CN110659998A - Data processing method, data processing apparatus, computer apparatus, and storage medium - Google Patents

Data processing method, data processing apparatus, computer apparatus, and storage medium Download PDF

Info

Publication number
CN110659998A
CN110659998A CN201910771254.6A CN201910771254A CN110659998A CN 110659998 A CN110659998 A CN 110659998A CN 201910771254 A CN201910771254 A CN 201910771254A CN 110659998 A CN110659998 A CN 110659998A
Authority
CN
China
Prior art keywords
parameters
target
historical
model
influence
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
Application number
CN201910771254.6A
Other languages
Chinese (zh)
Inventor
徐永胜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Life Insurance Company of China Ltd
Original Assignee
Ping An Life Insurance Company of China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Life Insurance Company of China Ltd filed Critical Ping An Life Insurance Company of China Ltd
Priority to CN201910771254.6A priority Critical patent/CN110659998A/en
Publication of CN110659998A publication Critical patent/CN110659998A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases
    • 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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Finance (AREA)
  • Technology Law (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

A method of data processing, comprising: acquiring historical result parameters of a historical object and historical influence parameters related to the historical result parameters of the historical object; fitting according to the historical influence parameters and the historical result parameters to obtain a plurality of model functions, and integrating the model functions to obtain a prediction model, wherein when input variables of the prediction model are influence parameters, output variables are result parameters; acquiring a target influence parameter of a target object; inputting the target influence parameters into the prediction model to obtain target result parameters of the target object; and creating a relational database, and correspondingly storing the target influence parameters and the target result parameters in the relational database. The invention also provides a data processing device, a computer device and a storage medium, and only the influence parameters need to be filled in the specific development of the insurance product through the preset development framework scheme, thereby being beneficial to improving the product development efficiency.

