Insurance product recommendation method and device, electronic equipment and storage medium

Abstract

The invention provides an insurance product recommendation method and device, electronic equipment and a storage medium, belongs to the technical field of data processing, and is suitable for the field of financial science and technology. The method comprises the following steps: acquiring target insurance product information, and creating a plurality of to-be-selected risk assessment elements for the target insurance product information; creating at least one piece of corresponding condition option information for each to-be-selected risk assessment element; any at least two to-be-selected risk assessment elements are selected from the multiple to-be-selected risk assessment elements, and initial recommendation information is formed based on the selected at least two to-be-selected risk assessment elements and the corresponding condition option information; establishing a corresponding preferential level for each piece of initial recommendation information, and obtaining each piece of corresponding target recommendation information based on each piece of initial recommendation information and the corresponding preferential level; and pushing corresponding target recommendation information to the target object according to a selection instruction of the target object for the plurality of to-be-selected risk assessment elements and the corresponding condition option information. The insurance product recommendation efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, is applicable to the field of financial technology, and in particular, to an insurance product recommendation method and device, electronic equipment, and storage medium. Background Art

[0002] In recent years, with the development of the economy and society, people have an increasing demand for insurance products to meet various types of protection in production or life. When recommending insurance products, the insurance system will conduct risk assessments for the recipients, thereby providing different preferential strategies for different recipients.

[0003] At present, more and more enterprises are moving towards intelligence, especially in the financial industry. The daily operation of enterprises has become increasingly inseparable from the support of automated products and equipment. Therefore, how to intelligently push insurance products has become a technical problem. In related technologies, there are various risk assessment factors required for insurance product evaluation. However, currently, risk assessment can only be performed manually based on the needs of the object, resulting in a low degree of automation in the process of recommending insurance products, which greatly reduces the efficiency of insurance product recommendations. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose an insurance product recommendation method and device, electronic device and storage medium, which can improve the efficiency of insurance product recommendation.

[0005] To achieve the above-mentioned objectives, the first aspect of an embodiment of the present application proposes an insurance product recommendation method, including: obtaining target insurance product information, and creating multiple risk assessment elements to be selected for the target insurance product information; creating at least one corresponding condition option information for each of the risk assessment elements to be selected; selecting any at least two of the multiple risk assessment elements to be selected, and forming initial recommendation information based on the selected at least two risk assessment elements to be selected and the corresponding condition option information; establishing a corresponding preferential level for each of the initial recommendation information, and obtaining corresponding target recommendation information based on each of the initial recommendation information and the corresponding preferential level; obtaining a selection instruction for the target object based on the target insurance product information for the multiple risk assessment elements to be selected and the corresponding condition option information, determining any one of the matching initial recommendation information according to the selection instruction, and pushing the corresponding target recommendation information to the target object.

[0006] In some embodiments, the method of obtaining the target object's selection instructions for multiple risk assessment elements to be selected and the corresponding condition option information based on the target insurance product information, determining any one of the matching initial recommendation information according to the selection instructions, and pushing the corresponding target recommendation information to the target object includes: displaying each of the risk assessment elements to be selected and the corresponding condition option information in a preset display interface; in response to the target object's selection instructions on the display interface, selecting at least two target risk assessment elements from the multiple risk assessment elements to be selected, and selecting the corresponding condition option information as the target condition option information; when the target risk assessment element and the target condition option information match any one of the initial recommendation information, pushing the corresponding target recommendation information to the target object.

[0007] In some embodiments, the risk assessment factors to be selected are obtained from a preset database, and the insurance product recommendation method also includes: obtaining coding information, data types and operators of risk assessment factors; generating original risk assessment factors based on the coding information, the data types and the operators; and using the original risk assessment factors as the risk assessment factors to be selected and storing them in the database.

[0008] In some embodiments, establishing a corresponding preferential level for each of the initial recommendation information, and obtaining corresponding target recommendation information based on each of the initial recommendation information and the corresponding preferential level, includes: creating multiple identity attribute information to be selected for the target insurance product information; establishing a corresponding preferential level for each of the initial recommendation information under different identity attribute information to be selected, and obtaining corresponding target recommendation information based on each of the initial recommendation information and the corresponding preferential level; when the target risk assessment factor and the target condition option information match any of the initial recommendation information, pushing the corresponding target recommendation information to the target object, includes: obtaining the target identity attribute information of the target object; matching among multiple initial recommendation information based on the target identity attribute information, the target risk assessment factor and the target condition option information, and pushing the corresponding target recommendation information to the target object according to the matched initial recommendation information.

[0009] In some embodiments, the insurance product recommendation method also includes: obtaining multiple historical selection instructions of the target object for multiple risk assessment elements to be selected based on the target insurance product information in history; sorting the number of selections of multiple risk assessment elements to be selected from most to least according to the multiple historical selection instructions to obtain a sorting result; determining, according to the sorting result, that the risk assessment element to be selected is the risk assessment element to be adjusted, deleting the risk assessment element to be adjusted and adjusting the preferential level of the corresponding initial recommendation information to obtain updated target recommendation information.

[0010] In some embodiments, the insurance product recommendation method also includes: obtaining newly created additional risk assessment elements for the target insurance product information; selecting any one of the initial recommendation information as the recommendation information to be combined, and determining the association result between the additional risk assessment element and the recommendation information to be combined; updating the preferential level corresponding to the recommendation information to be combined based on the association result to obtain an updated preferential level; adding the additional risk assessment element to the recommendation information to be combined, and obtaining an updated target recommendation information based on the updated preferential level.

[0011] In some embodiments, the selecting of any one of the initial recommendation information as the recommendation information to be combined and determining the association result between the newly added risk assessment factor and the recommendation information to be combined includes: extracting a first semantic feature of the newly added risk assessment factor and extracting a second semantic feature of the recommendation information to be combined; inputting the first semantic feature and the second semantic feature into a pre-trained association evaluation model to obtain the association result between the newly added risk assessment factor and the recommendation information to be combined.

