Information push method, device, electronic device and medium based on deep learning
Through the information push method based on deep learning, high-quality online customers are screened using the target network model, solving the problem of inaccurate customer screening caused by data loss in traditional technology, and improving marketing success rate and insurance marketing efficiency.
Patent Information
- Application Number
- CN202111267080.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-10-28
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-10-28
AI Technical Summary
In the prior art, when screening customers on the Internet based on traditional classification algorithms, the lack of data leads to insufficient push of high-quality customers, resulting in low marketing success rate and insurance marketing efficiency.
Using deep learning-based information push method, by obtaining user's network information, extracting insurance feature information and importing trained target network model, and calculating the user's target insurance level. If the level is higher than the preset value, the user information will be obtained and Send to the target user equipment to realize the selection and push of high-quality customers.
It improves marketing success rate and insurance marketing efficiency, and ensures accurate screening and pushing of high-quality online customers.
Smart Images

Figure CN113902575B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, electronic device and medium for pushing information based on deep learning. Background Art
[0002] With the rapid development of the national economy, the support of relevant policies and the further upgrading of national insurance awareness, the growth trend of domestic insurance demand is very obvious. However, insurance companies are not clear about the information and purchasing intentions of online customers, and spend almost the same time and energy on marketing for each customer, which causes a great waste of resources.
[0003] In the existing technology, the screening of such online customers is mainly based on traditional classification algorithms, such as SVM, KNN, etc. Due to the lack of data, the high-quality online customers finally pushed to the product account manager are not accurate enough, resulting in low marketing success rate and insurance marketing efficiency. Summary of the invention
[0004] The purpose of the present invention is to solve at least one of the above-mentioned technical defects, especially the inability to eliminate low-quality online customers among online customers, so as to improve the marketing success rate and the efficiency of insurance marketing by screening out high-quality online customers and pushing them to product account managers.
[0005] In a first aspect, an embodiment of the present application provides an information push method based on deep learning, the method comprising:
[0006] Acquire online access information of a first user, where the first user is a user who accesses insurance product information on a product page but does not purchase the insurance product, and the online access information is used to indicate the operation of the first user on the insurance product information on the product page;
[0007] Obtaining insurance characteristic information corresponding to the insurance index according to the online access information;
[0008] Importing the insurance feature information into the trained target network model to obtain the target insurance level of the first user, wherein the target insurance level refers to the insurance level of the first user, and the target network model is a network model constructed and trained using the insurance feature information of the first user and the second user as samples, and the second user is a user who accesses the insurance product information on the product page and purchases the insurance product;
[0009] If the target insurance level is greater than the preset insurance level, obtaining user information of the first user;
[0010] The user information is sent to a user device of a target user.
[0011] In a possible example, the insurance characteristic information includes the first user's online page column, online channel, online operation, online time, number of online visits, total online time, and insurance policy information viewed each time the online visit.
[0012] In a possible example, the target network model is obtained by performing the following operations:
[0013] Extracting insurance feature information from online information of the first user and the second user;
[0014] Extracting insurance feature information corresponding to part of the first user and part of the second user respectively, and constructing a training set;
[0015] Extract the remaining second users and the insurance feature information corresponding to the remaining second users respectively, and construct a test set;
[0016] Adopting multiple classification methods and constructing a classification model of the insurance grade to be tested according to the training set;
[0017] The test set is input into each insurance grade classification model to be tested respectively, the verification results of each insurance grade classification model to be tested are sorted, and several insurance grade classification models to be tested are selected as the insurance grade classification models according to the sorting.
[0018] In a possible example, the user information includes the current address of the first user, and sending the user information to a user device of a target user includes:
[0019] At least one target user whose office address is closest to the current address is determined according to the current address of the first user.
[0020] In a possible example, the user information includes the current address of the first user, and sending the user information to a user device of a target user includes:
[0021] Determine, based on the current residence of the first user, at least one third user whose office address is within a preset range from the current residence;
[0022] Acquire the points of the at least one third user, where the points are used to indicate the user service level;
[0023] A user with the highest score among the at least one third user is determined as the target user.
[0024] In a possible example, after importing the insurance feature information into a trained target network model to obtain the target insurance level of the first user, the method further includes: if the target insurance level is less than or equal to the preset insurance level, obtaining the first user's network access information.
