CN108520444A - Insurance products recommend method, unit and computer readable storage medium - Google Patents
Insurance products recommend method, unit and computer readable storage medium Download PDFInfo
- Publication number
- CN108520444A CN108520444A CN201810325267.6A CN201810325267A CN108520444A CN 108520444 A CN108520444 A CN 108520444A CN 201810325267 A CN201810325267 A CN 201810325267A CN 108520444 A CN108520444 A CN 108520444A
- Authority
- CN
- China
- Prior art keywords
- client
- insurance
- information
- insurance products
- products
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
Abstract
The invention discloses a kind of insurance products to recommend method, the insurance products that method is recommended to include the following steps：Obtain the insurance notch information of client；According to the insurance notch information, client's classification where the client is determined；Corresponding target recommended models are determined according to client's classification；The target recommended models are inputted using the insurance notch information as input parameter, obtain the insurance products to be recommended to the client.The invention also discloses a kind of insurance products recommendation apparatus, insurance products recommendation apparatus and computer readable storage mediums.Present invention improves specific aims and accuracy that insurance products are recommended.
Description
Technical field
The present invention relates to Products Show technical fields more particularly to a kind of insurance products to recommend method, unit and meter
Calculation machine readable storage medium storing program for executing.
Background technology
With the development of insurance industry and the diversification of customer demand, the type of insurance products is more and more, complexity
Also corresponding to improve, the selection difficulty of client increases.In insurance products field, the demand between different clients group often exists
Prodigious difference, even in the similar customer group of economic dispatch background, since the insurance notch of different clients is different, and
In view of the matching problem between the insurance products that will be bought and existing insurance products, cause suitably to insure production for lead referral
Product have prodigious difficulty.Currently, it is that client recommends to rely primarily on insurance agent personnel or insurance sales personnel, it is this to push away
Specific aim and the accuracy for recommending mode are poor, it is difficult to meet the needs of client.
The above is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that the above is existing skill
Art.
Invention content
The main purpose of the present invention is to provide a kind of insurance products to recommend method, it is intended to solve pushing away for above-mentioned insurance products
The technical problem for recommending specific aim and accuracy difference, to meet the needs of client.
To achieve the above object, the present invention provides a kind of insurance products recommendation method, and the insurance products recommend method packet
Include following steps：
Obtain the insurance notch information of client；
According to the insurance notch information, client's classification where the client is determined；
Corresponding target recommended models are determined according to client's classification；
The target recommended models are inputted using the insurance notch information as input parameter, are obtained to be recommended to the visitor
The insurance products at family.
Preferably, the step of insurance notch information for obtaining client includes：
Obtain the identity information of client；
According to the identity information, the insurance information that prestores of the client is read；
It receives the first of the client and confirms instruction, and confirm the insurance information that prestores described in instruction judgement according to described first
It is whether correct and complete；
If the insurance information that prestores is correct and complete, according to the insurance information that prestores, the insurance of the client is obtained
Notch information；
If the insurance information that prestores is incorrect or imperfect, the first revision directive of the client is received；
According to the insurance information that prestores described in the first revision directive modify or supplement；
According to the insurance information that prestores described in after modify or supplement, the insurance notch information of the client is obtained.
Preferably, according to the insurance notch information, the other step of customer class where determining the client includes：
According to the insurance notch information, the major category where the client is determined；
Obtain the economic information of the client；
According to the economic information, subclass of the client in the major category is determined, and the subclass is made
For client's classification.
Preferably, the step of according to the economic information, determining subclass of the client in the major category it
Afterwards, described according to the insurance information, the other step of customer class where determining the client further includes：
It receives the second of the client and confirms instruction, and confirm that whether just instruction judges the subclass according to described second
Really；
If the subclass is correct, using the subclass as client's classification where the client；
If the subclass is incorrect, the second revision directive of the client is received；
The subclass is changed according to second revision directive, using the modified subclass as the client institute
Client's classification.
Preferably, according to the insurance notch information, the other step of customer class where determining the client includes：
Obtain the identity information of the client；
According to the identity information, the associated client of the client is obtained；
Obtain the insurance notch information of the associated client；
According to the insurance notch information of insurance the notch information and the associated client of the client, the client institute is determined
Client's classification.
Preferably, the target recommended models are trained using deep learning algorithm；Described in the training of deep learning algorithm
The step of target recommended models includes：
Extract the insurance products of the client characteristics of portions of client and corresponding purchase in the corresponding client of client's classification；
Using the client characteristics of the portions of client as input parameter, the insurance products that the portions of client corresponds to purchase are defeated
Go out parameter, establishes training set and test set；
According to the training set and the test set, the target recommended models are trained using deep learning algorithm, until
The recommendation accuracy rate of the target recommended models is greater than or equal to the first default accuracy rate.
Preferably, the target recommended models are being inputted using the insurance notch information as input parameter, is obtaining waiting pushing away
After the step of recommending the insurance products to the client, the insurance products recommend method further comprising the steps of：
Obtain the insurance products of client's purchase；
According to the insurance products that the insurance products to be recommended to the client and the client buy, calculates the target and push away
Recommend the recommendation accuracy rate of model；
Compare the recommendation accuracy rate and the second default accuracy rate；
When the recommendation accuracy rate be less than the second default accuracy rate when, using deep learning algorithm again train described in
The corresponding target recommended models of client's classification.
In addition, to achieve the above object, the present invention also proposes that a kind of insurance products recommendation apparatus, the insurance products are recommended
Equipment includes：Memory, processor and it is stored in the computer program that can be run on the memory and on the processor,
The step of insurance products recommend method, the insurance products recommendation side are realized when the computer program is executed by the processor
Method includes the following steps：Obtain the insurance notch information of client；According to the insurance notch information, where determining the client
Client's classification；Corresponding target recommended models are determined according to client's classification；Join the insurance notch information as input
Number inputs the target recommended models, obtains the insurance products to be recommended to the client.
To achieve the above object, the present invention also proposes a kind of insurance products recommendation apparatus, the insurance products recommendation apparatus
Including：
Data obtaining module, to obtain the insurance notch information of client；
Client segmentation module, according to the insurance notch information, to determine client's classification where the client；
Model acquisition module, to determine corresponding target recommended models according to client's classification；
Products Show module, to input the target recommended models using the insurance notch information as input parameter,
Obtain the insurance products to be recommended to the client.