[0012] To achieve the above-mentioned purpose, the second aspect of an embodiment of the present application proposes an insurance product recommendation device, including: a risk assessment element creation module, used to obtain target insurance product information and create multiple risk assessment elements to be selected for the target insurance product information; a condition option information creation module, used to create at least one corresponding condition option information for each of the risk assessment elements to be selected; an element combination module, used to select any at least two of the multiple risk assessment elements to be selected, and form initial recommendation information based on the selected at least two risk assessment elements to be selected and the corresponding condition option information; a preferential level configuration module, used to establish a corresponding preferential level for each of the initial recommendation information, and obtain corresponding target recommendation information based on each of the initial recommendation information and the corresponding preferential level; a recommendation module, used to obtain a selection instruction of the target object for the multiple risk assessment elements to be selected and the corresponding condition option information based on the target insurance product information, determine any one of the matching initial recommendation information according to the selection instruction, and push the corresponding target recommendation information to the target object.

[0013] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the insurance product recommendation method described in the first aspect when executing the computer program.

[0014] To achieve the above objectives, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the insurance product recommendation method described in the first aspect.

[0015] The insurance product recommendation method and device, electronic device and storage medium proposed in the present application obtain target insurance product information, create multiple risk assessment elements to be selected for the target insurance product information, create at least one corresponding condition option information for each risk assessment element to be selected, select any at least two from the multiple risk assessment elements to be selected, and form initial recommendation information based on the selected at least two risk assessment elements to be selected and the corresponding condition option information, thereby forming a risk assessment element combination composed of different risk assessment elements to be selected and the corresponding condition option information; then, establish a corresponding preferential level for each initial recommendation information, obtain corresponding target recommendation information based on each initial recommendation information and the corresponding preferential level, so that different risk assessment element combinations are pre-configured with corresponding preferential levels; in the application process, the target object can obtain the selection instruction for multiple risk assessment elements to be selected and the corresponding condition option information based on the target insurance product information, determine any matching initial recommendation information according to the selection instruction, thereby find the risk assessment element combination that meets the needs of the target object, and finally push the corresponding target recommendation information to the target object, and then automatically push the matching preferential information to the target object. Therefore, the embodiment of the present application can improve the degree of automation in the insurance product recommendation process, thereby improving the efficiency of insurance product recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of the insurance product recommendation method provided in an embodiment of the present application;

[0017] Figure 2 yes Figure 1 Flow chart of step S105 in FIG.

[0018] Figure 3 is a flow chart of an insurance product recommendation method provided by another embodiment of the present application;

[0019] Figure 4 It is a schematic diagram of the application of the database provided in the embodiment of the present application;

[0020] Figure 5 yes Figure 1 Flow chart of step S104 in FIG.

[0021] Figure 6 yes Figure 1 Another flowchart of step S105 in;

[0022] Figure 7 It is a schematic diagram of the insurance system control process provided by the embodiment of the present application;

[0023] Figure 8 is a flow chart of an insurance product recommendation method provided by another embodiment of the present application;

[0024] Fig. 9 is a flow chart of an insurance product recommendation method provided by another embodiment of the present application;

[0025] Fig.10 yes Fig. 9 Flow chart of step S702 in FIG.

[0026] Fig.11 is a schematic diagram of the structure of the insurance product recommendation device provided in an embodiment of the present application;

[0027] Fig.12 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0029] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0031] First, some nouns involved in this application are analyzed:

[0032] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0033] In recent years, with the development of the economy and society, people have an increasing demand for insurance products to meet various types of protection in production or life. When recommending insurance products, the insurance system will conduct risk assessments for the recipients, thereby providing different preferential strategies for different recipients.

[0034] At present, more and more enterprises are moving towards intelligence, especially in the financial industry. The daily operation of enterprises has become increasingly inseparable from the support of automated products and equipment. Therefore, how to intelligently push insurance products has become a technical problem. In related technologies, the risk assessment factors required for insurance product evaluation are diverse. For example, the risk assessment factors in auto insurance products include different renewal histories, vehicle service life, and safe driving records, etc. However, at present, risk assessment can only be performed manually based on the needs of the object, resulting in a low degree of automation in the process of recommending insurance products, which greatly reduces the efficiency of insurance product recommendations.

[0035] Based on this, the embodiments of the present application provide an insurance product recommendation method and device, an electronic device and a storage medium, aiming to improve the quality of insurance product recommendations.

[0036] The insurance product recommendation method and device, electronic device and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the insurance product recommendation method in the embodiments of the present application is described.

[0037] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0038] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0039] The insurance product recommendation method provided in the embodiment of the present application relates to the field of artificial intelligence technology. The insurance product recommendation method provided in the embodiment of the present application can be applied to a terminal or system, can be applied to a server side, or can be software running in a terminal or server side. In some embodiments, the terminal or system can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the insurance product recommendation method, etc., but is not limited to the above forms.

[0040] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0041] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first. For example, when obtaining target insurance product information, user selection instructions, etc., it is necessary to obtain the user's permission or consent first. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for enabling the normal operation of the embodiment of the present application will be obtained.

[0042] Figure 1 is an optional flow chart of the insurance product recommendation method provided in the embodiment of the present application. Figure 1The method may include but is not limited to steps S101 to S105.

[0043] Step S101, obtaining target insurance product information, and creating a plurality of risk assessment elements to be selected for the target insurance product information;

[0044] Step S102, creating at least one corresponding condition option information for each risk assessment factor to be selected;

[0045] Step S103, selecting at least two of the multiple risk assessment elements to be selected, and forming initial recommendation information based on the selected at least two risk assessment elements to be selected and the corresponding condition option information;

[0046] Step S104, establishing a corresponding preferential level for each initial recommendation information, and obtaining corresponding target recommendation information based on each initial recommendation information and the corresponding preferential level;

[0047] Step S105, obtaining the target object's selection instructions for multiple candidate risk assessment factors and corresponding condition option information based on the target insurance product information, determining any matching initial recommendation information according to the selection instructions, and pushing the corresponding target recommendation information to the target object.

[0048] In the above step S101, the target insurance product information refers to the specific insurance product that the insurance system wants to recommend to the target object. The target insurance product information includes the type of product, such as auto insurance, health insurance, etc., and may also include the coverage, premium standards, compensation conditions, etc. of the insurance product. The embodiment of this application does not make specific restrictions on this.

[0049] In an embodiment of the present application, based on the characteristics and market positioning of the target insurance product, a series of risk assessment factors that may affect the premium, coverage or preferential policies can be set for the insurance product and used as optional risk assessment factors. The optional risk assessment factors are optional risk assessment factors created for the target insurance product information, which can help the insurance system evaluate the risk level of the target object, thereby determining the setting of insurance premiums and insurance terms. Therefore, the risk assessment factors can also be called "conversion hooks". By comprehensively considering these factors, the insurance system can more accurately evaluate potential claims risks and provide more personalized and suitable insurance plans for the target object.

