CN116485560A - Target user screening method and system based on feedback mechanism - Google Patents
Target user screening method and system based on feedback mechanism Download PDFInfo
- Publication number
- CN116485560A CN116485560A CN202310736513.8A CN202310736513A CN116485560A CN 116485560 A CN116485560 A CN 116485560A CN 202310736513 A CN202310736513 A CN 202310736513A CN 116485560 A CN116485560 A CN 116485560A
- Authority
- CN
- China
- Prior art keywords
- insurance
- product
- insurance product
- user
- products
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012216 screening Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000008713 feedback mechanism Effects 0.000 title claims abstract description 36
- 238000000265 homogenisation Methods 0.000 claims abstract description 42
- 239000013598 vector Substances 0.000 claims description 27
- 238000011156 evaluation Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008685 targeting Effects 0.000 claims 1
- 238000007418 data mining Methods 0.000 abstract description 6
- 230000008901 benefit Effects 0.000 description 9
- 238000006243 chemical reaction Methods 0.000 description 8
- 230000010354 integration Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 3
- 230000002860 competitive effect Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000013506 data mapping Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000011068 loading method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06F16/26—Visual data mining; Browsing structured data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to the field of insurance data mining, in particular to a target user screening method and system based on a feedback mechanism. The target user screening method based on the feedback mechanism comprises the following steps: acquiring product data and user data of insurance products of the same type; building an insurance feature model by utilizing the product data and the user data; selecting a reference insurance product and an insurance product to be evaluated from the insurance products of the same type; obtaining homogenization parameters of a reference insurance product and an insurance product to be evaluated through an insurance feature model; constructing a user characteristic model by using homogenization parameters of a reference insurance product and an insurance product to be evaluated; and screening target users of the insurance products to be evaluated from the insurance products of the same type through the user characteristic model. The target user screening method provided by the invention solves the homogenization problem between the insurance products of the same type by utilizing the existing data, and helps an insurance company to screen target clients.
Description
Technical Field
The invention relates to the field of insurance data mining, in particular to a target user screening method and system based on a feedback mechanism.
Background
The same type of insurance product refers to insurance contracts with similar guarantee objects and guarantee ranges, which are usually designed by insurance companies to meet the insurance needs of specific risk areas. The warranty content and claims coverage of these products may vary, but they are all warranted against the same class of risks. The same types of insurance products play an important role in the insurance market because they can meet the insurance needs of consumers for a particular risk, while also providing business growth opportunities for insurance companies.
However, the content and service features of the insurance products of the same type tend to be similar or identical, and lack of variability, so that it is difficult to meet the personalized demands of consumers. Thus, the phenomenon of homogeneity between the same type of insurance products can make it difficult for an insurance company to distinguish between the merits of the different products, and thus to define a target customer group. Meanwhile, consumers are difficult to distinguish the differences among products when facing homogenized insurance products, are easily influenced by price and marketing means, and cannot really know the guarantee range and characteristics of the products, so that the purchase will and the purchase capability of the consumers are difficult to determine. Therefore, a method for screening target users based on feedback mechanism is needed to transversely mine potential target users of the same type of insurance products by utilizing the existing insurance products and user data and processing means such as data mining and the like, so as to meet the increasing customer demands of the insurance industry.
Disclosure of Invention
Aiming at the shortages of the prior art and the demands of practical application, the invention provides a target user screening method based on a feedback mechanism, which aims to solve the problem of homogenization among insurance products of the same type by utilizing the existing data and help insurance companies to better meet the personalized demands of clients, and comprises the following steps: acquiring product data and user data of insurance products of the same type; building an insurance feature model by utilizing the product data and the user data; selecting a reference insurance product and an insurance product to be evaluated from the insurance products of the same type; obtaining homogenization parameters of a reference insurance product and an insurance product to be evaluated through an insurance feature model; constructing a user characteristic model by using homogenization parameters of a reference insurance product and an insurance product to be evaluated; and screening target users of the insurance products to be evaluated from the insurance products of the same type through the user characteristic model. The invention realizes personalized customization, cost saving, accurate marketing and competitive advantage by introducing a feedback mechanism and utilizing the existing data and model analysis. The invention can help insurance companies to accurately know the demands of users, provide personalized insurance products, improve the satisfaction degree of users and effectively save development cost and time. Through accurate target user screening and directional marketing, improve sales conversion rate and marketing effect. In addition, the invention also helps insurance companies stand out in the homogenization market, develop special products and obtain competitive advantages. The invention provides an innovative solution for the insurance industry, meets the personalized demands of clients, and improves the service level and market competitiveness of insurance companies.