To achieve the above object, the present invention also proposes a kind of computer readable storage medium, the computer-readable storage
It is stored with insurance products recommended program on medium, realizes that insurance products push away when the insurance products recommended program is executed by processor
The step of recommending method, the insurance products recommend method to include the following steps：Obtain the insurance notch information of client；According to described
Insure notch information, determines client's classification where the client；Determine that corresponding target recommends mould according to client's classification
Type；The target recommended models are inputted using the insurance notch information as input parameter, are obtained to be recommended to the client's
Insurance products.
In the present invention, insurance products recommend method to include the following steps：The insurance notch information for obtaining client, to bright
True customer demand；According to insurance notch information, client's classification where client is determined；Corresponding target is determined according to client's classification
Recommended models, for different customer demands, to recommend accurately and targetedly insurance products；Notch information conduct will be insured
Input parameter inputs target recommended models, the insurance products to be recommended to client is obtained, so that client preferably selects oneself institute
The insurance products needed.In a kind of insurance products recommendation method proposed by the present invention, according to the insurance notch information of client to client
Classify, client is collected with the insurance products needed most for client and most probable is bought, determines and the client
The corresponding target recommended models of classification use the information from customer class another edition of a book body to provide personalized insurance products for client
Recommend, to substantially increase the specific aim and accuracy of recommendation, improve customer experience, meeting the diversification of client needs
It asks.
Description of the drawings
Fig. 1 is the flow diagram that insurance products of the present invention recommend method first embodiment；
Fig. 2 is the refinement flow diagram that insurance products of the present invention recommend step S100 in method second embodiment；
Fig. 3 is the refinement flow diagram that insurance products of the present invention recommend step S200 in method 3rd embodiment；
Fig. 4 is the refinement flow diagram that insurance products of the present invention recommend step S200 in method fourth embodiment；
Fig. 5 is the refinement flow diagram that insurance products of the present invention recommend step S200 in the 5th embodiment of method；
Fig. 6 is that insurance products of the present invention are recommended to recommend mould using deep learning algorithm training objective in method sixth embodiment
The refinement flow diagram of type；
Fig. 7 is the flow diagram that insurance products of the present invention recommend the 7th embodiment of method；
Fig. 8 is the insurance products recommendation apparatus structural schematic diagram for the hardware running environment that the embodiment of the present invention is related to.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The primary solutions of the embodiment of the present invention are：Classified to client according to the insurance notch information of client, and
Target recommended models are determined for each client's classification, are lead referral insurance products.
It is lead referral insurance products due to relying primarily on insurance agent personnel or insurance sales personnel in the prior art, leads
Cause the specific aim recommended and accuracy poor, it is difficult to meet the needs of client.
The present invention provides a solution, according to the insurance notch information of client by client segmentation, and is directed to each class
Other client determines different target recommended models respectively, to rise to the specific aim and accuracy of lead referral insurance products,
Improve customer experience.
In the first embodiment of the present invention, as shown in Figure 1, insurance products recommend method to include the following steps：
Step S100, the insurance notch information of client is obtained；
The insurance notch information of client can directly be provided by client, such as the required insurance provided according to client, be determined
Insure notch information.Certainly, as the complexity of insurance products increasingly improves, client oneself is likely to scarce to the insurance needed for it
Weary accurate assurance, in such a case, it is possible to according to the existing insurance that client provides, in conjunction with the total size of full-scope safeguards, meter
Calculate the insurance notch information of client.Alternatively, the insurance notch information of client can also be according to client identity, economic dispatch information
It determines.For example, according to the identity information of client, the existing insurance information of client is read out in server or database, and tie
The economic information for closing client obtains the total size ensured needed for the client, calculates insurance notch information, hereinafter will also be detailed
It illustrates.It should be noted that when obtaining the existing insurance of client, which can be client oneself purchase, also may be used
With client be insurant it is that client buys to be other people, to ensure the accuracy of acquired insurance notch information.
Step S200, according to insurance notch information, client's classification where client is determined；
According to insurance notch information, classify to client, that is, needed most according to client and most possibly bought
Insurance classify to client, so as to targetedly be recommended according to the demand of client.Such as, it would be desirable to disease
The client point of danger is in sickness insurance one kind, it would be desirable to which the client of property insurance point is in property insurance one kind, or will need sickness insurance and wealth
The client point of production danger is a kind of in disease property insurance, to effectively integrate various insurances, realizes the reasonable disposition of resource.Certainly, right
The wide and more complex insurance kind in covering scopes such as sickness insurances can also be further subdivided into such as serious illness insurance class, common disorder danger
Class etc..It is more careful comprehensively according to the classification of insurance notch, recommend mould for target determined by client's classification in step below
Type is also more accurate.It, can also be other further combined with the identity of client, economic dispatch in client's classification where determining client
Information is finely divided, and hereinafter also will be apparent from.
Step S300, corresponding target recommended models are determined according to client's classification；
According to client's classification, determine that corresponding target recommended models, target recommended models are to be directed to different client's classifications
It is predetermined respectively, based on existing customer data in this client classification, that is, based on the insurance products purchase before client
It buys the behavior insurance products buying behavior following to it to predict, therefore there is good specific aim and accuracy.
Step S400, insurance notch information is inputted into target recommended models as input parameter, obtained to be recommended to client
Insurance products.
It is to be recommended to should to obtain by the insurance notch information input recommended models of client according to target recommended models
The insurance products of client.Wherein, insurance products can be a certain specific insurance, can also be several combinations specifically insured,
To improve the specific aim and accuracy of insurance products recommendation, the demand of client is preferably met.Further, Ke Yigen
Two or more insurance products to be recommended to client are obtained according to recommended models, to wait for that client selects, are on the one hand improved
On the other hand the selection degree of freedom of client builds training set by recording the selection result of client, and according to selection result,
Preferably recommended models can also be continued to optimize in the follow-up process, to adapt to the variation of customer demand.
In the present embodiment, insurance products recommend method to include the following steps：The insurance notch information for obtaining client, to
Specify customer demand；According to insurance notch information, client's classification where client is determined；Corresponding mesh is determined according to client's classification
Recommended models are marked, for different customer demands, to recommend accurately and targetedly insurance products；Insurance notch information is made
Target recommended models are inputted for input parameter, the insurance products to be recommended to client are obtained, so that client preferably selects oneself
Required insurance products.In a kind of insurance products recommendation method proposed by the present invention, according to the insurance notch information of client to visitor
Family is classified, and is collected to client with the insurance products needed most for client and most probable is bought, is determined and the visitor
Classification corresponding target recommended models in family use the information from customer class another edition of a book body to provide personalized insurance production for client
Product are recommended, and to substantially increase the specific aim and accuracy of recommendation, improve customer experience, meet the diversification of client and need
It asks.
