CN118096291A - Product recommendation method, device, equipment and storage medium - Google Patents
Product recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN118096291A CN118096291A CN202410047554.0A CN202410047554A CN118096291A CN 118096291 A CN118096291 A CN 118096291A CN 202410047554 A CN202410047554 A CN 202410047554A CN 118096291 A CN118096291 A CN 118096291A
- Authority
- CN
- China
- Prior art keywords
- insurance product
- client
- target
- preset
- product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012216 screening Methods 0.000 claims abstract description 16
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012502 risk assessment Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003062 neural network model 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Human Resources & Organizations (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application provides a product recommendation method, a device, equipment and a storage medium, belonging to the field of data processing, wherein the method comprises the following steps: acquiring client information of a client to be insured; performing insurance product clause matching on the client information through a preset clause matching model to obtain a plurality of candidate insurance product clauses matched by the client to be insured; screening according to the customer information and each candidate insurance product term to determine a plurality of target insurance product terms; recommending the insurance product for the client to be insured according to a plurality of target insurance product clauses. The scheme can accurately recommend more proper insurance products for the clients to be insured, greatly improves the accuracy of insurance product recommendation, can improve the reliability and satisfaction of the clients to insurance enterprises, and greatly improves the efficiency and the competitiveness of the insurance products. The application also relates to blockchain techniques to which the preset clause matching model may be stored.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a product recommendation method, device, equipment, and storage medium.
Background
With the rapid development of the insurance industry, the types of insurance products are more and more, each insurance product has different product clauses, application scenes and guarantee ranges, and at present, insurance operators recommend the insurance products to customers basically based on basic information of the customers according to sales experience, but the insurance operators recommend the insurance products to the customers, which cannot comprehensively know the risk condition of customers and the current guarantee condition of the customers, so that the insurance products recommended by the insurance operators are not necessarily suitable for corresponding users, and the recommendation accuracy of the insurance products is low.
Secondly, insurance product's premium calculation is comparatively complicated, relates to multiple risk factor and statistics, and the customer is difficult to estimate the premium and can't know the influence of different guarantee parameters to the premium directly perceivedly, leads to the customer to be difficult to select more suitable insurance product.
Therefore, how to select a more appropriate insurance product for customers is a current challenge.
Disclosure of Invention
The application mainly aims to provide a product recommending method, device, equipment and storage medium, aiming at improving the accuracy of recommending insurance products.
In a first aspect, the present application provides a product recommendation method, comprising the steps of:
Acquiring client information of a client to be insured;
Performing insurance product clause matching on the client information through a preset clause matching model to obtain a plurality of candidate insurance product clauses matched by the client to be insured;
Screening according to the customer information and the candidate insurance product clauses to determine a plurality of target insurance product clauses;
Recommending the insurance product for the client to be insured according to a plurality of target insurance product clauses.
In a second aspect, the present application further provides a product recommendation device, where the product recommendation device includes an acquisition module, a generation module, and a recommendation module, where:
The acquisition module is used for acquiring client information of a client to be insured;
The generation module is used for carrying out insurance product clause matching on the client information through a preset clause matching model to obtain a plurality of candidate insurance product clauses matched with the client to be insured, and the preset clause matching model is a pre-trained integrated algorithm model;
The generation module is further used for screening according to the client information and the candidate insurance product clauses to determine a plurality of target insurance product clauses;
And the recommending module is used for recommending the insurance product for the client to be insured according to the target insurance product clauses.
In a third aspect, the present application also provides a computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor implements the steps of the product recommendation method as described above.
In a fourth aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of a product recommendation method as described above.