Description

Data processing method, data processing apparatus, computer apparatus, and storage medium
Technical Field
The invention relates to the technical field of computers, in particular to a data processing method based on model prediction, a data processing device based on model prediction, a computer device and a computer readable storage medium.
Background
At present, when insurance products are developed, a large amount of data need to be collected, and complicated data analysis is carried out on the large amount of data to obtain pricing results of the insurance products. This method of pricing is inefficient, requires significant computer system resources, and is not highly accurate.
Disclosure of Invention
In view of the above, there is a need to provide a data processing method and apparatus, a computer apparatus and a computer readable storage medium based on model prediction, so as to solve the above problems.
A first aspect of the present application provides a data processing method based on model prediction, applied in a computer device, the method including:
acquiring historical result parameters of a historical object and historical influence parameters related to the historical result parameters of the historical object;
fitting according to the historical influence parameters and the historical result parameters to obtain a plurality of model functions, and integrating the model functions to obtain a prediction model, wherein when input variables of the prediction model are influence parameters, output variables are result parameters;
acquiring a target influence parameter of a target object;
calling the prediction model, and inputting the target influence parameters into the prediction model to obtain target result parameters of the target object;
creating a relational database, and correspondingly storing the target influence parameters and the target result parameters in the relational database;
and outputting a target result parameter corresponding to the target influence parameter.
A second aspect of the present application provides a data processing apparatus based on model prediction, characterized in that the apparatus comprises:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring historical result parameters of historical objects and historical influence parameters related to the historical result parameters of the historical objects;
the model establishing module is used for fitting according to the historical influence parameters and the historical result parameters to obtain a plurality of model functions and integrating the model functions to obtain a prediction model, wherein when input variables of the prediction model are influence parameters, output variables are result parameters;
the second acquisition module is used for acquiring target influence parameters of the target object;
the calling module is used for calling the prediction model and inputting the target influence parameters into the prediction model to obtain target result parameters of the target object;
the database creating module is used for creating a relational database and correspondingly storing the target influence parameters and the target result parameters in the relational database;
and the output module is used for outputting the target result parameters corresponding to the target influence parameters.
A third aspect of the application provides a computer arrangement comprising a processor for implementing the model prediction based data processing method as described above when executing a computer program stored in a memory.
A fourth aspect of the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the model prediction based data processing method as described above.
The invention creates the prediction model in advance, only needs to fill in the influence parameters in the concrete development of the target object, and the prediction model can automatically generate the result parameters of the target object according to the filled parameters, thereby being beneficial to improving the prediction accuracy and efficiency and effectively reducing the occupation of computer system resources.
Drawings
Fig. 1 is a flowchart of a data processing method based on model prediction according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a data processing apparatus based on model prediction according to a second embodiment of the present invention.
Fig. 3 is a schematic diagram of a computer device according to a third embodiment of the present invention.
Description of the main elements
Computer device 1
Memory 20
Processor 30
Computer program 40
Data processing device 10 based on model prediction
First acquisition module 101
Model building Module 102
Second acquisition module 103
Calling module 104
Database creation module 105
Output module 106
Parsing module 107
Search module 108
The following detailed description will further illustrate the invention in conjunction with the above-described figures.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a detailed description of the present invention will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention, and the described embodiments are merely a subset of the embodiments of the present invention, rather than a complete embodiment. 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.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. 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.
Example one
Fig. 1 is a flowchart illustrating a data processing method based on model prediction according to a first embodiment of the present invention. The data processing method based on model prediction is applied to a computer device. The order of the steps in the flow chart may be changed and some steps may be omitted according to different needs. The data processing method based on model prediction comprises the following steps:
step S1: acquiring historical result parameters of a historical object and historical influence parameters related to the historical result parameters of the historical object.
Wherein the history object may be an existing insurance product. The historical outcome parameters may include, but are not limited to, the premium, cash value, rebate funds available to the customer when the customer is rebated, and the profit expected to be obtained by the insurance company for the existing insurance product.
The historical influence parameters are the existing influence parameters which influence the historical pricing results of the historical objects. The historical impact parameters may include, but are not limited to, claim liability, mortality incidence, and the like. It should be noted that the type of the historical influence parameter may be obtained by manual analysis according to a specific insurance product, and may be specifically changed according to different types of insurance products.
