CN109858999A - A kind of insurance products recommended method, device, equipment and readable storage medium storing program for executing - Google Patents
A kind of insurance products recommended method, device, equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109858999A CN109858999A CN201811647487.7A CN201811647487A CN109858999A CN 109858999 A CN109858999 A CN 109858999A CN 201811647487 A CN201811647487 A CN 201811647487A CN 109858999 A CN109858999 A CN 109858999A
- Authority
- CN
- China
- Prior art keywords
- user
- insurance products
- recommended
- close
- insurance
- 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.)
- Withdrawn
Links
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention is suitable for data recommendation technical field, provides a kind of insurance products recommended method, device, equipment and can storage medium, wherein the described method includes: obtaining user's insurance products evaluation and test record；It is evaluated and tested and is recorded according to user's insurance products, most close user is calculated and determined；Otherness based on the user and most close the bought insurance products of user, determines insurance products to be recommended；The most close user is calculated to export to the recommendation of the insurance products to be recommended, and to user.This method, which effectively realizes, formulates more personalized, diversified insurance products real-time recommendation for user, and further improves recommendation efficiency, while being avoided that and the problem of privacy of user risk of leakage occur.
Description
Technical field
The invention belongs to data recommendation technical field more particularly to a kind of insurance products recommended method, device, equipment and can
Read storage medium.
Background technique
In Taobao's shopping, after clicking a commodity, can occur the picture of many similar commodity on webpage, it can also be attached
Add " having seen what the people of the part commodity also seen ", this is a kind of effectively marketing mode.
The implementation of existing recommendation pattern is main are as follows: when needing certain data and other data opening relationships,
Firstly the need of these data are stored, data relationship is then established, i.e., in relational database, is contacted different tables with external key
To together, when relationship is more, database can it is increasing, become increasingly complex, will be successive when being operated to some relationship
There are various recommendation failure problems, in addition, the data based on recommendation are mainly previously stored the data on user local terminal, because
This, there is also biggish privacy of user risk of leakage for this mode.
Summary of the invention
The embodiment of the present invention provides a kind of insurance products recommended method, it is intended to solve the above technical problem.
The embodiments of the present invention are implemented as follows, a kind of insurance products recommended method, which comprises
Obtain user's insurance products evaluation and test record；
It is evaluated and tested and is recorded according to user's insurance products, most close user is calculated and determined；
Otherness based on the user and most close the bought insurance products of user, determines insurance products to be recommended；
The most close user is calculated to export to the recommendation of the insurance products to be recommended, and to user.
The embodiment of the present invention also provides a kind of insurance products recommendation apparatus, and described device includes:
Acquiring unit, for obtaining user's insurance products evaluation and test record；
First determination unit records for being evaluated and tested according to user's insurance products, most close user is calculated and determined；
Second determination unit, for the otherness based on the user and most close the bought insurance products of user, really
Fixed insurance products to be recommended；And
Calculating and output unit, for calculating the most close user to the recommendation of the insurance products to be recommended, and
It is exported to user.
The embodiment of the present invention also provides a kind of computer equipment, and the computer equipment includes memory and processor, institute
It states and is stored with computer program in memory, when the computer program is executed by the processor, so that the processor is held
The step of row above-mentioned insurance products recommended method.
The embodiment of the present invention also provides a kind of computer readable storage medium, stores on the computer readable storage medium
There is computer program, when the computer program is executed by processor, so that the processor executes above-mentioned insurance products and recommends
The step of method.
In the embodiment of the present invention, is recorded by obtaining the evaluation and test of user's insurance products, most close user is calculated and determined, and
Otherness based on the user and most close the bought insurance products of user, determines insurance products to be recommended, and calculate institute
Most close user is stated to the recommendation of the insurance products to be recommended, and exports recommended insurance products to user, is embodied as
User formulates more personalized, diversified insurance products real-time recommendation, and further improves recommendation efficiency, while being avoided that out
The problem of current family privacy compromise risk.
