CN109961309B - Service recommendation method and system - Google Patents
Service recommendation method and system Download PDFInfo
- Publication number
- CN109961309B CN109961309B CN201711426356.1A CN201711426356A CN109961309B CN 109961309 B CN109961309 B CN 109961309B CN 201711426356 A CN201711426356 A CN 201711426356A CN 109961309 B CN109961309 B CN 109961309B
- Authority
- CN
- China
- Prior art keywords
- user
- service
- recommended
- characteristic value
- transaction
- 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.)
- Active
Links
Images
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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a service recommendation method and a system, which relate to the technical field of service recommendation and comprise the following steps: acquiring personal information of each user in a user group; determining key conditions of the service according to the service type; judging whether the personal information of each user in the user group meets the key condition one by one; if so, determining the users meeting the key conditions as the users of the service to be recommended; obtaining a characteristic value according to personal information of a service user to be recommended; and judging whether the user recommends the service for the service to be recommended according to the characteristic value. The method can determine the key conditions of the service through the service type, then roughly screen the customer information under the big data through the key conditions, take the screened users as the users to be recommended, then accurately screen the users to be recommended by following the characteristic value, and recommend the service to the people who pass through the accurate screening, so that the service recommendation with pertinence can be carried out, and the perception of the customers can be improved.
Description
Technical Field
The present invention relates to the field of service recommendation technologies, and in particular, to a service recommendation method and system.
Background
As internet technology continues to advance, more and more data is gathered on the internet, some of which are implicit, unknown a priori, and potentially contain useful information, which may be used to represent concepts, rules, laws, patterns, and so forth. Therefore, the relation between the data segments needs to be found from the mass data through an analysis tool, so that the prediction of business and industry development can be carried out.
In the related art, when recommending services to users, it often happens that different types of services are recommended to the same group of users stored in the database, which may cause some people who have purchased the related services to receive information or people who are not suitable for purchasing the related services to receive recommendation messages, which not only causes complaints of customers, resulting in a reduction in the good feeling of companies, but also wastes resources of the companies.
Disclosure of Invention
In view of this, the present invention aims to provide a service recommendation method and system, which can determine a key condition of a service according to a service type, then perform a rough screening on client information under big data according to the key condition, use a screened user as a user to be recommended, then accurately screen the user to be recommended along with a characteristic value, and recommend the service to a person who passes the accurate screening, so as to perform targeted service recommendation, thereby improving the perception of the client.
In a first aspect, an embodiment of the present invention provides a service recommendation method, including: acquiring personal information of each user in a user group; determining key conditions of the service according to the service type; judging whether the personal information of each user in the user group meets the key condition one by one; if yes, determining the users meeting the key conditions as the users of the service to be recommended; obtaining a characteristic value according to personal information of a service user to be recommended; and judging whether to recommend the service to the user of the service to be recommended or not according to the characteristic value.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, where the obtaining a feature value according to personal information of a service user to be recommended includes: acquiring a relation characteristic value according to personal information of a service user to be recommended; acquiring a clustering characteristic value according to personal information of a service user to be recommended; and carrying out weighting processing on the relation special value and the clustering characteristic value to obtain a characteristic value.
With reference to the first aspect, an embodiment of the present invention provides a second possible implementation manner of the first aspect, where the obtaining a relationship characteristic value according to personal information of a service user to be recommended includes: extracting trading users trading with the service users to be recommended from the user group; acquiring transaction information of the service user to be recommended and the transaction user, wherein the transaction information comprises transaction times and transaction amount; judging whether the transaction times meet the preset times and the transaction amount meets the preset amount or not in the transaction information corresponding to the transaction user; if yes, extracting the transaction user corresponding to the maximum value of the transaction times and the transaction amount; determining the grade of the transaction user corresponding to the maximum value; and determining the relation characteristic value of the user of the service to be recommended as a set value according to the grade.