In this embodiment, the computer device obtains the historical result parameters and the historical influence parameters from a data source. The data source may be an insurance Application (APP) or an insurance database of an insurance company, etc. For example, an electronic policy corresponding to a history object purchased by a user may be obtained through an insurance database of an insurance company, and a history result parameter and a history influence parameter of the history object recorded in the electronic policy may be obtained.
Step S2: and fitting according to the historical influence parameters and the historical result parameters to obtain a plurality of model functions, and integrating the model functions to obtain a prediction model, wherein when the input variables of the prediction model are influence parameters, the output variables are result parameters.
The following description will be given taking the historical influence parameters as the responsibility for claim settlement, and the historical result parameters (historical pricing results) as the annual premium payment and cash value. The model function comprises calculation functions of claim settlement responsibility, annual premium payment, cash value and the like.
Wherein the calculated function of the annual premium Ρ is:
Figure BDA0002173407300000051
wherein0O1Is a matrix O 01 st element in (1);0i1is a matrix I0The 1 st element in (1).
Matrix OtA discount matrix representing future responsibility, the discount rate being i:
Figure BDA0002173407300000052
wherein, tOsAnd when the t policy year is end and the insurance effective state is S, the subsidence rate of future responsibility is i.
Matrix IOAnd (3) representing that the future net cash corresponding to the 1-yuan premium flows into a discount matrix, wherein the discount rate is i:
Figure BDA0002173407300000053
wherein the content of the first and second substances,tiswhen the end of the t-policy year is represented and the insurance validity state is S, the future net cash flow corresponding to the 1-dollar premium is closed.
Cash value CtThe calculation function of (a) is:
Ct＝Ot-ΡIt (1.2)
as can be seen from the equations (1.1) and (1.2), the result of the annual premium and cash value is a cash matrix O through future liabilitytAnd (6) determining. And O istBy claim responsibility BtAnd survivor gold AtDetermining, in particular, a mapping matrix O of future responsibilitiestThe following recurrence relation is satisfied:
·t＝n
Figure BDA0002173407300000054
·t＜n
Figure BDA0002173407300000055
wherein, the matrix BtRepresenting the claims amount matrix:
Figure BDA0002173407300000056
wherein the content of the first and second substances,tbsKand (3) when the insurance validity state is S and the end of the t policy year, the settlement amount of the settlement responsibility K occurs in the t +1 yuan policy year.
Matrix AtRepresent survival gold matrix:
wherein the content of the first and second substances,tasindicating the survival fund at the beginning of the t +1 yuan policy year when the insurance effective state is S at the end of the t policy year.
And claim accountability BtAnd survivor gold AtYet further with the annual premium Pp and cash value CtAnd (4) correlating. Thus, the present embodiment integrates the model functions and calculates the annual premium Ρ and cash value C by means of a numerical solution methodt. Wherein, the data solving method is based on given initial values, and then the annual premium Pp and the cash value C are solved in an iterative waytSpecifically:
1. suppose yearPremium Pp and cash value CtAre respectively p(0)And Ct (0)；
2. Will be(0)And Ct (0)Substituting the values into the formulas (1.3) and (1.4) to obtain a mapping matrix O of future responsibilityt (1)；
3. Mixing O witht (1)Sequentially substituting the formula (1.1) and the formula (1.2) to obtain the annual premium P after the first iteration(1)And cash value Ct (1)；
4. Repeating the three steps to obtain the following annual premium and cash value sequence:
Ρ(ο)，Ρ(1)，Ρ(2)，…，Ρ(l)
Ct (ο)，Ct (1)，Ct (2)，…，Ct (l)；
5. setting a preset precision value K (e.g., K is 0.000001), stopping iteration when the following conditions are met:
Figure BDA0002173407300000062
where n denotes the warrant guarantee period, Pp(l)And Ct (l)Representing the final annual premium and cash value, respectively, Pp(l)And Ct (l)Equal to the historical result parameter of the historical object.
Step S3: and acquiring target influence parameters of the target object.
In this embodiment, the computer device may provide an operation interface for a developer to input the target influence parameter. More specifically, the operation interface is used for displaying a form, and the form has a field corresponding to the target influence parameter so that a developer can input the target influence parameter in the form.
Step S4: and calling the prediction model, and inputting the target influence parameters into the prediction model to obtain target result parameters of the target object.
Therefore, when a developer needs to predict the target result parameters, the developer only needs to input the target influence parameters into the prediction model, and the prediction model can output corresponding target result data according to the target influence parameters. Developers do not need to perform specific calculation, so that the error problem caused by manual calculation can be omitted, and the efficiency is improved.
Step S5: and creating a relational database, correspondingly storing the target influence parameters and the target result parameters of the target object in the relational database, and outputting the target result parameters corresponding to the target influence parameters.
In this embodiment, the relational database may be a mysql, sqlservice, oracle database, or the like. In this embodiment, the relational database is an oracle database.
Further, the computer device is further configured to obtain an object type of the target object, and store the target impact parameter, the target result parameter of the target object, and the object type in the relational database in a corresponding manner. When the target object is an insurance product, the object type of the target object is an insurance type, and the insurance type may be classified according to an insurance target, such as: personal insurance (such as life insurance, health insurance and accidental injury insurance), property insurance and the like. And the developer can also input the object type through the operation interface, and the computer device acquires the object type from the operation interface. In other embodiments, the insurance type may also be classified according to other insurance indicia.