The application provides a product recommendation method, a device, equipment and a storage medium, wherein the method is used for acquiring client information of a client to be insured; performing insurance product clause matching on the client information through a preset clause matching model to obtain a plurality of candidate insurance product clauses matched by the client to be insured; screening according to the customer information and each candidate insurance product term to determine a plurality of target insurance product terms; recommending the insurance product for the client to be insured according to a plurality of target insurance product clauses. The scheme can accurately recommend more proper insurance products for the clients to be insured, greatly improves the accuracy of insurance product recommendation, can improve the reliability and satisfaction of the clients to insurance enterprises, and greatly improves the efficiency and the competitiveness of the insurance products.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, 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 flow chart of a product recommendation method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of another product recommendation method according to an embodiment of the present application;
FIG. 3 is a schematic block diagram of a product recommendation device according to an embodiment of the present application;
FIG. 4 is a schematic block diagram of another product recommendation device according to an embodiment of the present application;
fig. 5 is a schematic block diagram of a computer device according to an embodiment of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
The embodiment of the application provides a product recommendation method, device, equipment and storage medium. The product recommendation method can be applied to computer equipment, and the computer equipment can be electronic equipment such as mobile phones, tablet computers, notebook computers, desktop computers, personal digital assistants and the like. For example, the computer device is a desktop computer, and the desktop computer obtains client information of a client to be insured; performing insurance product clause matching on the client information through a preset clause matching model to obtain a plurality of candidate insurance product clauses matched by the client to be insured; screening according to the customer information and each candidate insurance product term to determine a plurality of target insurance product terms; recommending insurance products for the clients to be insured according to the target insurance product clauses.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flow chart of a product recommendation method according to an embodiment of the application.
As shown in fig. 1, the product recommendation method includes steps S101 to S104.
Step S101, obtaining client information of clients to be insured.
The client information is basic feature information of the client to be insured, and the client information can be set according to practical situations, which is not particularly limited in the embodiment of the present invention, and for example, the client information can include information such as age, gender, occupation, family information, and physical health information.
In one embodiment, customer information of a customer to be insured is obtained to accurately recommend an appropriate insurance product for the customer to be insured based on the customer information.
In an embodiment, as shown in fig. 2, step S201 to step S204 are further included before step S101.
Step S201, a plurality of sample data are obtained, one sample data is selected from the plurality of sample data to serve as target sample data, and the sample data comprise customer information of a sample application client and sample insurance product clauses matched with the sample application client.
Wherein the sample data includes customer information of the sample application client and sample insurance product terms matched by the sample application client, the insurance product terms being restriction terms of the insurance product, the insurance product terms including at least time, age restriction, accountability restriction, disclaimer restriction, and the like.
In one embodiment, customer information of a sample application client and sample insurance product terms matched by the sample application client are obtained to obtain one sample data, and customer information of a different sample application client and sample insurance product terms matched by the sample application client are repeatedly obtained to obtain a plurality of sample data. By repeatedly acquiring the customer information of different sample insurance customers and the sample insurance product clauses matched by the sample insurance customers, a plurality of sample data can be accurately obtained, and the efficiency and accuracy of training the preset clause matching model are greatly improved.
In one embodiment, one sample data is selected from a plurality of sample data as target sample data, the target sample data including customer information of a sample application client and sample insurance product terms that the sample application client matches. It should be noted that, the manner of selecting the target sample data may be set according to the actual situation, which is not particularly limited in the embodiment of the present invention, for example, one sample data is randomly selected as the target sample data.
And step S202, carrying out insurance product clause matching on the target sample data through a preset clause matching model to obtain predicted insurance product clauses.
The preset term matching model may be selected according to actual situations, which is not limited in the embodiment of the present invention, for example, the preset term matching model may be an Adaboost ensemble learning algorithm, and the preset term matching model may also be a neural network model. It should be noted that, the embodiment of the present invention is exemplified by an Adaboost ensemble learning algorithm, but is not limited to other modes.
In one embodiment, insurance product clause matching is performed on the client information of the sample application client in the target sample data through a preset clause matching model, so as to obtain predicted insurance product clause. The customer information insurance product clause is matched through the preset clause matching model, so that the predicted insurance product clause can be accurately obtained, and the efficiency and accuracy of training the clause matching model are greatly improved.
In one embodiment, customer information of a sample insurance customer is input into a preset base classifier, and insurance product clauses are matched based on preset weight parameters, so that predicted insurance product clauses are obtained. The preset weight parameters are model parameters of a preset base classifier. The predicted insurance product clause can be accurately obtained by performing insurance product clause matching of the preset weight parameters in the preset base classifier.
Step 203, determining whether the preset clause matching model converges according to the predicted insurance product clause and the sample insurance product clause.
