CN109360072A - Insurance products recommended method, device, computer equipment and storage medium - Google Patents
Insurance products recommended method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109360072A CN109360072A CN201811347747.9A CN201811347747A CN109360072A CN 109360072 A CN109360072 A CN 109360072A CN 201811347747 A CN201811347747 A CN 201811347747A CN 109360072 A CN109360072 A CN 109360072A
- Authority
- CN
- China
- Prior art keywords
- insurance products
- personality
- label
- user
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention discloses a kind of insurance products recommended method, device, computer equipment and storage medium, include the following steps: the musical life data for obtaining user；The feature of the musical life data is input in preset personality identification neural network model, the personality label of the user is obtained；The target insurance products with the personality tag match are chosen from preset insurance products database, and the target insurance products are pushed in the webpage that the user logs in.Since music data can really reflect the character trait of user, it on the one hand can targetedly recommend insurance products, improve the purchase conversion rate of insurance products；On the other hand, for having for the user of purchase demand for insurance, the insurance products for meeting self-demand can be timely got, process is convenient, and then saves the energy of user.
Description
Technical field
The present embodiments relate to financial field, especially a kind of insurance products recommended method, device, computer equipment and
Storage medium.
Background technique
With the development of internet technology, more and more industries use internet form, for example, microblogging, music,
Shopping, communication, financial product etc., provide a great convenience for people's lives.Wherein, financial product includes various financing works
Tool, for example, insurance products.
Insurance is a kind of tool for planning life finance, is the basic means of risk management under condition of market economy,
It is the mainstay of finance and social security.With gradually increasing for people's finance sense, insurance becomes common financing means.
In the prior art, when user buys insurance products, need to seek advice from insurance agent to select the insurance products for being suitble to oneself, process
It is complex.Meanwhile insurance company, when recommending insurance products to user, without specific target user, cause to recommend turns
It is lower to change rate.
Summary of the invention
The embodiment of the present invention provides a kind of insurance products recommended method, device, computer equipment and storage medium.
In order to solve the above technical problems, the technical solution that the embodiment of the invention uses is: providing a kind of guarantor
Dangerous Products Show method, includes the following steps:
Obtain the musical life data of user；
The feature of the musical life data is input in preset personality identification neural network model, the use is obtained
The personality label at family；
The target insurance products with the personality tag match are chosen from preset insurance products database, and will be described
Target insurance products are pushed in the webpage that the user logs in.
Optionally, in the insurance products database, each insurance products include the personality label of applicable group；Institute
State the target insurance products chosen from preset insurance products database with the personality tag match, comprising:
The personality label of the user is compared with the label of insurance products in the insurance products database；
When the alignment is identical, insurance products pointed by consistent label will be compared as the target insurance products.
Optionally, described from default when the label of the personality label of the user and the insurance products is multiple
Insurance products database in choose and the target insurance products of the personality tag match, comprising:
The personality label of the user is compared with the label of insurance products in the insurance products database；
When there are identical marks for the personality label and the labels of insurance products in the insurance products database of the user
When label, number of labels identical with the personality label of the user in each insurance products is determined；
Using the most insurance products of number of labels as the target insurance products.
Optionally, the feature by the musical life data is input to preset personality identification neural network model
In, before obtaining the personality label of the user, further include
Feature is extracted to the musical life data by preset feature extraction software.
Optionally, described that the music data is input in preset personality identification neural network model, it obtains described
Before the personality label of user, further includes:
Obtain the music samples data for being marked with personality label；
Preset convolutional neural networks model is trained according to the music samples data, obtains identifying the personality
The personality of label identifies neural network model.
It is optionally, described that preset convolutional neural networks model is trained according to the music samples data, comprising:
Musical features are extracted from the music samples data, and calculate the expectation of musical features in every kind of personality label
Value；
The musical features are input in preset convolutional neural networks model, the convolutional neural networks model is obtained
In every kind of personality label excitation value；
Compare whether the distance between desired value and excitation value of every kind of personality label is less than or equal to preset threshold value, and
When the distance between the desired value and the excitation value are greater than threshold value, being updated by inverse algorithms for iterative cycles iteration is rolled up
Weight in product neural network model, until the distance between the desired value and the excitation value are less than or equal to preset first
Terminate when threshold value.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of insurance products recommendation apparatus, comprising:
Module is obtained, for obtaining the musical life data of user；
Processing module identifies neural network model for the feature of the musical life data to be input to preset personality
In, obtain the personality label of the user；
Execution module is insured for choosing from preset insurance products database with the target of the personality tag match
Product, and the target insurance products are pushed in the webpage that the user logs in.