The standardized management of the product data is realized through the relational database, so that the influence parameters of the similar insurance products can be called subsequently, the development process of the insurance products can be further reduced, and the product development efficiency is improved. In addition, the sharing of resources can be realized, and development cases are provided for other developers.
In this embodiment, the target impact parameters include at least one of structured data and unstructured data. The structured data refers to a data form, such as numbers, symbols, and the like, which can be represented by data or a unified structure. The unstructured data refers to data forms without fixed structures, such as various documents, pictures and the like. For the structured data, when a target influence parameter of a similar insurance product needs to be called, source data can be obtained from the relational database, and the source data is imported into a Distributed System (HDFS) through sqoop. For the unstructured data, when the target influence parameters of similar insurance products need to be called, the source data can be sent to a distributed publish-subscribe message system (Kafka), and the source data is synchronized into the HDFS through the distributed publish-subscribe message system. And then processing the source data imported into the HDFS by adopting a hive tool according to a preset requirement, and storing the source data into a hive data table, wherein the hive data table is stored in a text file form.
Subsequently, if a new target object (i.e., a new insurance product to be priced) needs to be developed, the target influence parameters corresponding to similar target objects stored in the relational database may be called. For this case, the data processing method based on model prediction may further include:
step S6: when a search instruction is received, the search instruction is analyzed to obtain at least one first object type.
Wherein, when a developer needs to develop an insurance product to be priced, the search instruction can be input to the computer device according to the first object type of the insurance product to be priced. More specifically, the developer may input the search instruction through the operation interface.
Step S7, searching at least one target object stored in the relational database and having an object type the same as the first object type according to the search instruction, obtaining a target influence parameter corresponding to the searched target object, taking the obtained target influence parameter as a reference influence parameter, and outputting the reference influence parameter.
Therefore, after the developer obtains the reference influence parameters, the developer can adjust the reference influence parameters according to actual needs and re-input the adjusted reference influence parameters into the computer device.
And step S8, receiving the adjusted reference influence parameters, recalling the prediction model, inputting the adjusted reference influence parameters into the prediction model, and obtaining the target result parameters of the insurance products to be priced.
The above-mentioned fig. 1 describes the data processing method based on model prediction in detail, and the functional modules of the software device for implementing the data processing method based on model prediction and the hardware device architecture for implementing the data processing method based on model prediction are described below with reference to fig. 2 to 3.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
Example two
FIG. 2 is a block diagram of a data processing apparatus based on model prediction according to a preferred embodiment of the present invention.
In some embodiments, the model prediction based data processing apparatus 10 operates in a computer apparatus. The model-based prediction data processing apparatus 10 may comprise a plurality of functional modules consisting of program code segments. Program code for various program segments in the model prediction based data processing apparatus 10 may be stored in a memory of a computer apparatus and executed by the at least one processor to implement model prediction based data processing functions.
In this embodiment, the data processing apparatus 10 based on model prediction may be divided into a plurality of functional modules according to the functions performed by the data processing apparatus. Referring to fig. 2, the functional modules may include: the system comprises a first acquisition module 101, a model building module 102, a second acquisition module 103, a calling module 104, a database creation module 105, an output module 106, a parsing module 107 and a search module 108. The module referred to herein is a series of computer program segments capable of being executed by at least one processor and capable of performing a fixed function and is stored in memory. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.
The first obtaining module 101 is configured to obtain a history result parameter of a history object and a history influence parameter related to the history result parameter of the history object.
Wherein the history object may be an existing insurance product. The historical outcome parameters may include, but are not limited to, the premium, cash value, rebate funds available to the customer when the customer is rebated, and the profit expected to be obtained by the insurance company for the existing insurance product.
The historical influence parameters are existing influence parameters which influence the historical result parameters of the historical objects. The historical impact parameters may include, but are not limited to, claim liability, mortality incidence, and the like. It should be noted that the type of the historical influence parameter may be obtained by manual analysis according to a specific insurance product, and may be specifically changed according to different types of insurance products.
In this embodiment, the first obtaining module 101 obtains the history result parameter and the history influence parameter from a data source. The data source may be an insurance Application (APP) or an insurance database of an insurance company, etc. For example, an electronic policy corresponding to a history object purchased by a user may be obtained through an insurance database of an insurance company, and a history result parameter and a history influence parameter of the history object recorded in the electronic policy may be obtained.
The model establishing module 102 is configured to fit the historical influence parameters and the historical result parameters to obtain a plurality of model functions, and integrate the model functions to obtain a prediction model, where when an input variable of the prediction model is an influence parameter, an output variable is a result parameter.