Further, as shown in Fig. 2, second embodiment of the invention provides a kind of insurance products recommendation method, based on above-mentioned
Embodiment shown in FIG. 1, step S100 include：
Step S110, the identity information of client is obtained；
Step S120, according to identity information, the insurance information that prestores of client is read；
Step S130, it receives the first of client and confirms instruction, and confirm that instruction judges that the insurance information that prestores is according to first
It is no correct and complete；
If the insurance information that prestores is correct and complete, executes step S140, according to the insurance information that prestores, obtain the insurance of client
Notch information；
If the insurance information that prestores is incorrect or imperfect, the first revision directive of step S151, reception client are executed；
Step S152, it is prestored insurance information according to the first revision directive modify or supplement；
Step S153, according to the insurance information that prestores after modify or supplement, the insurance notch information of client is obtained.
In general, insurance notch information obtain can directly according to the identity information of client this insurance company server
Or the corresponding insurance information that prestores is read in database, and the other insurance companies for having realized data sharing server or
The corresponding insurance information that prestores of client is read in database, alternatively, according to the identity information of client from information such as the banks of mandate
The middle corresponding insurance information that prestores of reading needs trouble caused by being manually entered insurance information to avoid client.But, it is contemplated that
Data sharing between part company or mechanism is more difficult or the data update of certain companies or mechanism is slower, all may
The insurance information that prestores for causing to read is incorrect or not comprehensively, influences subsequently that the insurance notch information to the client is really
It is fixed.Therefore, in the present embodiment, after reading the insurance information that prestores of client, receive the first of client and confirm instruction, and
Confirm according to the first of client and instruct the insurance information that judges to prestore whether complete and correct, while also allowing for client and understanding it at present
The case where possessed insurance.When the insurance information that prestores that client's confirmation is read is correct and complete, according to the insurance letter that prestores
Breath obtain client insurance notch information otherwise receive the first revision directive of client, modify to the insurance information that prestores or
Supplement, and according to the insurance notch information of the insurance information acquisition client that prestores after modify or supplement, to improve subsequent step
In the accuracy classified to client.First confirms that instruction and the first revision directive can also provide simultaneously, i.e., client has found
When the insurance information that prestores has mistake or missing, directly modifies or supplement to it.
As shown in figure 3, third embodiment of the invention provides a kind of insurance products recommendation method, based on above-mentioned shown in FIG. 1
Embodiment, step S200 include：
Step S210, according to insurance notch information, the major category where client is determined；
Step S220, the economic information of client is obtained；
Step S230, according to economic information, subclass of the client in major category is determined, and using subclass as customer class
Not.
During classifying to client, according to insurance notch information, the major category where client is determined, wherein
Major category mainly considers the demand of client.However, in order to further increase the accuracy of recommendation, the need of client are not only considered
It asks, it is also necessary in conjunction with the ability to take the burden of client, further classify.In the present embodiment, according to the economic information of client, visitor is determined
Subclass of the family in major category.Economic information includes the information of the deposit of client, real estate, movable property, debt etc., is considered
The weight occupied in classification foundation to various information, is finely divided the classification where client.For example, lacking personal guarantor
In client's major category of danger, there are booming income client subclass and low income client's subclass.In fact, the crowd of different incomes
Final selected insurance products are there may be very big difference, and booming income crowd may be more likely to selection full-scope safeguards,
And low-income groups often tends to selection basic guarantee.Therefore, the customer segmentation of personal insurance will further be lacked to difference
Client's classification, to have better specific aim and accuracy during follow-up training recommended models, to preferably full
Sufficient customer demand.
Further, as shown in figure 4, fourth embodiment of the invention provides a kind of insurance products recommendation method, based on above-mentioned
Embodiment shown in Fig. 3, after step S230, step S200 further includes：
Step S240, it receives the second of client and confirms instruction, and confirm that instruction judges whether subclass is correct according to second；
If subclass is correct, step S250 is executed, using subclass as client's classification where client；
If subclass is incorrect, the second revision directive of step S261, reception client are executed；
Step S262, subclass is changed according to the second revision directive, using modified subclass as the visitor where client
Family classification.
Further, after classifying automatically to client, confirm instruction by receive client second, confirm that client is
There are objections for no client's classification to where oneself.In view of some economic conditions are in client and the portion of classification critical point
Divide and clearly client is understood to the demand for insurance and preference of oneself, may be dissatisfied to the result classified automatically, pass through second
Confirm instruction and the second revision directive, client's classification where oneself is adjusted convenient for client, to meet its personalized need
It asks, improves the accuracy of recommendation.
As shown in figure 5, fifth embodiment of the invention provides a kind of insurance products recommendation method, based on above-mentioned shown in FIG. 1
Embodiment, step S200 include：
Step S271, the identity information of client is obtained；
Step S272, according to identity information, the associated client of client is obtained；
Step S273, the insurance notch information of associated client is obtained；
Step S274, according to the insurance notch information of insurance the notch information and associated client of client, client place is determined
Client's classification.
In the present embodiment, it is contemplated that client is usually in one family, and often there is also old man, youngsters in kinsfolk
Child etc. is difficult to the member of oneself purchase insurance products, also, when being the whole configuration for considering insurance products with family, be conducive into
The reasonability of one-step optimization insurance.Therefore, by obtaining the identity information of client, the associated client of client is obtained, association visitor
Family can be client relevant member etc. in the tissues such as the enterprise where other members or client in the family.It closes
The insurance notch information of connection client is also considered in the required insurance products of the client, when determining client's classification, according to
The insurance notch information of client itself and the insurance notch information of associated client are classified.Be conducive in subsequent training process
Middle realization is preferably integrated, to improve the satisfaction of client.
As shown in fig. 6, sixth embodiment of the invention provides a kind of insurance products recommendation method, target recommended models are using deep
Spend learning algorithm training；
Include using deep learning algorithm training objective recommended models：
Step S610, the client characteristics of portions of client and the insurance production of corresponding purchase in the corresponding client of extraction client's classification
Product；
Step S620, using the client characteristics of portions of client as input parameter, the insurance products that portions of client corresponds to purchase are
Output parameter establishes training set and test set；
Step S630, according to training set and test set, using deep learning algorithm training objective recommended models, until target
The recommendation accuracy rate of recommended models is greater than or equal to the first default accuracy rate.