With reference to the first aspect, an embodiment of the present invention provides a third possible implementation manner of the first aspect, where the obtaining a cluster feature value according to personal information of a service user to be recommended includes: extracting the users from the user group; acquiring personal information of the current user; performing cluster analysis on the personal information of the service user to be recommended and the personal information of the current user; and obtaining a clustering characteristic value according to a clustering analysis result.
With reference to the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, where the determining, according to the feature value, whether to recommend the service to be recommended user includes: judging whether the characteristic value is larger than a preset characteristic value or not; if so, recommending the service to the user of the service to be recommended.
In a second aspect, an embodiment of the present invention further provides a service recommendation system, including: the acquisition module is used for acquiring personal information of each user in the user group; the condition determining module is used for determining the key conditions of the service according to the service type; the judging module is used for judging whether the personal information of each user in the user group meets the key condition one by one; the user determining module is used for determining the users meeting the key conditions as the users of the service to be recommended if the users meet the key conditions; the obtaining characteristic module is used for obtaining a characteristic value according to the personal information of the service user to be recommended; and the recommendation service module is used for judging whether to recommend the service to the service user to be recommended according to the characteristic value.
With reference to the second aspect, an embodiment of the present invention provides a first possible implementation manner of the second aspect, where the obtaining a feature module includes: the relation characteristic value obtaining submodule is used for obtaining a relation characteristic value according to the personal information of the service user to be recommended; the sub-module for obtaining the clustering characteristic value obtains the clustering characteristic value according to the personal information of the service user to be recommended; and the weighting submodule is used for weighting the relation special value and the clustering characteristic value to obtain a characteristic value.
With reference to the second aspect, an embodiment of the present invention provides a second possible implementation manner of the second aspect, where the obtaining relationship characteristic value submodule is configured to: extracting trading users trading with the service users to be recommended from the user group; acquiring transaction information of the service user to be recommended and the transaction user, wherein the transaction information comprises transaction times and transaction amount; judging whether the transaction times meet the preset times and the transaction amount meets the preset amount or not in the transaction information corresponding to the transaction user; if yes, extracting the transaction user corresponding to the maximum value of the transaction times and the transaction amount; determining the grade of the transaction user corresponding to the maximum value; and determining the relation characteristic value of the user of the service to be recommended as a set value according to the grade.
With reference to the second aspect, an embodiment of the present invention provides a third possible implementation manner of the second aspect, where the module for obtaining a cluster feature value is configured to: extracting the users from the user group; acquiring personal information of the current user; performing cluster analysis on the personal information of the service user to be recommended and the personal information of the current user; and obtaining a clustering characteristic value according to the clustering analysis result.
With reference to the second aspect, an embodiment of the present invention provides a fourth possible implementation manner of the second aspect, where the recommendation service module is configured to: judging whether the characteristic value is larger than a preset characteristic value or not; and if so, recommending the service to be recommended user.
The embodiment of the invention has the following beneficial effects: the method can determine the key conditions of the service through the service type, then roughly screen the client information under the big data through the key conditions, take the screened users as the users to be recommended, and then accurately screen the users to be recommended by following the characteristic value, so that the service recommended by the people who pass through the accurate screening can be recommended with pertinence, and the perception of the client can be improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a service recommendation method according to an embodiment of the present invention;
fig. 2 is a flowchart of a service recommendation method according to another embodiment of the present invention;
fig. 3 is a flowchart of a service recommendation method according to another embodiment of the present invention;
fig. 4 is a block diagram of a service recommendation system according to an embodiment of the present invention.
Icon:
200-a service recommendation system; 210-an obtaining module; 220-determine conditions module; 230-a judgment module; 240-determine user module; 250-obtaining a feature module; 260-recommendation service Module.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without any creative effort, shall fall within the protection scope of the present invention.
