CN116402623A

CN116402623A - Insurance product object evaluation method and device, storage medium and electronic equipment

Info

Publication number: CN116402623A
Application number: CN202310223994.2A
Authority: CN
Inventors: 曹铸; 吴腾飞; 王洪彬; 张放; 陈捷思; 张程; 童成杰; 江发昌; 郑波; 孙振兴; 王流斌
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2023-03-03
Filing date: 2023-03-03
Publication date: 2023-07-07

Abstract

The specification discloses an insurance product object evaluation method, an apparatus, a storage medium and an electronic device, wherein the method comprises the following steps: and determining an object evaluation amount of the insurance product object based on the item reaction theoretical model after the model calculation processing.

Description

Insurance product object evaluation method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method and apparatus for evaluating an insurance product object, a storage medium, and an electronic device.

Background

Insurance products are often numerous, even though there are at least thousands of insurance of the same type. The insurance product involves a lot of expertise, and the information is quite unequal for users, so that misunderstanding and confusion are easy to generate when users understand the product clauses, and therefore, proper products are difficult to reasonably select, and even purchasing behavior is abandoned.

Disclosure of Invention

The specification provides an insurance product object evaluation method, an insurance product object evaluation device, a storage medium and electronic equipment, wherein the technical scheme is as follows:

in a first aspect, the present specification provides a method of evaluating an insurance product object, the method comprising:

determining a project reaction theoretical model aiming at an insurance product object, and acquiring at least one product characteristic evaluation index corresponding to the insurance product object;

performing model calculation processing on the project reaction theoretical model based on the product characteristic evaluation index to obtain potential specific mass and model parameters of the project reaction theoretical model;

and determining the object evaluation quantity of the insurance product object based on the project reaction theoretical model after model calculation processing.

In a second aspect, the present specification provides an insurance product object evaluation device, the device comprising:

the index determining module is used for determining a project response theoretical model aiming at the insurance product object and acquiring at least one product characteristic evaluation index corresponding to the insurance product object;

the model resolving module is used for performing model resolving processing on the project reaction theoretical model based on the product characteristic evaluation index to obtain potential special quality and model parameters of the project reaction theoretical model;

And the object evaluation module is used for determining the object evaluation quantity of the insurance product object based on the project reaction theoretical model after the model calculation processing.

In a third aspect, the present description provides a computer storage medium storing at least one instruction adapted to be loaded by a processor and to perform the method steps of one or more embodiments of the present description.

In a fourth aspect, the present description provides a computer program product storing at least one instruction adapted to be loaded by a processor and to perform the method steps of one or more embodiments of the present description.

In a fifth aspect, the present description provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of one or more embodiments of the present description.

The technical scheme provided by some embodiments of the present specification has the following beneficial effects:

in one or more embodiments of the present disclosure, an electronic device performs a model resolving process on a project reaction theoretical model based on at least one product feature evaluation index corresponding to an insurance product object by determining the project reaction theoretical model of the insurance product object, to obtain a potential specific quality and a model parameter of the project reaction theoretical model, and determines an object evaluation amount of the insurance product object based on the project reaction theoretical model after the model resolving process, where a result of evaluating the insurance product object depends on a data feature of the insurance product object, that is, a product feature evaluation index, and no artificial subjectivity factor is additionally introduced compared with a subjective comprehensive evaluation method, so that an effect of evaluating the insurance product object is ensured, and an accuracy of the evaluation is improved.

Drawings

In order to more clearly illustrate the technical solutions of the present specification or the prior art, the following description will briefly introduce the drawings that are required to be used in the embodiments or the prior art descriptions, it is obvious that the drawings in the following description are only some embodiments of the present specification, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic view of a scenario of an insurance product object evaluation system provided in the present specification;

FIG. 2 is a flow chart of an insurance product object evaluation method provided in the present specification;

FIG. 3 is a flow chart of another insurance product object evaluation method provided in the present specification;

FIG. 4 is a graph of the reaction probability corresponding to a first function representation provided in the present specification;

fig. 5 is a schematic structural view of an insurance product object evaluation device provided in the present specification;

FIG. 6 is a schematic diagram of a model calculation module provided in the present specification;

FIG. 7 is a schematic diagram of an electronic device provided in the present specification;

FIG. 8 is a schematic diagram of the architecture of the operating system and user space provided herein;

FIG. 9 is an architecture diagram of the android operating system of FIG. 8;

FIG. 10 is an architecture diagram of the IOS operating system of FIG. 8.

Detailed Description

The following description of the embodiments of the present invention will be made apparent from, and elucidated with reference to, the drawings of the present specification, in which embodiments described are only some, but not all, embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the present disclosure.

In the description of the present specification, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In the description of the present specification, it should be noted that, unless expressly specified and limited otherwise, "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus. The specific meaning of the terms in this specification will be understood by those of ordinary skill in the art in the light of the specific circumstances. In addition, in the description of the present specification, unless otherwise indicated, "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.

In the related art, users such as insurance consumers and the like usually assist in making purchase decisions with reference to the evaluation list of the insurance product objects, for example, can refer to the insurance product ranking list purchase decisions; however, most insurance evaluation gives a subjective comprehensive evaluation method such as a list using expert direct weighting or analytic hierarchy process, and larger subjective factors exist by adopting the subjective comprehensive evaluation method to cause inaccurate evaluation and poor evaluation effect of insurance product objects;

the present specification is described in detail below with reference to specific examples.

Referring to fig. 1, a schematic view of a scenario of an insurance product object evaluation system provided in the present specification is provided. As shown in fig. 1, the insurance product object evaluation system may include at least a client cluster and a service platform 100.

The client cluster may include at least one client, as shown in fig. 1, specifically including a client 1 corresponding to a user 1, a client 2 corresponding to a user 2, …, and a client n corresponding to a user n, where n is an integer greater than 0.

Each client in the client cluster may be a communication-enabled electronic device including, but not limited to: wearable devices, handheld devices, personal computers, tablet computers, vehicle-mounted devices, smart phones, computing devices, or other processing devices connected to a wireless modem, etc. Electronic devices in different networks may be called different names, for example: a user equipment, an access terminal, a subscriber unit, a subscriber station, a mobile station, a remote terminal, a mobile device, a user terminal, a wireless communication device, a user agent or user equipment, a cellular telephone, a cordless telephone, a personal digital assistant (personal digital assistant, PDA), an electronic device in a 5G network or future evolution network, and the like.

The service platform 100 may be a separate server device, such as: rack-mounted, blade, tower-type or cabinet-type server equipment or hardware equipment with stronger computing capacity such as workstations, mainframe computers and the like is adopted; the server cluster may also be a server cluster formed by a plurality of servers, and each server in the server cluster may be formed in a symmetrical manner, wherein each server is functionally equivalent and functionally equivalent in a transaction link, and each server may independently provide services to the outside, and the independent provision of services may be understood as no assistance of another server is needed.