Before determining corresponding target recommended models according to client's classification, need first to determine that corresponding target recommends mould
Type.In the present embodiment, target recommended models train to obtain using deep learning algorithm.Specifically, recommending mould in training
It during type, is trained respectively for different client's classifications, to improve the specific aim of model and the accuracy of recommendation.
During training corresponding recommended models for each client's classification, used training set and test set are all based on this visitor
Existing customer data in the classification of family, that is, based on the insurance products following to it of the insurance products buying behavior before client
Buying behavior is predicted.In general, in the case where the number of plies of enough, structure the recommended models of the sample number of training set is enough,
Trained effect is also better, but correspondingly, training efficiency may reduce, especially when the number of plies of recommended models is excessive,
It is also possible that overfitting problem.Therefore, it during training recommended models using deep learning algorithm, should take into consideration
Accuracy and efficiency builds training set and recommended models, and is verified using the recommended models that test set completes training, with
Improve the reliability of recommended models.Input parameter, hidden layer parameter, the selection of output parameter and the recommended models of recommended models
The number of plies selection etc., all to final training result and training effectiveness have large effect.Extract the corresponding visitor of client's classification
The insurance products of the client characteristics of portions of client and corresponding purchase in family, using the client characteristics of the portions of client as input parameter,
The insurance products of corresponding purchase are output parameter, establish training set and test set.Wherein, client characteristics can specifically include client
The information such as age, income, home background.When establishing training set, the sample number in training set is bigger, and sample covering is more complete
Face, final test effect are also better.According to training set and test set, recommended models are trained using deep learning algorithm, in conjunction with
Test set determines that hidden layer is joined to the test result of recommended models when recommending accuracy rate to be greater than or equal to the first default accuracy rate
Number is to obtain complete recommended models.
As shown in fig. 7, seventh embodiment of the invention provides a kind of insurance products recommendation method, based on above-mentioned shown in FIG. 1
Embodiment, after step S400, insurance products recommend method further comprising the steps of：
Step S510, the insurance products of client's purchase are obtained；
Step S520, the insurance products bought according to the insurance products to be recommended to client and client calculate target and recommend
The recommendation accuracy rate of model；
Step S530, it compares and recommends accuracy rate and the second default accuracy rate；
Step S540, when recommending accuracy rate to be less than the second default accuracy rate, using deep learning algorithm, training is objective again
The corresponding target recommended models of family classification.
In the present embodiment, it is contemplated that with the development of insurance products and the variation etc. of client's idea, same class client is most
The insurance products of selection purchase are likely to occur variation eventually.Therefore, when for lead referral insurance products, what client was bought in holding
The monitoring of insurance products, when the recommendation accuracy rate of target recommended models is less than the second default accuracy rate, training is objective again in time
The corresponding recommended models of family classification, to keep the specific aim and accuracy recommended.It is accurate in the recommendation for calculating target recommended models
It when rate, can be calculated according to prefixed time interval, that is, in accumulating to prefixed time interval, the insurance products of client's purchase
Related data when, calculate the recommendation accuracy rate of above-mentioned time interval.Alternatively, what the client for arriving preset number in accumulation bought
When insurance products, calculates and recommend accuracy rate.Wherein, the other recommendation accuracy rate of each customer class calculates separately, and is somebody's turn to do with determining
Whether the corresponding target recommended models of client's classification need to train again.It certainly, can also basis in the case where resource is enough
The insurance products of client's purchase remain the update training to recommended models, to improve the accuracy recommended.
As shown in figure 8, the insurance products recommendation apparatus knot for the hardware running environment that Fig. 8, which is the embodiment of the present invention, to be related to
Structure schematic diagram.
Insurance products of embodiment of the present invention recommendation apparatus can be PC, can also be smart mobile phone, tablet computer, portable meter
Calculation machine etc. has the packaged type terminal device of display function.
As shown in Figure 1, the insurance products recommendation apparatus may include：Processor 1001, such as CPU, network interface 1004,
User interface 1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing between these components
Connection communication.User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard), optional
User interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 may include optionally standard
Wireline interface, wireless interface (such as WI-FI interfaces).Memory 1005 can be high-speed RAM memory, can also be stable
Memory (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned
The storage device of processor 1001.
Optionally, insurance products recommendation apparatus can also include camera, RF (Radio Frequency, radio frequency) circuit,
Sensor, voicefrequency circuit, WiFi module etc..Wherein, sensor such as optical sensor, motion sensor and other sensings
Device.Specifically, optical sensor may include ambient light sensor and proximity sensor, wherein ambient light sensor can be according to environment
The light and shade of light adjusts the brightness of display screen, proximity sensor can when mobile terminal is moved in one's ear, close display screen and/
Or backlight.As a kind of motion sensor, gravity accelerometer can detect in all directions (generally three axis) and accelerate
The size of degree can detect that size and the direction of gravity when static, the application that can be used to identify mobile terminal posture is (such as vertical and horizontal
Shield switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, percussion) etc.；Certainly, mobile
Terminal can also configure the other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, no longer superfluous herein
It states.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of terminal structure shown in Fig. 8, can wrap
It includes than illustrating more or fewer components, either combines certain components or different components arrangement.
As shown in figure 8, as may include that operating system, network are logical in a kind of memory 1005 of computer storage media
Believe module, Subscriber Interface Module SIM and insurance products recommended program.
In insurance products recommendation apparatus shown in Fig. 8, network interface 1004 is mainly used for connecting background server, and rear
Platform server is into row data communication；User interface 1003 is mainly used for connecting client (user terminal), and data are carried out with client
Communication；And processor 1001 can be used for calling the insurance products recommended program stored in memory 1005, and execute following behaviour
Make：
Obtain the insurance notch information of client；
According to insurance notch information, client's classification where client is determined；
Corresponding target recommended models are determined according to client's classification；
Insurance notch information is inputted into target recommended models as input parameter, the insurance to be recommended to client is obtained and produces
Product.