[0050] Furthermore, depending on the target insurance product information, the risk assessment factors to be selected are also different. For example, if the target insurance product information is auto insurance, the risk assessment factors to be selected may include the vehicle's renewal history, the vehicle's age and the owner's safe driving record, etc. If the target insurance product information is health insurance, the risk assessment factors to be selected may include the target object's renewal history, age and medical history record, etc.

[0051] In the above step S102, after determining the risk assessment elements to be selected, the embodiment of the present application needs to define a series of conditional option information for each element, and these conditional options are used to describe the specific state or value of the element, so as to make selections according to the actual situation of the target object in the subsequent steps. For example, if the target insurance product is auto insurance, and a risk assessment element to be selected is the age of the vehicle, then under the element of the age of the vehicle, multiple conditional option information such as "within 1 year", "1-3 years", "3-5 years" can be set.

[0052] In the above step S103, the embodiment of the present application needs to select any at least two from a plurality of risk assessment factors to be selected, and form initial recommendation information based on the selected at least two risk assessment factors to be selected and the corresponding conditional option information. Therefore, different combinations of risk assessment factors are possible, so as to cover a wider range of risk assessment scenarios, and by selecting at least two risk assessment factors to be selected, it is ensured that the initial recommendation information formed each time is based on a comprehensive consideration of a plurality of risk assessment factors to be selected, rather than the decision of a single factor, which helps to improve the accuracy and comprehensiveness of the recommendation. For example, if the target insurance product is auto insurance, the risk assessment factors to be selected include the renewal history of the vehicle, the age of the vehicle, and the safe driving record of the owner, etc., then any two of the renewal history of the vehicle, the age of the vehicle, and the safe driving record of the owner can be selected as a combination, or the three of the renewal history of the vehicle, the age of the vehicle, and the safe driving record of the owner can be selected as a combination.

[0053] After selecting the risk assessment factors, the system will construct the initial recommendation information based on the conditional option information corresponding to each factor. By combining different risk assessment factors and their conditional option information, the system can generate multiple possible initial recommendation information, each of which represents a specific risk assessment scenario and preferential policy configuration.

[0054] In the above step S104, the embodiment of the present application can establish a corresponding preferential level for each initial recommendation information, and obtain corresponding target recommendation information based on each initial recommendation information and the corresponding preferential level. Different risk assessment factor combinations are set with different preferential levels, so that different risk assessment results or different target objects can enjoy different degrees of preferential treatment.

[0055] Furthermore, each initial recommendation information will be assigned one or more corresponding preferential levels. This mapping relationship enables the embodiment of the present application to quickly determine and push corresponding preferential information when the target object selects a specific risk assessment factor combination, and different preferential levels correspond to specific preferential items. For example, the higher the level, the greater the preferential margin, and vice versa. The preferential level can be dynamically adjusted according to market demand, competitive environment, and the operating strategy of the insurance system.

[0056] The target recommendation information not only includes the risk assessment factor combination in the initial recommendation information, but also includes the corresponding preferential level, so that the target object can clearly understand the preferential treatment it will receive when receiving the recommendation. Once the target recommendation information is formed, the embodiment of the present application is ready to push this information to the target object.

[0057] In the above step S105, the embodiment of the present application can obtain the target object's selection instructions for multiple risk assessment elements to be selected and corresponding condition option information based on the target insurance product information, determine any matching initial recommendation information according to the selection instructions, and push the corresponding target recommendation information to the target object. Specifically, the embodiment of the present application will first display the target insurance product information to the target object, and list multiple risk assessment elements to be selected and their corresponding condition option information. The target object will select or enter relevant risk assessment elements and condition options on the interface according to its own situation and needs. After the embodiment of the present application collects the selection instructions of the target object through the front-end interface, it will transmit these data back to the back-end server for further processing.

[0058] Next, the embodiment of the present application will search for matching records in the pre-generated initial recommendation information library according to the selection instruction of the target object, perform logical matching, and check whether the selected risk assessment factors and condition options selected by the target object are completely consistent with a certain initial recommendation information or meet the defined range. It should be pointed out that the matching logic can be adjusted according to actual needs, such as allowing a certain degree of fuzzy matching or matching according to priority, etc. Once the matching initial recommendation information is found, the embodiment of the present application will recommend the target recommendation information composed of the risk assessment factor combination and the corresponding preferential level in the information to the target object. Therefore, when the target object views or receives the target recommendation information, it can obtain the risk assessment factor combination and the corresponding preferential level selected by itself.

[0059] It should be noted that in the embodiment of the present application, by allowing the target object to select risk assessment factors and condition option information according to its own situation, it is possible to generate recommendation information that better meets its personalized needs, thereby improving the user experience. And by pushing preferential information closely related to the target object, it helps to stimulate its desire to buy, thereby increasing the conversion rate of insurance products. Furthermore, through automated execution, the need for manual intervention is reduced, and the efficiency and accuracy of insurance product recommendations are improved.

[0060] In summary, through the above steps S101 to S105, the embodiment of the present application obtains the target insurance product information, creates multiple risk assessment factors to be selected for the target insurance product information, creates at least one corresponding condition option information for each risk assessment factor to be selected, selects any at least two from the multiple risk assessment factors to be selected, and forms initial recommendation information based on the selected at least two risk assessment factors to be selected and the corresponding condition option information, thereby forming a risk assessment factor combination composed of different risk assessment factors to be selected and the corresponding condition option information; then, establishes a corresponding preferential level for each initial recommendation information, and obtains corresponding target recommendation information based on each initial recommendation information and the corresponding preferential level, so that different risk assessment factor combinations are pre-configured with corresponding preferential levels; in the application process, the target object can obtain the selection instructions for the multiple risk assessment factors to be selected and the corresponding condition option information based on the target insurance product information, and determine any matching initial recommendation information according to the selection instructions, so as to find the risk assessment factor combination that meets the needs of the target object, and finally pushes the corresponding target recommendation information to the target object, and the matching preferential information can be automatically pushed to the target object. Therefore, the embodiments of the present application can improve the degree of automation in the insurance product recommendation process, thereby improving the efficiency of insurance product recommendations.