Optionally, in the insurance products database, each insurance products include the personality label of applicable group；Institute
Stating execution module includes:
First processing submodule, for by insurance products in the personality label of the user and the insurance products database
Label be compared；
First implementation sub-module, for when the alignment is identical, will compare insurance products pointed by consistent label as
The target insurance products.
Optionally, when the label of the personality label of the user and the insurance products is multiple, the execution mould
Block includes:
Second processing submodule, for by insurance products in the personality label of the user and the insurance products database
Label be compared；
Second implementation sub-module, for when insurance products in the personality label and the insurance products database of the user
Label there are when identical label, determine number of tags identical with the personality label of the user in each insurance products
Amount；
Third implementation sub-module, for using the most insurance products of number of labels as the target insurance products.
Optionally, further includes:
Third handles submodule, for extracting feature to the musical life data by preset feature extraction software.
Optionally, further includes:
First acquisition submodule, for obtaining the music samples data for being marked with personality label；
Fourth process submodule, for being instructed according to the music samples data to preset convolutional neural networks model
Practice, obtains the personality identification neural network model for identifying the personality label.
Optionally, the fourth process submodule includes:
Second acquisition submodule for extracting musical features from the music samples data, and calculates every kind of personality mark
The desired value of musical features in label；
5th processing submodule is obtained for the musical features to be input in preset convolutional neural networks model
The excitation value of every kind of personality label in the convolutional neural networks model；
4th implementation sub-module, for comparing whether the distance between the desired value of every kind of personality label and excitation value are less than
Or it is equal to preset threshold value, and when the distance between the desired value and the excitation value are greater than threshold value, iterative cycles iteration
By inverse algorithms update convolutional neural networks model in weight, until the distance between the desired value and the excitation value
Terminate when less than or equal to preset first threshold.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of computer equipment, including memory and processing
Device is stored with computer-readable instruction in the memory, when the computer-readable instruction is executed by the processor, so that
The processor executes the step of insurance products recommended method described above.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of storage Jie for being stored with computer-readable instruction
Matter, when the computer-readable instruction is executed by one or more processors, so that one or more processors execute above-mentioned institute
The step of stating insurance products recommended method.
The beneficial effect of the embodiment of the present invention is: by the way that the feature of the musical life data of user is input to preset property
Lattice identify in neural network model, obtain the personality label of user, and recommend insurance products according to the personality label of user, by
It can really reflect the character trait of user in music data, therefore, on the one hand can targetedly recommend insurance products, mention
The purchase conversion rate of high insurance products；On the other hand, it for having for the user of purchase demand for insurance, can timely get
Meet the insurance products of self-demand, process is convenient, and then saves the energy of user.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the basic procedure schematic diagram of insurance products recommended method provided in an embodiment of the present invention；
Fig. 2 is that one kind provided in an embodiment of the present invention is chosen and personality tag match from preset insurance products database
Target insurance products method basic procedure schematic diagram；
Fig. 3 is that one kind provided in an embodiment of the present invention is chosen and the personality label from preset insurance products database
The basic procedure schematic diagram of the method for matched target insurance products；
Fig. 4 is a kind of basic procedure signal of training method of personality neural network model provided in an embodiment of the present invention
Figure；
Fig. 5 be it is provided in an embodiment of the present invention it is a kind of according to music samples data to preset convolutional neural networks model into
The basic procedure schematic diagram of the method for row training；
Fig. 6 is insurance products of embodiment of the present invention recommendation apparatus basic structure block diagram；
Fig. 7 is computer equipment of embodiment of the present invention basic structure block diagram.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.
In some processes of the description in description and claims of this specification and above-mentioned attached drawing, contain according to
Multiple operations that particular order occurs, but it should be clearly understood that these operations can not be what appears in this article suitable according to its
Sequence is executed or is executed parallel, and serial number of operation such as 101,102 etc. is only used for distinguishing each different operation, serial number
It itself does not represent and any executes sequence.In addition, these processes may include more or fewer operations, and these operations can
To execute or execute parallel in order.It should be noted that the description such as " first " herein, " second ", is for distinguishing not
Same message, equipment, module etc., does not represent sequencing, does not also limit " first " and " second " and be different type.
