An online insurance product sales system and method based on artificial intelligence

Abstract

The present application relates to an online insurance product sales system based on artificial intelligence, and relates to the field of electric digital data processing, the system comprises: a plurality of training devices, which perform multiple training on a hopfield neural network to obtain an AI sales prediction model; a sales prediction device, which uses the AI sales prediction model to intelligently predict the insurance mark of a current user with respect to a target insurance product within a preset time length after the current time according to a plurality of basic information. The present application also relates to an online insurance product sales method based on artificial intelligence. Through the present application, in the face of the technical problems that future sales data of online insurance products is difficult to be statistically predicted in advance and users with a future order tendency are difficult to guarantee an order, the present application can use an artificial intelligence mode to intelligently predict whether each user will complete the insurance of a target insurance product within a preset time length after the current time according to a plurality of basic information selected in a targeted manner, thereby solving the above technical problems.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of electric digital data processing, and in particular to an online insurance product sales system and method based on artificial intelligence. BACKGROUND

[0002] Insurance, originally intended to be a reliable guarantee, has been extended to a guarantee mechanism. It is a tool for planning personal finances and a basic means of risk management under market economy conditions. It is an important pillar of the financial system and the social security system. Specifically, it refers to a commercial insurance behavior in which the policyholder pays the insurance premium to the insurer according to the contract, and the insurer undertakes the compensation for the property loss caused by the occurrence of the accident as stipulated in the contract, or undertakes the payment of the insurance money when the insured person dies, is disabled, is ill, or meets the conditions stipulated in the contract, such as age and period. With the rapid development of electronic technology and network technology, the sales, display and ordering of insurance and other related behaviors have gradually shifted from offline to online.

[0003] For example, the online insurance product sales system proposed in Chinese invention patent publication CN113888203A includes an identity recognition module for collecting and identifying user information of insurance customers, an analysis module for automatically analyzing the user information of insurance customers to obtain an analysis verification code, a listing module for showing all related insurance products to the insurance customers according to the analysis verification code, a selection module for the insurance customers to select the most suitable insurance product in combination with their own needs and the suggestions of insurance practitioners, an interaction module for establishing a communication platform and a data transmission channel between the insurance customers and the insurance practitioners to facilitate their communication, and an order contract module for the insurance customers to sign an order contract with the insurance company to complete the online sales of insurance products.

[0004] For example, the Chinese invention patent publication CN114049229A proposes a long-risk online insurance policy generation method and generation system. The generation method includes: establishing a policy database; collecting the basic information of the policyholder and verifying it, finally obtaining the identity information of the policyholder; collecting the basic information of the insured person and verifying it, finally obtaining the insurance information of the insured person; determining whether the insured person has the insurance qualification; giving the insurance products that the policyholder can choose; calculating the single product price of the selected insurance product and the combined product price of the selected insurance product and other insurance products according to the insurance product selected by the policyholder and the insurance information of the insured person; and generating the corresponding insurance policy. Through the above content, it can quickly and efficiently generate an insurance policy according to the information data of the policyholder and the insured person, and give personalized policy prices through a neural network model to realize the win-win of the insurance company and the insured person.

[0005] Obviously, the above-mentioned prior art is only limited to the specific process implementation of online insurance product sales, and gives the sales, display and ordering approach and entrance of online insurance products. Artificial intelligence is only used to provide personalized policy prices, and is not used for online insurance product solicitation. Obviously, solicitation is a difficulty for various insurance products, whether online or offline. How to complete the judgment of the ordering tendency of each user through data analysis, and then concentrate limited sales resources to solicit and guide the ordering of users with ordering tendency, so as to avoid the loss of users with ordering tendency, is one of the main problems to be solved by the prior art. SUMMARY

[0006] In order to solve the technical problems in the prior art, the present application provides an online insurance product sales system and method based on artificial intelligence, which can use artificial intelligence mode to realize intelligent prediction of whether the current user will complete the insurance of the target insurance product within a preset length of time after the current time according to the targeted screening of multiple basic information, and pour more sales resources to the current user who will complete the insurance of the target insurance product within a preset length of time after the current time as a user with ordering tendency, and guide the ordering, so as to avoid the loss of users with ordering tendency and improve the statistical efficiency of future online insurance product sales data.

[0007] According to one aspect of the present application, an online insurance product sales system based on artificial intelligence is provided, which comprises:

[0008] a first capturing device configured to acquire a number of times that a current user browses a target insurance product marketing webpage of a set insurance product distributor within a preset time length before a current time and a time length that the current user reads a target insurance product introduction document in the target insurance product marketing webpage of the set insurance product distributor, and use the number of times and the time length as a plurality of attention data of the current user;

[0009] a second capturing device configured to acquire a number of kinds of a plurality of insurance products that are simultaneously sold by the set insurance product distributor, a plurality of numbers of in-force users corresponding to the plurality of insurance products respectively, a plurality of time lengths of obtaining sales licenses corresponding to the plurality of insurance products respectively, and a use time length of a longest use user of the target insurance product, and use the number of kinds, the plurality of numbers of in-force users, the plurality of time lengths of obtaining sales licenses, and the use time length of the longest use user as a plurality of configuration information corresponding to the set insurance product distributor;

[0010] a plurality of training devices configured to perform a plurality of times of training on the Hopfield neural network to obtain a Hopfield neural network after the plurality of times of training, and output the Hopfield neural network after the plurality of times of training as an AI sales prediction model;

[0011] a sales prediction device connected with the first capturing device, the second capturing device, and the plurality of training devices respectively, and configured to intelligently predict a purchase indication of the current user with respect to the target insurance product within a preset time length after the current time according to a past purchase indication of the target insurance product of the current user, age information of the current user, gender information of the current user, the preset time length, the plurality of attention data of the current user, and the plurality of configuration information corresponding to the set insurance product distributor by using the AI sales prediction model.