[0061] See also Figure 2 In some embodiments, step S105 may include but is not limited to steps S201 to S203:

[0062] Step S201, displaying each risk assessment factor to be selected and corresponding condition option information in a preset display interface;

[0063] Step S202, in response to a selection instruction of the target object on the display interface, selecting at least two target risk assessment elements from a plurality of risk assessment elements to be selected, and selecting corresponding condition option information as target condition option information;

[0064] Step S203: When the target risk assessment factor and the target condition option information match any initial recommendation information, the corresponding target recommendation information is pushed to the target object.

[0065] In the above steps, it is specifically described how to obtain the target object's selection instructions for risk assessment factors and condition option information in the actual application process, and determine the matching initial recommendation information based on this, and then push the corresponding target recommendation information.

[0066] Specifically, in the embodiment of the present application, the input information of the target object can be obtained through visual interaction, specifically including displaying each selected risk assessment element and the corresponding condition option information in a preset display interface, thereby providing a clear interface for the target object, displaying all the selectable risk assessment elements and the condition option information corresponding to each element. Furthermore, the selected risk assessment elements can be displayed in the form of a list, table or card, and the corresponding condition option information is listed next to each element to ensure that all information is clear and easy to read, including the name, description and specific content of the condition option of the risk assessment element, and provide intuitive interaction methods, such as check boxes, drop-down menus or radio buttons, etc., to facilitate the target object to make a selection.

[0067] Subsequently, in response to the selection instruction of the target object on the display interface, at least two target risk assessment elements are selected from a plurality of risk assessment elements to be selected, and the corresponding conditional option information is selected as the target conditional option information. Specifically, when a selection operation is detected, the embodiment of the present application extracts the selected risk assessment element and the corresponding conditional option information as the target risk assessment element and the target conditional option information. Furthermore, the embodiment of the present application may add some verification logic to ensure that the target object has selected at least two risk assessment elements to be selected, and each element has selected at least one conditional option information.

[0068] When the target risk assessment factor and target condition option information match any of the initial recommendation information, the corresponding target recommendation information is pushed to the target object. Specifically, after obtaining the selection instruction, the embodiment of the present application compares the target risk assessment factor and target condition option information selected by the target object with the records in the pre-generated initial recommendation information library, and screens out the initial recommendation information that fully matches the target object selection or meets the preset matching rules. According to the matching results, the corresponding target recommendation information is determined and automatically sent to the target object by email, SMS, APP push, or display on a preset display interface, thereby realizing the automatic push from the selection of the target object to the final recommendation information, greatly improving the automation and efficiency of insurance product recommendations.

[0069] In some embodiments, the risk assessment factors to be selected are obtained from a preset database, see Figure 3 The insurance product recommendation method may also include but is not limited to steps S301 to S303:

[0070] Step S301, obtaining the coding information, data type and operator of the risk assessment element;

[0071] Step S302, generating original risk assessment factors based on the coding information, data type and operator;

[0072] Step S303: The original risk assessment factors are used as candidate risk assessment factors and stored in a database.

[0073] In the above steps, the steps for preparing and constructing the candidate risk assessment elements are specifically described, which together constitute a process from basic data to candidate elements in practical applications.

[0074] Specifically, in the process of constructing the risk assessment elements to be selected, it is necessary to obtain the coding information, data type and operator of the risk assessment elements. Among them, the coding information is the unique identification of each risk assessment element to be selected. This identification is realized through the coding information. The coding information can be numbers, letters or a combination of them, which is used to uniquely identify and reference specific risk assessment elements to be selected in the system. The data type specifies how the value of the risk assessment element to be selected should be understood and processed by the system. For example, age is an integer type, while the vehicle type may be a string type. Clarifying the data type is crucial for subsequent data processing, analysis and storage. The operator defines how to perform logical judgments or calculations based on the value of the risk assessment element to be selected. For example, when judging whether the age exceeds a certain threshold, the "greater than" operator may be used. Therefore, the choice of operator depends on the specific needs and application scenarios of the risk assessment elements to be selected.

[0075] After obtaining the coding information, data types and operators, raw risk assessment elements can be generated. Raw risk assessment elements contain all the basic information required to define the risk assessment logic, but have not yet been associated with specific insurance products or target objects.

[0076] Finally, after the generation of the original risk assessment elements is completed, these elements are formally included in the selection range and stored in the system's database to facilitate subsequent retrieval, updating and use of these elements. The database design in the embodiment of the present application should take into account factors such as efficiency, scalability and security. For example, the retrieval efficiency can be improved through a reasonable indexing strategy, and the security of sensitive data can be protected through encryption measures. And storing the selected risk assessment elements in the database also provides a data basis for the subsequent automated recommendation process. When it is necessary to generate recommendation information for a specific insurance product or target object, the embodiment of the present application can retrieve the relevant selected risk assessment elements from the database, and form the final recommendation information based on the combination of these elements and conditional options.

[0077] If an initial recommendation information is used as a scenario, that is, the combination of multiple candidate risk assessment factors and the corresponding condition option information forms a specific insurance demand scenario, then Figure 4 The following are examples of the application of the above databases. Figure 4 , Figure 4 This is a schematic diagram of the application of the database provided in the embodiment of the present application. In the figure, after the developer has created the database and stored multiple specific scenarios, the operator can query the scenarios through the database to obtain the task details of each initial recommendation information, and even understand the specific discount level; the developer can also add scenarios, modify scenarios, delete scenarios, and perform other operations. In addition, through the database, message management can also be performed to obtain input information on the display interface, and to call or cancel related initial recommendation information.

[0078] See also Figure 5 In some embodiments, step S104 may include but is not limited to steps S401 to S402:

[0079] Step S401, creating multiple identity attribute information to be selected for target insurance product information;

[0080] Step S402, under different identity attribute information to be selected, a corresponding preferential level is established for each initial recommendation information, and corresponding target recommendation information is obtained based on each initial recommendation information and the corresponding preferential level;

[0081] Based on this, see Figure 6 In some embodiments, step S105 may also include but is not limited to steps S401 to S402:

[0082] Step S501, obtaining target identity attribute information of a target object;

[0083] Step S502: matching is performed among multiple initial recommendation information based on target identity attribute information, target risk assessment factors and target condition option information, and corresponding target recommendation information is pushed to the target object according to the matched initial recommendation information.