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those skilled in the art's every other implementation obtained without creative efforts
Example, shall fall within the protection scope of the present invention.
Embodiment
Those skilled in the art of the present technique are appreciated that " terminal " used herein above, " terminal device " both include wireless communication
The equipment of number receiver, only has the equipment of the wireless signal receiver of non-emissive ability, and including receiving and emitting hardware
Equipment, have on bidirectional communication link, can execute two-way communication reception and emit hardware equipment.This equipment
It may include: honeycomb or other communication equipments, shown with single line display or multi-line display or without multi-line
The honeycomb of device or other communication equipments；PCS (Personal Communications Service, PCS Personal Communications System), can
With combine voice, data processing, fax and/or communication ability；PDA (Personal Digital Assistant, it is personal
Digital assistants), it may include radio frequency receiver, pager, the Internet/intranet access, web browser, notepad, day
It goes through and/or GPS (Global Positioning System, global positioning system) receiver；Conventional laptop and/or palm
Type computer or other equipment, have and/or the conventional laptop including radio frequency receiver and/or palmtop computer or its
His equipment." terminal " used herein above, " terminal device " can be it is portable, can transport, be mounted on the vehicles (aviation,
Sea-freight and/or land) in, or be suitable for and/or be configured in local runtime, and/or with distribution form, operate in the earth
And/or any other position operation in space." terminal " used herein above, " terminal device " can also be communication terminal, on
Network termination, music/video playback terminal, such as can be PDA, MID (Mobile Internet Device, mobile Internet
Equipment) and/or mobile phone with music/video playing function, it is also possible to the equipment such as smart television, set-top box.
Client terminal in present embodiment is above-mentioned terminal.
Specifically, referring to Fig. 1, Fig. 1 is the basic procedure schematic diagram of the present embodiment insurance products recommended method.
As shown in Figure 1, insurance products recommended method includes the following steps:
S1100, the musical life data for obtaining user；
Musical life data are user in various platforms, such as the music often listened to or downloaded on music software, including
The audio file of multiple format, for example, MP3, WAVE, WMA, VQF, MIDI, AIFF, MPEG etc..
S1200, the feature of musical life data is input in preset personality identification neural network model, obtains user
Personality label；
Feature extraction is carried out to musical life data by predetermined software, for example, the audio in musical life data is defeated
Enter to obtain the spectrogram of the audio into software, for example, PC Sound Spectrum software, FFT spectrum analysis software,
SmaartLive software etc..In practical applications, in order to make, the frequency in frequency map is continuous, understands usually in transformation frequency figure
During spectrum, preemphasis, adding window and Fourier transformation are carried out to audio to be evaluated and handled.
In the embodiment of the present invention, feature is extracted to audio file by softmax software.Wherein, the feature of extraction
For frequency transformation map.
Personality identification neural network model is to first pass through to be marked with the music samples data of character trait and be trained in advance
Model.By the style difference for the music that the user of different characters feature is liked, so, it can often be received by analyzing user
It listens or the music downloaded analyzes the personality of user, for example, the more export-oriented user of personality is partial to listen to cheerful and light-hearted, dynamic sound
Happy, the more introversive user of personality is partial to listen to the music that comparison is expressed one's emotion, melody is soft.By musical features, i.e. audible spectrum
It is input in the personality neural network model, the character trait that the music is characterized can be obtained.
It is divided it should be noted that character trait can be divided into according to existing a variety of division rules, for example,
It can be divided into: lively type, strength type, perfect type and and flat pattern.
S1300, chosen from preset insurance products database with the target insurance products of personality tag match, and by mesh
Mark insurance products are pushed in the webpage of user's login.
Target insurance products are the insurance products for recommending user in embodiments of the present invention, wherein target insurance products
It may include various types of insurances, for example, serious illness insurance, vehicle insurance, life insurance, Shao Erxian, travelling danger, danger of returning goods, delay danger etc..Its
In, each insurance products is suitble to the crowd of different characters feature, for example, the people of perfect type personality is sensitive, is easy self-sacrifice,
Emotion is not easy to discharge, and the risk suffered from the disease is higher, is suitble to serious illness insurance, serious illness insurance can be pushed to the user of perfect type personality.