Optionally, the acquiring product data and user data of the same type of insurance product includes the following steps: determining a target insurance product type; selecting a specific insurance product under the type of the target insurance product; acquiring product data and user data of a specific insurance product; and finishing the product data and the user data to obtain an insurance database. By acquiring product data and user data of the same type of insurance products and arranging the product data and the user data into an insurance database, a reliable data base is provided for subsequent analysis and mining. By the aid of the method, characteristics of the insurance product and requirements of users can be accurately known, better decision support and market insight are provided for insurance companies, and accordingly product design is optimized and customer satisfaction is improved.
Optionally, the building an insurance feature model by using the product data and the user data includes the following steps: defining a basic feature vector; vectorizing the product data and the user data using the base feature vector; and building an insurance feature model according to the vectorization result. According to the invention, the insurance feature model is built, so that the product data and the user data are converted into vector representation, and the data are efficiently processed and analyzed. By the aid of the method, key characteristics of products and users can be captured more accurately, an insurance company is helped to understand the characteristics of the products and the requirements of the users in depth, and powerful tools and bases are provided for personalized customization and target user screening. Meanwhile, the insurance feature model based on vectorization also provides a wider application space for data mining and machine learning.
Optionally, the base feature vector satisfies the following model:wherein->Basic feature vector representing the ith insurance product of the same type of insurance products, < >>Price characteristic parameter representing the ith insurance product of the same type of insurance products +.>Representing the guarantee range characteristic parameter of the ith insurance product in the same type of insurance products, < + >>Representing the characteristic parameters of the pay mode of the ith insurance product in the same type of insurance products, +.>Representing the characteristic parameters of the insuring conditions of the ith insurance product in the same type of insurance products. The invention parameterizes the key features of the same type of insurance products through definition and modeling of basic feature vectors. By the method, the characteristics of price, guarantee range, pay mode, application conditions and the like of the product can be converted into numerical characteristic parameters, and calculation and comparison in a model are facilitated. Such parameterized representationsThe method is beneficial to extracting the difference and the similarity between the products, helping an insurance company to evaluate and compare the advantages and the disadvantages of different products more accurately, and providing more targeted recommendation and customization for screening of target users.
Optionally, the insurance feature model satisfies the following formula:
wherein->Indicating the homogeneity parameter of the ith insurance product relative to the reference insurance product, < >>，/>Number indicating insurance product->Indicating the number of categories of insurance products, +.>Representing the reference feature vector corresponding to the reference insurance product selected by the insurance feature model,representing the second order norm of the reference feature vector, +.>Basic feature vector representing the ith insurance product of the same type of insurance products, < >>Price characteristic parameter representing the ith insurance product of the same type of insurance products +.>Representing the guarantee range characteristic parameter of the ith insurance product in the same type of insurance products, < + >>Representing the characteristic parameters of the pay mode of the ith insurance product in the same type of insurance products, +.>Representing the characteristic parameters of the insuring conditions of the ith insurance product in the same type of insurance products. According to the invention, through the formula calculation of the insurance feature model, the homogeneous parameters of different insurance products relative to the reference insurance products can be obtained. This parameter can be used to measure similarity between insurance products, thereby providing more targeted recommendations and customizations for target user screening. By comparing the homogeneous parameters, the insurance company can accurately evaluate the quality of each product relative to the reference product, help them to better understand the characteristics and differences of the products, and select the most suitable insurance product for the target user. The method provides a scientific quantification means, provides a reliable basis for personalized insurance recommendation, and improves user satisfaction and market competitiveness.
Optionally, the selecting a reference insurance product and an insurance product to be evaluated from the insurance products of the same type includes the following steps: sorting different insurance products in the same type of insurance products; sequentially selecting reference insurance products according to the sorting result; and setting an insurance product to be evaluated according to the selection result of the reference insurance product, wherein the insurance product to be evaluated does not comprise the reference insurance product. The invention determines the reference insurance product and the insurance product to be evaluated by sequencing and selecting the insurance products of the same type, thereby realizing the processes of comparison and screening. By sorting, insurance products can be arranged according to a certain standard, which is helpful for insurance companies to quickly determine reference products. After the reference insurance product is selected, the insurance product to be evaluated can exclude the reference product, so that repeated evaluation and comparison are avoided. The selection step can improve the evaluation efficiency and accuracy, help insurance companies to better know market competition patterns and product differences, and screen out insurance products with the highest potential for target users.
Optionally, the number of insurance products to be evaluated is one or more. According to the invention, one or more insurance products to be evaluated are selected according to the requirements, so that the flexibility and diversity are increased, and different evaluation and comparison requirements are better met.
Optionally, the selection results of the reference insurance product and the insurance product to be evaluated include the following: the ith selection result: the ith insurance product is the reference insurance product, the thEach insurance product is an insurance product to be evaluated. According to the invention, by taking the ith insurance product as a reference insurance product and taking other insurance products as insurance products to be evaluated, the insurance company can be helped to evaluate and compare orderly, each product is ensured to have an opportunity to be evaluated, and the advantages and disadvantages of the insurance product and the reference product are effectively compared.