When recommending service to a client, the client is firstly portrait, namely the client is divided into groups, and the characteristics of the client are very similar in each group; and the characteristics of the customers have large differences among different groups. By distinguishing different groups, each group can be effectively managed and corresponding business expansion can be adopted. However, different types of services are usually recommended to the same user group stored in the database, which may result in some people who have purchased the related service receiving information or people who are not suitable for purchasing the related service receiving a recommendation message, which not only causes complaints from customers, resulting in a reduction in the good feeling of the company, but also wastes resources of the company. Based on this, the service recommendation method and system provided in the embodiments of the present invention may determine the key conditions of the service according to the service type, then perform a rough screening on the client information under the big data according to the key conditions, use the screened user as the user to be recommended, follow the feature value, perform an accurate screening on the user to be recommended, and recommend the service to the person who passes the accurate screening, so that the service recommendation can be performed with pertinence, and thus the goodness of the client can be improved.
To facilitate understanding of the embodiment, first, a service recommendation method disclosed in the embodiment of the present invention is described in detail, and as shown in fig. 1, the method includes:
s110: personal information of each user in the user group is acquired.
For example, taking a bank as an example, if the bank wants to recommend a financial product to its own user, a request for obtaining personal information of the user is first sent from a database in the bank, i.e., the personal information of each user in the user group can be obtained. The personal information includes at least fields: name, age, identification card number, address, mobile phone, income, marital status, business purchase time, amount, business type and other information. Particularly, when the financial recommendation service is carried out, data generally needs to be processed in a secret mode. For example: and performing data desensitization treatment on the original data to form desensitization data, and establishing mapping between the desensitization data and a platform for acquiring the original data so as to find the original data through the desensitization data. Namely, personal information of each user in the user group which is processed with secrecy is obtained. Desensitization data formats are as follows: name: plum, identification number: 1101011982, age: 35. and (3) address: tokyo district of Beijing, cell phone: 13901234, revenue: 20000 yuan/month, marital status: married, relevant business purchase time: 11 months in 2017, amount: 10 ten thousand yuan (RMB).
S120: and determining key conditions of the service according to the service type.
Specifically, a foreground service type is preset and standardized. Examples of traffic types: fund financing, purchasing personal insurance, and bond-preserving products, the type of recommended service, e.g., fund financing, is first determined, and then key conditions for fund financing are determined in step S120. The key condition is a condition that the user is determined to possibly purchase or subscribe the service according to the service type, for example, if the service type is determined to be fund financing, the key condition can be set to be that the monthly income is greater than 10000, or can be set to be that the address is within four broad and deep rings in the north; if the service type is determined to be a key protection product, the key condition can be set to be over 40 years old; if the business type is determined to be personal insurance, the key condition may be set to a group whose occupation is a dangerous occupation.
S130: and judging whether the personal information of each user in the user group meets the key conditions one by one.
For example, taking the recommended fund financing service and taking the condition that the monthly income is greater than 10000 as an example, the monthly income in the personal information of the user is compared with the key condition.
S140: and if so, determining the users meeting the key conditions as the users of the service to be recommended.
For example, if the obtained users in the user group satisfy the condition in step S130, the user satisfying the condition is determined to be the service to be recommended user. Namely, screening is carried out on big data through key conditions, and users which are obviously inconsistent with the service to be recommended are filtered.
S150: and obtaining the characteristic value according to the personal information of the service user to be recommended.
In some embodiments, step S150 includes: acquiring a relation characteristic value according to personal information of a service user to be recommended; acquiring a clustering characteristic value according to personal information of a service user to be recommended; and weighting the relation special value and the clustering characteristic value to obtain a characteristic value.
The relation characteristic value refers to a numerical value of the transaction information of the service user to be recommended. The clustering characteristic value is a numerical value obtained when the user of the service to be recommended performs clustering analysis.
Referring to fig. 2, obtaining the relationship characteristic value according to the personal information of the service user to be recommended includes:
s151: and extracting trading users trading with the service users to be recommended from the user group.
The transaction user refers to a user who has a transaction with the user to be recommended, and the transaction may be a user who has a remittance record with the user to be recommended, or a transaction with the user to be recommended for another money, such as a transfer by WeChat.
Specifically, whether the user has traded with the service to be recommended is confirmed from the trading record, if the user has traded, the user is considered as a trading user, and all users in the user group who have traded with the service to be recommended are found.
S152: and acquiring transaction information of the service user to be recommended and the transaction user, wherein the transaction information comprises transaction times and transaction amount.
Specifically, after the trading user is determined, the trading information between the business user to be recommended and the trading user is obtained, for example, bank account transfer is taken as an example, the user to be recommended is Zhang-Chun, the trading users who have the trading record with Zhang-Chun are Wei-Chun and Liu-Chun, the times of all trades of Wei-Chun and Zhang-Chun are added to obtain a total number of trades, the sum of all trades of Wei-Chun and Zhang-Chun is added to obtain a total amount of trades, and the trading information between Zhang-Chun and Wei is the total number of trades and the total amount of trades.
S153: and judging whether the transaction times meet the preset times and the transaction amount meets the preset amount in the transaction information corresponding to the transaction user.
Examples are: when the preset times are 20 times and the preset amount of money set for the transaction amount is 40 ten thousand, whether the transaction times and the transaction amount of the transaction users meet the conditions of 20 times and 40 ten thousand is judged.
S154: and if so, extracting the transaction user corresponding to the maximum value of the transaction times and the transaction amount.
Specifically, if the number of times of transaction and the transaction amount are available, the persons meeting the transaction number and the transaction amount are extracted, for example, if the transaction user opens a certain transaction number and the transaction amount is 30 to 50 thousands, if the transaction user closes a certain transaction number and the transaction amount is 10 to 40 thousands, if the transaction user closes a certain transaction number and the transaction amount is 40 to 100 thousands, then the condition of opening a certain transaction number and closing a certain transaction amount is met. And extracting the transaction user corresponding to the maximum value of the model.
S155: and determining the grade of the transaction user corresponding to the maximum value.
For example, the ranking rule is: in terms of actual production being every 20 in case, for example, the transfer is 100 ten thousand for 50, 80 ten thousand for 40. 20 times and 20 ten thousand are the first level, 40 times and 40 ten thousand are the second level, 60 times and 60 ten thousand are the third level, 80 times and 80 ten thousand are the fourth level, and so on.
For example, if the transaction user specifies a certain number of transactions and a transaction amount of 40 to 100 ten thousand, the user specifies a second rank according to the rank rule.
S156: and determining the relation characteristic value of the user of the service to be recommended as a set value according to the grade.
For example, a second rating of 50 points is given.
Referring to fig. 3, obtaining a cluster feature value according to personal information of a service user to be recommended includes:
s1511: and extracting the users from the user group.
The current user refers to a service that has bought the service type, for example, if a financial product is recommended to a specific customer, the human current user who bought the financial product.
S1512: personal information to and from the user is acquired.
Specifically, personal information of the user is acquired from the database.
S1513: and carrying out cluster analysis on the personal information of the user of the service to be recommended and the personal information of the user to and from the service to be recommended.
Specifically, the method comprises the following steps: firstly, training is carried out by utilizing personal information of a user group, a classifier is manufactured, not only is naive Bayes algorithm training carried out, but also desensitization data is utilized to train the naive Bayes algorithm through data mapping, the machine learning function in the algorithm modifies the naive Bayes algorithm characteristics according to the calculation result, and an inflection point is found, so that the algorithm training is completed.
For example: substituting fields of name, ID card number, age, address, mobile phone, income, marital status, time of purchase, amount, etc. into naive Bayes algorithm model, and using formula
By conversion into expressions
Conversion to example:
the 'inflection point' is found by converting a naive Bayes formula into three well-solved formulas, so that the characteristics of the service can be obtained through the classifier.
And then, carrying out feature clustering on the users of the service to be recommended by using the trained algorithm, and then carrying out data clustering on the users who have bought the service type and come and go through the trained naive Bayesian algorithm.
S1514: and obtaining a clustering characteristic value according to a clustering analysis result.
Specifically, if similar features can be found according to the cluster analysis result, according to the number of the similar features, the cluster feature value is determined to be different preset values, and the number of the similar features corresponds to different preset values, for example, 100 points are given for 4 same features; 3 identical features, score 90; etc., for example: and B is a financial user who does not purchase funds, and the result after clustering according to fields such as identity card number, age, address, mobile phone, income, marital status, related business purchase time, amount and the like is as follows: age 36, married, Beijing, income 20000 yuan/month; a is a user who purchases fund financing, and the naive Bayes algorithm obtains the characteristics that: 35 years old, married, Beijing, income 18000 yuan/month; both a and b are older than 30 years, married, living in front-line cities, and income greater than 10000, so b is given a score of 100 given by assuming it is a similar feature to those who purchased financial products. Scoring in step S154 yields 0.6 × 100+0.4 × 50 — 80, and the total score for b is 80 points. Of course, if B gets the result of clustering: if the person is 34 years old, not married, Beijing and income 20000 Yuan/month, then there are 3 similar characteristics between the person and the nail, and the score of B can be 90.
S160: and judging whether the user recommends the service for the service to be recommended according to the characteristic value.
Step S160 specifically includes: judging whether the characteristic value is larger than a preset characteristic value or not; and if so, recommending the service to be recommended user.
For example: and setting the preset characteristic value to be 75 points, wherein B is more than 75 points, and the recommendation requirement is met.
Referring to fig. 4, the service recommendation system 200 includes: the system comprises an acquisition module 210, a condition determining module 220, a judgment module 230, a user determining module 240, a feature obtaining module 250 and a service recommending module 260.
The obtaining module 210 is configured to obtain personal information of each user in the user group. The condition determining module 220 is used for determining the key conditions of the service according to the service type. The determining module 230 is configured to determine whether the personal information of each user in the user group satisfies the key condition one by one. And the user determining module is used for determining the users meeting the key conditions as the users of the service to be recommended if the users meet the key conditions. The obtaining characteristic module 240 is configured to obtain a characteristic value according to the personal information of the service user to be recommended. The recommendation service module 250 is configured to determine whether to recommend a service to the user of the service to be recommended according to the feature value.
In some embodiments, the obtain features module 250 includes: the relation characteristic value obtaining submodule is used for obtaining a relation characteristic value according to the personal information of the service user to be recommended; the sub-module for obtaining the clustering characteristic value obtains the clustering characteristic value according to the personal information of the service user to be recommended; and the weighting submodule is used for weighting the relation special value and the clustering characteristic value to obtain a characteristic value.
In some embodiments, the obtain relationship eigenvalues submodule is to: extracting trading users trading with the service users to be recommended from the user group; acquiring transaction information of a service user to be recommended and a transaction user, wherein the transaction information comprises transaction times and transaction amount; judging whether the transaction times of the transaction users meet the preset times and the transaction amount meets the preset amount; if yes, extracting the transaction user corresponding to the maximum value of the transaction amount and the transaction times; determining the grade of the transaction user corresponding to the maximum value; and determining the relation characteristic value of the user of the service to be recommended as a set value according to the grade.
In some embodiments, the obtain cluster feature value submodule is configured to: extracting a to-and-from user from the user group; acquiring personal information of the current user; performing cluster analysis on the personal information of the service user to be recommended and the personal information of the current user; and obtaining a clustering characteristic value according to a clustering analysis result.
In some embodiments, the recommendation service module 260 is configured to: judging whether the characteristic value is larger than a preset characteristic value or not; and if so, recommending the service to be recommended user.
The system provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, no mention is made to the system embodiments, and reference may be made to the corresponding contents in the method embodiments.