Above-mentioned insurance products recommended method is known by the way that the feature of the musical life data of user is input to preset personality
In other neural network model, the personality label of user is obtained, and recommend insurance products according to the personality label of user, due to sound
Happy data can really reflect the character trait of user, therefore, on the one hand can targetedly recommend insurance products, improve and protect
The purchase conversion rate of dangerous product；On the other hand, for having for the user of purchase demand for insurance, it can timely get and meet
The insurance products of self-demand, process is convenient, and then saves the energy of user.
In practical applications, terminal or server are preset with insurance products database, in insurance products database, often
A insurance products all include the personality label of applicable group, and the embodiment of the present invention provides a kind of from preset insurance products data
The method with the target insurance products of personality tag match is chosen in library, as shown in Fig. 2, Fig. 2 is provided in an embodiment of the present invention
A kind of basic procedure chosen from preset insurance products database with the method for the target insurance products of personality tag match
Schematic diagram.
Specifically, as shown in Fig. 2, step S1300 includes the following steps:
S1311, the personality label of user is compared with the label of insurance products in insurance products database；
The personality label of user is that the feature card of the corresponding musical life data of user is input to personality to identify nerve net
Label corresponding to output valve after network model.The tagging user indicates the personality classification of user, for example, the label can mark
For lively type, strength type, perfect type or and flat pattern, the personality divided for other personality division modes can also be marked special
Sign.
In the embodiment of the present invention, each insurance products in insurance database are marked with the label of suitable character trait, example
Such as, weight disease insurance products are marked with " perfect type ", and X travel accident insurance is marked with " lively type ", wherein insurance products are also marked with other
Personality division mode divide personality label.By the way that the text of user tag and insurance products label or user are indicated to mark
The symbol of label feature is compared.
S1312, when the alignment is identical, will compare insurance products pointed by consistent label as target insurance products.
It in the embodiment of the present invention, compares consistent, it is determined that the insurance products are matched with user, and the insurance which is directed toward produces
Product are target labels insurance products.For example, it is above-mentioned when the label of the label of user and insurance products is " perfect type ", then really
The heavy disease insurance products that fixed " perfect type " is directed toward are target insurance products.
In practical applications, since the division of character trait contains a variety of, and there may be two kinds of personality by each user
Feature, that is, in view of the centre of two kinds of character traits.In this case, when the personality label of user and the label of insurance products
When being multiple, the embodiment of the present invention provides one kind and chooses and the personality tag match from preset insurance products database
Target insurance products method, as shown in figure 3, Fig. 3 is provided in an embodiment of the present invention a kind of from preset insurance products number
According to the basic procedure schematic diagram chosen in library with the method for the target insurance products of the personality tag match.
Specifically, as shown in figure 3, step S1300 includes the following steps:
S1321, the personality label of user is compared with the label of insurance products in insurance products database；
In the embodiment of the present invention, the comparison of the label of insurance products in the personality label of user and the database of insurance products
Method is referring to embodiment shown in Fig. 2, and details are not described herein.
S1322, when there are identical labels for the personality label and the labels of insurance products in insurance products database of user
When, determine number of labels identical with the personality label of user in each insurance products；
S1323, using the most insurance products of number of labels as target insurance products.
When multiple labels compare it is consistent when, in order to improve matched precision, in the embodiment of the present invention, obtain the property of user
The label of case marker label and insurance products compares consistent quantity, for example, user has tetra- labels of A, B, C and D, insurance products 1 have
A, tri- labels of B and C, insurance products 2 have tetra- labels of A, B, D and E, and insurance products 3 have two labels of A and C, since insurance produces
There are two identical labels there are three identical label, insurance products 2 and insurance products 3 and user by product 1 and user, therefore, really
Determine insurance products 1 to match with user, the target insurance products of user are insurance products 1.
The embodiment of the present invention also provides a kind of training method of personality neural network model, as shown in figure 4, Fig. 4 is this hair
A kind of basic procedure schematic diagram of the training method for personality neural network model that bright embodiment provides.
Specifically, as shown in figure 4, further including following step before step S1200:
S1210, acquisition are marked with the music samples data of personality label；
Music samples data are the training sample image set for being trained to convolutional neural networks model, are to include
The audio set of a variety of character traits, the set are divided into multiple groups, and each group includes the multiple audios for being marked with identical character trait.
It should be noted that convolutional neural networks model is CNN convolutional neural networks model or VGG convolutional neural networks mould
Type.
S1220, preset convolutional neural networks model is trained according to music samples data, obtains identity case marker
The personality of label identifies neural network model.