[0084] In the above steps, in addition to considering risk assessment factors (such as renewal history, vehicle age, etc.), the identity attributes of the target object are also important factors affecting the recommendation results and preferential strategies. If the target object permits, the identity attributes may include age, gender, occupation, region, etc., to help the insurance system locate the target group more accurately and design more targeted preferential strategies accordingly.

[0085] Specifically, the embodiment of the present application will preset multiple possible identity attribute information as candidate items according to the characteristics of the target insurance product and market demand. These candidate identity attribute information will be used in the subsequent recommendation logic to match and recommend according to the actual identity attributes of the target object. Then, under different candidate identity attribute information, a corresponding preferential level is established for each initial recommendation information, and the corresponding target recommendation information is obtained based on each initial recommendation information and the corresponding preferential level. Each target recommendation information is targeted at a specific risk assessment factor combination and identity attribute combination, and is accompanied by a corresponding preferential level, so that the recommendation results are more personalized and accurate.

[0086] For example, for the same auto insurance product, the present application embodiment will provide a lower premium discount for young drivers (one identity attribute) because they may be more inclined to use new technologies and maintain good driving habits. For high-income people (another identity attribute), the present application embodiment will provide a higher insurance amount recommendation to meet their higher protection needs.

[0087] Furthermore, during the recommendation process, the embodiment of the present application needs to obtain the actual identity attribute information input by the target object, that is, the target identity attribute information. After obtaining the identity attribute information of the target object, the embodiment of the present application will match multiple initial recommendation information based on this information and the target risk assessment factors and target condition option information selected by the target object. Once the matching initial recommendation information is found, the embodiment of the present application will recommend the corresponding target recommendation information to the target object. In this way, the target object can receive an insurance product recommendation plan tailored to its personal situation and needs, including specific insurance products, premiums, insured amounts, and corresponding preferential information, thereby realizing intelligent recommendations of insurance products, improving the automation and efficiency of the recommendation process, and improving customer experience and satisfaction.

[0088] The following is an example of the insurance product recommendation method in the above embodiment.

[0089] See also Figure 7 , Figure 7It is a schematic diagram of the control flow of the insurance system provided by the embodiment of the present application. In the figure, the insurance system can be provided with three processes of data collection, condition arrangement and execution action. Among them, in the data collection process, the financial system can obtain the target insurance product information from the message queue (Message Queue, MQ) task data and the application programming interface (Application Programming Interface, API) task data, and obtain multiple risk assessment elements to be selected for the target insurance product information from the MQ task data and the API task data. Then, in the condition arrangement process, at least one corresponding condition option information is created for each risk assessment element to be selected, and condition arrangement is performed, wherein Freemarker can be used to write an execution script, thereby selecting at least two of the multiple risk assessment elements to be selected, and initial recommendation information is formed based on the selected at least two risk assessment elements to be selected and the corresponding condition option information, and corresponding preferential levels are established for each initial recommendation information, and finally an execution script is generated, and corresponding target recommendation information is obtained based on each initial recommendation information and the corresponding preferential level, and the calculation result is output through Aviator call, that is, each target recommendation information is output. Finally, during the execution of the action, information can be sent, including sending each target recommendation information, and obtaining the target object's selection instructions for multiple candidate risk assessment factors and corresponding condition option information based on the target insurance product information, determining any matching initial recommendation information according to the selection instruction, and pushing the corresponding target recommendation information to the target object. In addition, during the execution of the action, the number of draws can be increased, and some other discounts can be added to the target insurance product, and there is no specific restriction on this.

[0090] The above embodiment is further described below from the perspective of different execution stages of the insurance product recommendation method. The insurance product recommendation method may include a research and development stage, an online implementation and optimization stage, and a user interaction optimization stage.

[0091] (1) Research and development stage:

[0092] First, we can comprehensively deconstruct the risk assessment elements (conversion hooks) to ensure that each risk assessment element can exist independently and be traceable. We can also build a preset database to store the risk assessment elements, allow the registration of new risk assessment element hooks, and pay attention to the coding information, data type and operator of each risk assessment element to be selected, so as to achieve standardized management of the risk assessment elements to be selected. In addition, we can also design an intelligent template engine to automatically generate dynamic scripts based on the combination to simplify the production and launch process. At the same time, we integrate advanced calculation engines to instantly parse conditional logic to ensure calculation accuracy and efficiency.

[0093] (2) Online implementation and optimization:

[0094] Today, the system can provide an intuitive display interface to easily configure the risk assessment factors, condition option information, and identity attribute information to be selected. After the configuration is completed, the system will automatically generate accurate calculation expressions without manual intervention. Finally, it will be put online for real-time condition judgment to ensure seamless connection with operational activities.

[0095] (3) User interaction optimization:

[0096] During the operation of the financial system, the input data on the display interface can be collected in real time, covering key indicators such as clicks, browsing, and orders. The target object can also obtain the selection instructions for multiple risk assessment elements and corresponding condition option information based on the target insurance product information, dynamically generate personalized calculation expressions, and convert the data into the required format for calculation in real time. Finally, the condition matching calculation is completed quickly, the target recommendation information is output, and the downstream incentive system is delivered to improve the experience and participation.

[0097] In summary, the financial system in the embodiment of the present application can adjust the risk assessment factor combination and condition option information in real time by executing the insurance product recommendation method, realize the rapid iteration of complex scenarios, reduce the time cost and technical threshold of adjustment, and enable the risk assessment factors to keep up with market changes and object needs. In addition, the significant improvement in automation efficiency, through the generation and calculation process of automated expressions, not only greatly reduces manual errors and script writing workload, but also speeds up the conversion speed from configuration to actual execution, and improves the response efficiency and accuracy of overall operational conversion. Finally, the strengthening of data-driven decision-making, through real-time collection and analysis of user behavior data, the framework promotes the data-driven decision-making process, makes operational decisions more scientific and accurate, and provides strong support for continuous optimization of object journeys and improved conversion rates.