Detailed description of the invention
Fig. 1 is a kind of implementation flow chart of insurance products recommended method provided in an embodiment of the present invention；
Fig. 2 is the implementation flow chart of another insurance products recommended method provided in an embodiment of the present invention；
Fig. 3 is a kind of implementation flow chart of the insurance products recommended method of optimization provided in an embodiment of the present invention；
Fig. 4 is the implementation flow chart of the insurance products recommended method of another optimization provided in an embodiment of the present invention；
Fig. 5 is the implementation flow chart of the insurance products recommended method of another optimization provided in an embodiment of the present invention；
Fig. 6 is the implementation flow chart of the insurance products recommended method of another optimization provided in an embodiment of the present invention；
Fig. 7 is a kind of structural schematic diagram of insurance products recommendation apparatus provided in an embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
The term used in embodiments of the present invention is only to be not intended to be limiting merely for for the purpose of describing particular embodiments
The present invention.Packet is also intended in the "an" and "the" of the embodiment of the present invention and singular used in the attached claims
Most forms are included, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein is
Refer to and includes that one or more associated any or all of project listed may combine.
It will be appreciated that though various information may be described in embodiments of the present invention using term first, second etc., but
These information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.
The technical means and efficacy taken in order to which the present invention is further explained for the predetermined goal of the invention of realization, according to as follows
Insurance products recommended method provided in an embodiment of the present invention is described in detail in embodiment.
Insurance products recommended method provided in an embodiment of the present invention is calculated by obtaining user's insurance products evaluation and test record
And determine most close user, and the otherness based on the user and most close the bought insurance products of user, determination to
Recommend insurance products, and calculates the most close user and export institute to the recommendation of the insurance products to be recommended, and to user
The insurance products of recommendation are embodied as user and formulate more personalized, diversified insurance products real-time recommendation, and further improve
Recommend efficiency, while being avoided that and the problem of privacy of user risk of leakage occur.
Fig. 1 shows a kind of implementation process of insurance products recommended method provided in an embodiment of the present invention, for the ease of saying
It is bright, part related to the embodiment of the present invention is only shown, details are as follows:
In step s101, user's insurance products evaluation and test record is obtained.
In embodiments of the present invention, user's insurance products evaluation and test is recorded as user's history behavioral data collection, specific to wrap
User is included to have bought the data set of insurance products and browsed the data set of insurance products.
In step s 102, it is evaluated and tested and is recorded according to user's insurance products, most close user is calculated and determined.
In embodiments of the present invention, as shown in Fig. 2, the step S102, specifically includes the following steps:
In step s 201, it is evaluated and tested and is recorded according to user's insurance products, calculated based on cosine similarity algorithm related
Similarity between user.
In embodiments of the present invention, similarity, that is, measuring similarity (Similarity) calculates the similar journey between individual
Degree, the value of measuring similarity is smaller, and similarity is smaller between illustrating individual, and the value of similarity is bigger to illustrate that individual difference is bigger.It is right
How the similarity between them is calculated in multiple and different texts or short text conversation message, and a good way is just
It is that word in these texts is mapped to vector space, forms the mapping relations of text and vector data in text, pass through calculating
The size of the difference of several or multiple and different vectors, to calculate the similarity of text.
In embodiments of the present invention, cosine similarity, also referred to as COS distance are with two vector angles in vector space
Cosine value as measure two inter-individual differences size measurement.Cosine value closer to 1, indicate that angle closer to 0 degree,
Namely two vectors are more similar, this is just " cosine similarity ".
In embodiments of the present invention, it is evaluated and tested and is recorded according to user's insurance products, calculated based on cosine similarity algorithm
Similarity between associated user can be the historical behavior data set of user and associated user (as bought insurance products
Data set and browsed the data sets of insurance products), remove several keywords, be merged into a set, calculate each other
For the word frequency of the word in this set, respective word frequency vector is generated, and then calculates the cosine similarity of two vectors, value is got over
It means that greatly more similar.
In step S202, according to the similarity between the associated user, user to be recommended is determined.
In embodiments of the present invention, according to the similarity between the associated user, user to be recommended is determined, it is specific to wrap
Include: the value of cosine similarity is bigger, means that more similar, and corresponding associated user is determined as user to be recommended.
In step S203, the K in user to be recommended most close users are calculated based on K k-nearest neighbor.
In embodiments of the present invention, K k-nearest neighbor, that is, nearest neighbor algorithm, in other words K arest neighbors (kNN, k-Nearest
Neighbor) sorting algorithm is one of simplest method in Data Mining Classification technology.So-called K arest neighbors is exactly k nearest
Neighbours the meaning, what is said is that each sample can be represented with its immediate k neighbour.The thought of KNN algorithm is exactly
In the situation known to training intensive data and label, input test data are corresponding with training set by the feature of test data
Feature be compared to each other, find in training set the most similar preceding K data therewith, then the corresponding classification of the test data
It is exactly that classification that frequency of occurrence is most in K data, the description of algorithm are as follows: calculate test data and each training data
The distance between；It is ranked up according to the incremental relationship of distance；The smallest K point of selected distance；Classification where K point before determining
The frequency of occurrences；The highest classification of the frequency of occurrences is classified as the prediction of test data in K point before returning.
In step s 103, the otherness based on the user and most close the bought insurance products of user, determine to
Recommend insurance products.
In embodiments of the present invention, as shown in figure 3, the step S103, specifically includes:
In step S301, the insurance products purchaser record of the user and most close user are compared, determined
The different insurance products classifications that the user and most close user are bought.
In step s 302, the insurance products that most close user has bought but the user does not buy are obtained, and really
It is set to insurance products to be recommended.
In embodiments of the present invention, the comparison for the insurance products bought according to the user and most close user, obtains out
The insurance products that most close user has bought but the user does not buy, as insurance products to be recommended.
In embodiments of the present invention, it is now assumed that user's collection is combined into Q={ q1, q2, q3 ... qi }, wherein qi is indicated i-th
User property set；Insurance products collection is combined into X={ x1, x2, x3 ... xi }, and wherein xi indicates i-th kind of insurance products property set
It closes, every kind of insurance products have corresponding attribute value, indicate i-th kind of insurance products, j-th of attribute coding's value with xij；With 0,1 mark
Note has been bought and does not buy two kinds of behaviors, then { 0,1 } yi=, and user's history buys situation data, including a certain amount of positive example and
Two kinds of sample datas of counter-example.
In embodiments of the present invention, as shown in figure 4, the step S103, further includes:
In step S401, the insurance products that the user and most close user are bought are obtained, it is reversed based on error
Propagation algorithm is excavated to the characteristic attribute values of the insurance products, determines the preference intention of the user.
In embodiments of the present invention, the basic think of of error backpropagation algorithm (Error Back Propagation, BP)
Think it is that learning process is made of the forward-propagating of signal and two processes of backpropagation of error.
In embodiments of the present invention, the preference of dynamic of capture user's shopping, knot are removed by studying user's history behavioral data
It closes BP algorithm and excavates the closely bound up feature attribute of commodity collection of every user's purchasing habits, and establish the association based on characteristic attribute
Regular recommended models and recommended models based on timeliness, further promote the efficiency of personalized real-time recommendation system recommendation, and increase
Add its diversity.
In step S402, according to the preference intention of the user, insurance products to be recommended are determined.
In embodiments of the present invention, it is assumed that the collection for extracting the characteristic attribute value of insurance products is combined into P { p1, p2, p3 ...
Pn }, from the corresponding feature attribute of commodity set of every user, so that it may grasp the shopping preferences of the user substantially.For example, insurance produces
If in product characteristic attribute including unit price, which should compare when buying insurance products values this factor of cargo price, can root
The average price of commodity, which is bought, according to it carries out real-time recommendation for it.
In embodiments of the present invention, as shown in figure 5, the step S103, further includes:
In step S501, the insurance products record that the user and most close user are bought is obtained, based on association
Rule-based algorithm carries out the search of frequent item set, determines the purchase intention of the user.
In embodiments of the present invention, association rule algorithm, that is, FP-growth algorithm (Frequent Pattern-
Growth), a kind of data structure of deflation has been used to store all information required for searching frequent item set；Frequency will be provided
The database compressing of numerous item collection retains item collection related information to a FP-tree, and compressed database is then divided into one
Group condition database (a kind of data for projection library of specific type), each condition database are associated with a frequent item set.
In step S502, according to the purchase intention of the user, insurance products to be recommended are determined.
In embodiments of the present invention, it is known that the collection of the characteristic attribute value of the purchased insurance products of user be combined into P p1, p2,
P3 ... pn }, then situation table is bought in combination with user, can extract the insurance products record of the had a preference for purchase of user.Assuming that in the presence of
Following purchaser record { a, b, c, d；a,b,c；a,c,d,e；e,f；A, b, c, d, e, f }, with FP-tree association rule algorithm into
Frequency collection therein is generated one frequently according to associated mode first to scan database one time by the search of row frequent item set
Scheme-tree (FP-tree), is then divided, and forms several condition libraries, each library is related to the frequency collection that length is 1, finally
Specific condition library is carried out respectively and is excavated.In user's purchase, which can recommend its sense emerging for user
The insurance products and its Related product of interest, improve the diversity of real-time recommendation, to further increase user satisfaction, reach and stay
The purpose at dweller family.
In embodiments of the present invention, the preference of dynamic of capture user's shopping, knot are removed by studying user's history behavioral data
It closes BP algorithm and excavates the closely bound up feature attribute of commodity collection of every user's purchasing habits, and establish the association based on characteristic attribute
Regular recommended models and recommended models based on timeliness, further promote the efficiency of personalized real-time recommendation system recommendation, and increase
Add its diversity.
In step S104, the most close user is calculated to the recommendation of the insurance products to be recommended, and to user
Output.
In embodiments of the present invention, as shown in fig. 6, the step S104, specifically includes:
In step s 601, the most close user is obtained to the score value of the insurance products to be recommended, and calculates phase
The score average of corresponding insurance products to be recommended, and it is determined as the recommendation of insurance products to be recommended.
In embodiments of the present invention, most close user can be by from network to the score value of the insurance products to be recommended
The modes such as insurance score data library are obtained inside database or insurance company.
In step S602, the recommendation of the insurance to be recommended is ranked up, and is exported to user and recommends sequencing table.
Insurance products recommended method provided in an embodiment of the present invention is calculated by obtaining user's insurance products evaluation and test record
And determine most close user, and the otherness based on the user and most close the bought insurance products of user, determination to
Recommend insurance products, and calculates the most close user and export institute to the recommendation of the insurance products to be recommended, and to user
The insurance products of recommendation are embodied as user and formulate more personalized, diversified insurance products real-time recommendation, and further improve
Recommend efficiency, while being avoided that and the problem of privacy of user risk of leakage occur.
The structure that Fig. 7 shows a kind of insurance products recommendation apparatus of the embodiment of the present invention is only shown for ease of description
Part related to the embodiment of the present invention, details are as follows:
A kind of insurance products recommendation apparatus 700, comprising: acquiring unit 701, the first determination unit 702, the second determination unit
703 and calculate and output unit 704.
Acquiring unit 701, for obtaining user's insurance products evaluation and test record.
In embodiments of the present invention, acquiring unit 701 is for obtaining user's insurance products evaluation and test record；Wherein, the use
Family insurance products evaluation and test be recorded as user's history behavioral data collection, specifically include user bought insurance products data set and
The data set of insurance products is browsed.
First determination unit 702 records for being evaluated and tested according to user's insurance products, most close use is calculated and determined
Family.
In embodiments of the present invention, the first determination unit 702 is used to be evaluated and tested according to user's insurance products and record, and calculates
And determine most close user；Wherein, described evaluated and tested according to user's insurance products records, and most close user is calculated and determined,
Include: to be evaluated and tested to record according to user's insurance products, the similarity between associated user is calculated based on cosine similarity algorithm；
According to the similarity between the associated user, user to be recommended is determined；It is calculated in user to be recommended based on K k-nearest neighbor
K most close users.
Second determination unit 703, for the otherness based on the user and most close the bought insurance products of user,
Determine insurance products to be recommended.
In embodiments of the present invention, the second determination unit 703 is used to be bought based on the user and most close user
The otherness of insurance products determines insurance products to be recommended；Wherein, described to be bought based on the user and most close user
The otherness of insurance products determines insurance products to be recommended, comprising: purchases to the insurance products of the user and most close user
It buys record to be compared, determines the different insurance products classifications that the user and most close user are bought；Described in acquisition
The insurance products that most close user has bought but the user does not buy, and it is determined as insurance products to be recommended.
It calculates and output unit 704, for calculating the most close user to the recommendation of the insurance products to be recommended,
And it is exported to user.
In embodiments of the present invention, it calculates and output unit 704 is for calculating the most close user to described to be recommended
The recommendation of insurance products, and exported to user；Wherein, most close user described in the calculating is to the insurance products to be recommended
Recommendation, and exported to user, specifically include: obtaining the scoring of the most close user to the insurance products to be recommended
Value, and the score average of corresponding insurance products to be recommended is calculated, and be determined as the recommendation of insurance products to be recommended；It is right
The recommendation of the insurance to be recommended is ranked up, and is exported to user and recommended sequencing table.
Insurance products recommendation apparatus provided in an embodiment of the present invention is calculated by obtaining user's insurance products evaluation and test record
And determine most close user, and the otherness based on the user and most close the bought insurance products of user, determination to
Recommend insurance products, and calculates the most close user and export institute to the recommendation of the insurance products to be recommended, and to user
The insurance products of recommendation are embodied as user and formulate more personalized, diversified insurance products real-time recommendation, and further improve
Recommend efficiency, while being avoided that and the problem of privacy of user risk of leakage occur.
The embodiment of the invention also provides a kind of computer equipment, which includes processor, and processor is used for
The insurance products recommended method that above-mentioned each embodiment of the method provides is realized when executing the computer program stored in memory
Step.
The embodiments of the present invention also provide a kind of computer readable storage medium, it is stored thereon with computer program/refer to
It enables, which realizes that above-mentioned each embodiment of the method provides insurance products when being executed by above-mentioned processor push away
The step of recommending method.
Illustratively, computer program can be divided into one or more modules, one or more module is stored
In memory, and by processor it executes, to complete the present invention.One or more modules, which can be, can complete specific function
Series of computation machine program instruction section, the instruction segment is for describing implementation procedure of the computer program in computer equipment.Example
Such as, the computer program can be divided into the step of insurance products recommended method that above-mentioned each embodiment of the method provides.
It will be understood by those skilled in the art that the description of above-mentioned computer equipment is only example, do not constitute to calculating
The restriction of machine equipment may include component more more or fewer than foregoing description, perhaps combine certain components or different portions
Part, such as may include input-output equipment, network access equipment, bus etc..
Alleged processor can be central processing unit (Central Processing Unit, CPU), can also be it
His general processor, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng the processor is the control centre of the computer installation, utilizes various interfaces and the entire user terminal of connection
Various pieces.
The memory can be used for storing the computer program and/or module, and the processor is by operation or executes
Computer program in the memory and/or module are stored, and calls the data being stored in memory, described in realization
The various functions of computer equipment.The memory can mainly include storing program area and storage data area, wherein storage program
It area can application program (such as sound-playing function, image player function etc.) needed for storage program area, at least one function
Deng；Storage data area, which can be stored, uses created data (such as audio data, phone directory etc.) etc. according to mobile phone.In addition,
Memory may include high-speed random access memory, can also include nonvolatile memory, such as hard disk, memory, grafting
Formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card
(Flash Card), at least one disk memory, flush memory device or other volatile solid-state parts.
If the integrated module/unit of the computer equipment is realized in the form of SFU software functional unit and as independent
Product when selling or using, can store in a computer readable storage medium.Based on this understanding, the present invention is real
All or part of the process in existing above-described embodiment method, can also instruct relevant hardware come complete by computer program
At the computer program can be stored in a computer readable storage medium, which is being executed by processor
When, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program includes computer program code, described
Computer program code can be source code form, object identification code form, executable file or certain intermediate forms etc..The meter
Calculation machine readable medium may include: can carry the computer program code any entity or device, recording medium, USB flash disk,
Mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory
Device (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (10)
1. a kind of insurance products recommended method, which is characterized in that the described method includes:
Obtain user's insurance products evaluation and test record；
It is evaluated and tested and is recorded according to user's insurance products, most close user is calculated and determined；
Otherness based on the user and most close the bought insurance products of user, determines insurance products to be recommended；
The most close user is calculated to export to the recommendation of the insurance products to be recommended, and to user.
2. the method as described in claim 1, which is characterized in that described evaluated and tested according to user's insurance products records, and calculates
And determine most close user, it specifically includes:
It is evaluated and tested and is recorded according to user's insurance products, the similarity between associated user is calculated based on cosine similarity algorithm；
According to the similarity between the associated user, user to be recommended is determined；
The K in user to be recommended most close users are calculated based on K k-nearest neighbor.
3. the method as described in claim 1, which is characterized in that described to buy guarantor based on the user and most close user
The otherness of dangerous product determines insurance products to be recommended, specifically includes:
The insurance products purchaser record of the user and most close user are compared, determine the user and most close
The different insurance products classifications that user is bought；
The insurance products that most close user has bought but the user does not buy are obtained, and is determined as insurance to be recommended and produces
Product.
4. the method as described in claim 1, which is characterized in that described to buy guarantor based on the user and most close user
The otherness of dangerous product determines insurance products to be recommended, further includes:
The insurance products that the user and most close user are bought are obtained, based on error backpropagation algorithm to the insurance
The characteristic attribute value of product excavate, and determines the preference intention of the user；
According to the preference intention of the user, insurance products to be recommended are determined.
5. the method as described in claim 1, which is characterized in that described to buy guarantor based on the user and most close user
The otherness of dangerous product determines insurance products to be recommended, further includes:
The insurance products record that the user and most close user are bought is obtained, frequent episode is carried out based on association rule algorithm
The search of collection determines the purchase intention of the user；
According to the purchase intention of the user, insurance products to be recommended are determined.
6. the method as described in claim 1, which is characterized in that most close user is to the insurance to be recommended described in the calculating
The recommendation of product, and exported to user, it specifically includes:
The most close user is obtained to the score value of the insurance products to be recommended, and calculates corresponding insurance to be recommended and produces
The score average of product, and it is determined as the recommendation of insurance products to be recommended；
The recommendation of the insurance to be recommended is ranked up, and is exported to user and recommends sequencing table.
7. the method as described in claim 1, which is characterized in that user's insurance products evaluation and test is recorded as user's history behavior
Data set specifically includes user and has bought the data set of insurance products and browsed the data set of insurance products.
8. a kind of insurance products recommendation apparatus, which is characterized in that described device includes:
Acquiring unit, for obtaining user's insurance products evaluation and test record；
First determination unit records for being evaluated and tested according to user's insurance products, most close user is calculated and determined；
Second determination unit, for the otherness based on the user and most close the bought insurance products of user, determine to
Recommend insurance products；And
Calculate and output unit, for calculating the most close user to the recommendation of the insurance products to be recommended, and to
Family output.
9. a kind of computer equipment, which is characterized in that the computer equipment includes memory and processor, in the memory
It is stored with computer program, when the computer program is executed by the processor, so that the processor perform claim requires 1
To described in any one of 7 claims the step of insurance products recommended method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program, when the computer program is executed by processor, so that the processor perform claim requires any one of 1 to 7 right
It is required that the step of insurance products recommended method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811647487.7A CN109858999A (en) | 2018-12-29 | 2018-12-29 | A kind of insurance products recommended method, device, equipment and readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811647487.7A CN109858999A (en) | 2018-12-29 | 2018-12-29 | A kind of insurance products recommended method, device, equipment and readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109858999A true CN109858999A (en) | 2019-06-07 |
Family
ID=66893626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811647487.7A Withdrawn CN109858999A (en) | 2018-12-29 | 2018-12-29 | A kind of insurance products recommended method, device, equipment and readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109858999A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766559A (en) * | 2019-10-30 | 2020-02-07 | 海腾保险代理有限公司 | Label configuration method and device |
| CN110992109A (en) * | 2019-12-16 | 2020-04-10 | 重庆锐云科技有限公司 | Real estate customer analysis method, device and storage medium based on association rule |
| CN111179041A (en) * | 2020-01-22 | 2020-05-19 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Riding insurance product recommendation method and device |
| CN112488863A (en) * | 2020-12-01 | 2021-03-12 | 中国人寿保险股份有限公司 | Dangerous seed recommendation method and related equipment in user cold start scene |
| CN114663200A (en) * | 2022-05-23 | 2022-06-24 | 中国平安财产保险股份有限公司 | Product recommendation method and device, electronic equipment and storage medium |
-
2018
- 2018-12-29 CN CN201811647487.7A patent/CN109858999A/en not_active Withdrawn
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766559A (en) * | 2019-10-30 | 2020-02-07 | 海腾保险代理有限公司 | Label configuration method and device |
| CN110766559B (en) * | 2019-10-30 | 2023-09-29 | 海腾保险代理有限公司 | Label configuration method and device |
| CN110992109A (en) * | 2019-12-16 | 2020-04-10 | 重庆锐云科技有限公司 | Real estate customer analysis method, device and storage medium based on association rule |
| CN110992109B (en) * | 2019-12-16 | 2022-09-02 | 重庆锐云科技有限公司 | Real estate customer analysis method, apparatus and storage medium based on association rule |
| CN111179041A (en) * | 2020-01-22 | 2020-05-19 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Riding insurance product recommendation method and device |
| CN112488863A (en) * | 2020-12-01 | 2021-03-12 | 中国人寿保险股份有限公司 | Dangerous seed recommendation method and related equipment in user cold start scene |
| CN112488863B (en) * | 2020-12-01 | 2024-05-28 | 中国人寿保险股份有限公司 | Dangerous seed recommendation method and related equipment in user cold start scene |
| CN114663200A (en) * | 2022-05-23 | 2022-06-24 | 中国平安财产保险股份有限公司 | Product recommendation method and device, electronic equipment and storage medium |
| CN114663200B (en) * | 2022-05-23 | 2022-09-16 | 中国平安财产保险股份有限公司 | Product recommendation method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858999A (en) | A kind of insurance products recommended method, device, equipment and readable storage medium storing program for executing | |
| Cunha et al. | Metalearning and Recommender Systems: A literature review and empirical study on the algorithm selection problem for Collaborative Filtering | |
| Bag et al. | An integrated recommender system for improved accuracy and aggregate diversity | |
| CN102737333B (en) | For calculating user and the offer order engine to the coupling of small segmentation | |
| CN111815415A (en) | Commodity recommendation method, system and equipment | |
| CN103034680B (en) | For data interactive method and the device of terminal device | |
| Khatwani et al. | Building personalized and non personalized recommendation systems | |
| CN111695023A (en) | Information recommendation method and device, storage medium and equipment | |
| Xia et al. | Modeling consumer buying decision for recommendation based on multi-task deep learning | |
| Iwanaga et al. | Estimating product-choice probabilities from recency and frequency of page views | |
| CN109543107A (en) | Data processing method, medium, device and calculating equipment | |
| Yu et al. | Complementary recommendations: A brief survey | |
| Latifi et al. | Sequential recommendation: A study on transformers, nearest neighbors and sampled metrics | |
| CN111078997B (en) | Information recommendation method and device | |
| CN115659055A (en) | Commodity recommendation method, system, equipment and storage medium based on event sequence | |
| US20240013280A1 (en) | Product recommendation method and apparatus, computer storage medium, and system | |
| Liu et al. | Extracting, ranking, and evaluating quality features of web services through user review sentiment analysis | |
| CN114155009A (en) | Fraud detection method and device, electronic equipment and storage medium | |
| CA3035539A1 (en) | Systems and methods for measuring collected content significance | |
| CN115618126A (en) | Search processing method, system, computer readable storage medium and computer device | |
| Trappey et al. | Using Web Mining and Perceptual Mapping to Support Customer-Oriented Product Positions Designs | |
| Pinto et al. | Hybrid recommendation system based on collaborative filtering and fuzzy numbers | |
| Rana et al. | An introduction to basic concepts on recommender systems | |
| Dong et al. | Statistical and machine learning-based e-commerce sales forecasting | |
| CN108595498A (en) | Problem feedback method and device |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190607 |
|
| WW01 | Invention patent application withdrawn after publication |