The embodiment of the present invention, which also provides, a kind of instructs preset convolutional neural networks model according to music samples data
Experienced method, as shown in figure 5, Fig. 5 is provided in an embodiment of the present invention a kind of refreshing to preset convolution according to music samples data
The basic procedure schematic diagram for the method being trained through network model.
Specifically, as shown in figure 5, step S1220 includes the following steps:
S1221, musical features are extracted from music samples data, and calculate the expectation of musical features in every kind of personality label
Value；
In the embodiment of the present invention, it can use preset software and extract musical features from music samples data, for example, PC
Sound Spectrum software, FFT spectrum analysis software, SmaartLive software etc..In practical applications, in order to make frequency diagram
Frequency in spectrum is continuous, clear usually during transformation frequency map, carries out preemphasis, adding window and Fu to audio to be evaluated
In leaf transformation handle.
In the embodiment of the present invention, feature is extracted to audio file by softmax software.
The musical features of every group of character trait are input in convolutional neural networks model, the defeated of each musical features is obtained
It is worth out, and output valve is ranked up, takes median as the desired value of every group of character trait.
S1222, musical features are input in preset convolutional neural networks model, are obtained in convolutional neural networks model
The excitation value of every kind of personality label；
In the embodiment of the present invention, the musical features image of every group of character trait is sequentially inputted in neural network model,
Neural network model carries out feature extraction and classification to musical features image.
Excitation value is the excited data that convolutional neural networks model is exported according to the musical features image of input, in nerve
Network model is not trained to before convergence, and excitation value is the biggish numerical value of discreteness, when neural network model is trained to receipts
After holding back, excitation value is metastable data.
It is preset whether the distance between S1223, the desired value for comparing every kind of personality label and excitation value are less than or equal to
Threshold value, and when the distance between the desired value and the excitation value are greater than threshold value, passing through for iterative cycles iteration is reversely calculated
Method updates the weight in convolutional neural networks model, until the distance between the desired value and the excitation value are less than or equal in advance
If first threshold when terminate.
By loss function judge neural network model full articulamentum output excitation value and setting desired value whether one
It causes, when result is inconsistent, needs to be adjusted the weight in first passage by back-propagation algorithm.
In some embodiments, loss function by calculate excitation classification value and setting expectation classification value between away from
From (Euclidean distance or space length), whether the expectation classification value to determine excitation classification value and setting is consistent, setting first
Threshold value, when the distance between excitation value and the expectation classification value of setting are less than or equal to first threshold, it is determined that excitation classification
Value is consistent with the desired value of setting, and otherwise, then excitation value and the desired value of setting are inconsistent.
When the desired value of the excitation value of neural network model and setting is inconsistent, need using stochastic gradient descent algorithm
Weight in neural network model is corrected, so that the output result of convolutional neural networks model and classification judge information
Expected result is identical.By several training sample sets (by the photograph in all training sample sets when in some embodiments, training
Piece, which is upset, to be trained, with increase model by interference performance, enhance the stability of output.By training and correction repeatedly,
When the classification of neural network model output category data and each training sample reaches and (is not limited to) 99.5% referring to information comparison,
Training terminates.
The embodiment of the present invention also provides a kind of insurance products recommendation apparatus to solve above-mentioned technical problem.Referring specifically to figure
6, Fig. 6 be the present embodiment insurance products recommendation apparatus basic structure block diagram.
As shown in fig. 6, a kind of insurance products recommendation apparatus, comprising: obtain module 2100, processing module 2200 and execute mould
Block 2300.Wherein, module 2100 is obtained, for obtaining the musical life data of user；Processing module 2200 is used for the sound
The feature of happy activity data is input in preset personality identification neural network model, obtains the personality label of the user；It holds
Row module 2300, for choosing the target insurance products with the personality tag match from preset insurance products database,
And the target insurance products are pushed in the webpage that the user logs in.
Insurance products recommendation apparatus identifies mind by the way that the feature of the musical life data of user is input to preset personality
Recommend insurance products through in network model, obtaining the personality label of user, and according to the personality label of user, due to music number
It according to the character trait that can really reflect user, therefore, on the one hand can targetedly recommend insurance products, improve insurance and produce
The purchase conversion rate of product；On the other hand, for having for the user of purchase demand for insurance, it can timely get and meet itself
The insurance products of demand, process is convenient, and then saves the energy of user.