Further, processor 1001 can call the insurance products recommended program stored in memory 1005, obtain visitor
The operation of the insurance notch information at family includes：
Obtain the identity information of client；
According to identity information, the insurance information that prestores of client is read；
It receives the first of client and confirms instruction, and confirm according to first and instruct the insurance information that judges to prestore whether correct and complete
It is whole；
If the insurance information that prestores is correct and complete, according to the insurance information that prestores, the insurance notch information of client is obtained；
If the insurance information that prestores is incorrect or imperfect, the first revision directive of client is received；
It is prestored insurance information according to the first revision directive modify or supplement；
According to the insurance information that prestores after modify or supplement, the insurance notch information of client is obtained.
Further, processor 1001 can call the insurance products recommended program stored in memory 1005, according to guarantor
Dangerous notch information, the other operation of customer class where determining client include：
According to insurance notch information, the major category where client is determined；
Obtain the economic information of client；
According to economic information, subclass of the client in major category is determined, and using subclass as client's classification.
Further, processor 1001 can call the insurance products recommended program stored in memory 1005, in basis
Economic information after the operation for determining subclass of the client in major category, according to insurance information, determines the client where client
The operation of classification further includes：
It receives the second of client and confirms instruction, and confirm that instruction judges whether subclass is correct according to second；
If subclass is correct, using subclass as client's classification where client；
If subclass is incorrect, the second revision directive of client is received；
Subclass is changed according to the second revision directive, using modified subclass as client's classification where client.
Further, processor 1001 can call the insurance products recommended program stored in memory 1005, according to guarantor
Dangerous notch information, the other operation of customer class where determining client include：
Obtain the identity information of client；
According to identity information, the associated client of client is obtained；
Obtain the insurance notch information of associated client；
According to the insurance notch information of insurance the notch information and associated client of client, the customer class where client is determined
Not.
Further, processor 1001 can call the insurance products recommended program stored in memory 1005, target to push away
Model is recommended to train using deep learning algorithm；
Operation using deep learning algorithm training objective recommended models includes：
Extract the insurance products of the client characteristics of portions of client and corresponding purchase in the corresponding client of client's classification；
Using the client characteristics of portions of client as input parameter, the insurance products that portions of client corresponds to purchase are output parameter,
Establish training set and test set；
According to training set and test set, using deep learning algorithm training objective recommended models, until target recommended models
Recommendation accuracy rate be greater than or equal to the first default accuracy rate.
Further, processor 1001 can call the insurance products recommended program stored in memory 1005, will protect
Dangerous notch information inputs target recommended models as input parameter, after obtaining the operation of the insurance products to be recommended to client,
Also execute following operation：
Obtain the insurance products of client's purchase；
According to the insurance products that the insurance products to be recommended to client and client buy, the recommendation of target recommended models is calculated
Accuracy rate；
It compares and recommends accuracy rate and the second default accuracy rate；
When recommending accuracy rate to be less than the second default accuracy rate, client's classification is trained to correspond to again using deep learning algorithm
Target recommended models.
The embodiment of the present invention also proposes that a kind of insurance products recommendation apparatus, insurance products recommendation apparatus include：
Data obtaining module, to obtain the insurance notch information of client；
Client segmentation module, according to insurance notch information, to determine client's classification where client；
Model acquisition module, to determine corresponding target recommended models according to client's classification；
Products Show module inputs target recommended models as input parameter will insure notch information, obtains waiting pushing away
It recommends to the insurance products of client.
Further, data obtaining module includes：
First information acquiring unit, to obtain the identity information of client；
Information reading unit, according to identity information, to read the insurance information that prestores of client；
First amending unit confirms instruction to receive the first of client, and confirms that instruction judges the guarantor that prestores according to first
Whether dangerous information is correct and complete；If the insurance information that prestores is correct and complete, according to the insurance information that prestores, the insurance of client is obtained
Notch information；If the insurance information that prestores is incorrect or imperfect, the first revision directive of client is received；According to the first revision directive
Modify or supplement prestores insurance information；According to the insurance information that prestores after modify or supplement, the insurance notch information of client is obtained.
Further, client segmentation module includes：
Taxon, according to insurance notch information, to determine the major category where client；
Second information acquisition unit, to obtain the economic information of client；
Taxon also according to economic information, to determine subclass of the client in major category, and using subclass as
Client's classification.
Further, client segmentation module further includes：
Second amending unit confirms instruction to receive the second of client, and confirms that instruction judges subclass according to second
It is whether correct；If subclass is correct, using subclass as client's classification where client；If subclass is incorrect, client is received
The second revision directive；Subclass is changed according to the second revision directive, using modified subclass as the client where client
Classification.
Further, the second information acquisition unit is also obtaining the identity information of client；According to identity information, visitor is obtained
The associated client at family；Obtain the insurance notch information of associated client；
Taxon also to according to client insurance notch information and associated client insurance notch information, determine client
Client's classification at place.
Further, target recommended models are trained using deep learning algorithm, and insurance products recommendation apparatus further includes depth
Study module, to use deep learning algorithm training objective recommended models, deep learning module to include：
Extraction unit, to extract the guarantor of the client characteristics of portions of client and corresponding purchase in the corresponding client of client's classification
Dangerous product；
Unit is established, to using the client characteristics of portions of client as input parameter, portions of client corresponds to the insurance production of purchase
Product are output parameter, establish training set and test set；
Training unit, to according to training set and test set, using deep learning algorithm training objective recommended models, until
The recommendation accuracy rate of target recommended models is greater than or equal to the first default accuracy rate.
Further, insurance products recommendation apparatus further includes：
Product acquisition module, to obtain the insurance products of client's purchase；
Recommend accuracy rate module, to according to the insurance products of the insurance products to be recommended to client and client's purchase, meter
Calculate the recommendation accuracy rate of target recommended models；
Comparing module recommends accuracy rate and the second default accuracy rate to compare；
Deep learning module also to when recommend accuracy rate be less than the second default accuracy rate when, again using deep learning algorithm
The corresponding target recommended models of secondary trained client's classification.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with insurance products recommended program, following operation is realized when the insurance products recommended program is executed by processor：
Obtain the insurance notch information of client；
According to insurance notch information, client's classification where client is determined；
Corresponding target recommended models are determined according to client's classification；
Insurance notch information is inputted into target recommended models as input parameter, the insurance to be recommended to client is obtained and produces
Product.