In one or more embodiments of the present disclosure, the service platform 100 may establish a communication connection with at least one client in the client cluster, and complete data interaction in the process of evaluating the insurance product object based on the communication connection, for example, the service platform 100 may make an auxiliary recommendation to the client based on the object evaluation amount of the insurance product object obtained by the insurance product object evaluation method of the present disclosure;

it should be noted that, the service platform 100 establishes a communication connection with at least one client in the client cluster through a network for interactive communication, where the network may be a wireless network, or may be a wired network, where the wireless network includes, but is not limited to, a cellular network, a wireless local area network, an infrared network, or a bluetooth network, and the wired network includes, but is not limited to, an ethernet network, a universal serial bus (universal serial bus, USB), or a controller area network. In one or more embodiments of the specification, techniques and/or formats including HyperText Mark-up Language (HTML), extensible markup Language (Extensible Markup Language, XML), and the like are used to represent data exchanged over a network (e.g., target compression packages). All or some of the links may also be encrypted using conventional encryption techniques such as secure socket layer (Secure Socket Layer, SSL), transport layer security (Transport Layer Security, TLS), virtual private network (Virtual Private Network, VPN), internet protocol security (Internet Protocol Security, IPsec), and the like. In other embodiments, custom and/or dedicated data communication techniques may also be used in place of or in addition to the data communication techniques described above.

The embodiments of the insurance product object evaluation system provided in the present specification and the insurance product object evaluation method in one or more embodiments belong to the same concept, and an execution subject corresponding to the insurance product object evaluation method related to one or more embodiments in the present specification may be the service platform 100 described above; the execution subject corresponding to the insurance product object evaluation method related to one or more embodiments of the specification may also be an electronic device corresponding to the client, and specifically determined based on an actual application environment. The implementation process of the insurance product object evaluation system embodiment may be described in detail in the following method embodiment, which is not described herein.

Based on the schematic view of the scenario shown in fig. 1, the following describes in detail an insurance product object evaluation method provided in one or more embodiments of the present disclosure.

Referring to fig. 2, a flow diagram of an insurance product object evaluation method, which may be implemented in dependence on a computer program and may be run on a von neumann system-based insurance product object evaluation device, is provided for one or more embodiments of the present description. The computer program may be integrated in the application or may run as a stand-alone tool class application. The insurance product object evaluation device may be a service platform.

Specifically, the insurance product object evaluation method comprises the following steps:

s102: determining a project reaction theoretical model aiming at an insurance product object, and acquiring at least one product characteristic evaluation index corresponding to the insurance product object;

illustratively, the project response theory is a modern psychological measurement theory for measuring potential physical characteristics, also called potential characteristics theory or potential characteristics model, and in the modern psychological field, the project response theory generally involves using some project response theory model, and it is common to measure the ability of a tested user and the difficulty of a test question, and infer the probability that the tested user correctly answers the test question according to the result. The test question qi in the project reaction theory is represented by a pair of parameters ζi= (αi, βi), and the probability function of the correct answer is considered to be related to θi, αi and βi only, wherein θi represents the capability level of the user under test, αi represents the distinguishing capability of the test question, and βi represents the difficulty of the test question.

The product characteristic evaluation index is used for evaluating an insurance product object, and generally one or more product characteristics of the insurance product object can be used as an evaluation index for subjectively or objectively evaluating the quality or the quality of an insurance product, namely, a product characteristic evaluation index. The product characteristic evaluation index may be, for example, a fit of one or more of the types of career-able category, product reimbursement scope, product insurance scope, product premium, product risk, product payment period, product reimbursement proportion, and the like. Illustratively, after the insurance product is released, the at least one product characteristic evaluation index corresponding to the insurance product object can obtain the insurance detailed information of the insurance product object through the corresponding insurance public information obtaining channel, and the at least one product characteristic evaluation index of the insurance product object can be obtained based on the insurance detailed information.

In the actual application scene, the insurance product objects are often numerous, and the insurance function corresponding to the insurance product objects is complex, the use value of the insurance product objects is difficult to perceive, and the like. For the same or different types of insurance product objects, a better insurance product object evaluation mode is often required for users. In one or more embodiments of the present description, one or more ways of objectively and comprehensively evaluating different insurance product objects based on insurance product data in the insurance domain in combination with project response theory in the modern psychological domain are creatively shown, and objective comprehensive evaluation aims at enabling the final evaluation result of the insurance product object to be dependent on characteristics of the product itself rather than artificial subjective experience.

Schematically, an item reaction theoretical model for the insurance product object may be preset, and at least one product feature evaluation index corresponding to the insurance product object may be obtained.

S104: performing model calculation processing on the project reaction theoretical model based on the product characteristic evaluation index to obtain potential specific mass and model parameters of the project reaction theoretical model;

schematically, a project reaction theoretical model is determined, and for a researched insurance product object, abstract evaluation conceptual features of product object quality (or product object quality) of the insurance product object are modeled as potential specific quality theta, and one or more product feature evaluation indexes of the insurance product object are modeled as external observable variables X. Functional relationships satisfied by their inherent relations are modeled through a project reaction theoretical model, and product characteristic evaluation indexes based on insurance product objects can be used as model input data of the project reaction theoretical model after being processed by input data. The input data processing can convert different types of product characteristic evaluation indexes into data types compatible with the adopted project reaction theoretical model, for example, a certain project reaction theoretical model supports numerical type index data, and for example, a certain project reaction theoretical model supports binary type index data.

The project reaction theory model may be, illustratively, a three-parameter model, a two-parameter model, a single-parameter model, and so on.

Illustratively, in one or more embodiments of the present disclosure, θi represents a potential specific quality of the insurance product object, the insurance product object may be represented by parameters (αi, βi) in the project reaction theory model, and the reaction probability function of the insurance product object evaluation is considered to be related to θi, αi and βi only, αi represents a discrimination parameter of the insurance product object evaluation, βi represents a difficulty parameter of the insurance product object evaluation, and the foregoing modeling model is a dual-parameter model.

Illustratively, in one or more embodiments of the present disclosure, θi represents a potential specific quality of the insurance product object, the insurance product object may be represented by parameters (αi, βi, ci) in the project reaction theory model, and it is considered that the reaction probability function of the insurance product object evaluation is related to θi, αi, βi and ci only, αi represents a discrimination parameter of the insurance product object evaluation, βi represents a difficulty parameter of the insurance product object evaluation, and ci represents a guess parameter of the insurance product object evaluation, where the foregoing modeling model is a three-parameter model. The three-parameter model is usually based on a two-parameter model with the guess parameter ci added as the reaction probability.

Illustratively, in one or more embodiments of the present disclosure, the insurance product object may be represented by a parameter (βi) in the project reaction theory model, and the reaction probability function of the insurance product object evaluation is considered to be related to θi and βi only, where θi represents a potential quality of the insurance product object, and βi represents a difficulty parameter of the insurance product object evaluation, and the foregoing modeling model is a single parameter model.