In some embodiments, in the insurance products database, each insurance products include applicable group
Personality label；The execution module includes: the first processing submodule, for producing the personality label of the user and the insurance
The label of insurance products is compared in product database；First implementation sub-module, for that when the alignment is identical, will compare consistent
Insurance products pointed by label are as the target insurance products.
In some embodiments, when the label of the personality label of the user and the insurance products is multiple,
The execution module includes: second processing submodule, for by the personality label of the user and the insurance products database
The label of middle insurance products is compared；Second implementation sub-module, for being produced when the personality label of the user and the insurance
The label of insurance products determines the personality in each insurance products with the user there are when identical label in product database
The identical number of labels of label；Third implementation sub-module, for being protected using the most insurance products of number of labels as the target
Dangerous product.
In some embodiments, further includes: third handles submodule, is used for through preset feature extraction software to institute
It states musical life data and extracts feature.
In some embodiments, further includes: the first acquisition submodule, for obtaining the music sample for being marked with personality label
Notebook data；Fourth process submodule, for being instructed according to the music samples data to preset convolutional neural networks model
Practice, obtains the personality identification neural network model for identifying the personality label.
In some embodiments, the fourth process submodule includes: the second acquisition submodule, is used for from the music
Musical features are extracted in sample data, and calculate the desired value of musical features in every kind of personality label；5th processing submodule, is used
In the musical features are input in preset convolutional neural networks model, every kind is obtained in the convolutional neural networks model
The excitation value of personality label；4th implementation sub-module, between the desired value and excitation value for comparing every kind of personality label away from
From whether being less than or equal to preset threshold value, and when the distance between the desired value and the excitation value are greater than threshold value, instead
Multiple loop iteration updates the weight in convolutional neural networks model by inverse algorithms, until the desired value and the excitation value
The distance between be less than or equal to preset first threshold when terminate.
In order to solve the above technical problems, the embodiment of the present invention also provides computer equipment.It is this referring specifically to Fig. 7, Fig. 7
Embodiment computer equipment basic structure block diagram.
As shown in fig. 7, the schematic diagram of internal structure of computer equipment.As shown in fig. 7, the computer equipment includes passing through to be
Processor, non-volatile memory medium, memory and the network interface of bus of uniting connection.Wherein, the computer equipment is non-easy
The property lost storage medium is stored with operating system, database and computer-readable instruction, can be stored with control information sequence in database
Column, when which is executed by processor, may make processor to realize a kind of insurance products recommended method.The calculating
The processor of machine equipment supports the operation of entire computer equipment for providing calculating and control ability.The computer equipment
It can be stored with computer-readable instruction in memory, when which is executed by processor, processor may make to hold
A kind of insurance products recommended method of row.The network interface of the computer equipment is used for and terminal connection communication.Those skilled in the art
Member is appreciated that structure shown in Fig. 7, only the block diagram of part-structure relevant to application scheme, composition pair
The restriction for the computer equipment that application scheme is applied thereon, specific computer equipment may include than as shown in the figure more
More or less component perhaps combines certain components or with different component layouts.
Processor obtains module 2100, processing module 2200 and execution module for executing in present embodiment in Fig. 6
2300 particular content, program code and Various types of data needed for memory is stored with the above-mentioned module of execution.Network interface is used for
To the data transmission between user terminal or server.Memory in present embodiment is stored in insurance products recommended method
Program code needed for executing all submodules and data, server is capable of the program code of invoking server and data execute institute
There is the function of submodule.
Computer equipment identifies neural network by the way that the feature of the musical life data of user is input to preset personality
In model, the personality label of user is obtained, and recommend insurance products according to the personality label of user, since music data can be true
Therefore on the one hand the character trait of real reflection user can targetedly recommend insurance products, improve the purchase of insurance products
Buy conversion ratio；On the other hand, for having for the user of purchase demand for insurance, it can timely get and meet self-demand
Insurance products, process is convenient, and then saves the energy of user.
The present invention also provides a kind of storage mediums for being stored with computer-readable instruction, and the computer-readable instruction is by one
When a or multiple processors execute, so that one or more processors execute insurance products recommendation side described in any of the above-described embodiment
The step of method.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, which can be stored in a computer-readable storage and be situated between
In matter, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, storage medium above-mentioned can be
The non-volatile memory mediums such as magnetic disk, CD, read-only memory (Read-Only Memory, ROM) or random storage note
Recall body (Random Access Memory, RAM) etc..
