CN111768226A - Package recommendation method and system based on knowledge recommendation algorithm - Google Patents
Package recommendation method and system based on knowledge recommendation algorithm Download PDFInfo
- Publication number
- CN111768226A CN111768226A CN202010566260.0A CN202010566260A CN111768226A CN 111768226 A CN111768226 A CN 111768226A CN 202010566260 A CN202010566260 A CN 202010566260A CN 111768226 A CN111768226 A CN 111768226A
- Authority
- CN
- China
- Prior art keywords
- package
- user
- recommendation
- knowledge
- interactive
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000002452 interceptive effect Effects 0.000 claims abstract description 35
- 238000004891 communication Methods 0.000 claims description 19
- 238000007405 data analysis Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
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
- G06Q30/0241—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9532—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G06Q50/60—
Abstract
The invention discloses a package recommendation method based on a knowledge recommendation algorithm, which realizes package recommendation to a user through the following steps: s01, setting labels on the corresponding package names according to the set characteristic values; s02, setting interactive user questions according to the set labels and package classification conditions; s03, inputting initial preference by the user through interactive user question according to the user's own requirement; s04, providing corresponding and matching packages according to the initial preferences entered by the user; s05, the user modifies the preference according to the self requirement and feeds back through the interactive user question; s06, inputting the modified preferences fed back by the user to the knowledge-based recommendation system; s07, the recommender system presents the final matching recommended package based on the entered preferences. The invention also discloses a system based on the method. The invention has the advantages that: the method can adapt to various recommendation scenes, has high package recommendation accuracy, effectively solves the problem of package cold start, and realizes accurate intelligent package recommendation.
Description
Technical Field
The invention relates to the technical field of telecommunication service information, in particular to a package recommendation method and system based on a knowledge recommendation algorithm.
Background
With the development of communication technology and the popularization of the speed-increasing and cost-reducing policy, the demand of self-service handling of mobile communication service packages by users is greatly increased, the users can handle the package services independently through the mobile client APP, and the time of waiting in line for handling the services in a business hall is saved. Because the mobile communication service packages of the existing operators are various in number, strong in professional terms and frequent in replacement, users are difficult to select the packages most suitable for themselves. In addition, because the packages provided by the operators are various, the content-based recommendation mode needs the users to answer a great number of questions, so that the use experience of the users is greatly influenced, and a method capable of obtaining the packages which best meet the user standards from a large number of packages is lacked in the prior art.
Disclosure of Invention
The invention provides a package recommendation method and system based on a knowledge recommendation algorithm, aiming at the problem that packages meeting user standards cannot be obtained from a large number of packages in the prior art.
The invention discloses a package recommendation method based on a knowledge recommendation algorithm, which realizes package recommendation to a user through the following steps:
s01, setting labels on the corresponding package names according to the set characteristic values;
s02, setting interactive user questions according to the set labels and package classification conditions;
s03, inputting initial preference by the user through interactive user question according to the user's own requirement;
s04, providing corresponding and matching packages according to the initial preferences entered by the user;
s05, the user modifies the preference according to the self requirement and feeds back through the interactive user question;
s06, inputting the modified preferences fed back by the user to the knowledge-based recommendation system;
s07, the recommender system presents the final matching recommended package based on the entered preferences.
Further, in the step s07, if there is no recommendable result, a specified package is recommended to the user, where the specified package is a mainstream package.
Furthermore, the knowledge recommendation system based on big data analysis is based on the corresponding relation between the label set on the package name and the package.
Further, the labels in step s01 include directional traffic, national traffic, traffic value, city telephone, long distance, minutes, age, tariff price, campus package, business package, 4G package, and 5G package.
Further, the user questions in the step s02 include network type, package price, traffic range, number of voice minutes and number of short message.
Another object of the present invention is to provide a package recommendation system based on knowledge recommendation algorithm, which includes a server and a client, the server and the client communicate with each other, the server user recommends packages for users according to the user preferences fed back by the client according to the method of claim 1, and the client is used for providing interactive questions for users, modifying preferences and displaying packages recommended by the server.
Further, the server includes a knowledge-based recommendation system for recommending packages according to received user preferences, a memory for storing the method program, the server operating program, and package information as claimed in claim 1, a processor for executing the method program and the operating program stored in the memory, a processor for performing data communication with the user terminal, and a package matching system for obtaining matched packages according to interactive feedback of the user.