The following description will take the historical influence parameters as the responsibility of claim settlement, and the historical result parameters as the annual premium payment and the cash value. The model function comprises calculation functions of claim settlement responsibility, annual premium payment, cash value and the like.
Wherein the calculated function of the annual premium Ρ is:
Figure BDA0002173407300000101
wherein0O1Is a matrix O 01 st element in (1);0i1is a matrix I0The 1 st element in (1).
Matrix OtA discount matrix representing future responsibility, the discount rate being i:
Figure BDA0002173407300000102
wherein, tOsAnd when the t policy year is end and the insurance effective state is S, the subsidence rate of future responsibility is i.
Matrix IOAnd (3) representing that the future net cash corresponding to the 1-yuan premium flows into a discount matrix, wherein the discount rate is i:
Figure BDA0002173407300000103
wherein the content of the first and second substances,tiswhen the end of the t-policy year is represented and the insurance validity state is S, the future net cash flow corresponding to the 1-dollar premium is closed.
Cash value CtThe calculation function of (a) is:
Ct＝Ot-ΡIt (1.2)
as can be seen from the equations (1.1) and (1.2), the result of the annual premium and cash value is a cash matrix O through future liabilitytAnd (6) determining. And O istBy claim responsibility BtAnd survivor gold AtDetermining, in particular, a mapping matrix O of future responsibilitiestThe following recurrence relation is satisfied:
·t＝n
·t＜n
Figure BDA0002173407300000112
wherein, the matrix BtRepresenting the claims amount matrix:
Figure BDA0002173407300000113
wherein the content of the first and second substances,tbsKand (3) when the insurance validity state is S and the end of the t policy year, the settlement amount of the settlement responsibility K occurs in the t +1 yuan policy year.
Matrix AtRepresent survival gold matrix:
Figure BDA0002173407300000114
wherein the content of the first and second substances,tasindicating the survival fund at the beginning of the t +1 yuan policy year when the insurance effective state is S at the end of the t policy year.
And claim accountability BtAnd survivor gold AtYet further with the annual premium Pp and cash value CtAnd (4) correlating. Thus, the present embodiment integrates the model functions and calculates the annual premium Ρ and cash value C by means of a numerical solution methodt. Wherein, the data solving method is based on given initial values, and then the annual premium Pp and the cash value C are solved in an iterative waytSpecifically:
1. assume annual premium Pp and cash value CtAre respectively p(0)And Ct (0)；
2. Will be(0)And Ct (0)Substituting the values into the formulas (1.3) and (1.4) to obtain a mapping matrix O of future responsibilityt (1)；
3. Mixing O witht (1)Sequentially substituting the formula (1.1) and the formula (1.2) to obtain the annual premium P after the first iteration(1)And cash value Ct (1)；
4. Repeating the three steps to obtain the following annual premium and cash value sequence:
Ρ(ο)，Ρ(1)，Ρ(2)，…，Ρ(l)
Ct (ο)，Ct (1)，Ct (2)，…，Ct (l)；
5. setting a preset precision value K (e.g., K is 0.000001), stopping iteration when the following conditions are met:
Figure BDA0002173407300000121
where n denotes the warrant guarantee period, Pp(l)And Ct (l)Representing the final annual premium and cash value, respectively, Pp(l)And Ct (l)Equal to the historical result parameter of the historical object.
The second obtaining module 103 is configured to obtain a target influence parameter of a target object.
In this embodiment, the computer device may provide an operation interface for a developer to input the target influence parameter. More specifically, the operation interface is used for displaying a form, and the form has a field corresponding to the target influence parameter so that a developer can input the target influence parameter in the form.
The calling module 104 is configured to call the prediction model, and input the target influence parameter into the prediction model to obtain a target result parameter of the target object.
Therefore, when a developer needs to predict the target result parameters, the developer only needs to input the target influence parameters into the prediction model, and the prediction model can output corresponding target result data according to the target influence parameters. Developers do not need to perform specific calculation, so that the error problem caused by manual calculation can be omitted, and the efficiency is improved.
The database creating module 105 is configured to create a relational database, and store the target impact parameters and the target result parameters of the target object in the relational database correspondingly.
In this embodiment, the relational database may be a mysql, sqlservice, oracle database, or the like. In this embodiment, the relational database is an oracle database.
Further, the second obtaining module 103 is further configured to obtain an object type of the target object, and the database creating module 105 correspondingly stores the target impact parameter, the target result parameter of the target object, and the object type in the relational database. When the target object is an insurance product, the insurance type of the target object is an insurance type, and the insurance type may be classified according to the insurance target, such as: personal insurance (such as life insurance, health insurance and accidental injury insurance), property insurance and the like. The developer may also input the object type through the operation interface, and the second obtaining module 103 obtains the insurance type from the operation interface. In other embodiments, the insurance type may also be classified according to other insurance indicia.
The standardized management of the product data is realized through the relational database, so that the influence parameters of the similar insurance products can be called subsequently, the development process of the insurance products can be further reduced, and the product development efficiency is improved. In addition, the sharing of resources can be realized, and development cases are provided for other developers.
In this embodiment, the target impact parameters include at least one of structured data and unstructured data. The structured data refers to a data form, such as numbers, symbols, and the like, which can be represented by data or a unified structure. The unstructured data refers to data forms without fixed structures, such as various documents, pictures and the like. For the structured data, when a target influence parameter of a similar insurance product needs to be called, source data can be obtained from the relational database, and the source data is imported into a Distributed System (HDFS) through sqoop. For the unstructured data, when the target influence parameters of similar insurance products need to be called, the source data can be sent to a distributed publish-subscribe message system (Kafka), and the source data is synchronized into the HDFS through the distributed publish-subscribe message system. And then processing the source data imported into the HDFS by adopting a hive tool according to a preset requirement, and storing the source data into a hive data table, wherein the hive data table is stored in a text file form.
The output module 106 is configured to output a target result parameter corresponding to the target influence parameter.
Subsequently, if a new target object (i.e., a new insurance product to be priced) needs to be developed, the target influence parameters corresponding to similar target objects stored in the relational database may be called. For this case, the parsing module 107 is configured to, when a search instruction is received, parse the search instruction to obtain at least one first object type.
Wherein, when a developer needs to develop an insurance product to be priced, the search instruction can be input to the computer device according to the first object type of the insurance product to be priced. More specifically, the developer may input the search instruction through the operation interface.
The search module 108 is configured to search at least one target object stored in the relational database and having an object type that is the same as the first object type according to the search instruction, obtain a target impact parameter corresponding to the searched target object, use the obtained target impact parameter as a reference impact parameter, and output the reference impact parameter.
Therefore, after the developer obtains the reference influence parameters, the developer can adjust the reference influence parameters according to actual needs and re-input the adjusted reference influence parameters into the computer device.
The calling module 104 is further configured to receive the adjusted reference impact parameter, call the prediction model again, and input the adjusted reference impact parameter into the prediction model to obtain a result parameter of the insurance product to be priced.
As described above, in the embodiment of the present invention, the prediction model is created in advance, and only the influence parameters need to be filled in during the specific development of the insurance product, and the prediction model can automatically generate the result parameters of the insurance product according to the filled parameters, so that the improvement of the product development efficiency is facilitated, and the occupation of computer system resources can be effectively reduced; moreover, standardized management of product data is realized through a relational database (such as an oracle database), so that precious resources are accumulated for future product development.
EXAMPLE III
FIG. 3 is a diagram of a computer device according to a preferred embodiment of the present invention.
The computer device 1 comprises a memory 20, a processor 30 and a computer program 40, such as a model prediction based data processing program, stored in the memory 20 and executable on the processor 30. The processor 30, when executing the computer program 40, implements the steps of the above-described model prediction-based data processing method embodiments, such as the steps S1-S8 shown in fig. 1. Alternatively, the processor 30, when executing the computer program 40, implements the functions of the modules/units in the above-mentioned data processing apparatus embodiment based on model prediction, such as the module 101 and 108 in fig. 2.
Illustratively, the computer program 40 may be partitioned into one or more modules/units that are stored in the memory 20 and executed by the processor 30 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 40 in the computer apparatus 1. For example, the computer program 40 may be divided into a first obtaining module 101, a model building module 102, a second obtaining module 103, a calling module 104, a database creating module 105, an output module 106, a parsing module 107, and a search module 108 in fig. 2. See embodiment two for specific functions of each module.
The computer device 1 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. It will be appreciated by a person skilled in the art that the schematic diagram is merely an example of the computer apparatus 1, and does not constitute a limitation of the computer apparatus 1, and may comprise more or less components than those shown, or some components may be combined, or different components, for example, the computer apparatus 1 may further comprise an input and output device, a network access device, a bus, etc.
The Processor 30 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor 30 may be any conventional processor or the like, the processor 30 being the control center of the computer device 1 and connecting the various parts of the whole computer device 1 with various interfaces and lines.
The memory 20 may be used for storing the computer program 40 and/or the module/unit, and the processor 30 implements various functions of the computer device 1 by running or executing the computer program and/or the module/unit stored in the memory 20 and calling data stored in the memory 20. The memory 20 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data) created according to the use of the computer apparatus 1, and the like. Further, the memory 20 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a flash memory Card (FlashCard), at least one magnetic disk storage device, a flash memory device, or other non-volatile solid state storage device.
The modules/units integrated with the computer device 1 may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
In the embodiments provided in the present invention, it should be understood that the disclosed computer apparatus and method can be implemented in other ways. For example, the above-described embodiments of the computer apparatus are merely illustrative, and for example, the division of the units is only one logical function division, and there may be other divisions when the actual implementation is performed.
In addition, functional units in the embodiments of the present invention may be integrated into the same processing unit, or each unit may exist alone physically, or two or more units are integrated into the same unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. The units or computer means recited in the computer means claims may also be implemented by the same unit or computer means, either in software or in hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (9)