The relative steps of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
In all examples shown and described herein, any particular value should be construed as merely exemplary, and not as a limitation, and thus other examples of example embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through an intermediary, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in a specific case by those skilled in the art.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships indicated on the basis of the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are merely specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: those skilled in the art can still make modifications or changes to the technical solutions described in the foregoing embodiments or make equivalent substitutions for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (4)
1. A method for recommending services, comprising:
acquiring personal information of each user in a user group;
determining key conditions of the service according to the service type;
judging whether the personal information of each user in the user group meets the key condition one by one;
if yes, determining the users meeting the key conditions as the users of the service to be recommended;
obtaining a characteristic value according to personal information of a service user to be recommended;
judging whether to recommend the service to be recommended user according to the characteristic value;
the obtaining of the characteristic value according to the personal information of the service user to be recommended includes:
acquiring a relation characteristic value according to personal information of a service user to be recommended;
acquiring a clustering characteristic value according to personal information of a service user to be recommended;
weighting the relation characteristic value and the clustering characteristic value to obtain a characteristic value;
the obtaining of the relationship characteristic value according to the personal information of the service user to be recommended includes:
extracting trading users trading with the service users to be recommended from the user group;
acquiring transaction information of the service user to be recommended and the transaction user, wherein the transaction information comprises transaction times and transaction amount;
judging whether the transaction times meet the preset times and the transaction amount meets the preset amount or not in the transaction information corresponding to the transaction user;
if yes, extracting the transaction user corresponding to the maximum value of the transaction times and the transaction amount;
determining the grade of the transaction user corresponding to the maximum value;
determining the relation characteristic value of the user of the service to be recommended as a set value according to the grade;
the obtaining of the clustering characteristic value according to the personal information of the service user to be recommended includes:
extracting the users from the user group;
acquiring personal information of the current user;
performing cluster analysis on the personal information of the service user to be recommended and the personal information of the current user;
and obtaining a clustering characteristic value according to a clustering analysis result.
2. The service recommendation method according to claim 1, wherein said determining whether to recommend the service to be recommended user according to the feature value comprises:
judging whether the characteristic value is larger than a preset characteristic value or not;
and if so, recommending the service to be recommended user.
3. A business recommendation system, comprising:
the acquisition module is used for acquiring personal information of each user in the user group;
the condition determining module is used for determining the key conditions of the service according to the service type;
the judging module is used for judging whether the personal information of each user in the user group meets the key condition one by one;
the user determining module is used for determining the users meeting the key conditions as the users of the service to be recommended if the users meet the key conditions;
the obtaining characteristic module is used for obtaining a characteristic value according to the personal information of the service user to be recommended;
the recommending service module is used for judging whether to recommend the service to the service user to be recommended or not according to the characteristic value;
the obtain features module includes:
the relation characteristic value obtaining submodule is used for obtaining a relation characteristic value according to the personal information of the service user to be recommended;
the sub-module for obtaining the clustering characteristic value obtains the clustering characteristic value according to the personal information of the service user to be recommended;
the weighting submodule is used for weighting the relation characteristic value and the clustering characteristic value to obtain a characteristic value;
the relation characteristic value obtaining submodule is used for: extracting trading users trading with the service users to be recommended from the user group; acquiring transaction information of the service user to be recommended and the transaction user, wherein the transaction information comprises transaction times and transaction amount; judging whether the transaction times meet the preset times and the transaction amount meets the preset amount or not in the transaction information corresponding to the transaction user; if yes, extracting the transaction user corresponding to the maximum value of the transaction times and the transaction amount; determining the grade of the transaction user corresponding to the maximum value; determining the relation characteristic value of the user of the service to be recommended as a set value according to the grade;
the cluster characteristic value obtaining submodule is used for: extracting the users from the user group; acquiring personal information of the current user; performing cluster analysis on the personal information of the service user to be recommended and the personal information of the current user; and obtaining a clustering characteristic value according to a clustering analysis result.