Optionally, building a user feature model by using homogenization parameters of the reference insurance product and the insurance product to be evaluated, including the following steps: setting a homogenization threshold according to homogenization parameters of a reference insurance product and an insurance product to be evaluated; building a user characteristic model by using the homogenization threshold, wherein the user characteristic model meets the following formula:wherein->Indicating whether the user of the reference insurance product is a potential user evaluation value of the insurance product to be evaluated,indicating that the user of the reference insurance product is a potential user of the insurance product to be evaluated, < >>Indicating that the user of the reference insurance product is not a potential user of the insurance product to be evaluated, +.>Indicating the homogeneity of the ith insurance product relative to the reference insurance productParameters (I)>Representing a homogeneity threshold. By setting the homogenization threshold, the invention can judge whether the user of the reference insurance product is a potential user of the insurance product to be evaluated according to the evaluation value of the homogenization parameter. The user characteristic model can help an insurance company to accurately determine a target user, provide more targeted recommendation and customization, and improve sales conversion rate and customer satisfaction.
In a second aspect, in order to better execute the target user screening method based on the feedback mechanism, the invention further provides a target user screening system based on the feedback mechanism. The feedback mechanism-based target user screening system includes one or more processors; one or more input devices; the system comprises one or more output devices and a memory, wherein the processor, the input device, the output device and the memory are connected through a bus, the memory is used for storing a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the target user screening method based on the feedback mechanism. The target user screening system based on the feedback mechanism provided by the invention has high and stable performance and compact structure, and can be used for efficiently and accurately implementing the target user screening method provided by the invention.
Drawings
FIG. 1 is a flowchart of a target user screening method based on a feedback mechanism according to an embodiment of the present invention;
fig. 2 is a block diagram of a target user screening system based on a feedback mechanism according to an embodiment of the present invention.
Detailed Description
Specific embodiments of the invention will be described in detail below, it being noted that the embodiments described herein are for illustration only and are not intended to limit the invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that: no such specific details are necessary to practice the invention. In other instances, well-known circuits, software, or methods have not been described in detail in order not to obscure the invention.
Throughout the specification, references to "one embodiment," "an embodiment," "one example," or "an example" mean: a particular feature, structure, or characteristic described in connection with the embodiment or example is included within at least one embodiment of the invention. Thus, the appearances of the phrases "in one embodiment," "in an embodiment," "one example," or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. Moreover, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and that the illustrations are not necessarily drawn to scale.
In an alternative embodiment, please refer to fig. 1, fig. 1 is a flowchart of a target user screening method based on a feedback mechanism according to an embodiment of the present invention. Fig. 1 shows a flowchart of a target user screening method based on a feedback mechanism, which includes the following steps:
and S01, acquiring product data and user data of the same type of insurance products.
It should be understood that the same type of insurance product described in step S01 refers to insurance products having similar insurance clauses, insurance ranges, premium, etc. within the same insurance domain or sub-domain. For example, in the field of car insurance, the same type of insurance product may include traffic insurance, commercial car insurance, car damage, third party liability insurance, and the like. In the health risk area, the same type of insurance products may include heavy illness risk, medical risk, accident risk, and the like.
Wherein, the product data refers to various information data of insurance products, including but not limited to: product name, insurance amount, premium, insurance liability, underwriting scope, claims settlement process, etc. The user data refers to various information data of an insurance user corresponding to the insurance product, including but not limited to: age, gender, occupation, health status, family status, asset status, etc. Such data may be obtained through the product manuals and terms of the insurance company, internal data systems, market research, user surveys, online and offline marketing campaigns, customer relationship management, and the like.
Further, step S01 may collect product data and user data for a type of insurance product (e.g., car insurance, health insurance, etc.). Taking car insurance as an example, the product data comprises information such as insurance policy number, premium, insurance amount, insurance period and the like, and the user data comprises information such as car owner information (name, mobile phone number, license plate number, car type and the like), insurance purchase record, claim record and the like. Such data may be obtained from an insurance company's data platform, an insurance broker's system, an insurance industry association's data center, and so on. In addition, related data such as social media activities of the vehicle owners, related news reports and the like can be obtained from some public data sources (such as an open data platform, a social network and the like) on the internet, and the data can be used for building a subsequent insurance feature model and a user feature model.
In an alternative embodiment, the acquiring product data and user data of the same type of insurance product in step S01 includes the following steps:
s011, determining the type of the target insurance product.
Further, step S011 can determine the type of insurance product to be screened, such as car insurance, life insurance, accident insurance, etc., according to the actual requirement.
S012, selecting a specific insurance product under the target insurance product type.