1. A data processing method based on model prediction, applied to a computer device, is characterized in that the method comprises the following steps:
acquiring historical result parameters of a historical object and historical influence parameters related to the historical result parameters of the historical object;
fitting according to the historical influence parameters and the historical result parameters to obtain a plurality of model functions, and integrating the model functions to obtain a prediction model, wherein when input variables of the prediction model are influence parameters, output variables are result parameters;
acquiring a target influence parameter of a target object;
calling the prediction model, and inputting the target influence parameters into the prediction model to obtain target result parameters of the target object;
creating a relational database, and correspondingly storing the target influence parameters and the target result parameters in the relational database;
and outputting a target result parameter corresponding to the target influence parameter.
2. The model prediction-based data processing method of claim 1, wherein the relational database is one of mysql, sqlservice, and oracle databases.
3. The model prediction-based data processing method of claim 1, wherein the computer device is further configured to obtain an object type of the target object, and store the target impact parameter, the target result parameter, and the object type in the relational database.
4. The model prediction-based data processing method of claim 3, further comprising:
when a search instruction is received, analyzing the search instruction to obtain at least one first object type; and
searching at least one target object with the same object type as the first object type stored in the relational database according to the search instruction, and acquiring a target influence parameter corresponding to the searched target object; and
and taking the obtained target influence parameter as a reference influence parameter and outputting the reference influence parameter.
5. The model prediction-based data processing method of claim 4, further comprising:
receiving the adjusted reference impact parameters;
and recalling the prediction model, and inputting the adjusted reference influence parameters into the prediction model to obtain target result parameters of a new target object.
6. The model-prediction-based data processing method according to claim 1, wherein when the historical influence parameters include a claim settlement responsibility and the historical result parameters include an annual premium and a cash value, the model functions include calculation functions of the claim settlement responsibility, the annual premium and the cash value, the integrating the model functions to obtain the prediction model includes integrating the calculation functions of the claim settlement responsibility, the annual premium and the cash value, and calculating the annual premium and the cash value by numerical solution;
wherein the data is solved to solve for annual premium and cash value in an iterative manner based on a given initial value.
7. A data processing apparatus based on model prediction, the apparatus comprising:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring historical result parameters of historical objects and historical influence parameters related to the historical result parameters of the historical objects;
the model establishing module is used for fitting according to the historical influence parameters and the historical result parameters to obtain a plurality of model functions and integrating the model functions to obtain a prediction model, wherein when input variables of the prediction model are influence parameters, output variables are result parameters;
the second acquisition module is used for acquiring target influence parameters of the target object;
the calling module is used for calling the prediction model and inputting the target influence parameters into the prediction model to obtain target result parameters of the target object;
the database creating module is used for creating a relational database and correspondingly storing the target influence parameters and the target result parameters in the relational database;
and the output module is used for outputting the target result parameters corresponding to the target influence parameters.
8. A computer device, characterized by: the computer arrangement comprises a processor for implementing the method of model prediction based data processing according to any of claims 1-6 when executing a computer program stored in a memory.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when executed by a processor, implements a method of model prediction based data processing according to any of claims 1-6.
CN201910771254.6A 2019-08-20 2019-08-20 Data processing method, data processing apparatus, computer apparatus, and storage medium Pending CN110659998A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910771254.6A CN110659998A (en) 2019-08-20 2019-08-20 Data processing method, data processing apparatus, computer apparatus, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910771254.6A CN110659998A (en) 2019-08-20 2019-08-20 Data processing method, data processing apparatus, computer apparatus, and storage medium