[0012] The plurality of times of training on the Hopfield neural network to obtain the Hopfield neural network after the plurality of times of training, and outputting the Hopfield neural network after the plurality of times of training as the AI sales prediction model include that the number of times of training on the Hopfield neural network is positively correlated with the number of in-force users of the target insurance product and is positively correlated with a use time length of a longest use user of the target insurance product.

[0013] According to another aspect of the present application, there is provided an online insurance product sales method based on artificial intelligence, the method comprising:

[0014] acquiring a number of times that a current user browses a target insurance product marketing webpage of a set insurance product distributor within a preset time length before a current time and a time length that the current user reads a target insurance product introduction document in the target insurance product marketing webpage of the set insurance product distributor, and using the number of times and the time length as a plurality of attention data of the current user;

[0015] Obtaining the number of types of multiple insurance products sold by the set insurance product dealer at the same time, the number of multiple insurance products corresponding to multiple in-force users, the acquisition time length of multiple sales licenses corresponding to multiple insurance products, and the use time length of the longest user of the target insurance product as the respective configuration information corresponding to the set insurance product dealer;

[0016] Performing multiple training on the Hopfield neural network to obtain the Hopfield neural network after completing the multiple training, and outputting the Hopfield neural network after completing the multiple training as an AI sales prediction model;

[0017] Using the AI sales prediction model to intelligently predict the insurance purchase identification of the current user with respect to the target insurance product within the preset time length after the current time according to the past insurance purchase identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the multiple attention data of the current user, and the respective configuration information corresponding to the set insurance product dealer;

[0018] Among them, the number of times of training performed on the Hopfield neural network to obtain the Hopfield neural network after completing the multiple training, and outputting the Hopfield neural network after completing the multiple training as an AI sales prediction model includes that the number of times of training performed on the Hopfield neural network is positively correlated with the number of in-force users of the target insurance product and is positively correlated with the use time length of the longest user of the target insurance product.

[0019] Therefore, the present application has at least the following four outstanding substantive features:

[0020] Substantive feature one: providing an artificial intelligence solution for intelligently predicting whether the current user of the set insurance product dealer will complete the insurance purchase of the target insurance product within the preset time length after the current time, thereby providing convenience for the statistics of the sales data of the target insurance product and the subsequent centralized sales resource guaranteeing the current user with an existing insurance purchase tendency to perform an online insurance purchase, improving the statistical efficiency of the future sales data of the online insurance product while completing the effective customer acquisition of the online insurance product;

[0021] Substantive feature two: the intelligent prediction of the insurance purchase of the target insurance product is based on an artificial intelligence model with a customized structure, and the artificial intelligence model is an AI sales prediction model, specifically, the AI sales prediction model is a Hopfield neural network after completing multiple training, and the number of times of training performed on the Hopfield neural network is positively correlated with the number of in-force users of the target insurance product and is positively correlated with the use time length of the longest user of the target insurance product, thereby constructing AI sales prediction models with different structures for different insurance products;

[0022] The third substantial feature is that the intelligent prediction of the target insurance product is based on the screening of a plurality of basic information, including the past insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the plurality of attention data of the current user, and the configuration information corresponding to the set insurance product dealer. Specifically, the plurality of attention data of the current user includes the browsing times of the target insurance product marketing webpage of the set insurance product dealer browsed by the current user within the preset time length before the current time and the time length of the target insurance product introduction document read by the current user in the target insurance product marketing webpage of the set insurance product dealer. The configuration information corresponding to the set insurance product dealer includes the number of types of a plurality of insurance products sold by the set insurance product dealer, the number of in-force users corresponding to the plurality of insurance products, the time length of obtaining the sales license corresponding to the plurality of insurance products, and the use time length of the longest user of the target insurance product. The sufficient and comprehensive screening of the plurality of basic information ensures the stability and reliability of the intelligent prediction result.

[0023] The fourth substantial feature is that in each training of the Hopfield neural network, the insurance product of a certain user after a certain historical time is known within a preset time length relative to the target insurance product as a single output content of the Hopfield neural network, and the past insurance product of the certain user, the age information of the certain user, the gender information of the certain user, the preset time length, the plurality of attention data of the certain user, and the configuration information corresponding to the set insurance product dealer as a plurality of input contents of the Hopfield neural network, complete this training, so as to ensure the training effect of each training of the Hopfield neural network. BRIEF DESCRIPTION OF DRAWINGS

[0024] The embodiments of the present application will be described below with reference to the accompanying drawings, in which:

[0025] Figure 1 An internal structure diagram of an online insurance product sales system based on artificial intelligence according to the first embodiment of the present application is shown.

[0026] Figure 2 An internal structure diagram of an online insurance product sales system based on artificial intelligence according to the second embodiment of the present application is shown.

[0027] Figure 3 An internal structure diagram of an online insurance product sales system based on artificial intelligence according to the third embodiment of the present application is shown.

[0028] Figure 4 An internal structure diagram of an online insurance product sales system based on artificial intelligence according to the fourth embodiment of the present application is shown.

[0029] Figure 5 An internal structure diagram of an online insurance product sales system based on artificial intelligence according to a fifth embodiment of the present application is shown.