After determining the target insurance product type based on step S011, step S012 may select a specific insurance product under the target insurance product type by a product manual of an insurance company.
S013, acquiring product data and user data of the specific insurance product.
The product data of the specific insurance product can be obtained through channels such as a product manual of an insurance company, an official website, an insurance company agent, a third-party insurance price comparison website and the like. User data of a specific insurance product can be obtained through an internal data system, user investigation, social media analysis and other approaches.
S014, sorting the product data and the user data to obtain an insurance database.
The sorting of the product data and the user data in step S014 to obtain an insurance database may be implemented by existing technical means. Among these, data cleansing, data conversion, data integration, data storage and data analysis are the basic steps in building an insurance database.
Further, the data cleaning can clean and process the problems of errors, duplications, deletions, inconsistencies and the like in the data so as to ensure the accuracy and the integrity of the data. Specifically, the data cleaning can be implemented by using technical means such as a data mining tool, data preprocessing software, programming language, a database management system and the like.
Data conversion may convert data from different formats and structures to a unified format and structure to facilitate data integration and analysis. Specifically, the data conversion may be implemented by using technical means such as ETL (extraction, conversion, and loading) tools, data mapping tools, data conversion languages, and data integration software.
Data integration data from different data sources may be integrated and integrated to build a complete insurance database. In particular, the data integration may be implemented by using technical means such as data integration software, enterprise application integration software, web services, and APIs.
The data store may store the integrated data in an appropriate data storage facility to support subsequent data analysis and processing. Specifically, the data storage can be realized by using a relational database, a NoSQL database, a data warehouse, a data lake and other technical means.
It can be understood that the insurance database can enable the insurance company to perform centralized storage of various data in a unified format and structure, which is beneficial to follow-up work such as data mining and analysis, and further helps the insurance company to better understand market trend, customer requirements and risk prediction, so that decisions can be made more rapidly and accurately.
The steps S011 to S014 have the advantages of providing a data base for the subsequent steps, thereby realizing a target user screening method based on a feedback mechanism and improving the hit rate and service benefit of the target user. Meanwhile, by constructing a comprehensive, accurate, reusable and effective insurance database, support and guidance can be provided for the aspects of insurance product research and development, marketing, user portrayal and the like, and the competitiveness and innovation capability of enterprises are improved.
S02, building an insurance feature model by utilizing the product data and the user data.
The insurance feature model provided by the invention is a mathematical model based on product data and user data, and is used for extracting specific features from the product data and the user data and obtaining homogenization characterization parameters among the same type of insurance products according to the specific features. Further, the homogenization characterization parameter refers to a similarity parameter that is present between different insurance products of the same type. Specifically, in the insurance feature model provided by the invention, a series of feature parameters can be extracted by analyzing and processing the product data and the user data, and the parameters can represent the features and attributes of different insurance products. Then, by analyzing and comparing the characteristic parameters, the homogenization characterization parameters among the same type of insurance products can be obtained and used for describing the similarity among different insurance products.
In an alternative embodiment, the building of the insurance feature model using the product data and the user data in step S02 includes the following steps:
s021, defining a basic feature vector.
In this embodiment, the basic feature vector satisfies the following model:wherein->Basic feature vector representing the ith insurance product of the same type of insurance products, < >>Price characteristic parameter representing the ith insurance product of the same type of insurance products +.>Representing the guarantee range characteristic parameters of the ith insurance product in the same type of insurance products,representing the characteristic parameters of the pay mode of the ith insurance product in the same type of insurance products, +.>Representing the characteristic parameters of the insuring conditions of the ith insurance product in the same type of insurance products.
For price characteristic parametersPrice information for the insurance product may be extracted from the existing data. If there is a specific price value, it can be directly used as a characteristic parameter. If there are only price ranges or discrete price levels, a digitization process may be performed that maps it to a value.
Characteristic parameters aiming at guarantee rangeSpecific guarantee range information of the insurance can be extracted according to the clauses and description documents of the insurance product. Specifically, operations such as keyword extraction, classification, text vectorization, etc. can be performed according to text processing technology and natural language processing method, and the operations are converted into numerical representations.
Characteristic parameters for pay modeMay be extracted based on the terms and specifications of the payment of the insurance product. The pay mode may be converted into a class label or numerical code to represent different pay modes.
Feature parameters for insuring conditionsCan be extracted from the requirements and restrictions of the insurance product. The codes or classifications may be based on factors such as the age of the application, health, occupation, etc.
S022, vectorizing the product data and the user data by utilizing the basic feature vector.