In one embodiment, an error rate is determined based on the predicted insurance product terms and the sample insurance product terms; under the condition that the error rate is greater than or equal to a preset error rate, determining that a preset clause matching model is not converged; and under the condition that the error rate is smaller than the preset error rate, determining that the preset clause matching model is converged. The preset error rate may be set according to practical situations, which is not specifically limited in the embodiment of the present invention.
In one embodiment, the error rate may be determined based on the predicted insurance product terms and the sample insurance product terms by: and determining the number of the same clauses as the sample insurance product clauses in the predicted insurance product clauses to obtain the predicted correct clause number, dividing the predicted correct clause number by the sample insurance product clause number to obtain the correct rate, and subtracting the correct rate from the unit 1 to obtain the error rate. The error rate can be accurately obtained based on the predicted correct term number and the sample insurance product term number.
Step S204, under the condition that the preset clause matching model is not converged, updating model parameters of the preset clause matching model, and continuously executing the step of selecting one sample data from a plurality of sample data as target sample data until the preset clause matching model is converged.
And under the condition that the error rate is greater than or equal to the preset error rate, determining that the preset clause matching model is not converged, updating model parameters of the preset clause matching model, and continuously executing the step of selecting one sample data from the plurality of sample data as target sample data until the preset clause matching model is converged. By updating the model parameters and continuing training, a converged clause matching model can be accurately obtained. In one embodiment, the mode of updating the model parameters of the preset clause matching model may be: acquiring a preset first formula, wherein the preset first formula is beta=epsilon t/(1-epsilon t), beta is an error coefficient, epsilon t is an error rate, and the error coefficient is calculated based on the preset first formula and according to the error rate; and acquiring a preset second formula, wherein the preset second formula is alpha t=log (1/beta), beta is an error coefficient, alpha t is a weight coefficient, and the weight coefficient is calculated according to the error coefficient based on the preset second formula. Updating each parameter in the preset clause matching model according to the weight coefficient to generate an updated preset clause matching model.
In the above embodiment, by acquiring a plurality of sample data, one sample data is selected from the plurality of sample data as target sample data, the sample data including customer information of a sample application client and sample insurance product terms matched by the sample application client; performing insurance product clause matching on the target sample data through a preset clause matching model to obtain predicted insurance product clauses; determining whether a preset clause matching model is converged according to the predicted insurance product clause and the sample insurance product clause; under the condition that the preset clause matching model is not converged, updating model parameters of the preset clause matching model, and continuously executing the step of selecting one sample data from a plurality of sample data as target sample data until the preset clause matching model is converged, so that the clause matching model can be accurately obtained.
And step S102, carrying out insurance product clause matching on the client information through a preset clause matching model to obtain a plurality of candidate insurance product clauses matched by the client to be applied.
The candidate insurance product clauses are obtained by screening insurance product clauses conforming to clients to be insured through a preset clause matching model.
In one embodiment, matching customer information and each insurance product term through a preset term matching model to obtain a matching result of a customer to be applied and each insurance product term; and determining the insurance product clause with the matching result being the first matching result as the candidate insurance product clause, and obtaining a plurality of candidate insurance product clauses to be matched by the insuring client. And matching the customer information with each insurance product term through a preset term matching model, so that candidate insurance product terms can be accurately obtained.
It should be noted that, the matching result is obtained by matching each insurance product term by a preset term matching model, the matching result includes a first matching result and a second matching result, the first matching result is used for representing that the customer information is matched with the insurance product term, and the second matching result is used for representing that the customer information is not matched with the insurance product term.
In an embodiment, the customer information and the insurance product terms are matched through a preset term matching model, so that a matching result of the customer to be applied and each insurance product term is obtained, and the insurance product terms with the matching result being the second matching result are removed.
Step S103, screening is carried out according to the customer information and the candidate insurance product clauses, and a plurality of target insurance product clauses are determined.
Wherein the target insurance product clause is an insurance product clause which accords with the expected premium of the client to be insured.
In one embodiment, customer information is analyzed according to a preset risk assessment model, and expected premium parameters of customers to be insured are determined; and screening insurance product clauses from a plurality of candidate insurance product clauses according to the expected premium parameters to obtain a plurality of target insurance product clauses. The client information is analyzed through the preset risk assessment model, the expected premium parameters of the client to be insured can be accurately obtained, the target insurance product clause can be accurately determined according to the expected premium parameters, and the recommending efficiency and accuracy of the insurance product are greatly improved.