Further, when insurance products recommended program is executed by processor, the operation of the insurance notch information of client is obtained
Including：
Obtain the identity information of client；
According to identity information, the insurance information that prestores of client is read；
It receives the first of client and confirms instruction, and confirm according to first and instruct the insurance information that judges to prestore whether correct and complete
It is whole；
If the insurance information that prestores is correct and complete, according to the insurance information that prestores, the insurance notch information of client is obtained；
If the insurance information that prestores is incorrect or imperfect, the first revision directive of client is received；
It is prestored insurance information according to the first revision directive modify or supplement；
According to the insurance information that prestores after modify or supplement, the insurance notch information of client is obtained.
Further, when insurance products recommended program is executed by processor, according to insurance notch information, client place is determined
Customer class it is other operation include：
According to insurance notch information, the major category where client is determined；
Obtain the economic information of client；
According to economic information, subclass of the client in major category is determined, and using subclass as client's classification.
Further, when insurance products recommended program is executed by processor, according to economic information, determine client in main classes
After the operation of subclass in not, according to insurance information, the other operation of customer class where determining client further includes：
It receives the second of client and confirms instruction, and confirm that instruction judges whether subclass is correct according to second；
If subclass is correct, using subclass as client's classification where client；
If subclass is incorrect, the second revision directive of client is received；
Subclass is changed according to the second revision directive, using modified subclass as client's classification where client.
Further, when insurance products recommended program is executed by processor, according to insurance notch information, client place is determined
Customer class it is other operation include：
Obtain the identity information of client；
According to identity information, the associated client of client is obtained；
Obtain the insurance notch information of associated client；
According to the insurance notch information of insurance the notch information and associated client of client, the customer class where client is determined
Not.
Further, when insurance products recommended program is executed by processor, target recommended models use deep learning algorithm
Training；
Operation using deep learning algorithm training objective recommended models includes：
Extract the insurance products of the client characteristics of portions of client and corresponding purchase in the corresponding client of client's classification；
Using the client characteristics of portions of client as input parameter, the insurance products that portions of client corresponds to purchase are output parameter,
Establish training set and test set；
According to training set and test set, using deep learning algorithm training objective recommended models, until target recommended models
Recommendation accuracy rate be greater than or equal to the first default accuracy rate.
Further, when insurance products recommended program is executed by processor, notch information will insured as input parameter
Target recommended models are inputted, after obtaining the operation of the insurance products to be recommended to client, also execute following operation：
Obtain the insurance products of client's purchase；
According to the insurance products that the insurance products to be recommended to client and client buy, the recommendation of target recommended models is calculated
Accuracy rate；
It compares and recommends accuracy rate and the second default accuracy rate；
When recommending accuracy rate to be less than the second default accuracy rate, client's classification is trained to correspond to again using deep learning algorithm
Target recommended models.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements include not only those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this
There is also other identical elements in the process of element, method, article or system.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be expressed in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions use so that a station terminal equipment (can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of insurance products recommend method, which is characterized in that the insurance products recommend method to include the following steps：
Obtain the insurance notch information of client；
According to the insurance notch information, client's classification where the client is determined；
Corresponding target recommended models are determined according to client's classification；
The target recommended models are inputted using the insurance notch information as input parameter, are obtained to be recommended to the client's
Insurance products.
2. insurance products as described in claim 1 recommend method, which is characterized in that the insurance notch information for obtaining client
The step of include：
Obtain the identity information of client；
According to the identity information, the insurance information that prestores of the client is read；
Receive the client first confirm instruction, and according to it is described first confirm instruction judge described in prestore insurance information whether
It is correct and complete；
If the insurance information that prestores is correct and complete, according to the insurance information that prestores, the insurance notch of the client is obtained
Information；
If the insurance information that prestores is incorrect or imperfect, the first revision directive of the client is received；
According to the insurance information that prestores described in the first revision directive modify or supplement；
According to the insurance information that prestores described in after modify or supplement, the insurance notch information of the client is obtained.
3. insurance products as described in claim 1 recommend method, which is characterized in that according to the insurance notch information, determine
The other step of customer class where the client includes：
According to the insurance notch information, the major category where the client is determined；
Obtain the economic information of the client；
According to the economic information, subclass of the client in the major category is determined, and using the subclass as visitor
Family classification.
4. insurance products as claimed in claim 3 recommend method, which is characterized in that according to the economic information, determine institute
It is described according to the insurance information after the step of stating subclass of the client in the major category, determine the client place
The other step of customer class further include：
It receives the second of the client and confirms instruction, and confirm that instruction judges whether the subclass is correct according to described second；
If the subclass is correct, using the subclass as client's classification where the client；
If the subclass is incorrect, the second revision directive of the client is received；
The subclass is changed according to second revision directive, using the modified subclass as where the client
Client's classification.
5. insurance products as described in claim 1 recommend method, which is characterized in that according to the insurance notch information, determine
The other step of customer class where the client includes：
Obtain the identity information of the client；
According to the identity information, the associated client of the client is obtained；
Obtain the insurance notch information of the associated client；
According to the insurance notch information of insurance the notch information and the associated client of the client, where determining the client
Client's classification.
6. insurance products as described in claim 1 recommend method, which is characterized in that the target recommended models use depth
Practise algorithm training；
Include using the deep learning algorithm training target recommended models：
Extract the insurance products of the client characteristics of portions of client and corresponding purchase in the corresponding client of client's classification；
Using the client characteristics of the portions of client as input parameter, the insurance products that the portions of client corresponds to purchase are that output is joined
Number, establishes training set and test set；
According to the training set and the test set, the target recommended models are trained using deep learning algorithm, until described
The recommendation accuracy rate of target recommended models is greater than or equal to the first default accuracy rate.
7. insurance products as described in claim 1 recommend method, which is characterized in that using the insurance notch information as defeated
After the step of entering parameter and input the target recommended models, obtaining insurance products to be recommended to the client, the insurance
Products Show method is further comprising the steps of：
Obtain the insurance products of client's purchase；
According to the insurance products that the insurance products to be recommended to the client and the client buy, calculates the target and recommend mould
The recommendation accuracy rate of type；
Compare the recommendation accuracy rate and the second default accuracy rate；
When the recommendation accuracy rate is less than the second default accuracy rate, the client is trained using deep learning algorithm again
The corresponding target recommended models of classification.
8. a kind of insurance products recommendation apparatus, which is characterized in that the insurance products recommendation apparatus includes：Memory, processor
And it is stored in the computer program that can be run on the memory and on the processor, the computer program is by the place
Manage the step of insurance products recommendation method as described in any one of claim 1 to 7 is realized when device executes.