In the present embodiment, step S022 quantizes the product data and the user data obtained in step S01 according to the basic feature vector set in step S021. In particular, in the present embodiment, for a security product A, its price characteristic parameters1000, guarantee Range characteristic parameter->Is "high", pay mode characteristic parameter->For "pay-to-proportion", apply the conditional feature parameter +.>Is "over 18 years old". Therefore, the basic feature vector for insurance product A is: />= [1000, high, pay in proportion, 18 years old or older]. Further, the basic feature vector of the insurance product A is used as a label of a user, and user data is vectorized, so that the potential target user can be matched conveniently.
S023, building an insurance feature model according to the vectorization result.
The insurance feature model proposed in step S023 is used to compare and evaluate the homogeneity parameters between different insurance products, i.e. the feature similarity with respect to the reference insurance product. In this embodiment, the insurance feature model satisfies the following formula:wherein->Indicating the homogeneity parameter of the ith insurance product relative to the reference insurance product, < >>，/>Number indicating insurance product->Indicating the number of categories of insurance products, +.>Representing the reference feature vector corresponding to the reference insurance product selected by the insurance feature model,representing the second order norm of the reference feature vector, +.>Basic feature vector representing the ith insurance product of the same type of insurance products, < >>Price characteristic parameter representing the ith insurance product of the same type of insurance products +.>Representing the guarantee range characteristic parameter of the ith insurance product in the same type of insurance products, < + >>Representing the characteristic parameters of the pay mode of the ith insurance product in the same type of insurance products, +.>Representing the characteristic parameters of the insuring conditions of the ith insurance product in the same type of insurance products.
S03, selecting a reference insurance product and an insurance product to be evaluated from the insurance products of the same type.
In an alternative embodiment, the selecting the reference insurance product and the insurance product to be evaluated from the insurance products of the same type in step S03 includes the following steps:
s031, sorting different insurance products in the same type of insurance products.
The purpose of step S031 is to sort insurance products of the same type. By ordering, the relative order between insurance products, i.e., which insurance products are ranked higher under certain criteria, and which are ranked lower, can be determined. The purpose of this is to have a clear basis for selecting the reference insurance product and the insurance product to be evaluated in the subsequent steps, to ensure that the reference insurance product has a certain representativeness, and that the insurance product to be evaluated includes other insurance products than the reference insurance product. The ranking may be based on different criteria, such as price, scope of assurance, manner of payment, etc., to determine the relative order of insurance products based on particular needs and comparison objectives.
S032, selecting reference insurance products in sequence according to the sorting result.
According to the ordered results, the reference insurance products can be sequentially selected from the highest or lowest ranked insurance product. And one insurance product at a time is selected as a reference insurance product.
S033, setting an insurance product to be evaluated according to the selection result of the reference insurance product, wherein the insurance product to be evaluated does not comprise the reference insurance product.
It should be appreciated that the insurance product to be evaluated will include the remaining insurance products in addition to the reference insurance product. Further, the number of insurance products to be evaluated is one or more.
In an alternative embodiment, the number of insurance products to be evaluated is set to one, so that only a single insurance product needs to be evaluated, and further analysis and comparison can be performed. At the same time, by carefully evaluating individual insurance products, their features, advantages, and disadvantages, as well as differences and similarities to reference insurance products, can be more accurately appreciated. In this embodiment, 5 insurance products are ordered A, B, C, D, E for price from low to high. Selecting an insurance product A as a reference insurance product for the first time, and selecting an insurance product B as an insurance product to be evaluated; selecting an insurance product A as a reference insurance product for the second time, and selecting an insurance product C as an insurance product to be evaluated; thirdly, selecting an insurance product A as a reference insurance product, and taking an insurance product D as an insurance product to be evaluated; and selecting the insurance product A as a reference insurance product for the fourth time, and taking the insurance product E as an insurance product to be evaluated.
In yet another alternative embodiment, the number of insurance products to be evaluated is set to be plural, so that by evaluating plural insurance products, the differences, advantages and disadvantages between them, and their manifestations on different characteristic parameters, can be comprehensively understood; and meanwhile, a plurality of insurance products are selected to cover different characteristics and strategies, so that more observation results and analysis insights are obtained, more comprehensive and accurate decisions are facilitated, and a plurality of insurance products to be evaluated are selected to disperse the evaluation risk, so that the evaluation result excessively dependent on a single insurance product is avoided.
Further, in an alternative embodiment, the insurance products other than the reference insurance product are set as the insurance products to be evaluated, as shown in the following table:
in the above table, a represents that the product with the corresponding serial number is the reference insurance product, and B represents that the product with the corresponding serial number is the insurance product to be evaluated. The selected result in the table meets the following rules: the ith selection result: the ith insurance product is the reference insurance product, the thEach insurance product is an insurance product to be evaluated.
S04, obtaining homogenization parameters of the reference insurance product and the insurance product to be evaluated through the insurance feature model.