Schematically, determining and constructing a project reaction theoretical model for the insurance product object, processing input data according to a plurality of product characteristic evaluation indexes corresponding to the insurance product object, and then taking the processed product characteristic evaluation indexes as model input data of the project reaction theoretical model, and calculating and estimating model parameters in the project reaction theoretical model to obtain potential specific mass and model parameters of the project reaction theoretical model.

It can be understood that after the project reaction theoretical model is constructed, the model input data can be used as the model input data of the project reaction theoretical model after the input data is processed according to the product characteristic evaluation indexes corresponding to the insurance product objects, and after the model input data is input into the project reaction theoretical model, the model calculation can be realized by adopting a related parameter estimation algorithm, so that the potential quality and model parameters of the project reaction theoretical model are obtained. Illustratively, the correlation parameter estimation algorithm may be a desired maximum EM algorithm, a markov chain monte carlo algorithm, or the like.

It is understood that the model parameter is kneading of at least one or more of the foregoing parameters.

S106: and determining the object evaluation quantity of the insurance product object based on the project reaction theoretical model after model calculation processing.

The object evaluation amount may be understood as an evaluation quantification value for the insurance product object, e.g. the object evaluation amount may be a score, a rating, etc. for the insurance product object.

In one possible implementation, the project response theoretical model after the model calculation processing can obtain the potential special quality thereof, and the object evaluation quantity of the insurance product object is determined based on the potential special quality.

Illustratively, the potential quality may be used as an evaluation criterion for each insurance product object, and the potential quality may be used as an object evaluation amount for the insurance product object.

In a possible implementation manner, object evaluation amounts of a plurality of insurance product objects can be determined, and the plurality of insurance product objects are ranked based on the object evaluation amounts to obtain an insurance product ranking list.

It can be understood that, for different insurance product objects, the method for evaluating an insurance product object according to one or more embodiments of the present disclosure may be used to obtain an object evaluation amount of each insurance product object, and then an insurance product ranking list for a plurality of insurance product objects is obtained by using the object evaluation amount as a ranking criterion, where the insurance product ranking list may be intuitively pushed or displayed to a user, so as to assist the user in selecting the insurance product object.

In one or more embodiments of the present disclosure, modeling in the field of evaluation of insurance product objects based on a project response theory in the field of modern psychology is an objective comprehensive evaluation method, and the result of evaluation of the insurance product object depends on the data characteristics of the insurance product object, that is, the product characteristic evaluation index, and no additional artificial subjective factor is introduced compared with the subjective comprehensive evaluation method.

In one or more embodiments of the present disclosure, a conventional objective comprehensive evaluation method under a related scenario can only use data features as a result, that is, directly adopts one or more evaluation indexes as an evaluation result, which has a disadvantage that the evaluation result cannot be consistent with the purpose of evaluating the insurance product, a probability model from the evaluation index to the final evaluation result is built by using the model related to the present disclosure, and the evaluation index is formulated around the purpose of evaluating the insurance product, so that the consistency of the model evaluation result and the evaluation purpose can be ensured, and the effect of evaluating the insurance product object can be ensured.

Referring to fig. 3, fig. 3 is a schematic flow diagram illustrating a model calculation process according to one or more embodiments of the present disclosure. Specific:

S2002: performing object evaluation modeling on the insurance product object based on the project reaction theoretical model to determine a model observation variable of the project reaction theoretical model based on the product characteristic evaluation index and model object quality conceptual characteristics of the insurance product object as potential special qualities of the project reaction theoretical model;

illustratively, a project reaction theoretical model used for evaluating the insurance product object is determined, an abstract evaluation conceptual feature of the product object of the insurance product object (or the product object quality) is modeled as a potential specific mass θ for the studied insurance product object, and one or more product feature evaluation indexes of the insurance product object are modeled as an external model observation variable X (also referred to as a model-observable variable).

Alternatively, the model observation variable X may be a binary data type, i.e., the model observation variable X is a 0/1 binary class variable.

In a possible implementation manner, taking a project response theoretical model using a dual parameter model as an example for explanation, the electronic device executing the object evaluation modeling on the insurance product object based on the project response theoretical model may be:

Characterizing the project reaction theoretical model by adopting a first function characterization type to perform object evaluation modeling on the insurance product object based on the project reaction theoretical model;

the first function characterization satisfies the following formula:

wherein p is the reaction probability of the project reaction theoretical model, and θ _i For the potential specific mass of the project reaction theoretical model, the X _ij Model observation variables for the project reaction theory model, the alpha _j And beta _j For the model parameters of the project reaction theoretical model, the alpha _j A degree of differentiation parameter for the project reaction theoretical model, the beta _j And (3) as the difficulty parameter of the project reaction theoretical model, i is the sample number of the insurance product object, and j is the feature number corresponding to the feature evaluation index.

As shown in fig. 4, fig. 4 is a graph of reaction probability corresponding to a first function representation related to the present specification, where α is a discrimination parameter, and β is a difficulty parameter, and the model is called a Logistic model.

For example: and taking a certain product characteristic evaluation index corresponding to the insurance product object as the price of the insurance product object is lower than the xx element, and defining the model observation variable X as the price lower than the xx element. The difficulty parameter beta describes the difficulty corresponding to the purpose of evaluating the insurance product object, and the larger the beta is, the fewer products with the price lower than xx elements are reflected to the data layer for the all-industry insurance product object. The distinguishing degree parameter alpha describes the uncertainty of the magnitude characteristics of the potential specific quantity theta and the difficulty parameter beta reflected to the model observation variable X, the larger the alpha is, the smaller the uncertainty is, and the more the model observation variable X is determined (the larger the probability) by taking 1 when theta is larger than beta.

In a possible implementation manner, the electronic device executes the model observation variable for determining the item reaction theoretical model based on the product characteristic evaluation index, which may be:

a2: determining a first characteristic data type corresponding to the product characteristic evaluation index and a second characteristic data type corresponding to a model observation variable of the item reaction theoretical model;

illustratively, after the adopted project reaction theoretical model is determined, product characteristic evaluation indexes based on insurance product objects can be used as model input data of the project reaction theoretical model after being processed by input data, and the input data processing can convert different types of product characteristic evaluation indexes into (characteristic) data types compatible with the adopted project reaction theoretical model, for example, a certain project reaction theoretical model supports numerical (characteristic) type index data, and for example, a certain project reaction theoretical model supports binary (characteristic) type index data.

Illustratively, a first characteristic data type corresponding to a product characteristic evaluation index and a second characteristic data type corresponding to a model observation variable of the project reaction theoretical model can be determined, taking the project reaction theoretical model characterized by the first function characterization as an example, the model observation variable of the project reaction theoretical model usually supports a binarization characteristic type, and different product characteristic evaluation indexes can correspond to different characteristic data types, for example, the product characteristic evaluation indexes can be a numerical characteristic type, a binarization characteristic type, a characteristic character type, an enumeration characteristic and the like;

A4: and carrying out feature type conversion processing aiming at the project reaction theoretical model on the product feature evaluation index based on the first feature data type and the second feature data type to obtain a model observation variable corresponding to the project reaction theoretical model.