4. The service recommendation system according to claim 3, wherein said recommendation service module is configured to: judging whether the characteristic value is larger than a preset characteristic value or not; and if so, recommending the service to be recommended user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711426356.1A CN109961309B (en) | 2017-12-25 | 2017-12-25 | Service recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711426356.1A CN109961309B (en) | 2017-12-25 | 2017-12-25 | Service recommendation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109961309A CN109961309A (en) | 2019-07-02 |
| CN109961309B true CN109961309B (en) | 2021-09-28 |
Family
ID=67021560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711426356.1A Active CN109961309B (en) | 2017-12-25 | 2017-12-25 | Service recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109961309B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598110B (en) * | 2019-09-16 | 2021-09-28 | 腾讯科技（深圳）有限公司 | Service pushing method and device |
| CN111127077A (en) * | 2019-11-29 | 2020-05-08 | 中国建设银行股份有限公司 | Recommendation method and device based on stream computing |
| CN111144990B (en) * | 2019-12-27 | 2022-08-05 | 蚂蚁胜信(上海)信息技术有限公司 | Recommendation method and system |
| CN113538036A (en) * | 2021-06-04 | 2021-10-22 | 深圳市英创艾伦智能科技有限公司 | 5G, AI edge calculation and Internet of things digital management system, method and device |
| CN114169976A (en) * | 2021-12-27 | 2022-03-11 | 中国建设银行股份有限公司 | Financial data recommendation method, device and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577988A (en) * | 2012-07-24 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and device for recognizing specific user |
| CN104239338A (en) * | 2013-06-19 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Information recommendation method and information recommendation device |
| CN104239335A (en) * | 2013-06-19 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Method and device for acquiring information of specific users |
| CN105931066A (en) * | 2015-09-24 | 2016-09-07 | 中国银联股份有限公司 | Transaction data processing method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150081391A1 (en) * | 2013-09-16 | 2015-03-19 | International Business Machines Corporation | Analytics-driven product recommendation for financial services |
-
2017
- 2017-12-25 CN CN201711426356.1A patent/CN109961309B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577988A (en) * | 2012-07-24 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and device for recognizing specific user |
| CN104239338A (en) * | 2013-06-19 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Information recommendation method and information recommendation device |
| CN104239335A (en) * | 2013-06-19 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Method and device for acquiring information of specific users |
| CN105931066A (en) * | 2015-09-24 | 2016-09-07 | 中国银联股份有限公司 | Transaction data processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109961309A (en) | 2019-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961309B (en) | Service recommendation method and system | |
| CN109564669B (en) | Searching entities based on trust scores and geographic scope | |
| WO2020119272A1 (en) | Risk identification model training method and apparatus, and server | |
| CN105677831B (en) | Method and device for determining recommended merchants | |
| CN109583966B (en) | High-value customer identification method, system, equipment and storage medium | |
| US20150363875A1 (en) | System and Method for Filtering and Analyzing Transaction Information | |
| CN112529716B (en) | Method, device and computer readable storage medium for predicting credit | |
| CN112102073A (en) | Credit risk control method and system, electronic device and readable storage medium | |
| CN113742492B (en) | Insurance scheme generation method and device, electronic equipment and storage medium | |
| WO2020048056A1 (en) | Risk decision method and apparatus | |
| Lohokare et al. | Automated data collection for credit score calculation based on financial transactions and social media | |
| CN113722611A (en) | Method, device and equipment for recommending government affair service and computer readable storage medium | |
| CN111639690A (en) | Fraud analysis method, system, medium, and apparatus based on relational graph learning | |
| CN111461859A (en) | Loan pairing system and method | |
| US11966933B2 (en) | System and method for correlating and enhancing data obtained from distributed sources in a network of distributed computer systems | |
| CN110619535A (en) | Data processing method and device | |
| CN111062808A (en) | Credit card limit evaluation method, device, computer equipment and storage medium | |
| CN113988221A (en) | Insurance user classification model establishing method, classification method, device and equipment | |
| CN110197426A (en) | A kind of method for building up of credit scoring model, device and readable storage medium storing program for executing | |
| CN110941644A (en) | Policy data generation method, device, equipment and storage medium | |
| CN107563588A (en) | A kind of acquisition methods of personal credit and acquisition system | |
| CN112950359B (en) | User identification method and device | |
| Asali | Social media analysis for investigating consumer sentiment on mobile banking | |
| CN111245815A (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| Gu et al. | Gif sentiment and stock returns |
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 |