It should be understood that the homogenization parameters described in step S04 are relative homogenization parameters between the insurance product to be evaluated and the reference insurance product obtained by taking the basic feature vector of the reference insurance product as a reference. Step S04 can calculate homogenization parameters of any reference insurance product and corresponding insurance products to be evaluated through the insurance feature model. These homogenization parameters may be used to compare similarities and differences between different insurance products in order to make more accurate assessments and decisions.
S05, constructing a user characteristic model by using homogenization parameters of the reference insurance product and the insurance product to be evaluated.
In an alternative embodiment, the step S05 of constructing a user feature model by using the homogenization parameters of the reference insurance product and the insurance product to be evaluated includes the following steps:
and S051, setting a homogenization threshold according to homogenization parameters of the reference insurance product and the insurance product to be evaluated.
The homogenization threshold described in step S051 is used to determine whether the user of the reference insurance product is a potential user of the insurance product to be evaluated. Further, the homogeneity threshold is a set value for determining the magnitude of the homogeneity parameter. It is determined whether the user of the reference insurance product is considered a potential user of the insurance product to be evaluated.
It should be noted that the selection of the homogeneity threshold may need to be adjusted according to the specific application scenario and requirements. A higher homogenization threshold may result in a more stringent user screening, while a lower homogenization threshold may relax the user screening conditions. Therefore, in practical application, experiments and adjustment can be performed according to practical situations and requirements so as to obtain a more suitable user characteristic model.
S052, building a user characteristic model by utilizing the homogenization threshold, wherein the user characteristic model meets the following formula:wherein->Indicating whether the user of the reference insurance product is a potential user evaluation value of the insurance product to be evaluated, +.>Indicating that the user of the reference insurance product is a potential user of the insurance product to be evaluated, < >>Indicating that the user of the reference insurance product is not a potential user of the insurance product to be evaluated, +.>Indicating the homogeneity parameter of the ith insurance product relative to the reference insurance product, < >>Representing a homogeneity threshold.
In the present embodiment, if the absolute value of the homogenization parameter is equal to or greater than the homogenization threshold value) The user referring to the insurance product is considered to be a potential user of the insurance product to be evaluated (+)>). If the absolute value of the homogenization parameter is smaller than the homogenization threshold value (+>) The user of the reference insurance product is not considered to be a potential user of the insurance product to be evaluated (+)>）。
S06, screening target users of the security products to be evaluated from the security products of the same type through the user feature model.
Step S06 aims to screen out target users of the security products to be evaluated among the security products of the same type through the user feature model. The method is characterized in that according to the evaluation result of the user characteristic model, which users are interested in the insurance product to be evaluated or have potential requirements is determined, so that accurate target market positioning is realized.
Further, the step S06 of screening the target users of the security products to be evaluated from the security products of the same type through the user feature model includes the following steps:
and S061, obtaining a potential user evaluation value of the insurance product to be evaluated through the user characteristic model.
The user characteristic model takes homogenization parameters between a reference insurance product and an insurance product to be evaluated as input, judges according to a set homogenization threshold value, and outputs a potential user evaluation value #）。
And S062, screening target users of the security products to be evaluated from the security products of the same type according to the potential user evaluation value.
And screening the users in the same type of insurance products by using the evaluation value of the user characteristic model to determine the target users of the insurance products to be evaluated. Each user is evaluated according to the formula of the user characteristic model, if the potential user evaluation value is 1 #, the potential user evaluation value is calculated according to the formula of the user characteristic model) The user is considered a potential user of the insurance product to be evaluated, otherwise a non-target user.
The invention can help insurance companies to accurately know the demands of users, provide personalized insurance products, improve the satisfaction degree of users and effectively save development cost and time. Through accurate target user screening and directional marketing, improve sales conversion rate and marketing effect. In addition, the invention also helps insurance companies stand out in the homogenization market, develop special products and obtain competitive advantages. The invention provides an innovative solution for the insurance industry, meets the personalized demands of clients, and improves the service level and market competitiveness of insurance companies.
In an alternative embodiment, please refer to fig. 2, fig. 2 is a block diagram of a target user screening system based on a feedback mechanism according to an embodiment of the present invention. As shown in fig. 2, the feedback mechanism-based target user screening system provided by the present invention includes one or more processors 201; one or more input devices 202; one or more output devices 203 and a memory 204, said processor 201, said input device 202, said output device 203 and said memory 204 being connected by a bus, said memory 204 being for storing a computer program comprising program instructions, said processor 201 being configured for invoking said program instructions for performing the feedback mechanism based target user screening method provided by the present invention. The target user screening system based on the feedback mechanism provided by the invention has high and stable performance and compact structure, and can efficiently and accurately implement the target user screening method based on the feedback mechanism.