Schematically, if the first characteristic data type is not matched with the second characteristic data type, converting the product characteristic evaluation index into a data characteristic type supported by a model observation variable, and finishing characteristic type conversion processing, thereby obtaining the model observation variable corresponding to the project reaction theoretical model.

Further, taking a second characteristic data type as an example of a binarization characteristic type, if the first characteristic data type is not matched with the second characteristic data type, determining a data information quantity corresponding to the product characteristic evaluation index, and determining a binary variable coding number and a variable value field fractional number based on the data information quantity;

the data information quantity is the information quantity corresponding to the product characteristic evaluation index, and the information quantity corresponding to different product characteristic evaluation indexes is different.

The binary variable code number is used for indicating that several binary variables are used for describing or characterizing the product characteristic evaluation index. If the information quantity of the product characteristic evaluation index-characteristic index A is determined to be 2.3 based on the information quantity calculation formula in the related technology, the characteristic index A can be represented by adopting 2 binary variables by rounding down to 2.

The variable value range quantile is used for determining the value of the binary variable. The value of the fractional number of the variable value range is generally larger than the value of the coded number of the binary variable, for example, if the value of the coded number of the binary variable is assumed to be n, the value of the fractional number of the normal value range can be 2+1, that is, the value of the binary variable converted from the product characteristic evaluation index is determined by adopting 3 quantiles.

Further, after the binary variable coding number and the variable value range score are determined based on the data information quantity, the product characteristic evaluation index is converted into a model observation variable corresponding to the binary characteristic type of the item reaction theoretical model based on the binary variable coding number and the variable value range score.

Illustratively, taking the product feature evaluation index corresponding to the insurance product object as an enumeration type feature as an example, the enumeration type feature can be converted into a numerical type feature first, and then the numerical type feature is converted into a binary variable feature.

Input data processing

1. Converting the enumerated class characteristics into numerical class characteristics, taking the product characteristic evaluation index corresponding to the insurance product object as the protectable occupation class as an example:

(the direction of the product characteristic evaluation index needs to be ensured, namely, the larger the numerical value is, the better the insurance product object is)

Through the above-mentioned numerical coding processing, the index of the "insured occupation type" corresponding to the insurance product object can be converted into the numerical value type feature, if the "insured occupation type" corresponding to a certain insurance product object is coverage type 1-4 occupation type, it is converted into numerical coding type 2 through the above-mentioned feature type conversion processing, namely, the numerical value type feature is 2;

2. converting the numerical class characteristics into binary variable characteristics:

(the number of the binary variable is determined by the information quantity of the product characteristic evaluation index, the information quantity of the product characteristic evaluation index is large, the binary variable is large, the coding mode is that the binary variable coding is determined by the magnitude relation between the numerical value of the numerical value class characteristic and the value domain score.)

Illustratively, the number of binary variable codes is determined to be 2 based on the information quantity of the product characteristic evaluation index, namely, two binary variable codes are adopted, namely, a binary variable x1 and a binary variable x2; the variable value range fraction can be 2+1, namely the variable value range fraction adopts three quantiles, and the coding mode is that the numerical value of the numerical value class characteristic is compared with the magnitudes of the first three quantiles and the second three quantiles respectively.

Namely, binary variable x1: whether the value of the value class feature is greater than a first third quantile (e.g., 5*1/3), if so, the binary variable x1=1, otherwise, the binary variable x1=0;

Namely, binary variable x2: whether the value of the value class feature is greater than the second third quantile (e.g., 5*2/3), if so, the binary variable x2=1, otherwise, the binary variable x2=0;

illustratively, taking the example that the numerical code is 3, the numerical code 3 is larger than the first third fractional number (e.g. 5*1/3), the binary variable x1=1, and the numerical code 3 is smaller than the second third fractional number (e.g. 5*2/3), and the binary variable x1=0; the binary variable whose numerical code is 3 is "10".

According to the method, the product characteristic evaluation index is converted into the model observation variable corresponding to the binarization characteristic type of the project reaction theoretical model based on the binary variable coding number and the variable value range score.

S2004: and inputting the model observation variable into the project reaction theoretical model to perform model parameter resolving processing to obtain the potential specific mass and model parameters of the project reaction theoretical model.

Further, assuming that for some insurance product objects, the product feature evaluation indexes corresponding to the insurance product objects are A, B, C three evaluation indexes respectively, and a total of 100 insurance product object samples, calculating the information quantity of the insurance product object samples to be used for determining how many binary variables are used for describing the insurance product objects, for example, for the feature A, calculating the information quantity of the insurance product objects to be 2.3, and the binary variable coding number is rounded down to be 2, determining to be used for describing the product feature evaluation indexes by using 2 binary variables, and using value domain scores: the (2+1) quantile determines the value of the binary variable.

Furthermore, it is not necessary to set up A, B, C three evaluation indexes to be described by 2, 3 and 4 binary variables respectively, so that after transformation, there are 9 binary features of the input model in total, and 100 samples, namely, the input of the item reaction theoretical model, namely, a matrix or vector in the form of "01" of 9 x 100 of the model observation variables. And inputting the model observation variable into a project reaction theoretical model to carry out model parameter resolving processing and solving, so that potential specific mass and model parameters can be resolved.

Optionally, the electronic device executes the model observation variable input to the project reaction theoretical model to perform model parameter resolving processing, so as to obtain a potential specific mass and model parameters of the project reaction theoretical model, which may be:

schematically, the model observation variable is input into the project reaction theoretical model, model parameter resolving processing is carried out on the project reaction theoretical model by adopting a target constraint resolving mode, parameter estimation is carried out, and potential quality and model parameters of the project reaction theoretical model are obtained.

Illustratively, the target constraint solving mode involved in the model parameter solving process may be a desired maximum EM algorithm, a markov chain monte carlo algorithm, or the like.

In a possible implementation manner, the target constraint solving manner is a desired maximum EM solving manner, the electronic device executes the model parameter solving process for the project reaction theoretical model by adopting the target constraint solving manner, so as to obtain the potential specific mass and the model parameter of the project reaction theoretical model, which may be:

c2: carrying out parameter iterative calculation processing on the project reaction theoretical model by adopting an expected maximum EM calculation mode;

and C4: setting model parameters known in the step E, adopting a second function to represent the expected of the potential special quality calculated in the step E, setting the potential special quality known in the step M, and adopting a third function to represent the expected likelihood function corresponding to the potential special quality to carry out maximum likelihood estimation until the project reaction theoretical model converges to obtain the potential special quality and model parameters of the project reaction theoretical model;

the second function characterization satisfies the following formula:

the third function characterization satisfies the following formula:

wherein E is the desire for the potential specific quantity, θ _i For the potential specific mass, the X _ij The model observation variable of the project reaction theoretical model is represented by p, the reaction probability of the project reaction theoretical model is represented by alpha _j And beta _j To be the instituteModel parameters of the project reaction theoretical model, the alpha _j A degree of differentiation parameter for the project reaction theoretical model, the beta _j And (3) as the difficulty parameter of the project reaction theoretical model, i is the sample number of the insurance product object, and j is the feature number corresponding to the feature evaluation index.

Illustratively, the model parameter calculation is performed by adopting a desired maximum EM calculation mode. The expected maximum EM solving mode mainly comprises two steps, wherein the step E is to assume that model parameters of a project reaction theoretical model are known, and solve hidden variables-potential specific mass expectation; m steps assuming hidden variables-potential characteristics are known, solving model parameters alpha corresponding to the second function representation when expected to take maximum value _j And beta _j . After the solution begins to initialize the model parameters, the hidden variable values and the model parameters can be obtained by continuously iterating the E step and the M step to finally achieve convergence.

In one or more embodiments of the present disclosure, due to the small sample size of the insurance product object, there may be a large variance of the result and a correlation phenomenon caused by the above data processing method, in the parameter iteration calculation process, the data sampling is performed by using a random-like forest algorithm to perform parameter estimation, that is, the model parameter estimation is performed by using the method of sampling the input features and sampling the samples of the project reaction theoretical model, and the average is taken as the final model parameter after multiple model parameter estimation, as follows:

D2: acquiring at least one reference sample object corresponding to an insurance product object and at least one reference product characteristic evaluation index corresponding to the reference sample object;

for example: acquiring at least one reference sample object corresponding to a certain insurance product object, and assuming that the reference sample object is x (e.g. 100) insurance product object samples, wherein at least one reference product characteristic evaluation index corresponding to any reference sample object shares y (e.g. 40) product characteristic evaluation indexes after binarization;

d4, carrying out at least one round of input data sampling processing on the reference sample object and the reference product characteristic evaluation index to obtain at least one sample object and at least one product characteristic evaluation index corresponding to the sample object;

for example: by way of illustration in the above example, x1 (e.g., 50) sample objects can be randomly drawn from x (e.g., 100) insurance product object samples at a time, and y1 (e.g., 20) sample product feature evaluation indices can be randomly drawn from y (e.g., 40) product feature evaluation indices at a time;

and D6, generating sampling model observation variables aiming at the project reaction theoretical model in each round based on the at least one sample product characteristic evaluation index after each round of input data sampling processing.

On the basis, the step of inputting the model observation variable into the project reaction theoretical model to perform model parameter resolving processing to obtain the potential specific mass and model parameters of the project reaction theoretical model, namely the step of parameter resolving can be referred to as follows:

it can be understood that the sample model observation variable of each round aiming at the project reaction theoretical model can be input into the project reaction theoretical model to carry out model parameter resolving processing, so as to obtain the sample potential specific mass and the sample model parameter of the project reaction theoretical model, and the sample potential specific mass and the sample model parameter after each round of model parameter resolving processing are stored;

and then carrying out parameter average processing based on the potential specific mass of each sample and the model parameters of each sample to obtain the potential specific mass and model parameters aiming at the project reaction theoretical model.

For example: by way of illustration in the above example, y1 (e.g. 20) sample product feature evaluation indexes and x1 (e.g. 50) sample objects can be randomly extracted each time in each round of input data sampling processing, so as to estimate model parameters (α, β) and sample potential specific mass of sampling model observation variables generated by the y1 (e.g. 20) sample product feature evaluation indexes after the model calculation process, and record results (αj, βj) and sample potential specific mass of the sampling model calculation in this round. The parameters of each type (such as alpha, beta and sample potential specific mass) are averaged after multiple calculations to obtain the final potential specific mass and model parameters.

Illustratively, the feature sampling data processing mode of the quasi-random forest algorithm is introduced to relieve the phenomenon that the sample size is smaller than the feature size, reduce the parameter estimation variance, enable the model to be more in line with the local independence assumption of the model, and ensure the evaluation effect of the insurance product object.

The following explains how the process of calculating the object evaluation amount in the case of sampling is:

in a possible implementation manner, the determining, by the electronic device, the object evaluation amount of the insurance product object based on the item reaction theoretical model after the model resolving process may be:

e2, acquiring the potential special quality, a sample distinguishing parameter { alpha } in the model parameters and a sampling model observation variable { X } corresponding to a product characteristic evaluation index based on the project reaction theoretical model after model calculation processing;

e4, determining a sufficient statistic corresponding to the potential special quantity based on the sampling model observation variable and the sample area division parameter, and taking the sufficient statistic as an object evaluation quantity of the insurance product object;

illustratively, the determining, based on the sampling model observation variable and the sample discrimination parameter, a sufficient statistic corresponding to the potential feature quantity, and taking the sufficient statistic as the object evaluation quantity of the insurance product object may be:

Inputting the observation variable of the sampling model and the division parameter of the sample area into a fourth function representation type to obtain full statistics corresponding to the potential characteristic quality;

the fourth function characterization satisfies the following formula:

T＝α1X1+α2X2+...αnXn

wherein, T is the sufficient statistics, alpha 1, alpha 2..alpha n are the sample distinguishing degree parameters, X1, X2...Xn are the sampling model observation variables, and n is the sampling model observation variable number corresponding to the product characteristic evaluation index.

In one or more embodiments of the present disclosure, by calculating the linear sufficient statistics of the potential specific mass inputs, the interpretability of the project response theoretical model for evaluation is improved, and the evaluation effect of the insurance product object is better. By testing the insurance product object evaluation method related to the specification, the consistency between the insurance product object evaluation method and expert weighting models of the fine calculation experts on each insurance track based on the product data of the insurance product object in the industry is 0.8-0.9 (spearman correlation coefficient), the evaluation effect of the insurance product object is ensured, and the evaluation resource consumption is saved.

In one or more embodiments of the present disclosure, a model built by project reaction theory better meets the requirements of comprehensive evaluation methods for insurance product objects. For example, in the method in the mode, the final result is directly modeled into one-dimensional evaluation quantity which can be directly sequenced; meanwhile, the relationship between the evaluation index and the final result is passivated by using the discrimination parameter alpha probability, and the co-variability requirement in the data is changed into a local independence requirement, so that the requirement that the evaluation index of an insurance product object should be diversified is met.

The insurance product object evaluation device provided in this specification will be described in detail with reference to fig. 5. For convenience of explanation, the insurance product object evaluation device shown in fig. 5 is used to execute the method of the embodiment shown in fig. 1 to 4 of the present specification, only the portion relevant to the present specification is shown, and specific technical details are not disclosed, and reference is made to the embodiment shown in fig. 1 to 4 of the present specification.

Referring to fig. 5, a schematic structural diagram of the insurance product object evaluation device of the present specification is shown. The insurance product object evaluation device 1 may be implemented as all or a part of an electronic device by software, hardware, or a combination of both. According to some embodiments, the insurance product object evaluation device 1 includes an index determination module 11, a model calculation module 12, and an object evaluation module 13, specifically for:

the index determining module 11 is configured to determine an item reaction theoretical model for an insurance product object, and obtain at least one product feature evaluation index corresponding to the insurance product object;

the model resolving module 12 is configured to perform a model resolving process on the project reaction theoretical model based on the product feature evaluation index, so as to obtain a potential specific quality and model parameters of the project reaction theoretical model;

an object evaluation module 13, configured to determine an object evaluation amount of the insurance product object based on the item reaction theoretical model after the model calculation processing.

Alternatively, as shown in fig. 6, the model resolving module 12 includes:

an evaluation modeling unit 121 for performing object evaluation modeling on the insurance product object based on the project reaction theoretical model to determine a model observation variable of the project reaction theoretical model based on the product feature evaluation index and to model object quality conceptual features of the insurance product object as potential specific qualities of the project reaction theoretical model;

The parameter calculation unit 122 is configured to input the model observation variable into the project reaction theoretical model to perform a model parameter calculation process, so as to obtain a potential specific mass and a model parameter of the project reaction theoretical model.

Optionally, the evaluation modeling unit 121 is specifically configured to:

the first function characterization satisfies the following formula:

Optionally, the evaluation modeling unit 121 is specifically configured to:

determining a first characteristic data type corresponding to the product characteristic evaluation index and a second characteristic data type corresponding to a model observation variable of the item reaction theoretical model;

And carrying out feature type conversion processing aiming at the project reaction theoretical model on the product feature evaluation index based on the first feature data type and the second feature data type to obtain a model observation variable corresponding to the project reaction theoretical model.

Optionally, the second feature data type is a binarized feature type, and the evaluation-based modeling unit 121 is specifically configured to:

and performing feature type conversion processing on the product feature evaluation index aiming at the project reaction theoretical model based on the first feature data type and the second feature data type to obtain a model observation variable corresponding to the project reaction theoretical model, wherein the method comprises the following steps:

if the first characteristic data type is not matched with the second characteristic data type, determining the data information quantity corresponding to the product characteristic evaluation index, and determining the binary variable coding number and the variable value domain quantile based on the data information quantity;

and converting the product characteristic evaluation index into a model observation variable corresponding to the binarization characteristic type of the project reaction theoretical model based on the binary variable coding number and the variable value range score.

Optionally, the parameter resolving unit 122 is configured to:

inputting the model observation variable into the project reaction theoretical model, and carrying out model parameter resolving processing on the project reaction theoretical model by adopting a target constraint resolving mode to obtain the potential specific mass and model parameters of the project reaction theoretical model.

Optionally, the target constraint solving means is a desired maximum EM solving means, and the parameter solving unit 122 is configured to:

carrying out parameter calculation estimation processing on the project reaction theoretical model by adopting an expected maximum EM calculation mode;

in the parameter calculation and estimation process, setting model parameters known in the step E, adopting a second function to represent the expected of calculating the potential specific quality, setting the potential specific quality known in the step M, and adopting a third function to represent the expected likelihood function corresponding to the potential specific quality to carry out model parameter estimation to obtain the potential specific quality and model parameters of the project reaction theoretical model;

the second function characterization satisfies the following formula:

the third function characterization satisfies the following formula:

wherein E is the desire for the potential specific quantity, θ _i For the potential specific mass, the X _ij The model observation variable of the project reaction theoretical model is represented by p, the reaction probability of the project reaction theoretical model is represented by alpha _j And beta _j For the model parameters of the project reaction theoretical model, the alpha _j A degree of differentiation parameter for the project reaction theoretical model, the beta _j And (3) as the difficulty parameter of the project reaction theoretical model, i is the sample number of the insurance product object, and j is the feature number corresponding to the feature evaluation index.

Optionally, the device 1 is further configured to:

acquiring at least one reference sample object corresponding to an insurance product object and at least one reference product characteristic evaluation index corresponding to the reference sample object;

at least one round of input data sampling processing is carried out on the reference sample object and the reference product characteristic evaluation index, so that at least one sample object and at least one sample product characteristic evaluation index corresponding to the sample object are obtained;

and generating sampling model observation variables aiming at the project reaction theoretical model in each round based on the at least one sample product characteristic evaluation index after each round of input data sampling processing.

Optionally, the device 1 is further configured to:

Inputting sampling model observation variables of each round of the project reaction theoretical model into the project reaction theoretical model for carrying out model parameter resolving processing to obtain sample potential specific mass and sample model parameters of the project reaction theoretical model, and storing the sample potential specific mass and the sample model parameters after each round of model parameter resolving processing;

and carrying out parameter average processing based on the potential specific mass of each sample and the sample model parameters to obtain the potential specific mass and model parameters aiming at the project reaction theoretical model.

Optionally, the object evaluation module 13 is configured to:

and acquiring the potential special quantity, a sample distinguishing degree parameter in the model parameters and a sampling model observation variable corresponding to the product characteristic evaluation index based on the project reaction theoretical model after model calculation processing, determining a full statistic corresponding to the potential special quantity based on the sampling model observation variable and the sample distinguishing degree parameter, and taking the full statistic as the object evaluation quantity of the insurance product object.

Optionally, the object evaluation module 13 is configured to:

The fourth function characterization satisfies the following formula:

T＝α1X1+α2X2+...αnXn

Optionally, the device 1 is configured to:

determining object evaluation amounts of a plurality of the insurance product objects;

and sorting the plurality of insurance product objects based on the object evaluation amount to obtain an insurance product ranking list.

It should be noted that, when the insurance product object evaluation device provided in the foregoing embodiment performs the insurance product object evaluation method, only the division of the foregoing functional modules is used as an example, in practical application, the foregoing functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the insurance product object evaluation device and the insurance product object evaluation method provided in the foregoing embodiments belong to the same concept, which embody detailed implementation procedures in the method embodiments, and are not described herein again.

The foregoing description is provided for the purpose of illustration only and does not represent the advantages or disadvantages of the embodiments.

The present disclosure further provides a computer storage medium, where the computer storage medium may store a plurality of instructions, where the instructions are adapted to be loaded by a processor and executed by the processor, where the specific execution process may refer to the specific description of the embodiment shown in fig. 1 to 4, and the description is omitted herein.

The present disclosure further provides a computer program product, where at least one instruction is stored in the computer program product, where the at least one instruction is loaded by the processor and executed by the processor to implement the insurance product object evaluation method according to the embodiment shown in fig. 1 to fig. 4, and the specific implementation process may refer to the specific description of the embodiment shown in fig. 1 to fig. 4, which is not repeated herein.

Referring to fig. 7, a block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown. The electronic device in this specification may include one or more of the following: processor 110, memory 120, input device 130, output device 140, and bus 150. The processor 110, the memory 120, the input device 130, and the output device 140 may be connected by a bus 150.

Processor 110 may include one or more processing cores. The processor 110 utilizes various interfaces and lines to connect various portions of the overall electronic device, perform various functions of the electronic device 100, and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 120, and invoking data stored in the memory 120. Alternatively, the processor 110 may be implemented in at least one hardware form of digital signal processing (digital signal processing, DSP), field-programmable gate array (field-programmable gate array, FPGA), programmable logic array (programmable logic Array, PLA). The processor 110 may integrate one or a combination of several of a central processor (central processing unit, CPU), an image processor (graphics processing unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for being responsible for rendering and drawing of display content; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 110 and may be implemented solely by a single communication chip.

The memory 120 may include a random access memory (random Access Memory, RAM) or a read-only memory (ROM). Optionally, the memory 120 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). Memory 120 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 120 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, which may be an Android (Android) system, including an Android system-based deep development system, an IOS system developed by apple corporation, including an IOS system-based deep development system, or other systems, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The storage data area may also store data created by the electronic device in use, such as phonebooks, audiovisual data, chat log data, and the like.

Referring to FIG. 8, the memory 120 may be divided into an operating system space in which the operating system is running and a user space in which native and third party applications are running. In order to ensure that different third party application programs can achieve better operation effects, the operating system allocates corresponding system resources for the different third party application programs. However, the requirements of different application scenarios in the same third party application program on system resources are different, for example, under the local resource loading scenario, the third party application program has higher requirement on the disk reading speed; in the animation rendering scene, the third party application program has higher requirements on the GPU performance. The operating system and the third party application program are mutually independent, and the operating system often cannot timely sense the current application scene of the third party application program, so that the operating system cannot perform targeted system resource adaptation according to the specific application scene of the third party application program.

In order to enable the operating system to distinguish specific application scenes of the third-party application program, data communication between the third-party application program and the operating system needs to be communicated, so that the operating system can acquire current scene information of the third-party application program at any time, and targeted system resource adaptation is performed based on the current scene.

Taking an operating system as an Android system as an example, as shown in fig. 9, a program and data stored in the memory 120 may be stored in the memory 120 with a Linux kernel layer 320, a system runtime library layer 340, an application framework layer 360 and an application layer 380, where the Linux kernel layer 320, the system runtime library layer 340 and the application framework layer 360 belong to an operating system space, and the application layer 380 belongs to a user space. The Linux kernel layer 320 provides the underlying drivers for various hardware of the electronic device, such as display drivers, audio drivers, camera drivers, bluetooth drivers, wi-Fi drivers, power management, and the like. The system runtime layer 340 provides the main feature support for the Android system through some C/c++ libraries. For example, the SQLite library provides support for databases, the OpenGL/ES library provides support for 3D graphics, the Webkit library provides support for browser kernels, and the like. Also provided in the system runtime library layer 340 is a An Zhuoyun runtime library (Android run) which provides mainly some core libraries that can allow developers to write Android applications using the Java language. The application framework layer 360 provides various APIs that may be used in building applications, which developers can also build their own applications by using, for example, campaign management, window management, view management, notification management, content provider, package management, call management, resource management, location management. At least one application program is running in the application layer 380, and these application programs may be native application programs of the operating system, such as a contact program, a short message program, a clock program, a camera application, etc.; and may also be a third party application developed by a third party developer, such as a game-like application, instant messaging program, photo beautification program, etc.

Taking an operating system as an IOS system as an example, the programs and data stored in the memory 120 are shown in fig. 10, the IOS system includes: core operating system layer 420 (Core OS layer), core service layer 440 (Core Services layer), media layer 460 (Media layer), and touchable layer 480 (Cocoa Touch Layer). The core operating system layer 420 includes an operating system kernel, drivers, and underlying program frameworks that provide more hardware-like functionality for use by the program frameworks at the core services layer 440. The core services layer 440 provides system services and/or program frameworks required by the application, such as a Foundation (Foundation) framework, an account framework, an advertisement framework, a data storage framework, a network connection framework, a geographic location framework, a sports framework, and the like. The media layer 460 provides an interface for applications related to audiovisual aspects, such as a graphics-image related interface, an audio technology related interface, a video technology related interface, an audio video transmission technology wireless play (AirPlay) interface, and so forth. The touchable layer 480 provides various commonly used interface-related frameworks for application development, with the touchable layer 480 being responsible for user touch interactions on the electronic device. Such as a local notification service, a remote push service, an advertisement framework, a game tool framework, a message User Interface (UI) framework, a User Interface UIKit framework, a map framework, and so forth.

Among the frameworks illustrated in fig. 10, frameworks related to most applications include, but are not limited to: the infrastructure in core services layer 440 and the UIKit framework in touchable layer 480. The infrastructure provides many basic object classes and data types, providing the most basic system services for all applications, independent of the UI. While the class provided by the UIKit framework is a basic UI class library for creating touch-based user interfaces, iOS applications can provide UIs based on the UIKit framework, so it provides the infrastructure for applications to build user interfaces, draw, process and user interaction events, respond to gestures, and so on.

The manner and principle of implementing data communication between the third party application program and the operating system in the IOS system may refer to the Android system, and this description is not repeated here.

The input device 130 is configured to receive input instructions or data, and the input device 130 includes, but is not limited to, a keyboard, a mouse, a camera, a microphone, or a touch device. The output device 140 is used to output instructions or data, and the output device 140 includes, but is not limited to, a display device, a speaker, and the like. In one example, the input device 130 and the output device 140 may be combined, and the input device 130 and the output device 140 are a touch display screen for receiving a touch operation thereon or thereabout by a user using a finger, a touch pen, or any other suitable object, and displaying a user interface of each application program. Touch display screens are typically provided on the front panel of an electronic device. The touch display screen may be designed as a full screen, a curved screen, or a contoured screen. The touch display screen can also be designed to be a combination of a full screen and a curved screen, and a combination of a special-shaped screen and a curved screen is not limited in this specification.

In addition, those skilled in the art will appreciate that the configuration of the electronic device shown in the above-described figures does not constitute a limitation of the electronic device, and the electronic device may include more or less components than illustrated, or may combine certain components, or may have a different arrangement of components. For example, the electronic device further includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, a wireless fidelity (wireless fidelity, wiFi) module, a power supply, and a bluetooth module, which are not described herein.

In this specification, the execution subject of each step may be the electronic device described above. Optionally, the execution subject of each step is an operating system of the electronic device. The operating system may be an android system, an IOS system, or other operating systems, which is not limited in this specification.

The electronic device of the present specification may further have a display device mounted thereon, and the display device may be various devices capable of realizing a display function, for example: cathode ray tube displays (cathode ray tubedisplay, CR), light-emitting diode displays (light-emitting diode display, LED), electronic ink screens, liquid crystal displays (liquid crystal display, LCD), plasma display panels (plasma display panel, PDP), and the like. A user may utilize a display device on electronic device 101 to view displayed text, images, video, etc. The electronic device may be a smart phone, a tablet computer, a gaming device, an AR (Augmented Reality ) device, an automobile, a data storage device, an audio playing device, a video playing device, a notebook, a desktop computing device, a wearable device such as an electronic watch, electronic glasses, an electronic helmet, an electronic bracelet, an electronic necklace, an electronic article of clothing, etc.