It should be noted that, the preset risk assessment model is set based on the user bearing capacity and the risk status, and the preset risk assessment model may be set according to the actual situation, which is not particularly limited in the embodiment of the present invention.
And step S104, recommending the insurance product for the customer to be insured according to a plurality of target insurance product clauses.
The recommended insurance product is the most suitable insurance product for the client to be insured.
In one embodiment, determining whether an insurance product comprising each of the target insurance product terms is present; in the event that there is an insurance product containing the terms of each target insurance product, the insurance product is referred to as the target of the customer to be insured. By recommending the insurance product as a target including the terms of each target insurance product, the efficiency and accuracy of the insurance product is greatly improved.
Illustratively, the target insurance product terms of the customer to be insured include terms 1, 5, 7, 12 and 22, and the product terms of the insurance product D include terms 1,4, 5, 7, 10, 12, 15, 18, 20, 22, 25 and 30, whereby the insurance product D includes terms 1, 5, 7, 12 and 22 of the target insurance product, and the insurance product D is determined as the target recommended insurance product of the customer to be insured.
In an embodiment, in the case that no insurance product containing each target insurance product term exists, according to each target insurance product term and the client information, selecting the insurance product with the highest matching degree as the target recommended insurance product of the client to be insured. And the insurance product with the highest product clause matching is used as the target recommended insurance product of the client to be insured, so that the efficiency and accuracy of insurance product recommendation are greatly improved.
Illustratively, the target insurance product terms of the customer to be insured include terms 1, 5, 7, 12 and 22, the product terms of the insurance product D include terms 1, 5, 7 and 12 (other terms omitted), and the product terms of the insurance product M include terms 1, 5 and 22, and the insurance product D is determined as the target recommended insurance product of the customer to be insured.
In one embodiment, in the absence of an insurance product containing target insurance product terms, multiple insurance products are selected for the customer to be insured to combine as target recommended insurance products for the customer to be insured according to the target insurance product terms and customer information. The target insurance product clauses and the customer information are used for selecting a plurality of insurance products to be combined, so that the customer to be insured can select the satisfied insurance products, the accuracy of insurance product recommendation is greatly improved, the reliability and satisfaction of the customer to insurance enterprises can be improved, and the efficiency and competitiveness of the insurance products are greatly improved.
According to the product recommendation method provided by the embodiment, the client information of the client to be insured is obtained; performing insurance product clause matching on the client information through a preset clause matching model to obtain a plurality of candidate insurance product clauses matched by the client to be insured; screening according to the customer information and each candidate insurance product term to determine a plurality of target insurance product terms; recommending the insurance product for the client to be insured according to a plurality of target insurance product clauses. The scheme can accurately recommend more proper insurance products for the clients to be insured, greatly improves the accuracy of insurance product recommendation, can improve the reliability and satisfaction of the clients to insurance enterprises, and greatly improves the efficiency and the competitiveness of the insurance products.
Referring to fig. 3, fig. 3 is a schematic block diagram of a product recommendation device according to an embodiment of the present application;
as shown in fig. 3, the product recommendation device 300 includes an acquisition module 310, a generation module 320, and a recommendation module 330, where:
the acquiring module 310 is configured to acquire client information of a client to be insured;
The generating module 320 is configured to perform insurance product clause matching on the client information through a preset clause matching model, so as to obtain a plurality of candidate insurance product clauses matched by the client to be insured, where the preset clause matching model is a pre-trained integrated algorithm model;
the generating module 320 is further configured to screen according to the customer information and each of the candidate insurance product terms, and determine a plurality of target insurance product terms;
The recommending module 330 is configured to recommend an insurance product for the customer to be insured according to a plurality of target insurance product terms.
In an embodiment, the generating module 320 is further configured to:
Matching the client information with each insurance product term through the preset term matching model to obtain a matching result of the client to be applied and each insurance product term;
And determining the insurance product clause with the matching result being the first matching result as the candidate insurance product clause, and obtaining a plurality of candidate insurance product clauses matched by the client to be insured.