[0098] In some embodiments, the present application embodiment can also adjust the target recommendation information according to the historical selection of the risk assessment factors to be selected, see Figure 8 The insurance product recommendation method may also include but is not limited to steps S601 to S603:

[0099] Step S601, obtaining a plurality of historical selection instructions of a target object for a plurality of risk assessment elements to be selected based on target insurance product information in history;

[0100] Step S602, sorting the selection times of multiple risk assessment elements to be selected from most to least according to multiple historical selection instructions to obtain a sorting result;

[0101] Step S603: determine, according to the sorting result, the risk assessment factor to be selected at the end of the sorting as the risk assessment factor to be adjusted, delete the risk assessment factor to be adjusted, and adjust the preferential level of the corresponding initial recommendation information to obtain updated target recommendation information.

[0102] In the above steps, in order to further optimize the performance and efficiency of the recommendation system, the embodiment of the present application can focus on dynamically adjusting risk assessment factors and preferential policies based on historical data to ensure that the insurance system can more accurately reflect the preferences and market trends of the target objects.

[0103] Specifically, in the embodiment of the present application, multiple historical selection instructions of the target object for multiple risk assessment elements to be selected based on the target insurance product information in history can be obtained. For example, the system will retrieve and collect the target object's selection records of multiple risk assessment elements for the target insurance product in the past period of time (for example, the past year or more) from its database. These selection records, i.e., historical selection instructions, are the choices made by the target object for each risk assessment element to be selected (such as vehicle age, safe driving record, etc.) based on personal circumstances or preferences when purchasing or consulting insurance products in the past.

[0104] Next, the embodiment of the present application can sort the selection times of multiple risk assessment elements to be selected from most to least according to multiple historical selection instructions to obtain a sorting result. Among them, the system will analyze the collected historical selection instructions and count the number of times each risk assessment element to be selected. Then, based on these statistical results, the system will sort all the risk assessment elements to be selected, with the risk assessment elements with the most selection times at the front and the risk assessment elements with the least selection times at the back, so as to identify which risk assessment elements to be selected are of most concern to the target object and which are relatively less important.

[0105] Finally, according to the sorting result, the risk assessment factors to be selected at the end of the sorting are determined to be risk assessment factors to be adjusted, the risk assessment factors to be adjusted are deleted, and the preferential level of the corresponding initial recommendation information is adjusted to obtain the updated target recommendation information. Based on the sorting results, the embodiment of the present application will identify those risk assessment factors that are selected less times, that is, the risk assessment factors to be selected at the end of the sorting, as risk assessment factors to be adjusted. For these risk assessment factors to be adjusted, the embodiment of the present application deletes them from the risk assessment factor list to reduce the decision-making burden of the target object. At the same time, the embodiment of the present application will also adjust the preferential level of the initial recommendation information formed based on these risk assessment factors according to the adjustment of the risk assessment factors, so that the financial system is more in line with the current user's preferences and market demand, and improves the accuracy and attractiveness of the recommendation.

[0106] Exemplarily, there are multiple ways to adjust the preferential level of the corresponding initial recommendation information to obtain the updated target recommendation information. For example, when a candidate risk assessment factor is determined to be a risk assessment factor to be adjusted and deleted, it is possible to consider increasing the preferential level of the initial recommendation information containing the remaining candidate risk assessment factors, which can motivate the target object to more actively consider these remaining, more popular risk assessment factor combinations; or, based on the importance and attractiveness of the remaining candidate risk assessment factors, reallocate preferential resources, such as the preferential treatment originally allocated to the deleted risk assessment factor can be partially or completely transferred to other candidate risk assessment factors, or used to create new, more attractive preferential strategies; or, it is also possible to consider introducing new preferential strategies to attract target objects, for example, providing additional value-added services, point rewards or long-term discounts to target objects who choose the remaining candidate risk assessment factor combinations.

[0107] Finally, after adjusting the above steps, the embodiment of the present application will obtain updated target recommendation information, which will more accurately match the actual needs and preferences of the target objects, thereby improving the efficiency and satisfaction of insurance product recommendations.

[0108] In some embodiments, the present application can also receive newly created risk assessment elements and add and adjust them to the original recommendation information. Fig. 9 The insurance product recommendation method may also include but is not limited to steps S701 to S704:

[0109] Step S701, obtaining newly created and added risk assessment elements for target insurance product information;

[0110] Step S702, selecting any initial recommendation information as the recommendation information to be combined, and determining the association result between the newly added risk assessment factor and the recommendation information to be combined;

[0111] Step S703, updating the preferential level corresponding to the recommended information to be combined based on the association result to obtain an updated preferential level;

[0112] Step S704: Add the newly added risk assessment factor to the recommendation information to be combined, and obtain updated target recommendation information based on the updated preferential level.

[0113] In the above steps, step S701 to step S704 are an extended process in the insurance product recommendation method, which is used to handle the situation of newly added risk assessment factors, ensuring that the recommendation system can flexibly respond to new risk assessment requirements while maintaining the accuracy and attractiveness of the recommended information.

[0114] Specifically, the embodiment of the present application can obtain newly created risk assessment factors for target insurance product information. In practical applications, with changes in the market, etc., it is necessary to introduce new risk assessment factors to more accurately assess risks, so as to provide insurance product recommendations that better meet market demand. These newly added risk assessment factors may involve multiple aspects such as personal characteristics, behavioral data, and historical records of newly considered objects in the process of purchasing insurance products.

[0115] Subsequently, any one of the initial recommendation information is selected as the recommendation information to be combined, and the association result between the newly added risk assessment factor and the recommendation information to be combined is determined. This embodiment of the application needs to select one or more from one or more existing initial recommendation information as "recommendation information to be combined", and these initial recommendation information are formed based on the previously defined risk assessment factors and conditional option information. Then, this embodiment of the application needs to analyze the correlation or compatibility between the newly added risk assessment factors and these recommendation information to be combined, in order to determine whether and how the newly added risk assessment factors affect the existing recommendation information.

[0116] Next, the preferential level corresponding to the recommended information to be combined is updated based on the association result to obtain an updated preferential level. After determining the association result between the newly added risk assessment factor and the recommended information to be combined, the embodiment of the present application needs to adjust the preferential level corresponding to the recommended information to be combined according to this result. This is because the newly added risk assessment factor may change the risk assessment result, thereby affecting the pricing and preferential strategy of the target insurance product. The system calculates the new preferential level through a certain algorithm or business rule to ensure that the recommended information is in the interests of the insurance company and can attract target customers.