Furthermore, the user side comprises an interactive problem module, a preference setting module and a communication module, the interactive problem module is used for displaying and providing interactive user problems for the user and recording and transmitting the user problems to the server side, the preference setting module is used for providing a user-defined preference setting interface for the user and recording and transmitting the user problems to the server side, and the communication module is used for data communication between the user side and the server side.
Compared with the prior art, the invention has the beneficial effects that:
the method and the system have the advantages that the mobile packages are subjected to label classification, so that the method and the system are suitable for various recommendation scenes, the package recommendation accuracy is improved through interaction with a user and big data analysis, and the problem of package cold start is effectively solved; the recommendation technology based on the user big data analysis realizes intelligent recommendation of package through user historical data analysis and user question and answer.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
The invention is described in further detail below with reference to the attached drawing figures:
example 1
Referring to a flow chart of a method in fig. 1, the present embodiment discloses a package recommendation method based on a knowledge recommendation algorithm, which implements package recommendation for a user by the following steps:
s01, according to the set eigenvalue, setting label on the corresponding package name, feasible, this step is operated at the server, the operator sets label on the package in the server, thereby improving the accuracy of recommending package, in this specific embodiment, detailed package label can be performed, the package label is such as directional flow, national flow, flow value, city telephone, long distance, minute number, age, price of charge, campus package, business package, 4G package, 5G package, etc. Specifically, the package name may be labeled in the form of a database mapping relationship on the package corresponding to the corresponding pair, or the label name may be set as a feature value to the package name. For example, if a certain package is a 4G national flow unlimited package and a city phone 300 minutes, and each member of a large video website is given, the corresponding set of labels includes a national flow unlimited package, a city phone, and a 4G package with an age period of 16-30.
s02, setting interactive user problems according to the set labels and package classification conditions, setting the interactive problems at the server side, setting the interactive functions at the user side, presetting the user side equipment through APP updating modes, completing the interaction of the user through filling the interactive problems at the terminal of the user, receiving the interactive problem results of the user by the server, and matching the package according to the interactive problems. The user questions in this step include network type, package price, flow range, number of voice minutes, and number of short message lines. For example, whether the network system of the question is 5G, 4G or other network systems can be set, for example, the price of the package currently used, the flow range used per month is below 1G, 1-2G, 2-5G, 5-10G, above 10G, etc., the voice minutes are within 50 minutes, 50-100 minutes, 100 and 200 minutes, 200 and 300 minutes, 300 and 500 minutes, and the operation of the user can be effectively reduced by adopting the interactive question of the option type, so that the preference data of the user can be more easily acquired.
s03, the user inputs the initial preference through the interactive user question according to his own requirement, the user can click and select according to the question check or radio box provided by the user terminal, and other preference selection methods and other preference setting options can be adopted in other embodiments of the present invention.
s04, providing corresponding and matched packages according to the initial preference input by the user, answering the preference input by the user at the terminal, the operator server automatically matching packages with higher label correlation according to the preference to form a data packet and sending the data packet to the terminal of the user for display for the user to select.
s05, the user modifies the preference according to the self requirement and feeds back through the interactive user problem, the interactive problem is different from the preference input by the previous user, in the step, the user can modify the previously set preference and set the preference aiming at the recommended package, for example, the pushed package can be chosen to be interested or not interested, the recommended package can be scored, the scoring standard can be formulated to the option of the language habit of the user, for example, the package accords with the requirement degree of your, the option for selection can be very accordant, generally accordant, non-accordant, completely unnecessary and the like, and the specific setting can also be according to more accordant results obtained after analyzing the big data of the user. According to the initial preference of the user for the topic, the user can answer all the questions at one time or answer the questions step by step.
s06, inputting the modified preference fed back by the user into a knowledge-based recommendation system, wherein the knowledge-based recommendation system can be obtained by sorting the big data analysis results of the feedback data of the recommended package system in the APP according to a large number of users, the recommendation method can be to match the label characteristics of the preference information fed back by the user, evaluate the user by combining the big data, and recommend the package according to the evaluation result, and in other specific embodiments of the invention, a recommendation system obtaining professional knowledge according to other modes can also be adopted. The operator can appoint special personnel to research corresponding professional knowledge according to own requirements, and the obtained rules and the evaluation method are used as the recommendation rules of the recommendation system. In a specific implementation process, an operator can input the corresponding relation between the label of the package and the name of the corresponding package and can simultaneously input the corresponding relation between the conventional cognition of the user and the package as knowledge according to the recommendation system.
s07, the recommendation system gives the final matching recommended package according to the input preferences, and the operator server recommends the package to the user according to the user preferences and based on the expertise in the system according to the rules of the knowledge-based recommendation system. If possible, in step s07, if there is no recommendable result, a specified package is recommended to the user, and the specified package is the mainstream package.