In an embodiment, the generating module 320 is further configured to:
analyzing the client information according to a preset risk assessment model, and determining expected premium parameters of the client to be insured;
And screening insurance product clauses from a plurality of candidate insurance product clauses according to the expected premium parameters to obtain a plurality of target insurance product clauses.
In an embodiment, the recommendation module 330 is further configured to:
determining whether an insurance product comprising each of said target insurance product terms exists;
and in the case that the insurance product containing each target insurance product term exists, taking the insurance product as a target recommended insurance product of the client to be insured.
In an embodiment, the recommendation module 330 is further configured to:
and under the condition that the insurance product containing each target insurance product term does not exist, selecting the insurance product with the highest matching degree as the target recommended insurance product of the customer to be insured according to each target insurance product term and the customer information.
Referring to fig. 4, fig. 4 is a schematic block diagram of another product recommendation device according to an embodiment of the present application;
as shown in fig. 4, the product recommendation device 400 includes an obtaining module 410, a selecting module 420, a generating module 430, a determining module 440, and an updating module 450, wherein:
the obtaining module 410 is configured to obtain a plurality of sample data, where the sample data includes customer information of a sample application client and sample insurance product terms matched by the sample application client;
The selecting module 420 is configured to select one sample data from the plurality of sample data as target sample data;
The generating module 430 is configured to perform insurance product clause matching on the target sample data through a preset clause matching model to obtain predicted insurance product clauses;
the generating module 430 is further configured to determine whether the preset term matching model converges according to the predicted insurance product term and the sample insurance product term;
The updating module 450 is configured to update the model parameters of the preset clause matching model if the preset clause matching model does not converge, and continue to perform the step of selecting one sample data from the plurality of sample data as the target sample data until the preset clause matching model converges.
It should be noted that, for convenience and brevity of description, specific working processes of the product recommendation device may refer to corresponding processes in the foregoing product recommendation method embodiments, and will not be described herein again
Referring to fig. 5, fig. 5 is a schematic block diagram of a computer device according to an embodiment of the present application.
As shown in fig. 5, the computer device 500 includes a processor 502 and a memory 503 connected by a system bus 501, wherein the memory 503 may include a storage medium and an internal memory.
The storage medium may store a computer program. The computer program comprises program instructions that, when executed, cause the processor to perform any of a number of product recommendation methods.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device.
The internal memory provides an environment for the execution of a computer program in a storage medium that, when executed by a processor, causes the processor to perform any of a number of product recommendation methods.
It will be appreciated by those skilled in the art that the structure shown in FIG. 5 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
It should be appreciated that the Processor may be a central processing unit (Central Processing Unit, CPU), it may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein in one embodiment, the processor 502 is configured to execute a computer program stored in a memory to implement the steps of:
Acquiring client information of a client to be insured;
Performing insurance product clause matching on the client information through a preset clause matching model to obtain a plurality of candidate insurance product clauses matched by the client to be insured;
Screening according to the customer information and the candidate insurance product clauses to determine a plurality of target insurance product clauses;
Recommending the insurance product for the client to be insured according to a plurality of target insurance product clauses.
In one embodiment, when implementing the insurance product clause matching on the client information through the preset clause matching model, the processor 502 is configured to implement:
Matching the client information with each insurance product term through the preset term matching model to obtain a matching result of the client to be applied and each insurance product term;
And determining the insurance product clause with the matching result being the first matching result as the candidate insurance product clause, and obtaining a plurality of candidate insurance product clauses matched by the client to be insured.
In one embodiment, the processor 502 is configured to, when implementing the filtering based on the customer information and each of the candidate insurance product terms, determine a plurality of target insurance product terms:
analyzing the client information according to a preset risk assessment model, and determining expected premium parameters of the client to be insured;
And screening insurance product clauses from a plurality of candidate insurance product clauses according to the expected premium parameters to obtain a plurality of target insurance product clauses.
In one embodiment, the processor 502, when implementing the recommending insurance product for the customer to be insured according to a plurality of the target insurance product terms, is configured to implement:
determining whether an insurance product comprising each of said target insurance product terms exists;
and in the case that the insurance product containing each target insurance product term exists, taking the insurance product as a target recommended insurance product of the client to be insured.
In one embodiment, the processor 502, in effecting the determining whether an insurance product containing each of the target insurance product terms, is operative to effect:
and under the condition that the insurance product containing each target insurance product term does not exist, selecting the insurance product with the highest matching degree as the target recommended insurance product of the customer to be insured according to each target insurance product term and the customer information.
In one embodiment, before implementing the acquiring the client information of the client to be insured, the processor 502 is further configured to implement:
Acquiring a plurality of sample data, and selecting one sample data from the plurality of sample data as target sample data, wherein the sample data comprises client information of a sample application client and sample insurance product clauses matched with the sample application client;
performing insurance product clause matching on the target sample data through a preset clause matching model to obtain predicted insurance product clauses;
determining whether the preset clause matching model converges according to the predicted insurance product clause and the sample insurance product clause;
and under the condition that the preset clause matching model is not converged, updating model parameters of the preset clause matching model, and continuously executing the step of selecting one sample data from a plurality of sample data as target sample data until the preset clause matching model is converged.
In one embodiment, the processor 502 is configured to, when implementing the determining whether the preset term matching model converges according to the predicted insurance product term and the sample insurance product term, implement:
determining an error rate based on the predicted insurance product terms and the sample insurance product terms;
determining that the preset clause matching model is not converged under the condition that the error rate is greater than or equal to a preset error rate;
and under the condition that the error rate is smaller than a preset error rate, determining that the preset clause matching model is converged.
It should be noted that, for convenience and brevity of description, specific working processes of the computer device described above may refer to corresponding processes in the foregoing product recommendation method embodiments, and will not be described herein again.
Embodiments of the present application also provide a computer readable storage medium having a computer program stored thereon, where the computer program includes program instructions, where the method implemented when the program instructions are executed may refer to various embodiments of the product recommendation method of the present application.
The computer readable storage medium may be an internal storage unit of the computer device according to the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may be nonvolatile or may be volatile. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like, which are provided on the computer device.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
It is to be understood that the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in the present specification refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments. While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application.
Claims (10)
1. A method of product recommendation, comprising:
Acquiring client information of a client to be insured;
Performing insurance product clause matching on the client information through a preset clause matching model to obtain a plurality of candidate insurance product clauses matched by the client to be insured;
Screening according to the customer information and the candidate insurance product clauses to determine a plurality of target insurance product clauses;
Recommending the insurance product for the client to be insured according to a plurality of target insurance product clauses.
2. The product recommendation method of claim 1, wherein said performing insurance product clause matching on said customer information by means of a preset clause matching model to obtain a plurality of candidate insurance product clauses matched by said customer to be insured, comprises:
Matching the client information with each insurance product term through the preset term matching model to obtain a matching result of the client to be applied and each insurance product term;
And determining the insurance product clause with the matching result being the first matching result as the candidate insurance product clause, and obtaining a plurality of candidate insurance product clauses matched by the client to be insured.
3. The product recommendation method of claim 1 wherein said screening based on said customer information and each of said candidate insurance product terms to determine a plurality of target insurance product terms comprises:
analyzing the client information according to a preset risk assessment model, and determining expected premium parameters of the client to be insured;
And screening insurance product clauses from a plurality of candidate insurance product clauses according to the expected premium parameters to obtain a plurality of target insurance product clauses.
4. The product recommendation method of claim 1, wherein said recommending an insurance product for said customer to be insured according to a plurality of said target insurance product terms comprises:
determining whether an insurance product comprising each of said target insurance product terms exists;
and in the case that the insurance product containing each target insurance product term exists, taking the insurance product as a target recommended insurance product of the client to be insured.
5. The product recommendation method of claim 4 wherein said determining whether an insurance product exists that includes each of said target insurance product terms comprises:
and under the condition that the insurance product containing each target insurance product term does not exist, selecting the insurance product with the highest matching degree as the target recommended insurance product of the customer to be insured according to each target insurance product term and the customer information.
6. The product recommendation method as claimed in any one of claims 1 to 5, wherein prior to said obtaining customer information of a customer to be insured, further comprising:
Acquiring a plurality of sample data, and selecting one sample data from the plurality of sample data as target sample data, wherein the sample data comprises client information of a sample application client and sample insurance product clauses matched with the sample application client;
performing insurance product clause matching on the target sample data through a preset clause matching model to obtain predicted insurance product clauses;
determining whether the preset clause matching model converges according to the predicted insurance product clause and the sample insurance product clause;
and under the condition that the preset clause matching model is not converged, updating model parameters of the preset clause matching model, and continuously executing the step of selecting one sample data from a plurality of sample data as target sample data until the preset clause matching model is converged.
7. The product recommendation method of claim 6 wherein said determining whether said preset term matching model converges based on said predicted insurance product terms and sample insurance product terms comprises:
determining an error rate based on the predicted insurance product terms and the sample insurance product terms;
determining that the preset clause matching model is not converged under the condition that the error rate is greater than or equal to a preset error rate;
and under the condition that the error rate is smaller than a preset error rate, determining that the preset clause matching model is converged.
8. The product recommending device is characterized by comprising an acquisition module, a generation module and a recommending module, wherein:
The acquisition module is used for acquiring client information of a client to be insured;
The generation module is used for carrying out insurance product clause matching on the client information through a preset clause matching model to obtain a plurality of candidate insurance product clauses matched with the client to be insured, and the preset clause matching model is a pre-trained integrated algorithm model;
The generation module is further used for screening according to the client information and the candidate insurance product clauses to determine a plurality of target insurance product clauses;
And the recommending module is used for recommending the insurance product for the client to be insured according to the target insurance product clauses.
9. A computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor implements the steps of the product recommendation method according to any of claims 1 to 7.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of the product recommendation method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410047554.0A CN118096291A (en) | 2024-01-11 | 2024-01-11 | Product recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410047554.0A CN118096291A (en) | 2024-01-11 | 2024-01-11 | Product recommendation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118096291A true CN118096291A (en) | 2024-05-28 |
Family
ID=91146910
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410047554.0A Pending CN118096291A (en) | 2024-01-11 | 2024-01-11 | Product recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118096291A (en) |
-
2024
- 2024-01-11 CN CN202410047554.0A patent/CN118096291A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11734609B1 (en) | Customized predictive analytical model training | |
| US20240185130A1 (en) | Normalizing text attributes for machine learning models | |
| CN109326353B (en) | Method and device for predicting disease endpoint event and electronic equipment | |
| EP2700049A2 (en) | Predictive modeling | |
| US20220351004A1 (en) | Industry specific machine learning applications | |
| JP7139932B2 (en) | Demand forecasting method, demand forecasting program and demand forecasting device | |
| CN108829668B (en) | Text information generation method and device, computer equipment and storage medium | |
| CN112070545B (en) | Method, apparatus, medium, and electronic device for optimizing information reach | |
| JP2017146888A (en) | Design support device and method and program | |
| WO2022135765A1 (en) | Using disentangled learning to train an interpretable deep learning model | |
| WO2022055964A1 (en) | Generating realistic counterfactuals with residual generative adversarial nets | |
| Zhan et al. | Methods for dealing with unequal cluster sizes in cluster randomized trials: A scoping review | |
| CN112470172A (en) | Computational efficiency of symbol sequence analysis using random sequence embedding | |
| AU2021276239A1 (en) | Identifying claim complexity by integrating supervised and unsupervised learning | |
| CN116680401A (en) | Document processing method, document processing device, apparatus and storage medium | |
| CN118096291A (en) | Product recommendation method, device, equipment and storage medium | |
| CN113591458B (en) | Medical term processing method, device, equipment and storage medium based on neural network | |
| CN113435741A (en) | Training plan generation method, device, equipment and storage medium | |
| CN112988699B (en) | Model training method, and data label generation method and device | |
| Slabchenko et al. | Development of models for imputation of data from social networks on the basis of an extended matrix of attributes | |
| Sánchez-Gutiérrez et al. | Addressing the class imbalance in tabular datasets from a generative adversarial network approach in supervised machine learning | |
| US20220277209A1 (en) | Provider performance scoring using supervised and unsupervised learning | |
| CN117312533B (en) | Text generation method, device, equipment and medium based on artificial intelligent model | |
| US20230281275A1 (en) | Identification method and information processing device | |
| Korolev et al. | Applying Time Series for Background User Identification Based on Their Text Data Analysis |
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 |