[0117] Finally, the newly added risk assessment factors are added to the recommended information to be combined, and the updated target recommendation information is obtained based on the updated preferential level. The embodiment of the present application adds the newly added risk assessment factors to the selected recommended information to be combined to form new recommendation information containing more risk assessment factors. At the same time, according to the calculated updated preferential level, the embodiment of the present application generates the corresponding updated target recommendation information, which not only contains more risk assessment factors, but also has attractive preferential strategies, so as to more accurately meet the needs of the target objects and improve the efficiency and success rate of insurance product recommendations.

[0118] See also Fig.10 In some embodiments, step S702 may include but is not limited to steps S801 to S802:

[0119] Step S801, extracting a first semantic feature of a newly added risk assessment factor, and extracting a second semantic feature of the recommendation information to be combined;

[0120] Step S802: input the first semantic feature and the second semantic feature into a pre-trained association evaluation model to obtain an association result between the newly added risk assessment factor and the recommended information to be combined.

[0121] In the above steps, step S801 and step S802 are the refinement process of determining the association result between the newly added risk assessment factors and the recommended information to be combined in step S702. These two steps use natural language processing (NLP) and machine learning (ML) technology to automatically analyze and evaluate the association between the two.

[0122] Specifically, the embodiment of the present application needs to extract the first semantic feature of the newly added risk assessment element, and extract the second semantic feature of the recommended information to be combined. The first semantic feature is to extract key information and meaning from the newly added risk assessment element, which can express the semantics of the newly added risk assessment element. Exemplarily, NLP techniques such as word segmentation, part-of-speech tagging, named entity recognition, etc. can be used to convert text into a structured data form, and then, word vectors (such as Word2Vec, G l oVe) or more advanced models (such as BERT, GPT, etc.) may be used to convert the text into high-dimensional semantic vectors, which can capture the semantic relationship between texts. The second semantic feature is similar to the first semantic feature extraction, but the semantic information extracted from the recommended information to be combined.

[0123] It should be noted that the association evaluation model is a pre-trained machine learning or deep learning model, and its function is to evaluate the association or correlation between two texts (or semantic vectors). The association evaluation model is obtained by training with text pairs marked with the degree of association as training data, or by unsupervised learning training, and the embodiments of the present application do not impose specific restrictions on this. For the association evaluation model, it can use the first semantic feature and the second semantic feature as input data, that is, obtain the high-dimensional semantic vectors of the two texts, and then output an association result. The association result can be a numerical value (such as a floating point number between 0 and 1), indicating the degree of association or the strength of correlation between the newly added risk assessment factor and the recommended information to be combined.

[0124] Exemplarily, the associated evaluation model can select various types of machine learning or deep learning models, such as logistic regression, support vector machine (SVM), neural network (especially deep neural network such as convolutional neural network CNN, recurrent neural network RNN ​​or Transformer, etc.). The selection and training process of the model will depend on the specific application scenario, data volume and quality, and computing resources, and this embodiment of the application does not impose specific restrictions on this.

[0125] See also Fig.11The embodiment of the present application further provides an insurance product recommendation device, which can implement the above-mentioned insurance product recommendation method, and the device includes:

[0126] The risk assessment element creation module 1101 is used to obtain target insurance product information and create a plurality of risk assessment elements to be selected for the target insurance product information;

[0127] The condition option information creation module 1102 is used to create at least one corresponding condition option information for each risk assessment factor to be selected;

[0128] The element combination module 1103 is used to select at least two of the risk assessment elements to be selected, and form initial recommendation information based on the selected at least two risk assessment elements to be selected and the corresponding condition option information;

[0129] The preferential level configuration module 1104 is used to establish a corresponding preferential level for each initial recommendation information, and obtain corresponding target recommendation information based on each initial recommendation information and the corresponding preferential level;

[0130] The recommendation module 1105 is used to obtain the target object's selection instructions for multiple candidate risk assessment factors and corresponding condition option information based on the target insurance product information, determine any matching initial recommendation information according to the selection instructions, and push the corresponding target recommendation information to the target object.

[0131] Exemplarily, the insurance product recommendation device can implement the insurance product recommendation method in the above embodiment, by obtaining the target insurance product information, and creating multiple risk assessment elements to be selected for the target insurance product information, creating at least one corresponding condition option information for each risk assessment element to be selected, selecting any at least two from the multiple risk assessment elements to be selected, and forming initial recommendation information based on the selected at least two risk assessment elements to be selected and the corresponding condition option information, thereby forming a risk assessment element combination composed of different risk assessment elements to be selected and the corresponding condition option information; then, establishing a corresponding preferential level for each initial recommendation information, and obtaining corresponding target recommendation information based on each initial recommendation information and the corresponding preferential level, so that different risk assessment element combinations are pre-configured with corresponding preferential levels; in the application process, the target object can obtain the selection instruction for multiple risk assessment elements to be selected and the corresponding condition option information based on the target insurance product information, and determine any matching initial recommendation information according to the selection instruction, so as to find the risk assessment element combination that meets the needs of the target object, and finally push the corresponding target recommendation information to the target object, and then automatically push the matching preferential information to the target object. Therefore, the embodiment of the present application can improve the degree of automation in the insurance product recommendation process, thereby improving the efficiency of insurance product recommendation.

[0132] The specific implementation of the insurance product recommendation device is basically the same as the specific implementation of the insurance product recommendation method described above, and will not be repeated here. On the premise of meeting the requirements of the embodiment of the present application, the insurance product recommendation device can also be provided with other functional modules to implement the insurance product recommendation method in the above embodiment.

[0133] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned insurance product recommendation method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0134] See also Fig.12 , Fig.12 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0135] The processor 1201 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0136] The memory 1202 may be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1202 may store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1202, and the processor 1201 calls and executes the insurance product recommendation method of the embodiment of this application;

[0137] Input / output interface 1203, used to implement information input and output;

[0138] The communication interface 1204 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WI FI, Bluetooth, etc.);

[0139] A bus 1205 that transmits information between various components of the device (e.g., the processor 1201, the memory 1202, the input / output interface 1203, and the communication interface 1204);

[0140] The processor 1201 , the memory 1202 , the input / output interface 1203 and the communication interface 1204 are connected to each other in communication within the device via the bus 1205 .

[0141] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned insurance product recommendation method is implemented.