9. a kind of insurance products recommendation apparatus, which is characterized in that the insurance products recommendation apparatus includes：
Data obtaining module, to obtain the insurance notch information of client；
Client segmentation module, according to the insurance notch information, to determine client's classification where the client；
Model acquisition module, to determine corresponding target recommended models according to client's classification；
Products Show module obtains to input the target recommended models using the insurance notch information as input parameter
Insurance products to be recommended to the client.
10. a kind of computer readable storage medium, which is characterized in that be stored with insurance production on the computer readable storage medium
Product recommended program is realized when the insurance products recommended program is executed by processor as described in any one of claim 1 to 7
Insurance products recommend the step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810325267.6A CN108520444B (en) | 2018-04-12 | 2018-04-12 | Insurance product recommendation method, equipment, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810325267.6A CN108520444B (en) | 2018-04-12 | 2018-04-12 | Insurance product recommendation method, equipment, device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108520444A true CN108520444A (en) | 2018-09-11 |
| CN108520444B CN108520444B (en) | 2023-06-27 |
Family
ID=63432422
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810325267.6A Active CN108520444B (en) | 2018-04-12 | 2018-04-12 | Insurance product recommendation method, equipment, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108520444B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109285082A (en) * | 2018-09-25 | 2019-01-29 | 中国平安人寿保险股份有限公司 | Insurance products recommended method, device and computer readable storage medium |
| CN109300054A (en) * | 2018-11-27 | 2019-02-01 | 泰康保险集团股份有限公司 | Insurance products recommended method, device, server and storage medium |
| CN109360032A (en) * | 2018-12-07 | 2019-02-19 | 泰康保险集团股份有限公司 | Client's appraisal procedure, device, equipment and storage medium |
| CN109377388A (en) * | 2018-09-13 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Medical insurance is insured method, apparatus, computer equipment and storage medium |
| CN109460944A (en) * | 2018-12-14 | 2019-03-12 | 平安健康保险股份有限公司 | Core based on big data protects method, apparatus, equipment and readable storage medium storing program for executing |
| CN109543095A (en) * | 2018-09-29 | 2019-03-29 | 中国平安人寿保险股份有限公司 | Insurance products data push method, device and relevant device based on big data |
| CN109559190A (en) * | 2018-10-22 | 2019-04-02 | 中国平安人寿保险股份有限公司 | Insurance products data push method, device, medium and computer equipment |
| CN109712001A (en) * | 2018-11-29 | 2019-05-03 | 平安科技（深圳）有限公司 | Information recommendation method, device, computer equipment and storage medium |
| CN109785149A (en) * | 2018-12-13 | 2019-05-21 | 中国平安人寿保险股份有限公司 | Ensure analytical equipment, method and the storage medium of data |
| CN110135943A (en) * | 2019-04-12 | 2019-08-16 | 中国平安财产保险股份有限公司 | Products Show method, apparatus, computer equipment and storage medium |
| CN110399559A (en) * | 2019-07-26 | 2019-11-01 | 阳光保险集团股份有限公司 | Intelligence insurance recommender system and computer storage medium |
| CN110415048A (en) * | 2019-08-06 | 2019-11-05 | 即悟(上海)智能科技有限公司 | A kind of advertisement recommended method, equipment, system, computer equipment and storage medium |
| CN110910255A (en) * | 2019-10-28 | 2020-03-24 | 世纪保众(北京)网络科技有限公司 | Product matching method and device based on family risk evaluation result |
| CN111353899A (en) * | 2018-12-21 | 2020-06-30 | 深圳市保罗科技服务有限公司 | Policy information data processing method and device, computer equipment and storage medium |
| CN111680941A (en) * | 2019-03-11 | 2020-09-18 | 顺丰科技有限公司 | Premium recommendation method, device, equipment and storage medium |
| CN111967998A (en) * | 2020-08-19 | 2020-11-20 | 中国银行股份有限公司 | Product recommendation processing method and device |
| WO2021098265A1 (en) * | 2019-11-22 | 2021-05-27 | 深圳壹账通智能科技有限公司 | Missing information prediction method and apparatus, and computer device and storage medium |
| CN113672804A (en) * | 2021-08-02 | 2021-11-19 | 上海浦东发展银行股份有限公司 | Recommendation information generation method, system, computer device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070156463A1 (en) * | 2006-01-05 | 2007-07-05 | Guidewire Software, Inc. | Insurance product model-based apparatus and method |
| US20100010837A1 (en) * | 2008-07-09 | 2010-01-14 | Hartford Fire Insurance Company | System and method for use in billing for group benefit insurance |
| US9712509B1 (en) * | 2011-10-20 | 2017-07-18 | Allstate Insurance Company | Product and coverage review and recommendation |
| CN107689008A (en) * | 2017-06-09 | 2018-02-13 | 平安科技（深圳）有限公司 | A kind of user insures the method and device of behavior prediction |
| CN107688987A (en) * | 2017-08-31 | 2018-02-13 | 平安科技（深圳）有限公司 | Electronic installation, insurance recommendation method and computer-readable recording medium |
| CN107730389A (en) * | 2017-09-30 | 2018-02-23 | 平安科技（深圳）有限公司 | Electronic installation, insurance products recommend method and computer-readable recording medium |
| KR20180036628A (en) * | 2016-09-30 | 2018-04-09 | 주식회사 디레몬 | System and method for providing insurance information |
-
2018
- 2018-04-12 CN CN201810325267.6A patent/CN108520444B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070156463A1 (en) * | 2006-01-05 | 2007-07-05 | Guidewire Software, Inc. | Insurance product model-based apparatus and method |
| US20100010837A1 (en) * | 2008-07-09 | 2010-01-14 | Hartford Fire Insurance Company | System and method for use in billing for group benefit insurance |
| US9712509B1 (en) * | 2011-10-20 | 2017-07-18 | Allstate Insurance Company | Product and coverage review and recommendation |
| KR20180036628A (en) * | 2016-09-30 | 2018-04-09 | 주식회사 디레몬 | System and method for providing insurance information |
| CN107689008A (en) * | 2017-06-09 | 2018-02-13 | 平安科技（深圳）有限公司 | A kind of user insures the method and device of behavior prediction |
| CN107688987A (en) * | 2017-08-31 | 2018-02-13 | 平安科技（深圳）有限公司 | Electronic installation, insurance recommendation method and computer-readable recording medium |