[0030] Figure 6 A step flow chart of an online insurance product sales method based on artificial intelligence according to a sixth embodiment of the present application is shown. DETAILED DESCRIPTION

[0031] The specific technical process of the present application is as follows:

[0032] Technical process A: for setting whether the current user of the insurance product distributor will complete the intelligent prediction of the target insurance product insurance within a preset time length after the current time, designing a customized structure of an artificial intelligence model, which is an AI sales prediction model;

[0033] Specifically, the customization of the structure of the AI sales prediction model mainly manifests in the following aspects:

[0034] Firstly, the AI sales prediction model is a Hopfield neural network after completing multiple training;

[0035] Secondly, the number of times of training performed on the Hopfield neural network is positively correlated with the number of users of the target insurance product and the use time length of the longest user of the target insurance product, thereby constructing AI sales prediction models with different structures for different insurance products;

[0036] Finally, in each training performed on the Hopfield neural network, the known insurance identification of a certain user with respect to the target insurance product within a preset time length after a certain historical time is taken as the single output content of the Hopfield neural network, and the past insurance identification of the target insurance product of the certain user, the age information of the certain user, the gender information of the certain user, the preset time length, the multiple attention data of the certain user, and each piece of configuration information corresponding to the insurance product distributor are taken as the multiple input contents of the Hopfield neural network, thereby completing the training and ensuring the training effect of each training of the Hopfield neural network;

[0037] Specifically, the preset time length is used to represent the length of a time period, and the current time is taken as the boundary, the past time interval corresponding to the preset time length before the current time is a past time period, and the future time interval corresponding to the preset time length after the current time is a future time period, so that the time axis is divided into time periods, which can facilitate the intelligent prediction of the sequential insurance identification;

[0038] Technical process B: in order to set the intelligent prediction of whether the current user of the insurance product distributor will complete the insurance of the target insurance product within the preset time length after the current time, a plurality of basic information is screened;

[0039] For example, the plurality of basic information includes the past insurance identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the plurality of attention data of the current user, and the corresponding configuration information of the set insurance product distributor;

[0040] Further example, the plurality of attention data of the current user includes the browsing times of the current user browsing the target insurance product marketing webpage of the set insurance product distributor within the preset time length before the current time, and the time length of the current user reading the target insurance product introduction document in the target insurance product marketing webpage of the set insurance product distributor, the corresponding configuration information of the set insurance product distributor includes the number of types of a plurality of insurance products sold by the set insurance product distributor at the same time, the number of a plurality of in-force users corresponding to the plurality of insurance products respectively, the plurality of sales license acquisition time lengths corresponding to the plurality of insurance products respectively, and the use time length of the longest user of the target insurance product;

[0041] For example, the set insurance product distributor has three link icons at its homepage, which are "vehicle insurance", "life insurance" and "property insurance", and "vehicle insurance", "life insurance" and "property insurance" have their own marketing webpages, any one of "vehicle insurance", "life insurance" and "property insurance" can be taken as the target insurance product;

[0042] Here, through the sufficient and comprehensive screening of the plurality of basic information, the stability and reliability of the intelligent prediction result are ensured;

[0043] Technical process C: the AI sales prediction model designed by technical process A intelligently predicts whether the current user of the set insurance product distributor will complete the insurance of the target insurance product within the preset time length after the current time according to the plurality of basic information screened by technical process C;

[0044] It is worth noting that even if it is intelligently predicted that the current user will complete the insurance of the target insurance product within the preset time length after the current time, it is only an intelligent prediction result, not an actual fact, and only the current user is a key target user with a single order tendency in the future time interval, and there is a value of key guiding single order;

[0045] Technical procedure D: when the intelligent prediction is that the current user will complete the insurance of the target insurance product within the preset time length after the current time, the set insurance product distributor that operates and sells the target insurance product regards the current user as a key target user with a tendency to place an order, and pours more sales resources for the current user in the future time interval to ensure that the current user actually places an order and insures in the future time interval;

[0046] Specifically, the set insurance product distributor that operates and sells the target insurance product can operate and sell multiple insurance products including the target insurance product, and the multiple insurance products are sold through an online channel;

[0047] In this way, through the sequential execution of the above technical procedures, the intelligent prediction of whether each user of the set insurance product distributor will complete the insurance of the target insurance product within the preset time length after the current time can be completed in an artificial intelligence mode, thereby providing convenience for the intelligent prediction of the key target user with a tendency to place an order and the subsequent concentrated sales resource guaranteeing the execution of the order placement and insurance by the key target user, completing the effective online insurance product customer acquisition, and improving the statistical efficiency of the future sales data of the online insurance product.

[0048] The key point of the present application is that the intelligent prediction of whether each user of the set insurance product distributor will complete the insurance of the target insurance product within the future time interval introduces a plurality of basic information for targeted screening, a customized design of an AI sales prediction model with different structures of different insurance products, and a key pouring of sales resources for the key target user with a tendency to place an order.

[0049] In the following, an online insurance product sales system and method based on artificial intelligence according to the present application will be described in detail in the form of an embodiment.

[0050] First embodiment

[0051] Figure 1 An internal structure diagram of an online insurance product sales system based on artificial intelligence according to the first embodiment of the present application is shown.

[0052] As shown in Figure 1 The online insurance product sales system based on artificial intelligence includes the following components:

[0053] A first capturing device is used to acquire the number of times that a current user browses a target insurance product marketing webpage of a set insurance product distributor within a preset time length before a current time, and the time length that the current user reads a target insurance product introduction document in the target insurance product marketing webpage of the set insurance product distributor, as a plurality of attention data of the current user;

[0054] For example, the browsing times of the current user for browsing the target insurance product marketing webpage of the insurance product distributor within a preset time length before the current time and the time length of the current user for reading the target insurance product introduction document in the target insurance product marketing webpage of the insurance product distributor are acquired as the multiple pieces of attention data of the current user, and the target insurance product introduction document in the target insurance product marketing webpage can be an electronic document embedded in the target insurance product marketing webpage and needs to be opened and displayed under the click of the current user.

[0055] The second capturing device is configured to acquire the number of types of the multiple insurance products simultaneously sold by the insurance product distributor, the number of in-force users corresponding to the multiple insurance products respectively, the time length of obtaining the sales license corresponding to the multiple insurance products respectively, and the use time length of the longest use user of the target insurance product, as the respective pieces of configuration information corresponding to the insurance product distributor.