The method and the system have the advantages that the mobile packages are subjected to label classification, so that the method and the system are suitable for various recommendation scenes, the package recommendation accuracy is improved through interaction with a user and big data analysis, and the problem of package cold start is effectively solved; the recommendation technology based on the user big data analysis realizes intelligent recommendation of package through user historical data analysis and user question and answer.
Example 2
The specific embodiment discloses a package recommendation system based on a knowledge recommendation algorithm, which comprises a server and a user, wherein the server and the user are communicated with each other, the server user recommends packages for users according to user preferences fed back by the user according to the method in the embodiment 1, and the user is used for providing interactive questions for the users, modifying the preferences and displaying the packages recommended by the server. The user terminal may be an APP installed on the mobile terminal, such as a palm business hall installed on a mobile phone of the user, and may also be a service page, such as a web page terminal, in other embodiments of the present invention.
The server includes a knowledge-based recommendation system, a memory, a processor, a communication server, and a package matching system, where the knowledge-based recommendation system is configured to recommend a package according to a received user preference, the memory is configured to store a method program, an operation program of the server, and package information as in embodiment 1, the processor is configured to execute the method program and the operation program stored in the memory, the communication server is configured to perform data communication with the user side, and the package matching system is configured to obtain a matching package according to an interactive feedback of the user. The server terminal may be a server of an operator, and the setting of other system parts may be performed by using a conventional technique in the art, which is the same as the method of other recommendation methods, and in addition, other necessary support components of the server and the user terminal should be known by those skilled in the art and may be performed by using a common setting in the prior art, which is not described in detail in the present invention, such as a power supply and a display device.
In addition, the user side comprises an interactive problem module, a preference setting module and a communication module, the interactive problem module is used for displaying and providing interactive user problems for the user and recording and transmitting the user problems to the server side, the preference setting module is used for providing a user-defined preference setting interface for the user and recording and transmitting the user problems to the server side, and the communication module is used for data communication between the user side and the server side. The modules may be modules arranged in, for example, a user side APP. The communication is performed through a terminal used by a user, for example, the communication is performed through a 4G network, a 5G network or a WIFI connection internet.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A package recommendation method based on a knowledge recommendation algorithm is characterized by comprising the following steps of:
s01, setting labels on the corresponding package names according to the set characteristic values;
s02, setting interactive user questions according to the set labels and package classification conditions;
s03, inputting initial preference by the user through interactive user question according to the user's own requirement;
s04, providing corresponding and matching packages according to the initial preferences entered by the user;
s05, the user modifies the preference according to the self requirement and feeds back through the interactive user question;
s06, inputting the modified preferences fed back by the user to the knowledge-based recommendation system;
s07, the recommender system presents the final matching recommended package based on the entered preferences.
2. The package recommendation method based on knowledge recommendation algorithm of claim 1, wherein said step s07 is to recommend the specified package to the user if there is no recommendable result, said specified package is the mainstream package.
3. The package recommendation method based on the knowledge recommendation algorithm according to claim 1, wherein the knowledge recommendation system based on big data analysis is based on a correspondence between a label set on a package name and a package.
4. The package recommending method based on the knowledge recommendation algorithm of claim 1, wherein the labels of step s01 include directional traffic, national traffic, traffic value, city telephone, long distance, minutes, age, tariff price, campus package, business package, 4G package and 5G package.
5. The package recommendation method based on knowledge recommendation algorithm of claim 1, wherein said user questions of step s02 include network format, package price, traffic range, number of voice minutes and number of short message.
6. A package recommendation system based on a knowledge recommendation algorithm, comprising a server and a client, wherein the server and the client are in communication with each other, the server user recommends packages for a user according to the user preference fed back by the client according to the method of claim 1, and the client is configured to provide interactive questions to the user, modify the preference, and display the packages recommended by the server.
7. The package recommendation system based on knowledge recommendation algorithm according to claim 6, wherein the server comprises a knowledge-based recommendation system for recommending packages according to received user preferences, a memory for storing the method program, the server running program and the package information as in claim 1, a processor for executing the method program and the running program stored in the memory, a communication server for performing data communication with the client, and a package matching system for obtaining a matching package according to the interactive feedback of the user.
8. The package recommendation system based on the knowledge recommendation algorithm of claim 6, wherein the user side comprises an interactive question module, a preference setting module and a communication module, the interactive question module is used for presenting interactive user questions for the user and recording and transmitting the interactive user questions to the server side, the preference setting module is used for providing a customized preference setting interface for the user and recording and transmitting the user questions to the server side, and the communication module is used for data communication between the user side and the server side.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010566260.0A CN111768226A (en) | 2020-06-19 | 2020-06-19 | Package recommendation method and system based on knowledge recommendation algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010566260.0A CN111768226A (en) | 2020-06-19 | 2020-06-19 | Package recommendation method and system based on knowledge recommendation algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111768226A true CN111768226A (en) | 2020-10-13 |
Family
ID=72721350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010566260.0A Pending CN111768226A (en) | 2020-06-19 | 2020-06-19 | Package recommendation method and system based on knowledge recommendation algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111768226A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030046170A1 (en) * | 2001-08-28 | 2003-03-06 | Lutnick Howard W. | Systems and methods for providing interactive assistance on purchase decision-making |
| CN102760128A (en) * | 2011-04-26 | 2012-10-31 | 华东师范大学 | Telecommunication field package recommending method based on intelligent customer service robot interaction |
| CN109522556A (en) * | 2018-11-16 | 2019-03-26 | 北京九狐时代智能科技有限公司 | A kind of intension recognizing method and device |
-
2020
- 2020-06-19 CN CN202010566260.0A patent/CN111768226A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030046170A1 (en) * | 2001-08-28 | 2003-03-06 | Lutnick Howard W. | Systems and methods for providing interactive assistance on purchase decision-making |
| CN102760128A (en) * | 2011-04-26 | 2012-10-31 | 华东师范大学 | Telecommunication field package recommending method based on intelligent customer service robot interaction |
| CN109522556A (en) * | 2018-11-16 | 2019-03-26 | 北京九狐时代智能科技有限公司 | A kind of intension recognizing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805694B (en) | Credit consultation service method, apparatus, device and computer readable storage medium | |
| KR101812222B1 (en) | Counseling system and method through robo advisor | |
| US20220129908A1 (en) | Method, apparatus and system of processing information | |
| US20070294725A1 (en) | Message-to-wap link for content and advertising | |
| KR20010072568A (en) | Assistance method and apparatus | |
| CN110807085A (en) | Fault information query method and device, storage medium and electronic device | |
| CA3124349A1 (en) | System and method of real-time wiki knowledge resources | |
| US20080201199A1 (en) | System and method for behaviorial psychology and personality profiling to adapt customer service communications | |
| US8392392B1 (en) | Voice request broker | |
| CN108140055A (en) | Trigger application message | |
| CN108629011A (en) | Method and apparatus for sending feedback information | |
| KR101307578B1 (en) | System for supplying a representative phone number information with a search function | |
| KR100904691B1 (en) | Apparatus and method for providing question and answer services | |
| CN106407480A (en) | Information search method and system | |
| CN111768226A (en) | Package recommendation method and system based on knowledge recommendation algorithm | |
| WO2002008854A2 (en) | Method and apparatus for providing context sensitive advertisements to mobile users | |
| KR20170142964A (en) | Counseling system and method through robo advisor | |
| KR20160104462A (en) | Device and System for providing phone number service by providing advertisements using emotion analysis of customer and method thereof | |
| CN112527991A (en) | Information processing method, apparatus and medium | |
| KR100813237B1 (en) | System and method for managing of contents information, and mobile communication terminal using the same | |
| CN112260933A (en) | Communication method, communication device, electronic equipment and medium | |
| CN110929144A (en) | Business data management method, system and readable storage medium | |
| KR20000050047A (en) | Method for servicing calling-card information over the internet | |
| CN109377152A (en) | A kind of method and device of scheduling application | |
| KR20040040115A (en) | Network-based question and answer service method and its system capable of load balancing |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201013 |