In the electronic device shown in fig. 7, the processor 110 may be configured to call an application program stored in the memory 120, and specifically perform the following operations:

In one embodiment, the processor 110 performs the following operations when performing the model calculation process on the project response theoretical model based on the product feature evaluation index to obtain the potential specific quantity and the model parameter of the project response theoretical model:

performing object evaluation modeling on the insurance product object based on the project reaction theoretical model to determine a model observation variable of the project reaction theoretical model based on the product characteristic evaluation index and model object quality conceptual characteristics of the insurance product object as potential special qualities of the project reaction theoretical model;

And inputting the model observation variable into the project reaction theoretical model to perform model parameter resolving processing to obtain the potential specific mass and model parameters of the project reaction theoretical model.

In one embodiment, the processor 110, when executing the object assessment modeling of the insurance product object based on the project response theory model, performs the steps of:

the first function characterization satisfies the following formula:

wherein p is the reaction probability of the project reaction theoretical model, and θ _i For the potential specific mass of the project reaction theoretical model, the X _ij Model observation variables for the project reaction theory model, the alpha _j And beta _j For the model parameters of the project reaction theoretical model, the alpha _j A degree of differentiation parameter for the project reaction theoretical model, the beta _j The item reflects the difficulty parameter of the theoretical model, the i is the sample number of the insurance product object, thej is the feature number corresponding to the feature evaluation index.

In one embodiment, the processor 110, when executing the determining the model observation variable of the project reaction theoretical model based on the product characteristic evaluation index, executes the following steps:

In one embodiment, the second feature data type is a binarized feature type, and the processor 110 performs the feature type conversion process for the item reaction theoretical model on the product feature evaluation index based on the first feature data type and the second feature data type to obtain a model observation variable corresponding to the item reaction theoretical model, and performs the following steps:

In one embodiment, the processor 110 performs the following steps when executing the process of inputting the model observation variable into the project reaction theoretical model to perform model parameter calculation, to obtain the potential specific quantity and the model parameter of the project reaction theoretical model:

In one embodiment, the target constraint solving mode is a desired maximum EM solving mode, and the processor 110 performs the model parameter solving process on the project reaction theoretical model by using the target constraint solving mode to obtain a potential specific quantity and a model parameter of the project reaction theoretical model, and performs the following steps:

the second function characterization satisfies the following formula:

the third function characterization satisfies the following formula:

wherein E is the desire for the potential specific quantity, θ _i For the potential specific mass, the X _ij The model observation variable of the project reaction theoretical model is represented by p, the reaction probability of the project reaction theoretical model is represented by alpha _j And beta _j For the model parameters of the project reaction theoretical model, the alpha _j A degree of differentiation parameter for the project reaction theoretical model, the beta _j Theoretical model for the project reactionI is the sample number of the insurance product object, and j is the feature number corresponding to the feature evaluation index.

In one embodiment, the processor 110 determines the object evaluation amount of the insurance product object after performing the model-based solution process according to the item reaction theory model, and performs the following steps:

acquiring a sampling model observation variable corresponding to the potential special quantity, a sample distinguishing degree parameter in the model parameters and the product characteristic evaluation index based on the project reaction theoretical model after model calculation processing, determining a full statistic corresponding to the potential special quantity based on the sampling model observation variable and the sample distinguishing degree parameter, and taking the full statistic as an object evaluation quantity of the insurance product object; or alternatively, the first and second heat exchangers may be,

determining an object rating amount of the insurance product object based on the potential quality; or alternatively, the first and second heat exchangers may be,

an object rating scale for the insurance product object is determined based on the potential quality.

In one embodiment, the processor 110, when executing the determining the sufficient statistics for the potential feature quantity based on the sampling model observation variables and the sample region division parameters, comprises:

the fourth function characterization satisfies the following formula:

T＝α1X1+α2X2+...αnXn

In one embodiment, the processor 110, when executing the insurance product object evaluation method, further performs the steps of:

Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, or the like.

It should be noted that, information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, presented data, etc.), and signals according to the embodiments of the present disclosure are all authorized by the user or are fully authorized by the parties, and the collection, use, and processing of relevant data is required to comply with relevant laws and regulations and standards of relevant countries and regions. For example, the product characteristic evaluation index, the insurance product object, and the like referred to in this specification are all acquired with sufficient authorization.

The foregoing disclosure is only illustrative of the preferred embodiments of the present invention and is not to be construed as limiting the scope of the claims, which follow the meaning of the claims of the present invention.

Claims

1. A method of insurance product object assessment, the method comprising:

2. The method of claim 1, wherein the performing a model calculation process on the project reaction theoretical model based on the product feature evaluation index to obtain the potential specific mass and the model parameters of the project reaction theoretical model comprises:

3. The method of claim 2, the modeling the object assessment of the insurance product object based on the project response theoretical model, comprising:

the first function characterization satisfies the following formula:

wherein p is the project reactionReaction probability quantity of theoretical model, θ _i For the potential specific mass of the project reaction theoretical model, the X _ij Model observation variables for the project reaction theory model, the alpha _j And beta _j For the model parameters of the project reaction theoretical model, the alpha _j A degree of differentiation parameter for the project reaction theoretical model, the beta _j And (3) as the difficulty parameter of the project reaction theoretical model, i is the sample number of the insurance product object, and j is the feature number corresponding to the feature evaluation index.

4. The method of claim 2, the determining model observation variables of the project reaction theoretical model based on the product characteristic evaluation index, comprising:

5. The method according to claim 4, wherein the second feature data type is a binarized feature type, the performing feature type conversion processing on the product feature evaluation index for the project reaction theoretical model based on the first feature data type and the second feature data type to obtain a model observation variable corresponding to the project reaction theoretical model, includes:

6. The method according to claim 2, wherein the inputting the model observation variable into the project reaction theoretical model for model parameter calculation processing, to obtain the potential specific mass and model parameters of the project reaction theoretical model, includes:

7. The method according to claim 6, wherein the target constraint solving mode is a desired maximum EM solving mode, and the performing model parameter solving processing on the project reaction theoretical model by using the target constraint solving mode to obtain a potential specific mass and model parameters of the project reaction theoretical model includes:

The second function characterization satisfies the following formula:

the third function characterization satisfies the following formula:

8. The method of claim 2, the determining model observation variables of the project reaction theoretical model based on the product characteristic evaluation index, comprising:

9. The method of claim 8, wherein the inputting the model observation variable into the project reaction theoretical model for model parameter calculation processing, to obtain the potential specific mass and the model parameter of the project reaction theoretical model, comprises:

10. The method of claim 8, the determining the object rating amount of the insurance product object based on the model-resolved item reaction theoretical model, comprising:

11. The method of claim 10, the determining the sufficient statistics for the potential feature quantity based on the sampling model observation variables and the sample area division parameters, comprising:

the fourth function characterization satisfies the following formula:

T＝α1X1+α2X2+...αnXn

12. The method of claim 1, the method further comprising:

13. An insurance product object evaluation device, the device comprising:

14. A computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the method steps of any one of claims 1 to 12.

15. A computer program product storing at least one instruction for loading by a processor and performing the method steps of any one of claims 1 to 12.

16. An electronic device, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1-12.