[0056] Specifically, the number of types of the multiple insurance products simultaneously sold by the insurance product distributor, the number of in-force users corresponding to the multiple insurance products respectively, the time length of obtaining the sales license corresponding to the multiple insurance products respectively, and the use time length of the longest use user of the target insurance product are acquired as the respective pieces of configuration information corresponding to the insurance product distributor, and the multiple information capturing components can be adopted to acquire the number of types of the multiple insurance products simultaneously sold by the insurance product distributor, the number of in-force users corresponding to the multiple insurance products respectively, the time length of obtaining the sales license corresponding to the multiple insurance products respectively, and the use time length of the longest use user of the target insurance product respectively.

[0057] For example, the multiple information capturing components can be adopted to acquire the number of types of the multiple insurance products simultaneously sold by the insurance product distributor, the number of in-force users corresponding to the multiple insurance products respectively, the time length of obtaining the sales license corresponding to the multiple insurance products respectively, and the use time length of the longest use user of the target insurance product respectively, and the time length of obtaining the sales license and the use time length of the longest use user can be represented in the mode of days.

[0058] The multiple training device is configured to perform multiple training on the Hofit neural network to obtain the Hofit neural network after the multiple training is completed, and output the Hofit neural network after the multiple training is completed as the AI sales prediction model.

[0059] For example, the multiple times of training the Hopfield neural network to obtain the Hopfield neural network after the multiple times of training and outputting the Hopfield neural network after the multiple times of training as the AI sales prediction model include that the test and simulation of the model construction process of training the Hopfield neural network multiple times to obtain the Hopfield neural network after the multiple times of training and outputting the Hopfield neural network after the multiple times of training as the AI sales prediction model can be completed in a numerical simulation mode.

[0060] The sales prediction device is connected with the first capturing device, the second capturing device and the multiple training device respectively, and is used for intelligently predicting the insurance application identification of the current user with respect to the target insurance product within the preset time length after the current time according to the past insurance application identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user and the configuration information corresponding to each piece of the set insurance product distributor.

[0061] Specifically, the preset time length is used to represent the length of a time period, and the past time interval corresponding to the preset time length before the current time is a past time period, and the future time interval corresponding to the preset time length after the current time is a future time period, so that the time axis is divided into time periods, and the intelligent prediction of the sequential insurance application identification can be facilitated.

[0062] The multiple times of training the Hopfield neural network to obtain the Hopfield neural network after the multiple times of training and outputting the Hopfield neural network after the multiple times of training as the AI sales prediction model include that the number of times of training the Hopfield neural network is positively correlated with the number of in-force users of the target insurance product and is positively correlated with the use time length of the longest use user of the target insurance product.

[0063] For example, the number of times of training the Hopfield neural network is positively correlated with the number of in-force users of the target insurance product and is positively correlated with the use time length of the longest use user of the target insurance product include that when the number of in-force users of the target insurance product is in the order of millions and the use time length of the longest use user of the target insurance product is 5 years, the number of times of training the Hopfield neural network is 500, when the number of in-force users of the target insurance product is in the order of millions and the use time length of the longest use user of the target insurance product is 6 years, the number of times of training the Hopfield neural network is 550, when the number of in-force users of the target insurance product is in the order of five hundred thousand and the use time length of the longest use user of the target insurance product is 5 years, the number of times of training the Hopfield neural network is 600, and so on.

[0064] The obtaining of the number of times of browsing the target insurance product marketing webpage of the current user before the preset length of time and the time length of reading the target insurance product introduction document of the current user before the preset length of time are used as the multiple pieces of attention data of the current user, and the multiple pieces of attention data of the current user include: the multiple insurance products including the target insurance product sold by the set insurance product dealer, and the multiple insurance products have respective marketing webpages;

[0065] Specifically, the multiple insurance products including the target insurance product sold by the set insurance product dealer have respective marketing webpages, and the respective marketing webpages of the multiple insurance products have respective link icons at the home page of the set insurance product dealer;

[0066] For example, the set insurance product dealer has three link icons at the home page, which are "vehicle insurance", "life insurance" and "property insurance", and the "vehicle insurance", "life insurance" and "property insurance" have respective marketing webpages;

[0067] The AI sales prediction model is used to intelligently predict the insurance purchasing identifier of the current user with respect to the target insurance product in the preset length of time after the current time according to the past insurance purchasing identifier of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset length of time, the multiple pieces of attention data of the current user and the respective pieces of configuration information of the set insurance product dealer, and the insurance purchasing identifier of the current user with respect to the target insurance product in the preset length of time after the current time is used to indicate whether the current user orders the target insurance product through the target insurance product marketing webpage in the preset length of time after the current time;

[0068] The Hofit neural network is trained multiple times to obtain the Hofit neural network after the multiple times of training, and the Hofit neural network after the multiple times of training is output as the AI sales prediction model, and each time the Hofit neural network is trained, the known insurance purchasing identifier of a certain user with respect to the target insurance product in a preset length of time after a certain historical time is used as the single output content of the Hofit neural network, and the past insurance purchasing identifier of the target insurance product of the certain user, the age information of the certain user, the gender information of the certain user, the preset length of time, the multiple pieces of attention data of the certain user and the respective pieces of configuration information of the set insurance product dealer are used as the multiple input contents of the Hofit neural network, and the training is completed;

[0069] And wherein, in each training performed on the Hofmann neural network, a known insurance purchase identification of a certain user relative to a target insurance product within a preset time length after a certain historical time is taken as a single output content of the Hofmann neural network, past insurance purchase identification of the target insurance product of the certain user, age information of the certain user, gender information of the certain user, the preset time length, multiple pieces of attention data of the certain user, and each piece of configuration information corresponding to a set insurance product distributor are taken as multiple input contents of the Hofmann neural network, and the current training is completed, including that the certain user is a user of the set insurance product distributor, and the past insurance purchase identification of the target insurance product of the certain user is used to indicate whether the certain user has placed an order for the target insurance product through the target insurance product marketing webpage within a preset time length before a certain historical time.

[0070] Second embodiment

[0071] Figure 2 An internal structure diagram of an online insurance product sales system based on artificial intelligence according to a second embodiment of the present application.