| CN107730389A (en) * | 2017-09-30 | 2018-02-23 | 平安科技（深圳）有限公司 | Electronic installation, insurance products recommend method and computer-readable recording medium |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109377388A (en) * | 2018-09-13 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Medical insurance is insured method, apparatus, computer equipment and storage medium |
| CN109377388B (en) * | 2018-09-13 | 2023-08-18 | 深圳平安医疗健康科技服务有限公司 | Medical insurance application method, medical insurance application device, computer equipment and storage medium |
| CN109285082A (en) * | 2018-09-25 | 2019-01-29 | 中国平安人寿保险股份有限公司 | Insurance products recommended method, device and computer readable storage medium |
| CN109543095A (en) * | 2018-09-29 | 2019-03-29 | 中国平安人寿保险股份有限公司 | Insurance products data push method, device and relevant device based on big data |
| CN109559190A (en) * | 2018-10-22 | 2019-04-02 | 中国平安人寿保险股份有限公司 | Insurance products data push method, device, medium and computer equipment |
| CN109300054A (en) * | 2018-11-27 | 2019-02-01 | 泰康保险集团股份有限公司 | Insurance products recommended method, device, server and storage medium |
| CN109712001A (en) * | 2018-11-29 | 2019-05-03 | 平安科技（深圳）有限公司 | Information recommendation method, device, computer equipment and storage medium |
| CN109360032A (en) * | 2018-12-07 | 2019-02-19 | 泰康保险集团股份有限公司 | Client's appraisal procedure, device, equipment and storage medium |
| CN109360032B (en) * | 2018-12-07 | 2021-04-06 | 泰康保险集团股份有限公司 | Customer evaluation method, apparatus, device and storage medium |
| CN109785149A (en) * | 2018-12-13 | 2019-05-21 | 中国平安人寿保险股份有限公司 | Ensure analytical equipment, method and the storage medium of data |
| CN109460944A (en) * | 2018-12-14 | 2019-03-12 | 平安健康保险股份有限公司 | Core based on big data protects method, apparatus, equipment and readable storage medium storing program for executing |
| CN111353899A (en) * | 2018-12-21 | 2020-06-30 | 深圳市保罗科技服务有限公司 | Policy information data processing method and device, computer equipment and storage medium |
| CN111680941B (en) * | 2019-03-11 | 2024-03-29 | 顺丰科技有限公司 | Method, device, equipment and storage medium for price-keeping recommendation |
| CN111680941A (en) * | 2019-03-11 | 2020-09-18 | 顺丰科技有限公司 | Premium recommendation method, device, equipment and storage medium |
| CN110135943B (en) * | 2019-04-12 | 2024-02-02 | 中国平安财产保险股份有限公司 | Product recommendation method, device, computer equipment and storage medium |
| CN110135943A (en) * | 2019-04-12 | 2019-08-16 | 中国平安财产保险股份有限公司 | Products Show method, apparatus, computer equipment and storage medium |
| CN110399559A (en) * | 2019-07-26 | 2019-11-01 | 阳光保险集团股份有限公司 | Intelligence insurance recommender system and computer storage medium |
| CN110415048A (en) * | 2019-08-06 | 2019-11-05 | 即悟(上海)智能科技有限公司 | A kind of advertisement recommended method, equipment, system, computer equipment and storage medium |
| CN110910255A (en) * | 2019-10-28 | 2020-03-24 | 世纪保众(北京)网络科技有限公司 | Product matching method and device based on family risk evaluation result |
| WO2021098265A1 (en) * | 2019-11-22 | 2021-05-27 | 深圳壹账通智能科技有限公司 | Missing information prediction method and apparatus, and computer device and storage medium |
| CN111967998A (en) * | 2020-08-19 | 2020-11-20 | 中国银行股份有限公司 | Product recommendation processing method and device |
| CN113672804A (en) * | 2021-08-02 | 2021-11-19 | 上海浦东发展银行股份有限公司 | Recommendation information generation method, system, computer device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108520444B (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108520444A (en) | Insurance products recommend method, unit and computer readable storage medium | |
| KR102012676B1 (en) | Method, Apparatus and System for Recommending Contents | |
| WO2020077500A1 (en) | System and method for providing real-time product interaction assistance | |
| US11288748B2 (en) | Systems and methods for providing customized financial advice | |
| CN109684047A (en) | Event-handling method, device, equipment and computer storage medium | |
| US11526701B2 (en) | Method and system of performing data imbalance detection and correction in training a machine-learning model | |
| US20180341378A1 (en) | Computer-implemented frameworks and methodologies configured to enable delivery of content and/or user interface functionality based on monitoring of activity in a user interface environment and/or control access to services delivered in an online environment responsive to operation of a risk assessment protocol | |
| CN106415470B (en) | Multivariate testing of mobile applications | |
| KR102384860B1 (en) | Operating method of open market platform with improved product upload convenience by providing templates | |
| US20180357557A1 (en) | Identification of decision bias with artificial intelligence program | |
| CN111815169B (en) | Service approval parameter configuration method and device | |
| CN107688950A (en) | Household electrical appliances consultation method, electronic equipment and computer-readable recording medium after sale | |
| US10776758B1 (en) | Systems and methods for processing and presentation of advisor-related data | |
| US20210182913A1 (en) | Electronic device and method for controlling same | |
| CN109101511A (en) | Products Show method, equipment and computer readable storage medium | |
| KR20230169016A (en) | Electronic apparatus and controlling method thereof | |
| US20220138237A1 (en) | Systems, devices, and methods for content selection | |
| CN110472162A (en) | Appraisal procedure, system, terminal and readable storage medium storing program for executing | |
| CN113919432A (en) | Classification model construction method, data classification method and device | |
| US20210027172A1 (en) | Learning method of ai model and electronic apparatus | |
| US11762545B1 (en) | Future state graphical visualization generator | |
| KR102485874B1 (en) | AR Vision Service System to Prevent Failure Cost | |
| CN112529679A (en) | Construction method, device and equipment of enterprise trust model and readable storage medium | |
| KR102464356B1 (en) | Method of operating open market platform that matches users with sellers who automatically recommend products to users based on artificial intelligence | |
| CN110210979A (en) | Investment project management-control method, device, equipment and readable storage medium storing program for executing |
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 |