In yet another alternative embodiment, processor 201 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The input device 202 may be used to input product data and user data. The output device 203 may display relevant information such as the result obtained based on the feedback mechanism-based target user screening method provided by the present invention. The memory 204 may include read only memory and random access memory and provides instructions and data to the processor 201. A portion of memory 204 may also include non-volatile random access memory. For example, the memory 204 may also store information of device type.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (10)
1. The target user screening method based on the feedback mechanism is characterized by comprising the following steps of:
acquiring product data and user data of insurance products of the same type;
building an insurance feature model by utilizing the product data and the user data;
selecting a reference insurance product and an insurance product to be evaluated from the insurance products of the same type;
obtaining homogenization parameters of a reference insurance product and an insurance product to be evaluated through an insurance feature model;
constructing a user characteristic model by using homogenization parameters of a reference insurance product and an insurance product to be evaluated;
and screening target users of the insurance products to be evaluated from the insurance products of the same type through the user characteristic model.
2. The feedback mechanism-based target user screening method according to claim 1, wherein the acquiring product data and user data of the same type of insurance product comprises the steps of:
determining a target insurance product type;
selecting a specific insurance product under the type of the target insurance product;
acquiring product data and user data of a specific insurance product;
and finishing the product data and the user data to obtain an insurance database.
3. The feedback mechanism-based target user screening method according to claim 1, wherein said building an insurance feature model using said product data and said user data comprises the steps of:
defining a basic feature vector;
vectorizing the product data and the user data using the base feature vector;
and building an insurance feature model according to the vectorization result.
4. The feedback mechanism-based target user screening method of claim 3, wherein the base feature vector satisfies the following model:wherein->Basic feature vector representing the ith insurance product of the same type of insurance products, < >>Price characteristic parameter representing the ith insurance product of the same type of insurance products +.>Representing the guarantee range characteristic parameter of the ith insurance product in the same type of insurance products, < + >>Representing the characteristic parameters of the pay mode of the ith insurance product in the same type of insurance products, +.>Representing the characteristic parameters of the insuring conditions of the ith insurance product in the same type of insurance products.
5. The feedback mechanism-based targeting of claim 4The user screening method is characterized in that the insurance feature model satisfies the following formula:wherein->Indicating the homogeneity parameter of the ith insurance product relative to the reference insurance product, < >>，/>Number indicating insurance product->Indicating the number of categories of insurance products, +.>Reference feature vector corresponding to reference insurance product representing insurance feature model selection, < ->Representing the second order norm of the reference feature vector, +.>Basic feature vector representing the ith insurance product of the same type of insurance products, < >>Price characteristic parameter representing the ith insurance product of the same type of insurance products +.>Representing the guarantee range characteristic parameter of the ith insurance product in the same type of insurance products, < + >>Representing the characteristic parameters of the pay mode of the ith insurance product in the same type of insurance products, +.>Representing the characteristic parameters of the insuring conditions of the ith insurance product in the same type of insurance products.
6. The feedback mechanism-based target user screening method according to claim 1, wherein the selecting a reference insurance product and an insurance product to be evaluated from among the insurance products of the same type comprises the steps of:
sorting different insurance products in the same type of insurance products;
sequentially selecting reference insurance products according to the sorting result;
and setting an insurance product to be evaluated according to the selection result of the reference insurance product, wherein the insurance product to be evaluated does not comprise the reference insurance product.
7. The feedback mechanism-based targeted user screening method of claim 6, wherein the number of insurance products to be evaluated is one or more.
8. The feedback mechanism-based targeted user screening method of claim 7, wherein the selection of the reference insurance product and the insurance product to be evaluated comprises the following steps: the ith selection result: the ith insurance product is the reference insurance product, the thEach insurance product is an insurance product to be evaluated.
9. The feedback mechanism-based target user screening method of claim 8, wherein constructing the user feature model using the homogenization parameters of the reference insurance product and the insurance product to be evaluated, comprises the steps of:
setting a homogenization threshold according to homogenization parameters of a reference insurance product and an insurance product to be evaluated;
building a user characteristic model by using the homogenization threshold, wherein the user characteristic model meets the following formula:wherein->Indicating whether the user of the reference insurance product is a potential user evaluation value of the insurance product to be evaluated, +.>Indicating that the user of the reference insurance product is a potential user of the insurance product to be evaluated, < >>The user representing the reference insurance product is not a potential user of the insurance product to be evaluated,indicating the homogeneity parameter of the ith insurance product relative to the reference insurance product, < >>Representing a homogeneity threshold.