[0072] As Figure 2 shown, compared with Figure 1 , the online insurance product sales system based on artificial intelligence further comprises:

[0073] A resource allocation device connected with the sales prediction device, configured to, when the received insurance purchase identification of the current user relative to the target insurance product indicates that the current user will place an order for the target insurance product through the target insurance product marketing webpage within a preset time length after the current time, allocate more sales resources to the current user within the preset time length after the current time.

[0074] When the received insurance purchase identification of the current user relative to the target insurance product indicates that the current user will place an order for the target insurance product through the target insurance product marketing webpage within a preset time length after the current time, allocating more sales resources to the current user within the preset time length after the current time includes that the number of sales resources allocated to the current user within the preset time length after the current time is greater than the default number of sales resources allocated to each user by the set insurance product distributor.

[0075] The insurance application identifier of the current user relative to the target insurance product within the preset length of time after the current time indicates that the current user will place an order for the target insurance product through the target insurance product marketing webpage within the preset length of time after the current time, and the allocation of more sales resources to the current user within the preset length of time after the current time further includes that the sales resources are an advertising frequency of the target insurance product and / or a number of sales personnel of the target insurance product.

[0076] Third embodiment

[0077] Figure 3 An internal structure diagram of an online insurance product sales system based on artificial intelligence according to a third embodiment of the present application is shown.

[0078] As shown in Figure 3 , compared with Figure 2 , the online insurance product sales system based on artificial intelligence further includes:

[0079] The model processing device is connected with the multiple training device, and is configured to receive the AI sales prediction model and complete model storage of the AI sales prediction model through each model data of the AI sales prediction model.

[0080] Fourth embodiment

[0081] Figure 4 An internal structure diagram of an online insurance product sales system based on artificial intelligence according to a fourth embodiment of the present application is shown.

[0082] As shown in Figure 4 , compared with Figure 3 , the online insurance product sales system based on artificial intelligence further includes:

[0083] The content display device is connected with the sales prediction device, and is configured to receive the insurance application identifier of the current user relative to the target insurance product within the preset length of time after the current time, and display the insurance application identifier of the current user relative to the target insurance product within the preset length of time after the current time in real time.

[0084] Fifth embodiment

[0085] Figure 5 An internal structure diagram of an online insurance product sales system based on artificial intelligence according to a fifth embodiment of the present application is shown.

[0086] As shown in Figure 5 , compared with Figure 4 , the online insurance product sales system based on artificial intelligence further includes:

[0087] The wireless transmission device is connected with the sales prediction device, and is used for receiving the insurance application identification of the current user relative to the target insurance product within a preset time length after the current time, and transmitting the insurance application identification to the big data storage network element of the set insurance product distributor through a wireless transmission link.

[0088] Next, further description will be made on various embodiments of the present application.

[0089] In the above various embodiments, optionally, in the online insurance product sales system based on artificial intelligence:

[0090] The number of kinds of the plurality of insurance products sold by the set insurance product distributor, the number of the plurality of in-force insurance policies corresponding to the plurality of insurance products respectively, the plurality of sales license acquisition time lengths corresponding to the plurality of insurance products respectively, and the use time length of the longest use user of the target insurance product are obtained as each piece of configuration information corresponding to the set insurance product distributor, and the plurality of sales license acquisition time lengths corresponding to the plurality of insurance products sold by the set insurance product distributor are each represented by a numerical value in days.

[0091] The AI sales prediction model is used to intelligently predict the insurance application identification of the current user relative to the target insurance product within the preset time length after the current time according to the past insurance application identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the plurality of attention data of the current user, and each piece of configuration information corresponding to the set insurance product distributor, and the past insurance application identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the plurality of attention data of the current user, and each piece of configuration information corresponding to the set insurance product distributor are input into the AI sales prediction model in parallel.

[0092] The past insurance application identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the plurality of attention data of the current user, and each piece of configuration information corresponding to the set insurance product distributor are input into the AI sales prediction model in parallel, and the past insurance application identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the plurality of attention data of the current user, and each piece of configuration information corresponding to the set insurance product distributor are respectively subjected to numerical normalization processing before being input into the AI sales prediction model in parallel.

[0093] The AI sales prediction model is used to intelligently predict the insurance application identifier of the current user with respect to the target insurance product within the preset time length after the current time according to the past insurance application identifier of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the plurality of attention data of the current user, and the configuration information corresponding to the insurance product distributor set.

[0094] The AI sales prediction model is used to intelligently predict the insurance application identifier of the current user with respect to the target insurance product within the preset time length after the current time according to the past insurance application identifier of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the plurality of attention data of the current user, and the configuration information corresponding to the insurance product distributor set.

[0095] In the above various embodiments, optionally, in the online insurance product sales system based on artificial intelligence:

[0096] The number of times of training performed on the Hopfield neural network is positively correlated with the number of in-force users of the target insurance product and is positively correlated with the use duration of the longest use user of the target insurance product at the same time, which includes that a double-input single-output numerical mapping function is used to represent the numerical mapping relationship between the number of in-force users of the target insurance product and the use duration of the longest use user of the target insurance product and the number of times of training performed on the Hopfield neural network.

[0097] The number of times of training performed on the Hopfield neural network is positively correlated with the number of in-force users of the target insurance product and is positively correlated with the use duration of the longest use user of the target insurance product at the same time, which includes that a double-input single-output numerical mapping function is used to represent the numerical mapping relationship between the number of in-force users of the target insurance product and the use duration of the longest use user of the target insurance product and the number of times of training performed on the Hopfield neural network.

[0098] The number of times of training performed on the Hopfield neural network is positively correlated with the number of in-force users of the target insurance product and is positively correlated with the use duration of the longest use user of the target insurance product at the same time, which includes that a double-input single-output numerical mapping function is used to represent the numerical mapping relationship between the number of in-force users of the target insurance product and the use duration of the longest use user of the target insurance product and the number of times of training performed on the Hopfield neural network.