Publications (1)

Publication Number Publication Date
CN110659998A true CN110659998A (en) 2020-01-07

Family

ID=69037637

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910771254.6A Pending CN110659998A (en) 2019-08-20 2019-08-20 Data processing method, data processing apparatus, computer apparatus, and storage medium

Country Status (1)

Country Link
CN (1) CN110659998A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111930350A (en) * 2020-08-05 2020-11-13 深轻(上海)科技有限公司 Actuarial model establishing method based on calculation template
CN112182118A (en) * 2020-09-29 2021-01-05 中国平安人寿保险股份有限公司 Target object prediction method based on multiple data sources and related equipment thereof
CN113570124A (en) * 2021-07-15 2021-10-29 上海淇玥信息技术有限公司 Object assignment method and device and electronic equipment

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111930350A (en) * 2020-08-05 2020-11-13 深轻(上海)科技有限公司 Actuarial model establishing method based on calculation template
CN111930350B (en) * 2020-08-05 2024-04-09 深轻(上海)科技有限公司 Calculation template-based fine calculation model establishment method
CN112182118A (en) * 2020-09-29 2021-01-05 中国平安人寿保险股份有限公司 Target object prediction method based on multiple data sources and related equipment thereof
CN112182118B (en) * 2020-09-29 2023-12-05 中国平安人寿保险股份有限公司 Target object prediction method based on multiple data sources and related equipment thereof
CN113570124A (en) * 2021-07-15 2021-10-29 上海淇玥信息技术有限公司 Object assignment method and device and electronic equipment

Similar Documents

Publication Publication Date Title
CN110140118B (en) System and method for determining relationships between data elements
Ardia et al. Generalized autoregressive score models in R: The GAS package
US7035786B1 (en) System and method for multi-phase system development with predictive modeling
CN112256720B (en) Data cost calculation method, system, computer device and storage medium
CN110659998A (en) Data processing method, data processing apparatus, computer apparatus, and storage medium
CN108241529B (en) Salary calculation method, application server and computer readable storage medium
CN110728422A (en) Building information model, method, device and settlement system for construction project
US20220335023A1 (en) Database validation and repair tool
CN113283675B (en) Index data analysis method, device, equipment and storage medium
Bladt et al. Matrix representations of life insurance payments
JP2009032237A (en) Method and apparatus for calculating credit risk of portfolio
CN112241433A (en) Product demonstration method and device, computer equipment and storage medium
CN110352405B (en) Computer-readable medium, computing system, method, and electronic device
Xu et al. Multiscale quantile correlation coefficient: measuring tail dependence of financial time series
US20150170068A1 (en) Determining analysis recommendations based on data analysis context
US10025838B2 (en) Extract transform load input suggestion
CN114926082A (en) Artificial intelligence-based data fluctuation early warning method and related equipment
US11500840B2 (en) Contrasting document-embedded structured data and generating summaries thereof
US11651281B2 (en) Feature catalog enhancement through automated feature correlation
CN113592263A (en) Resource return increment prediction method and device based on dynamic resource return increase ratio
CN113094386A (en) Supervision index configuration method and device, electronic equipment and medium
CN112667721A (en) Data analysis method, device, equipment and storage medium
D'amico et al. Bivariate semi-Markov process for counterparty credit risk
CN111079991A (en) Service index prediction method, device, equipment and storage medium
WO2019136628A1 (en) Method, apparatus and system for assisting in enterprise listing

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