It should be understood that although each step in the flow chart of attached drawing is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, can execute in the other order.Moreover, at least one in the flow chart of attached drawing
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, execution sequence, which is also not necessarily, successively to be carried out, but can be with other
At least part of the sub-step or stage of step or other steps executes in turn or alternately.
The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of recommended method of insurance products, which is characterized in that include the following steps:
Obtain the musical life data of user；
The feature of the musical life data is input in preset personality identification neural network model, obtains the user's
Personality label；
Chosen from preset insurance products database with the target insurance products of the personality tag match, and by the target
Insurance products are pushed in the webpage that the user logs in.
2. the recommended method of insurance products according to claim 1, which is characterized in that in the insurance products database,
Each insurance products include the personality label of applicable group；It is described from preset insurance products database choose with it is described
The target insurance products of personality tag match, comprising:
The personality label of the user is compared with the label of insurance products in the insurance products database；
When the alignment is identical, insurance products pointed by consistent label will be compared as the target insurance products.
3. the recommended method of insurance products according to claim 1, which is characterized in that when the user personality label and
It is described to be chosen and the personality label from preset insurance products database when the label of the insurance products is multiple
The target insurance products matched, comprising:
The personality label of the user is compared with the label of insurance products in the insurance products database；
When the label of insurance products in the personality label of the user and the insurance products database is there are when identical label,
Determine number of labels identical with the personality label of the user in each insurance products；
Using the most insurance products of number of labels as the target insurance products.
4. the recommended method of insurance products according to claim 1, which is characterized in that described by the musical life data
Feature be input in preset personality identification neural network model, before obtaining the personality label of the user, further include
Feature is extracted to the musical life data by preset feature extraction software.
5. the recommended method of insurance products according to any one of claims 1 to 4, which is characterized in that described by the sound
Happy data are input in preset personality identification neural network model, before obtaining the personality label of the user, further includes:
Obtain the music samples data for being marked with personality label；
Preset convolutional neural networks model is trained according to the music samples data, obtains identifying the personality label
Personality identify neural network model.
6. the recommended method of insurance products according to claim 5, which is characterized in that described according to the music samples number
It is trained according to preset convolutional neural networks model, comprising:
Musical features are extracted from the music samples data, and calculate the desired value of musical features in every kind of personality label；
The musical features are input in preset convolutional neural networks model, are obtained every in the convolutional neural networks model
The excitation value of kind personality label；
It compares whether the distance between desired value and excitation value of every kind of personality label is less than or equal to preset threshold value, and works as institute
When stating the distance between desired value and the excitation value greater than threshold value, iterative cycles iteration updates convolution mind by inverse algorithms
Through the weight in network model, until the distance between the desired value and the excitation value are less than or equal to preset first threshold
When terminate.
7. a kind of insurance products recommendation apparatus characterized by comprising
Module is obtained, for obtaining the musical life data of user；
Processing module, for the feature of the musical life data to be input in preset personality identification neural network model,
Obtain the personality label of the user；
Execution module is produced for choosing to insure with the target of the personality tag match from preset insurance products database
Product, and the target insurance products are pushed in the webpage that the user logs in.
8. the recommendation apparatus of insurance products according to claim 7, which is characterized in that in the insurance products database,
Each insurance products include the personality label of applicable group；The execution module includes:
First processing submodule, for by the mark of insurance products in the personality label of the user and the insurance products database
Label are compared；
First implementation sub-module, for when the alignment is identical, insurance products pointed by consistent label will to be compared as described in
Target insurance products.
9. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, it is described
When computer-readable instruction is executed by the processor, so that the processor executes such as any one of claims 1 to 6 right
It is required that the step of insurance products recommended method.
10. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes, so that one or more processors execute the insurance products as described in any one of claims 1 to 6 claim and push away
The step of recommending method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811347747.9A CN109360072B (en) | 2018-11-13 | 2018-11-13 | Insurance product recommendation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811347747.9A CN109360072B (en) | 2018-11-13 | 2018-11-13 | Insurance product recommendation method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109360072A true CN109360072A (en) | 2019-02-19 |
| CN109360072B CN109360072B (en) | 2023-06-23 |
Family
ID=65344987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811347747.9A Active CN109360072B (en) | 2018-11-13 | 2018-11-13 | Insurance product recommendation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109360072B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135942A (en) * | 2019-04-12 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus and computer readable storage medium |
| CN112991025A (en) * | 2021-05-08 | 2021-06-18 | 明品云(北京)数据科技有限公司 | Intelligent insurance recommendation method, system and equipment and computer readable storage medium |
| CN113256397A (en) * | 2021-07-02 | 2021-08-13 | 佛山市墨纳森智能科技有限公司 | Commodity recommendation method and system based on big data and computer-readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180101887A1 (en) * | 2016-10-10 | 2018-04-12 | International Business Machines Corporation | Offering Personalized and Interactive Decision Support Based on Learned Model to Predict Preferences from Traits |
| CN108108465A (en) * | 2017-12-29 | 2018-06-01 | 北京奇宝科技有限公司 | A kind of method and apparatus for pushing recommendation |
| CN108446688A (en) * | 2018-05-28 | 2018-08-24 | 北京达佳互联信息技术有限公司 | Facial image Sexual discriminating method, apparatus, computer equipment and storage medium |
| CN108492194A (en) * | 2018-03-06 | 2018-09-04 | 平安科技（深圳）有限公司 | Products Show method, apparatus and storage medium |
-
2018
- 2018-11-13 CN CN201811347747.9A patent/CN109360072B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180101887A1 (en) * | 2016-10-10 | 2018-04-12 | International Business Machines Corporation | Offering Personalized and Interactive Decision Support Based on Learned Model to Predict Preferences from Traits |
| CN108108465A (en) * | 2017-12-29 | 2018-06-01 | 北京奇宝科技有限公司 | A kind of method and apparatus for pushing recommendation |
| CN108492194A (en) * | 2018-03-06 | 2018-09-04 | 平安科技（深圳）有限公司 | Products Show method, apparatus and storage medium |
| CN108446688A (en) * | 2018-05-28 | 2018-08-24 | 北京达佳互联信息技术有限公司 | Facial image Sexual discriminating method, apparatus, computer equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135942A (en) * | 2019-04-12 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus and computer readable storage medium |
| CN112991025A (en) * | 2021-05-08 | 2021-06-18 | 明品云(北京)数据科技有限公司 | Intelligent insurance recommendation method, system and equipment and computer readable storage medium |
| CN113256397A (en) * | 2021-07-02 | 2021-08-13 | 佛山市墨纳森智能科技有限公司 | Commodity recommendation method and system based on big data and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109360072B (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11983269B2 (en) | Deep neural network system for similarity-based graph representations | |
| CN109583970A (en) | Advertisement placement method, device, computer equipment and storage medium | |
| US20170300814A1 (en) | Wide and deep machine learning models | |
| US20150356601A1 (en) | Recommendations based on purchase patterns | |
| US10438133B2 (en) | Spend data enrichment and classification | |
| CN109213868A (en) | Entity level sensibility classification method based on convolution attention mechanism network | |
| EP4009219A1 (en) | Analysis of natural language text in document using hierarchical graph | |
| CN107851443A (en) | Voice activity detection | |
| US20110289025A1 (en) | Learning user intent from rule-based training data | |
| CN105550173A (en) | Text correction method and device | |
| CN106845999A (en) | Risk subscribers recognition methods, device and server | |
| CN109360072A (en) | Insurance products recommended method, device, computer equipment and storage medium | |
| CN109445759A (en) | Generation method, device, computer equipment and the storage medium of insurance products | |
| CN108959453B (en) | Information extraction method and device based on text clustering and readable storage medium | |
| CN112632256A (en) | Information query method and device based on question-answering system, computer equipment and medium | |
| CN111125491A (en) | Commodity information searching method and device, storage medium and electronic device | |
| CN110503453A (en) | Customer-action analysis method, apparatus, computer equipment and storage medium | |
| CN104915440A (en) | Commodity de-duplication method and system | |
| CN109033427A (en) | The screening technique and device of stock, computer equipment and readable storage medium storing program for executing | |
| Stavinova et al. | Predictability classes for forecasting clients behavior by transactional data | |
| CA2814177C (en) | Device, method and system of automatically defining a financial instrument | |
| US20230027530A1 (en) | Artificial intelligence (ai) engine assisted creation of production descriptions | |
| CN115827864A (en) | Processing method for automatic classification of bulletins | |
| CN112989801B (en) | Sequence labeling method, device and equipment | |
| CN113688222A (en) | Insurance sales task conversational recommendation method, system and equipment based on context semantic understanding |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |