of individual level forecasts | |
| Tsaousoglou et al. | Forecasting the trends of financial ratios of Greek construction companies | |
| Peng et al. | Intelligent Optimization Model of Enterprise Financial Account Receivable Management | |
| Fovargue et al. | Running on debt: Financing land protection with loans | |
| Xiao et al. | Research on Multi-factor Stock Selection Strategy based on Improved Particle Swarm Support Vector Machine | |
| CN109657895B (en) | Early warning method, device, equipment and storage medium for fluidity notch | |
| US20230169607A1 (en) | Systems and Methods for Constructing, Valuing, and Reselling Stakes in Legal Claims | |
| Su | A rule extraction based approach in predicting derivative use for financial risk hedging in construction companies | |
| Bhatt | Validate Peter-Lynch Model on Indian Stock Market |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180706 |
|
| RJ01 | Rejection of invention patent application after publication |