[0142] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0143] The insurance product recommendation method and device, electronic device and storage medium provided by the embodiment of the present application obtain target insurance product information, create multiple risk assessment elements to be selected for the target insurance product information, create corresponding at least one condition option information for each risk assessment element to be selected, select any at least two from the multiple risk assessment elements to be selected, and form initial recommendation information based on the selected at least two risk assessment elements to be selected and the corresponding condition option information, thereby forming a risk assessment element combination composed of different risk assessment elements to be selected and the corresponding condition option information; then, establish a corresponding preferential level for each initial recommendation information, obtain corresponding target recommendation information based on each initial recommendation information and the corresponding preferential level, so that different risk assessment element combinations are pre-configured with corresponding preferential levels; in the application process, the target object can obtain the selection instruction for multiple risk assessment elements to be selected and the corresponding condition option information based on the target insurance product information, determine any matching initial recommendation information according to the selection instruction, thereby find the risk assessment element combination that meets the needs of the target object, and finally push the corresponding target recommendation information to the target object, and then automatically push the matching preferential information to the target object. Therefore, the embodiment of the present application can improve the degree of automation in the insurance product recommendation process, thereby improving the efficiency of insurance product recommendation.

[0144] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0145] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0146] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0147] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0148] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0149] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0150] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0151] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0152] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0153] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0154] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for recommending insurance products, characterized in that: include: Obtain target insurance product information, and create multiple risk assessment elements to be selected for the target insurance product information; Creating at least one corresponding condition option information for each of the risk assessment elements to be selected; Selecting at least two of the risk assessment elements to be selected, and forming initial recommendation information based on the selected at least two risk assessment elements to be selected and the corresponding condition option information; Establishing a corresponding preferential level for each of the initial recommendation information, and obtaining corresponding target recommendation information based on each of the initial recommendation information and the corresponding preferential level; Obtain the target object's selection instructions for the multiple risk assessment factors to be selected and the corresponding condition option information based on the target insurance product information, determine any matching initial recommendation information according to the selection instructions, and push the corresponding target recommendation information to the target object.

2. The insurance product recommendation method according to claim 1, characterized in that: The step of obtaining a selection instruction of the target object for the plurality of risk assessment elements to be selected and the corresponding condition option information based on the target insurance product information, determining any one of the matching initial recommendation information according to the selection instruction, and pushing the corresponding target recommendation information to the target object includes: Displaying each of the risk assessment elements to be selected and the corresponding condition option information in a preset display interface; In response to a selection instruction of the target object on the display interface, at least two target risk assessment elements are selected from the plurality of risk assessment elements to be selected, and the corresponding condition option information is selected as the target condition option information; When the target risk assessment factor and the target condition option information match any one of the initial recommendation information, the corresponding target recommendation information is pushed to the target object.

3. The insurance product recommendation method according to claim 1, characterized in that: The risk assessment factors to be selected are obtained from a preset database, and the insurance product recommendation method further includes: Obtain coding information, data types, and operators for risk assessment elements; generating an original risk assessment factor based on the encoding information, the data type, and the operator; The original risk assessment factor is used as the candidate risk assessment factor and stored in the database.

4. The insurance product recommendation method according to claim 1, characterized in that: The step of establishing a corresponding preferential level for each of the initial recommendation information, and obtaining corresponding target recommendation information based on each of the initial recommendation information and the corresponding preferential level, includes: Creating a plurality of identity attribute information to be selected for the target insurance product information; Under different identity attribute information to be selected, a corresponding preferential level is established for each of the initial recommendation information, and corresponding target recommendation information is obtained based on each of the initial recommendation information and the corresponding preferential level; When the target risk assessment factor and the target condition option information match any one of the initial recommendation information, pushing the corresponding target recommendation information to the target object includes: Acquire target identity attribute information of the target object; Based on the target identity attribute information, the target risk assessment factor and the target condition option information, matching is performed in a plurality of the initial recommendation information, and the corresponding target recommendation information is pushed to the target object according to the matched initial recommendation information.

5. The insurance product recommendation method according to claim 1, characterized in that: The insurance product recommendation method further includes: Acquire a plurality of historical selection instructions of the target object for the plurality of risk assessment elements to be selected based on the target insurance product information in history; According to the plurality of historical selection instructions, the selection times of the plurality of risk assessment elements to be selected are sorted from most to least to obtain a sorting result; The risk assessment factor to be selected and located at the end of the sorting is determined as the risk assessment factor to be adjusted according to the sorting result, the risk assessment factor to be adjusted is deleted, and the preferential level of the corresponding initial recommendation information is adjusted to obtain updated target recommendation information.

6. The insurance product recommendation method according to claim 1, characterized in that: The insurance product recommendation method further includes: Acquire newly created additional risk assessment elements for the target insurance product information; Selecting any one of the initial recommendation information as the recommendation information to be combined, and determining the association result between the newly added risk assessment factor and the recommendation information to be combined; Based on the association result, the preferential level corresponding to the recommended information to be combined is updated to obtain an updated preferential level; The newly added risk assessment factor is added to the recommendation information to be combined, and updated target recommendation information is obtained based on the updated preferential level.

7. The insurance product recommendation method according to claim 6, characterized in that: The selecting any one of the initial recommendation information as the recommendation information to be combined, and determining the association result between the newly added risk assessment factor and the recommendation information to be combined, includes: Extracting a first semantic feature of the newly added risk assessment factor, and extracting a second semantic feature of the recommendation information to be combined; The first semantic feature and the second semantic feature are input into a pre-trained association evaluation model to obtain an association result between the newly added risk assessment factor and the recommended information to be combined.

8. An insurance product recommendation device, characterized in that: include: A risk assessment element creation module is used to obtain target insurance product information and create multiple candidate risk assessment elements for the target insurance product information; A condition option information creation module, used to create at least one corresponding condition option information for each of the risk assessment elements to be selected; An element combination module, used to select any at least two of the multiple risk assessment elements to be selected, and form initial recommendation information based on the selected at least two risk assessment elements to be selected and the corresponding condition option information; A preferential level configuration module, used to establish a corresponding preferential level for each of the initial recommendation information, and obtain corresponding target recommendation information based on each of the initial recommendation information and the corresponding preferential level; A recommendation module is used to obtain the target object's selection instructions for multiple selected risk assessment factors and corresponding condition option information based on the target insurance product information, determine any matching initial recommendation information according to the selection instructions, and push the corresponding target recommendation information to the target object.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the insurance product recommendation method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the insurance product recommendation method according to any one of claims 1 to 7 is implemented.

Images