10. A feedback mechanism based target user screening system, wherein the feedback mechanism based target user screening system comprises one or more processors; one or more input devices; one or more output devices and a memory, the processor, the input device, the output device and the memory being connected by a bus, the memory being for storing a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the feedback mechanism based target user screening method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310736513.8A CN116485560A (en) | 2023-06-21 | 2023-06-21 | Target user screening method and system based on feedback mechanism |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310736513.8A CN116485560A (en) | 2023-06-21 | 2023-06-21 | Target user screening method and system based on feedback mechanism |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116485560A true CN116485560A (en) | 2023-07-25 |
Family
ID=87212236
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310736513.8A Pending CN116485560A (en) | 2023-06-21 | 2023-06-21 | Target user screening method and system based on feedback mechanism |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116485560A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109447687A (en) * | 2018-09-27 | 2019-03-08 | 中国平安人寿保险股份有限公司 | Usage mining method and device based on big data analysis |
| CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
| CN112100489A (en) * | 2020-08-27 | 2020-12-18 | 北京百度网讯科技有限公司 | Object recommendation method, device and computer storage medium |
| CN114997916A (en) * | 2022-05-27 | 2022-09-02 | 上海宝尊电子商务有限公司 | Prediction method, system, electronic device and storage medium of potential user |
| CN115423637A (en) * | 2022-09-23 | 2022-12-02 | 平安健康保险股份有限公司 | Insurance industry potential customer mining method, insurance industry potential customer mining device and storage medium |
| CN115700705A (en) * | 2021-07-27 | 2023-02-07 | 京东科技信息技术有限公司 | Product analysis method and device, electronic equipment and readable storage medium |
| WO2023011382A1 (en) * | 2021-07-31 | 2023-02-09 | 华为技术有限公司 | Recommendation method, recommendation model training method, and related product |
-
2023
- 2023-06-21 CN CN202310736513.8A patent/CN116485560A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109447687A (en) * | 2018-09-27 | 2019-03-08 | 中国平安人寿保险股份有限公司 | Usage mining method and device based on big data analysis |
| CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
| CN112100489A (en) * | 2020-08-27 | 2020-12-18 | 北京百度网讯科技有限公司 | Object recommendation method, device and computer storage medium |
| CN115700705A (en) * | 2021-07-27 | 2023-02-07 | 京东科技信息技术有限公司 | Product analysis method and device, electronic equipment and readable storage medium |
| WO2023011382A1 (en) * | 2021-07-31 | 2023-02-09 | 华为技术有限公司 | Recommendation method, recommendation model training method, and related product |
| CN114997916A (en) * | 2022-05-27 | 2022-09-02 | 上海宝尊电子商务有限公司 | Prediction method, system, electronic device and storage medium of potential user |
| CN115423637A (en) * | 2022-09-23 | 2022-12-02 | 平安健康保险股份有限公司 | Insurance industry potential customer mining method, insurance industry potential customer mining device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 叶立武;吴倩;王玮;王东;: "数据挖掘方法在保险领域的应用前景", 保险职业学院学报, no. 02 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564286B (en) | Artificial intelligent financial wind-control credit assessment method and system based on big data credit investigation | |
| US20210365963A1 (en) | Target customer identification method and device, electronic device and medium | |
| WO2019214248A1 (en) | Risk assessment method and apparatus, terminal device, and storage medium | |
| García Rodríguez et al. | Public procurement announcements in spain: regulations, data analysis, and award price estimator using machine learning | |
| CN112990386B (en) | User value clustering method and device, computer equipment and storage medium | |
| US7853550B1 (en) | Decision support systems and methods | |
| CN110738527A (en) | feature importance ranking method, device, equipment and storage medium | |
| CN111639690A (en) | Fraud analysis method, system, medium, and apparatus based on relational graph learning | |
| US20230281722A1 (en) | Smart estimatics methods and systems | |
| CN112434884A (en) | Method and device for establishing supplier classified portrait | |
| CN115423578A (en) | Bidding method and system based on micro-service containerization cloud platform | |
| CN112990989B (en) | Value prediction model input data generation method, device, equipment and medium | |
| CN112035775B (en) | User identification method and device based on random forest model and computer equipment | |
| CN113554310A (en) | Enterprise credit dynamic evaluation model based on intelligent contract | |
| Neumann et al. | Machine Learning-based predictions of customers’ decisions in car insurance | |
| CN116485560A (en) | Target user screening method and system based on feedback mechanism | |
| CN111680941A (en) | Premium recommendation method, device, equipment and storage medium | |
| CN114861989A (en) | Method and device for predicting insurance added service | |
| BULUT et al. | Financial Failure Estimation with Logistic Regression Model: A Study on Technology Sector Companies Treated in BIST | |
| CN113743752A (en) | Data processing method and device | |
| KR20180074218A (en) | System of valuation of technology | |
| Pribil et al. | A churn analysis using data mining techniques: Case of electricity distribution company | |
| Delina et al. | Quality of Artificial Intelligence Driven Procurement Decision Making and Transactional Data Structure. | |
| CN115187387B (en) | Identification method and equipment for risk merchant | |
| US11593388B2 (en) | Indexing based on feature importance |
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 |