[0099] The sixth embodiment

[0100] Figure 6 A step flowchart of an online insurance product sales method based on artificial intelligence according to the sixth embodiment of the present application is shown.

[0101] As Figure 6As shown, the online insurance product sales method based on artificial intelligence comprises the following steps:

[0102] The number of times of browsing the target insurance product marketing webpage of the set insurance product dealer by the current user within a preset length of time before the current time and the time length of reading the target insurance product introduction document in the target insurance product marketing webpage of the set insurance product dealer by the current user are obtained as multiple attention data of the current user;

[0103] For example, the number of times of browsing the target insurance product marketing webpage of the set insurance product dealer by the current user within a preset length of time before the current time and the time length of reading the target insurance product introduction document in the target insurance product marketing webpage of the set insurance product dealer by the current user are obtained as multiple attention data of the current user, which includes that the target insurance product introduction document in the target insurance product marketing webpage can be an electronic document embedded in the target insurance product marketing webpage and needs to be opened and displayed under the click of the current user;

[0104] The number of types of multiple insurance products sold by the set insurance product dealer, the number of multiple in-force users corresponding to the multiple insurance products, the time length of obtaining multiple sales licenses corresponding to the multiple insurance products, and the use time length of the longest use user of the target insurance product are obtained as each configuration information corresponding to the set insurance product dealer;

[0105] Specifically, the number of types of multiple insurance products sold by the set insurance product dealer, the number of multiple in-force users corresponding to the multiple insurance products, the time length of obtaining multiple sales licenses corresponding to the multiple insurance products, and the use time length of the longest use user of the target insurance product are obtained as each configuration information corresponding to the set insurance product dealer, which includes that multiple information capture components can be used to respectively obtain the number of types of multiple insurance products sold by the set insurance product dealer, the number of multiple in-force users corresponding to the multiple insurance products, the time length of obtaining multiple sales licenses corresponding to the multiple insurance products, and the use time length of the longest use user of the target insurance product;

[0106] For example, multiple information capture components can be used to respectively obtain the number of types of multiple insurance products sold by the set insurance product dealer, the number of multiple in-force users corresponding to the multiple insurance products, the time length of obtaining multiple sales licenses corresponding to the multiple insurance products, and the use time length of the longest use user of the target insurance product, which includes that the time length of obtaining sales licenses and the use time length of the longest use user can both be represented in the mode of days;

[0107] performing multiple training on the Hopfield neural network to obtain the Hopfield neural network after the multiple training is completed, and outputting the Hopfield neural network after the multiple training is completed as the AI sales prediction model;

[0108] For example, performing multiple training on the Hopfield neural network to obtain the Hopfield neural network after the multiple training is completed, and outputting the Hopfield neural network after the multiple training is completed as the AI sales prediction model includes that the test and simulation of the model construction process of performing multiple training on the Hopfield neural network to obtain the Hopfield neural network after the multiple training is completed, and outputting the Hopfield neural network after the multiple training is completed as the AI sales prediction model can be completed in a numerical simulation mode;

[0109] Using the AI sales prediction model to intelligently predict the insurance purchasing identification of the current user with respect to the target insurance product within the preset time length after the current time according to the past purchasing identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and each piece of configuration information corresponding to the insurance product distributor set;

[0110] Specifically, the preset time length is used to represent the length of a time period, and the current time is taken as the boundary. The past time interval corresponding to the preset time length before the current time is a past time period, and the future time interval corresponding to the preset time length after the current time is a future time period. In this way, the time axis is divided into time periods, and the intelligent prediction of the sequential insurance purchasing identification can be facilitated.

[0111] The number of times of training performed on the Hopfield neural network is positively correlated with the number of in-force users of the target insurance product, and is positively correlated with the use duration of the longest use user of the target insurance product at the same time.

[0112] For example, the number of times of training performed on the Hopfield neural network is positively correlated with the number of in-force users of the target insurance product, and is positively correlated with the use duration of the longest use user of the target insurance product at the same time includes that when the number of in-force users of the target insurance product is in the order of millions and the use duration of the longest use user of the target insurance product is 5 years, the number of times of training performed on the Hopfield neural network is 500, when the number of in-force users of the target insurance product is in the order of millions and the use duration of the longest use user of the target insurance product is 6 years, the number of times of training performed on the Hopfield neural network is 550, when the number of in-force users of the target insurance product is in the order of five hundred thousand and the use duration of the longest use user of the target insurance product is 5 years, the number of times of training performed on the Hopfield neural network is 600, and so on.

[0113] The obtaining of the number of times of browsing the target insurance product marketing webpage of the current user for browsing the set insurance product distributor within a preset time length before the current time and the time length of reading the target insurance product introduction document of the current user for reading the target insurance product marketing webpage of the set insurance product distributor as the multiple attention data of the current user includes that the set insurance product distributor sells multiple insurance products including the target insurance product, and the multiple insurance products have respective marketing webpages;

[0114] Specifically, the set insurance product distributor sells multiple insurance products including the target insurance product, and the multiple insurance products have respective marketing webpages, which includes that the respective marketing webpages of the multiple insurance products have respective link icons at the home page of the set insurance product distributor;

[0115] For example, the set insurance product distributor has three link icons at the home page, which are "vehicle insurance", "life insurance" and "property insurance", and the "vehicle insurance", "life insurance" and "property insurance" have respective marketing webpages;

[0116] The intelligent prediction of the AI sales prediction model according to the past insurance purchasing identifier of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the multiple attention data of the current user and the respective configuration information of the set insurance product distributor to predict the insurance purchasing identifier of the current user relative to the target insurance product within the preset time length after the current time includes that the insurance purchasing identifier of the current user relative to the target insurance product within the preset time length after the current time is used to indicate whether the current user orders and purchases the target insurance product through the target insurance product marketing webpage within the preset time length after the current time;