[0025] In a second aspect, an embodiment of the present application provides an information push device based on deep learning, the device comprising:
[0026] a network access information acquisition unit, configured to acquire network access information of a first user, wherein the first user is a user who accesses insurance product information on a product page but does not purchase the insurance product, and the network access information is used to indicate the operation of the first user on the insurance product information on the product page;
[0027] An insurance characteristic information acquisition unit, used to obtain insurance characteristic information corresponding to the insurance index according to the online information;
[0028] an insurance grade acquisition unit, configured to import the insurance feature information into a trained target network model to obtain a target insurance grade of the first user, wherein the target insurance grade refers to the insurance grade of the first user, and the target network model is a network model constructed and trained using the insurance feature information of the first user and the second user as samples, wherein the second user is a user who accesses insurance product information on a product page and purchases an insurance product;
[0029] A user information acquisition unit, configured to acquire user information of the first user if the target insurance level is greater than a preset insurance level;
[0030] The communication unit is used to send the user information to the user equipment of the target user.
[0031] In a possible example, the insurance characteristic information includes the first user's online page column, online channel, online operation, online time, number of online visits, total online time, and insurance policy information viewed each time the online visit.
[0032] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for executing the steps in the method shown in the first aspect.
[0033] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps in the method shown in the first aspect.
[0034] It can be seen that in the embodiment of the present application, first, after obtaining the online information of the first user who accessed the insurance product information on the product page but did not purchase the insurance product, the insurance characteristic information corresponding to the insurance index is obtained according to the online information, and then the insurance characteristic information is imported into the network model constructed and trained using the insurance characteristic information of the first user and the second user as samples to obtain the target insurance level of the first user. The second user is a user who accesses the insurance product information on the product page and purchases the insurance product. If the target insurance level is greater than the preset insurance level, the user information of the first user is obtained, and then the user information is sent to the user device of the target user. It can be seen that by adopting the present application, potential insured customers with higher insurance levels screened out from online customers are pushed to product account managers, thereby improving the marketing success rate and the efficiency of insurance marketing. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0036] Figure 1 An application environment diagram provided for an embodiment of the present application;
[0037] Figure 2 It is a flowchart of a method for pushing information based on deep learning provided in an embodiment of the present application;
[0038] Figure 3 It is a structural schematic diagram of an information push device based on deep learning provided in an embodiment of the present application;
[0039] Figure 4 It is a structural schematic diagram of an electronic device provided in another embodiment of the present application. DETAILED DESCRIPTION
[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0041] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, device, storage medium, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.
[0042] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0043] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
[0044] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.
[0045] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0046] At present, the screening of online customers who access insurance product information on product pages but do not purchase insurance products is mainly based on traditional classification algorithms, such as SVM and KNN. Due to the lack of data, the high-quality online customers finally pushed to product account managers are not accurate enough, resulting in low marketing success rate and insurance marketing efficiency.
[0047] Based on the above problems, an embodiment of the present invention provides an information push method based on deep learning, which is described in detail as follows.
[0048] See also Figure 1 , Figure 1 is an application environment diagram of an embodiment of the present invention; in this embodiment, the technical solution of the present invention can be implemented on a mobile electronic device, such as Figure 1 In the embodiment, the first electronic device 120, the second electronic device 130 and the third electronic device 140 can access the server 110 through the internet network, and the corresponding clients can be installed on the first electronic device 120, the second electronic device 130 and the third electronic device 140 respectively in the form of APP, etc. The user interacts with the server 110 by logging in to the client, and implements relevant functions on the user side on the client. In the embodiment of the present invention, the first user can log in through the first electronic device 120, the second user can log in through the second electronic device 130, and the third user can log in through the third electronic device 140; the server 110 referred to here refers to a server device that implements various background functions. Considering the actual situation of server processing at present, the device mentioned here may also refer to a cluster of one device or multiple devices. Figure 1 In the figure, three users and corresponding mobile electronic devices are used as an example to illustrate, and it can be applied to scenarios with other numbers of users in other usage scenarios.
[0049] See also Figure 2 , Figure 2 A flowchart of a method for pushing information based on deep learning is provided in an embodiment of the present application, such as Figure 2 As shown, the information push method based on deep learning specifically includes the following steps S101 to S105.
[0050] S101. Obtain the Internet access information of the first user.
[0051] Among them, the first user, also known as the online user, refers to a user who accesses the insurance product information on the product page but does not purchase the insurance product, and the online information is used to indicate the first user's operation on the insurance product information on the product page.
[0052] Among them, the online access information may include but is not limited to the first user's gender, age, place of residence, native place, online access page column, online access channel, online access operation, online access time, number of online access times and total online access time, etc.
[0053] S102: Obtain insurance characteristic information corresponding to the insurance index according to the online access information.
[0054] Among them, the insurance characteristic information includes the first user's online page column, online channel, online operation, online time, number of online access, total online time and insurance policy information viewed each time online.
[0055] S103: Import the insurance feature information into the trained target network model to obtain the target insurance level of the first user.
[0056] Among them, the target insurance level refers to the insurance level of the first user, and the target network model is a network model constructed and trained using the insurance feature information of the first user and the second user as samples. The second user is a user who accesses the insurance product information on the product page and purchases the insurance product.
[0057] It should be noted that the higher the insurance level, the higher the possibility that the user will be covered.
[0058] There is no specific limitation on the total number of insurance levels. For example, the total number of insurance levels can be 4, 6, 7, and so on.
[0059] S104: If the target insurance level is greater than a preset insurance level, obtaining user information of the first user.
[0060] Among them, the user information includes but is not limited to at least one of the first user's name, gender, age, current address, native place, online page column, online channel, online operation, online time, number of online accesses and total online time.
[0061] S105: Send the user information to a user device of the target user.
[0062] The target user may be a product manager of insurance, that is, a promoter of insurance products.
[0063] Among them, the preset insurance level can be set according to actual needs without any specific restrictions.
[0064] It can be seen that in the embodiment of the present application, first, after obtaining the online information of the first user who accessed the insurance product information on the product page but did not purchase the insurance product, the insurance characteristic information corresponding to the insurance index is obtained according to the online information, and then the insurance characteristic information is imported into the network model constructed and trained using the insurance characteristic information of the first user and the second user as samples to obtain the target insurance level of the first user. The second user is a user who accesses the insurance product information on the product page and purchases the insurance product. If the target insurance level is greater than the preset insurance level, the user information of the first user is obtained, and then the user information is sent to the user device of the target user. It can be seen that by adopting the present application, potential insured customers with higher insurance levels screened out from online customers are pushed to product account managers, thereby improving the marketing success rate and the efficiency of insurance marketing.
[0065] In a possible example, the target network model is obtained by performing the following operations: extracting insurance feature information from the online access information of the first user and the second user; extracting the insurance feature information corresponding to part of the first user and part of the second user respectively to construct a training set; extracting the insurance feature information corresponding to the remaining second user and the remaining second user respectively to construct a test set; using multiple classification methods and constructing an insurance grade classification model to be tested based on the training set; inputting the test set into each insurance grade classification model respectively, sorting the verification results of each insurance grade classification model, and selecting several insurance grade classification models to be tested as the insurance grade classification model according to the sorting.
[0066] In the specific implementation, the feature input layer of the insurance grade classification model to be tested is designed according to the feature dimensions of online customers, and the number of neurons is the same as the number of feature dimensions.
[0067] For example, the training process of the target network model includes: the feature input layer is connected to a fully connected layer with 256 neurons, and then the Relu function is used as the activation function; batch normalization layer and Dropout layer are used to avoid model overfitting, and the dropout parameter is set to 0.4; then two fully connected layers are connected in succession, containing 128 and 64 neurons respectively, and the Relu function is used as the activation function to complete the further abstract representation of the data features; finally, a decision layer with 6 neurons is used to determine the insurance level of each customer. The softmax function will output the probability of the customer corresponding to the 6 insurance levels. We take the highest one among the six insurance levels as the insurance level of this customer.
[0068] In one possible example, the user information includes the current address of the first user, and sending the user information to a user device of a target user includes: determining, based on the current address of the first user, at least one of the target users whose office address is closest to the current address.
[0069] In the specific implementation, if the current address of user A who accesses the insurance product information on the product page but does not purchase the insurance product is A, and the target insurance level of user A is greater than the preset insurance level, and the office addresses of insurance product account manager B, insurance product account manager C, and insurance product account manager D are all closest to A, then insurance product account manager B, insurance product account manager C, and insurance product account manager D will be determined as target users.
[0070] It can be seen that in this example, the user information of online users with high insurance levels can be sent to the user device of the nearest insurance product account manager, so that the nearest insurance product account manager can serve the online users with high insurance levels.
[0071] In one possible example, the user information includes the current address of the first user, and sending the user information to a user device of a target user includes: determining, based on the current address of the first user, at least one third user whose office address is within a preset range from the current address; obtaining points from the at least one third user, wherein the points are used to indicate the user service level; and determining the user with the highest points among the at least one third user as the target user.
[0072] Among them, the higher the points, the higher the qualifications and stronger the ability of the insurance product account manager. The points can be determined by factors such as the insurance product account manager's signing volume, customer visits, and signing rate.
[0073] In the specific implementation, if the current address of user A who accesses the insurance product information on the product page but does not purchase the insurance product is A, and the target insurance level of user A is greater than the preset insurance level, and the office addresses of insurance product account manager B, insurance product account manager C, and insurance product account manager D are all closest to A, then the points of insurance product account manager B, insurance product account manager C, and insurance product account manager D will be obtained. If the points of insurance product account manager B, insurance product account manager C, and insurance product account manager D are 100 points, 2001 points, and 300 points respectively, insurance product account manager C will be determined as the target user.
[0074] It can be seen that in this example, the user information of online users with high insurance levels can be sent to the user device of the nearest most capable insurance product account manager, so that the nearest most capable insurance product account manager can serve the online users with high insurance levels.
[0075] In a possible example, after importing the insurance feature information into a trained target network model to obtain the target insurance level of the first user, the method further includes: if the target insurance level is less than or equal to the preset insurance level, obtaining the first user's network access information.
[0076] It can be seen that in this example, when the target insurance level is less than or equal to the preset insurance level, the first user's online information will be continuously obtained, that is, when the online user is not a high-quality online user, the online information of the online user will be continuously tracked, and when the online user becomes a high-quality online user, timely service can be provided to him.
[0077] In the case of integrated units, see Figure 3 , Figure 3 A block diagram of the functional units of an information push device based on deep learning is provided. The information push device based on deep learning 200 includes:
[0078] The online information acquisition unit 210 is used to acquire online information of a first user, where the first user is a user who accesses insurance product information on a product page but does not purchase the insurance product, and the online information is used to indicate the operation of the first user on the insurance product information on the product page;
[0079] The insurance characteristic information acquisition unit 220 is used to obtain the insurance characteristic information corresponding to the insurance index according to the online information;
[0080] The insurance grade acquisition unit 230 is used to import the insurance feature information into the trained target network model to obtain the target insurance grade of the first user, wherein the target insurance grade refers to the insurance grade of the first user, and the target network model is a network model constructed and trained using the insurance feature information of the first user and the second user as samples, and the second user is a user who accesses the insurance product information on the product page and purchases the insurance product;
[0081] A user information acquisition unit 240, configured to acquire user information of the first user if the target insurance level is greater than a preset insurance level;
[0082] The communication unit 250 is configured to send the user information to a user equipment of a target user.
[0083] The information push device 200 based on deep learning may further include a storage unit 260 for storing program code and data of the terminal. The storage unit 260 may be a memory. When the storage unit 260 is a memory, the information push device 200 based on deep learning involved in the embodiment of the present application may be Figure 4 Electronic equipment shown.
[0084] It should be noted that the specific implementation of each operation can be found in the above Figure 1 The description in the method embodiment shown will not be repeated in detail here.
[0085] It can be seen that in the embodiment of the present application, first, after obtaining the online information of the first user who accessed the insurance product information on the product page but did not purchase the insurance product, the insurance characteristic information corresponding to the insurance index is obtained according to the online information, and then the insurance characteristic information is imported into the network model constructed and trained using the insurance characteristic information of the first user and the second user as samples to obtain the target insurance level of the first user. The second user is a user who accesses the insurance product information on the product page and purchases the insurance product. If the target insurance level is greater than the preset insurance level, the user information of the first user is obtained, and then the user information is sent to the user device of the target user. It can be seen that by adopting the present application, potential insured customers with higher insurance levels screened out from online customers are pushed to product account managers, thereby improving the marketing success rate and the efficiency of insurance marketing.
[0086] In a possible example, the insurance characteristic information includes the first user's online page column, online channel, online operation, online time, online number of times, total online time, and insurance policy information viewed each time the online user accesses the Internet.
[0087] In a possible example, the target network model is obtained by performing the following operations: extracting insurance feature information from the online access information of the first user and the second user; extracting the insurance feature information corresponding to part of the first user and part of the second user respectively to construct a training set; extracting the insurance feature information corresponding to the remaining second user and the remaining second user respectively to construct a test set; using multiple classification methods and constructing an insurance grade classification model to be tested based on the training set; inputting the test set into each insurance grade classification model to be tested respectively, sorting the verification results of each insurance grade classification model to be tested, and selecting several insurance grade classification models to be tested as the insurance grade classification model according to the sorting.
[0088] In one possible example, user information includes but is not limited to at least one of the following: the name, gender, age, current address, native place, etc. of the customer who accesses the Internet and purchases the insurance policy, the type of insurance policy purchased each time, the premium, the insurance period, the purchase channel, the insurer of the insurance policy purchased each time, and the relationship between the customer who accesses the Internet and purchases the insurance policy and the insurer.
[0089] In one possible example, the user information includes the current address of the first user. In terms of sending the user information to the user device of the target user, the communication unit 250 is specifically used to determine at least one of the target users whose office address is closest to the current address based on the current address of the first user.
[0090] In one possible example, the user information includes the current address of the first user. In terms of sending the user information to the user device of the target user, the communication unit 250 is specifically used to: determine at least one third user whose office address is within a preset range from the current address of the first user; obtain points from the at least one third user, wherein the points are used to indicate the user service level; and determine the user with the highest points among the at least one third user as the target user.
[0091] In a possible example, the network access information acquisition unit is also used to: after importing the insurance feature information into a trained target network model to obtain the target insurance level of the first user, if the target insurance level is less than or equal to the preset insurance level, obtain the network access information of the first user.
[0092] See also Figure 4 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 4 The electronic device 300 in the embodiment shown may include: a processing module 310, a memory 320, a communication interface 330, and one or more programs 321, wherein the one or more programs 321 are stored in the memory 320 and are configured to be executed by the processing module 310, and the one or more programs 321 include instructions for executing the steps in the method described below:
[0093] Acquire online access information of a first user, where the first user is a user who accesses insurance product information on a product page but does not purchase the insurance product, and the online access information is used to indicate the operation of the first user on the insurance product information on the product page;
[0094] Obtaining insurance characteristic information corresponding to the insurance index according to the online access information;
[0095] Importing the insurance feature information into the trained target network model to obtain the target insurance level of the first user, wherein the target insurance level refers to the insurance level of the first user, and the target network model is a network model constructed and trained using the insurance feature information of the first user and the second user as samples, and the second user is a user who accesses the insurance product information on the product page and purchases the insurance product;
[0096] If the target insurance level is greater than the preset insurance level, obtaining user information of the first user;
[0097] The user information is sent to a user device of a target user.
[0098] The processing module 310 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0099] It should be noted that the specific implementation of each operation can be found in the above Figure 2 The description in the method embodiment shown will not be repeated in detail here.
[0100] It can be seen that in the embodiment of the present application, first, after obtaining the online information of the first user who accessed the insurance product information on the product page but did not purchase the insurance product, the insurance characteristic information corresponding to the insurance index is obtained according to the online information, and then the insurance characteristic information is imported into the network model constructed and trained using the insurance characteristic information of the first user and the second user as samples to obtain the target insurance level of the first user. The second user is a user who accesses the insurance product information on the product page and purchases the insurance product. If the target insurance level is greater than the preset insurance level, the user information of the first user is obtained, and then the user information is sent to the user device of the target user. It can be seen that by adopting the present application, potential insured customers with higher insurance levels screened out from online customers are pushed to product account managers, thereby improving the marketing success rate and the efficiency of insurance marketing.
[0101] In a possible example, the insurance characteristic information includes the first user's online page column, online channel, online operation, online time, online number of times, total online time, and insurance policy information viewed each time the online user accesses the Internet.
[0102] In a possible example, the target network model is obtained by performing the following operations: extracting insurance feature information from the online access information of the first user and the second user; extracting the insurance feature information corresponding to part of the first user and part of the second user respectively to construct a training set; extracting the insurance feature information corresponding to the remaining second user and the remaining second user respectively to construct a test set; using multiple classification methods and constructing an insurance grade classification model to be tested based on the training set; inputting the test set into each insurance grade classification model to be tested respectively, sorting the verification results of each insurance grade classification model to be tested, and selecting several insurance grade classification models to be tested as the insurance grade classification model according to the sorting.
[0103] In one possible example, user information includes but is not limited to at least one of the following: the name, gender, age, current address, native place, etc. of the customer who accesses the Internet and purchases the insurance policy, the type of insurance policy purchased each time, the premium, the insurance period, the purchase channel, the insurer of the insurance policy purchased each time, and the relationship between the customer who accesses the Internet and purchases the insurance policy and the insurer.
[0104] In one possible example, the user information includes the current address of the first user, and in terms of sending the user information to the user device of the target user, the instructions in the one or more programs 321 are specifically used to: determine at least one of the target users whose office address is closest to the current address based on the current address of the first user.
[0105] In one possible example, the user information includes the current address of the first user. In terms of sending the user information to the user device of the target user, the instructions in the one or more programs 321 are specifically used to: determine at least one third user whose office address is within a preset range from the current address of the first user; obtain points from the at least one third user, wherein the points are used to indicate the user service level; and determine the user with the highest points among the at least one third user as the target user.
[0106] In a possible example, the network access information acquisition unit is also used to: after importing the insurance feature information into a trained target network model to obtain the target insurance level of the first user, if the target insurance level is less than or equal to the preset insurance level, obtain the network access information of the first user.
[0107] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the following is implemented: Figure 2 The information push method based on deep learning shown in the embodiment.
[0108] The computer-readable storage medium may be an internal storage unit of the electronic device described in any of the foregoing embodiments, such as a hard disk or memory of a control device. The computer-readable storage medium may also be an external storage device of the control device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the control device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the control device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the control device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
[0109] As an example, the computer-readable storage medium may be deployed on a computer device for execution, or deployed on multiple computer devices located at one location for execution, or executed on multiple computer devices distributed at multiple locations and interconnected through a communication network. Multiple computer devices distributed at multiple locations and interconnected through a communication network may constitute a blockchain network.
[0110] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
[0111] In the embodiments provided by the present invention, user data such as the customer's name, gender, age, current address, native place, type of policy purchased each time, premium, insurance period, purchase channel, the insurer of each policy purchased, and the relationship between the customer who accesses the Internet and purchases the policy and the insurer are all obtained with the user's consent, and the obtained user data comply with the provisions of relevant policies and laws and regulations.
Claims
1. A method for pushing information based on deep learning, characterized in that: include: Acquire online access information of a first user, where the first user is a user who accesses insurance product information on a product page but does not purchase the insurance product, and the online access information is used to indicate the operation of the first user on the insurance product information on the product page; Obtaining insurance characteristic information corresponding to the insurance index according to the online access information; The insurance characteristic information includes the first user's online access page column, online access channel, online access operation, online access time, online access number, total online access time, and insurance policy information viewed each time online access; Importing the insurance feature information into the trained target network model to obtain the target insurance level of the first user, wherein the target insurance level refers to the insurance level of the first user, and the target network model is a network model constructed and trained using the insurance feature information of the first user and the second user as samples, and the second user is a user who accesses the insurance product information on the product page and purchases the insurance product; If the target insurance level is greater than the preset insurance level, obtaining user information of the first user; Sending the user information to a user device of a target user; The target network model is obtained by performing the following operations: Extracting insurance feature information from online information of the first user and the second user; Extracting insurance feature information corresponding to part of the first user and part of the second user respectively, and constructing a training set; Extract the remaining second users and the insurance feature information corresponding to the remaining second users respectively, and construct a test set; Adopting multiple classification methods and constructing a classification model of the insurance grade to be tested according to the training set; Input the test set into each insurance grade classification model to be tested respectively, sort the verification results of each insurance grade classification model to be tested, and select several insurance grade classification models to be tested as the insurance grade classification model according to the sorting; The training process of the target network model includes: connecting the feature input layer with a fully connected layer having 256 neurons, and then using the Relu function as an activation function; using a batch normalization layer and a Dropout layer to avoid model overfitting, and the dropout parameter is set to 0.4; then continuously connecting two fully connected layers, which contain 128 and 64 neurons respectively, and both use the Relu function as an activation function to complete a further abstract representation of the data features; finally, using a decision layer with 6 neurons to determine the insurance grade of each customer, the softmax function will output the probability of the customer corresponding to the 6 insurance grades, and the one with the highest probability among the 6 insurance grades will be taken as the insurance grade of this customer.
2. The method according to claim 1, characterized in that The user information includes the current address of the first user, and sending the user information to the user equipment of the target user includes: At least one target user whose office address is closest to the current address is determined according to the current address of the first user.
3. The method according to claim 1, characterized in that: The user information includes the current address of the first user, and sending the user information to the user equipment of the target user includes: Determine, based on the current residence of the first user, at least one third user whose office address is within a preset range from the current residence; Acquire points of the at least one third user, where the points are used to indicate a user service level; A user with the highest score among the at least one third user is determined as the target user.
4. The method according to claim 1, characterized in that: After importing the insurance feature information into the trained target network model to obtain the target insurance level of the first user, the method further includes: If the target insurance level is less than or equal to the preset insurance level, the network access information of the first user is obtained.
5. A device for information push based on deep learning, characterized in that: include: a network access information acquisition unit, configured to acquire network access information of a first user, wherein the first user is a user who accesses insurance product information on a product page but does not purchase the insurance product, and the network access information is used to indicate the operation of the first user on the insurance product information on the product page; an insurance characteristic information acquisition unit, configured to obtain insurance characteristic information corresponding to the insurance index according to the online access information; the insurance characteristic information includes the online access page column, online access channel, online access operation, online access time, online access number, total online access time, and insurance policy information viewed each time the online access is performed by the first user; an insurance grade acquisition unit, configured to import the insurance feature information into a trained target network model to obtain a target insurance grade of the first user, wherein the target insurance grade refers to the insurance grade of the first user, and the target network model is a network model constructed and trained using the insurance feature information of the first user and the second user as samples, wherein the second user is a user who accesses insurance product information on a product page and purchases an insurance product; A user information acquisition unit, configured to acquire user information of the first user if the target insurance level is greater than a preset insurance level; A communication unit, used to send the user information to a user equipment of a target user; The target network model is obtained by performing the following operations: Extracting insurance feature information from online information of the first user and the second user; Extracting insurance feature information corresponding to part of the first user and part of the second user respectively, and constructing a training set; Extract the remaining second users and the insurance feature information corresponding to the remaining second users respectively, and construct a test set; Adopting multiple classification methods and constructing a classification model of the insurance grade to be tested according to the training set; Input the test set into each insurance grade classification model to be tested respectively, sort the verification results of each insurance grade classification model to be tested, and select several insurance grade classification models to be tested as the insurance grade classification model according to the sorting; The training process of the target network model includes: connecting the feature input layer with a fully connected layer having 256 neurons, and then using the Relu function as an activation function; using a batch normalization layer and a Dropout layer to avoid model overfitting, and the dropout parameter is set to 0.4; then continuously connecting two fully connected layers, which contain 128 and 64 neurons respectively, and both use the Relu function as an activation function to complete a further abstract representation of the data features; finally, using a decision layer with 6 neurons to determine the insurance grade of each customer, the softmax function will output the probability of the customer corresponding to the 6 insurance grades, and the one with the highest probability among the 6 insurance grades will be taken as the insurance grade of this customer.
6. An electronic device, characterized in that: The method comprises a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for executing the steps in the method according to any one of claims 1 to 4.
7. A computer-readable storage medium, characterized in that: A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the steps in the method according to any one of claims 1 to 4.