[0117] The multiple training of the Hofit neural network to obtain the Hofit neural network after the multiple training, and the Hofit neural network after the multiple training as the output of the AI sales prediction model further includes that in each training of the Hofit neural network, the known insurance purchasing identifier of a certain user relative to the target insurance product within a preset time length after a certain historical time is taken as the single output content of the Hofit neural network, and the past insurance purchasing identifier of the target insurance product of the certain user, the age information of the certain user, the gender information of the certain user, the preset time length, the multiple attention data of the certain user and the respective configuration information of the set insurance product distributor are taken as the multiple input contents of the Hofit neural network, and the training is completed;

[0118] And wherein, in each training performed on the Hofmann neural network, a known insurance purchase identification of a certain user relative to a target insurance product within a preset time length after a certain historical time is taken as a single output content of the Hofmann neural network, past insurance purchase identification of the target insurance product of the certain user, age information of the certain user, gender information of the certain user, the preset time length, multiple pieces of attention data of the certain user, and each piece of configuration information corresponding to a set insurance product distributor are taken as multiple input contents of the Hofmann neural network, and the training this time includes: the certain user is a user of the set insurance product distributor, and the past insurance purchase identification of the target insurance product of the certain user is used to indicate whether the certain user has placed an order for the target insurance product through the target insurance product marketing webpage within a preset time length before a certain historical time.

[0119] In addition, in an online insurance product sales system and method based on artificial intelligence according to the present application:

[0120] After performing numerical normalization processing on the past insurance purchase identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and each piece of configuration information corresponding to the set insurance product distributor, respectively, and then inputting them into the AI sales prediction model in parallel, the method further includes: performing binary numerical conversion processing on the past insurance purchase identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and each piece of configuration information corresponding to the set insurance product distributor, respectively, and then inputting them into the AI sales prediction model in parallel.

[0121] And wherein, after performing numerical normalization processing on the past insurance purchase identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and each piece of configuration information corresponding to the set insurance product distributor, respectively, and then inputting them into the AI sales prediction model in parallel, the method further includes: using a parallel control device to complete the parallel input of the past insurance purchase identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and each piece of configuration information corresponding to the set insurance product distributor after performing numerical normalization processing, into the AI sales prediction model.

[0122] For example, the parallel control device used to complete parallel input of the past insurance application identification of the target insurance product of the current user after performing the numerical normalization processing respectively, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user and the multiple pieces of configuration information corresponding to the insurance product distributors set by the current user into the AI sales prediction model includes that the parallel control device is a programmable logic device designed by using a VHDL language;

[0123] In addition, the insurance application identification of the current user with respect to the target insurance product within the preset time length after the current time in the numerical normalized numerical representation form includes that the insurance application identification of the current user with respect to the target insurance product within the preset time length after the current time is in a binary numerical numerical representation form.

[0124] It should be noted that the relational terms herein such as first and second and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any such actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0125] Each of the embodiments in the specification is described in a related manner, and the same and similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the device / electronic device / computer readable storage medium / computer program product embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment. The above only describes the preferred embodiments of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An artificial intelligence based online insurance product selling system characterized in that, The system comprises: A first capturing device for acquiring the number of times that a current user browses a target insurance product marketing webpage of a designated insurance product distributor within a preset time length before a current time and the length of time that the current user reads a target insurance product introduction document in the target insurance product marketing webpage of the designated insurance product distributor, and taking the two as multiple pieces of attention data of the current user; A second capturing device for acquiring the number of types of multiple insurance products that the designated insurance product distributor sells simultaneously, the number of in-force users corresponding to the multiple insurance products respectively, the length of time for obtaining the sales license corresponding to the multiple insurance products respectively, and the length of time for which a longest user of the target insurance product uses the target insurance product, to serve as each piece of configuration information corresponding to the designated insurance product distributor; A multiple training device for performing multiple training on the Hopfield neural network to obtain a Hopfield neural network after the multiple training, and outputting the Hopfield neural network after the multiple training as an AI sales prediction model; A sales prediction device connected with the first capturing device, the second capturing device, and the multiple training device respectively, for intelligently predicting, by using the AI sales prediction model, the in-force identification of the current user with respect to the target insurance product within a preset time length after the current time according to the past in-force identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and each piece of configuration information corresponding to the designated insurance product distributor; The number of times of training performed on the Hopfield neural network to obtain the Hopfield neural network after the multiple training is positively correlated with the number of in-force users of the target insurance product and positively correlated with the length of time for which the longest user of the target insurance product uses the target insurance product; The in-force identification of the current user with respect to the target insurance product within the preset time length after the current time indicates whether the current user places an order for the target insurance product through the target insurance product marketing webpage within the preset time length after the current time; The past in-force identification of the target insurance product of the current user, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and each piece of configuration information corresponding to the designated insurance product distributor are respectively subjected to binary value conversion processing before being input into the AI sales prediction model; The in-force identification of the current user with respect to the target insurance product within the preset time length after the current time is in the form of a binary value.

2. The online insurance product sales system based on artificial intelligence according to claim 1, wherein: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises:

4. The online insurance product sales system based on artificial intelligence as claimed in claim 3, wherein, The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further comprises: The system further The resource allocation device is connected with the sales prediction device, and is used for allocating more sales resources to the current user within the preset time length after the current time when the received current user insurance application identification within the preset time length after the current time indicates that the current user will place an order for the target insurance product through the target insurance product marketing webpage within the preset time length after the current time. The current user insurance application identification within the preset time length after the current time indicates that the current user will place an order for the target insurance product through the target insurance product marketing webpage within the preset time length after the current time, and the current user is allocated more sales resources within the preset time length after the current time, which includes that the number of sales resources allocated to the current user within the preset time length after the current time is greater than the default number of sales resources allocated to each user by the set insurance product distributor. The current user insurance application identification within the preset time length after the current time indicates that the current user will place an order for the target insurance product through the target insurance product marketing webpage within the preset time length after the current time, and the current user is allocated more sales resources within the preset time length after the current time, which further includes that the sales resources are the advertising frequency of the target insurance product and / or the number of sales personnel of the target insurance product. 5.The online insurance product sales system based on artificial intelligence of claim 3, wherein, The system further comprises: The model processing device is connected with the multiple training device, and is used for receiving the AI sales prediction model, and completing model storage of the AI sales prediction model through each model data of the AI sales prediction model.

6. The online insurance product sales system based on artificial intelligence according to claim 3, wherein, The system further comprises: The content display device is connected with the sales prediction device, and is used for receiving the current user insurance application identification within the preset time length after the current time, and displaying the current user insurance application identification within the preset time length after the current time in real time.

7. The online insurance product sales system based on artificial intelligence according to claim 3, wherein, The system further comprises: The wireless transmission device is connected with the sales prediction device, and is used for receiving the current user insurance application identification within the preset time length after the current time, and wirelessly transmitting the current user insurance application identification within the preset time length after the current time to the big data storage network element of the set insurance product distributor through a wireless transmission link.

8. The online insurance product sales system based on artificial intelligence according to any one of claims 3-7, wherein: The number of types of multiple insurance products simultaneously sold by the set insurance product distributor, the number of multiple insurance products corresponding to multiple in-force users, the acquisition time length of multiple sales licenses corresponding to multiple insurance products, and the use time length of the longest user of the target insurance product are obtained as each part of the configuration information corresponding to the set insurance product distributor, and the acquisition time length of multiple sales licenses corresponding to multiple insurance products sold by the set insurance product distributor simultaneously is represented by days. The AI sales prediction model is used to intelligently predict the insurance purchasing identifier of the current user with respect to the target insurance product within the preset time length after the current time according to the past insurance purchasing identifier of the current user for the target insurance product, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and the configuration information corresponding to the insurance product distributor; The parallel input of the past insurance purchasing identifier of the current user for the target insurance product, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and the configuration information corresponding to the insurance product distributor to the AI sales prediction model includes: performing numerical normalization processing on the past insurance purchasing identifier of the current user for the target insurance product, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and the configuration information corresponding to the insurance product distributor respectively, and then performing parallel input to the AI sales prediction model; The AI sales prediction model is used to intelligently predict the insurance purchasing identifier of the current user with respect to the target insurance product within the preset time length after the current time according to the past insurance purchasing identifier of the current user for the target insurance product, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and the configuration information corresponding to the insurance product distributor; The running of the AI sales prediction model to obtain the insurance purchasing identifier of the current user with respect to the target insurance product within the preset time length after the current time output by the AI sales prediction model includes: running the AI sales prediction model to obtain the insurance purchasing identifier of the current user with respect to the target insurance product within the preset time length after the current time output by the AI sales prediction model in the form of a numerical value normalized.

9. The online insurance product sales system based on artificial intelligence according to any one of claims 3-7, wherein: The number of times of training performed on the Hopfield neural network is positively correlated with the number of users of the target insurance product in force and the use time length of the longest user of the target insurance product at the same time includes: using a double-input single-output numerical mapping function to represent the numerical mapping relationship between the number of users of the target insurance product in force and the use time length of the longest user of the target insurance product and the number of times of training performed on the Hopfield neural network. The numerical mapping relationship between the number of insured users of the target insurance product and the use time length of the longest user of the target insurance product and the number of times of training performed on the Hopfield neural network is represented by a double-input single-output numerical mapping function, including: taking the number of insured users of the target insurance product and the use time length of the longest user of the target insurance product as double-input values of the numerical mapping function; The numerical mapping relationship between the number of insured users of the target insurance product and the use time length of the longest user of the target insurance product and the number of times of training performed on the Hopfield neural network is represented by a double-input single-output numerical mapping function, including: taking the number of insured users of the target insurance product and the use time length of the longest user of the target insurance product as double-input values of the numerical mapping function.

10. An online insurance product selling method based on artificial intelligence, characterized by, The method comprises: obtaining the number of times of browsing the target insurance product marketing webpage of the set insurance product distributor by the current user within a preset time length before the current time, and the time length of reading the target insurance product introduction document in the target insurance product marketing webpage of the set insurance product distributor by the current user, as multiple pieces of attention data of the current user; obtaining the number of types of multiple insurance products sold by the set insurance product distributor, the number of insured users corresponding to the multiple insurance products respectively, the time length of obtaining the sales license corresponding to the multiple insurance products respectively, and the use time length of the longest user of the target insurance product, as each piece of configuration information corresponding to the set insurance product distributor; performing multiple times of training on the Hopfield neural network to obtain the Hopfield neural network after completing the multiple times of training, and outputting the Hopfield neural network after completing the multiple times of training as an AI sales prediction model; using the AI sales prediction model to intelligently predict the insurance purchase identifier of the current user with respect to the target insurance product within a preset time length after the current time according to the past insurance purchase identifier of the current user with respect to the target insurance product, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and each piece of configuration information corresponding to the set insurance product distributor; The number of times of training performed on the Hopfield neural network to obtain the Hopfield neural network after completing the multiple times of training, and outputting the Hopfield neural network after completing the multiple times of training as an AI sales prediction model, including: the number of times of training performed on the Hopfield neural network is positively correlated with the number of insured users of the target insurance product, and is also positively correlated with the use time length of the longest user of the target insurance product; The insurance purchase identifier of the current user with respect to the target insurance product within a preset time length after the current time is used to represent whether the current user places an order to purchase the target insurance product through the target insurance product marketing webpage within a preset time length after the current time; The past insurance purchase identifier of the current user with respect to the target insurance product, the age information of the current user, the gender information of the current user, the preset time length, the multiple pieces of attention data of the current user, and each piece of configuration information corresponding to the set insurance product distributor are respectively subjected to binary value conversion processing before being input to the AI sales prediction model. The binary number value of the insurance application mark of the current user relative to the target insurance product in a preset time length after the current time is represented in a numerical form.

Images