CN107563217A - A kind of recommendation method and apparatus for protecting user privacy information - Google Patents
A kind of recommendation method and apparatus for protecting user privacy information Download PDFInfo
- Publication number
- CN107563217A CN107563217A CN201710707636.3A CN201710707636A CN107563217A CN 107563217 A CN107563217 A CN 107563217A CN 201710707636 A CN201710707636 A CN 201710707636A CN 107563217 A CN107563217 A CN 107563217A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- protection module
- secret protection
- video
- 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
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention discloses a kind of recommendation method for protecting user privacy information, it is characterised in that this method includes：Secret protection module reads user's history behavioral data A from user terminal；The secret protection module is changed the user's history behavioral data A, and by the data after conversionIt is sent to commending system；The secret protection module receives the recommending data B of the commending system output；The secret protection module is modified to the recommending data B, and by revised recommending dataIt is sent to the user terminal.The inventive method realizes the protection to user DI and the reinforcement of interest by setting up secret protection module between user terminal and commending system, can realize the purpose for ensureing or even improving while privacy of user is protected to recommend accuracy.
Description
Technical field
The present invention relates to information security field, more particularly, to a kind of recommendation method for protecting user privacy information and
Device.
Background technology
Extensive the booming of online service website has attracted increasing isdn user, but at the same time, it is individual
Property recommendation service bring privacy of user disclosure risk while turn into the main competitive method in website.In fact, processing user
Historical behavior record mean that user privacy information can be collected, stored and be used for recommend.In extensive online service
In system, in most cases, users to trust commending system, and it is expected that commending system can be carried based on the interest preference of oneself
For high-quality personalized ventilation system.However, user is not intended to commending system, to obtain other people in addition to interest preference hidden
Personal letter ceases, particularly user's demographic information (Demographic Information, DI).Especially in current interconnection
Net epoch, the foundation and application of big data platform, the mutual beneficial co-operation between similar website constantly promote data sharing to exchange.With
Family is worried, once institute's commending system can obtain user DI, then and because the mutual benefit of data is shared, user DI, which will face, to be leaked to
Unknown or even mistrustful third-party risk.At present, substantial amounts of research work is distorted by disturbance of data and fuzzy method
User's history behavior record, to reduce the accuracy that user DI classification is inferred, unfortunately, this data distortion is inevitably
Sacrifice the accuracy of personalized recommendation.Although in extensive online service system, protection privacy of user can cause recommendatory
Loss of energy has become the widespread consensus of research work, but existing research work in user DI safety and recommends accuracy
Between balance way user can not be made very satisfied.
Due to protecting the privacy of user to cause recommendatory loss of energy, so current framework main function is exactly
Weigh user privacy information leak degree and recommend the loss of accuracy.However, the interest preference of user is not by certain a kind of user
DI is uniquely determined, accordingly, it is desirable to provide a kind of recommendation method and apparatus for protecting user privacy information.
The content of the invention
It is an object of the invention to provide a kind of recommendation method and apparatus for protecting user privacy information, the invention can be real
Ensure even to improve the purpose for recommending accuracy while protection user DI now.
To reach above-mentioned purpose, the present invention uses following technical proposals：
A kind of recommendation method for protecting user privacy information, this method include：S101：Secret protection module is read from user terminal
Take family historical behavior data A；S103：The secret protection module is changed the user's history behavioral data A, and will
Data after conversionIt is sent to commending system；S105：The secret protection module receives the privacy through the commending system
Inference module inferred after recommending data B；S107：The secret protection module is modified to the recommending data B, and
By revised recommending dataIt is sent to the user terminal.
Preferably, when the secret protection module carries out data conversion to the user's history behavioral data A, according to described
The characteristic of video in user's history behavioral data A, select the dominant video of opposite characteristic, the characteristic tendency parameter of the video
Can be by being obtained based on training set data, the characteristic of the video is one or more interior in user's demographic information
Hold, including sex, age.
Preferably, the secret protection module regarding using the average score of the video of the opposite characteristic as selected addition
The virtual marking value of frequency.
Preferably, when the secret protection module carries out data conversion to the user's history behavioral data A, selection is given
User's video interested and/or the more popular video of selection are added in the user's history behavioral data A.
Preferably, the video that the commending system is recommended is entered for the secret protection module in any of the above-described scheme
Row amendment, to meeting the transmission of video of user's history behavior to user terminal.
A kind of recommendation apparatus for protecting user privacy information, including user terminal, secret protection module and commending system, wherein
User terminal is operated in the front end of secret protection module, and commending system is operated in the rear end of secret protection module, and the device includes：Read
Take data module：It is configured to the secret protection module and reads user's history behavioral data A from the user terminal；Data conversion mould
Block：The secret protection module is configured to be changed the user's history behavioral data A, and by the data after conversionHair
Give the commending system；Data reception module：It is configured to the secret protection module and receives the privacy through the commending system
Inference module inferred after recommending data B；Data correction module：The secret protection module is configured to the recommendation number
It is modified according to B, and by revised recommending dataIt is sent to the user terminal.
Preferably, when the secret protection module carries out data conversion to the user's history behavioral data A, according to described
The characteristic of video in user's history behavioral data, select the dominant video of opposite characteristic, the characteristic tendency parameter of the video
Can be by being obtained based on training set data, the characteristic of the video is one or more interior in user's demographic information
Hold, including sex, age.
Preferably, the secret protection module regarding using the average score of the video of the opposite characteristic as selected addition
The virtual marking value of frequency.
Preferably, the secret protection module is arranged in the user terminal.
Preferably, it is characterised in that for the secret protection module in any of the above-described scheme by the commending system
The video of recommendation is modified, to meeting the transmission of video of user's history behavior to user terminal.
Beneficial effects of the present invention are as follows：
Technical scheme of the present invention is realized pair by the secret protection module set up between user terminal and commending system
User DI protection and the reinforcement of interest, it can realize and ensure even while protecting privacy of user not inferred by Accurate classification
Improve the quality of recommendation service.
Brief description of the drawings
The embodiment of the present invention is described in further detail below in conjunction with the accompanying drawings.
Fig. 1 shows the structured flowchart of the recommendation method of protection user privacy information of the present invention；
Fig. 2 shows the flow chart of the recommendation method of protection user privacy information of the present invention；
Fig. 3 shows the block diagram of the recommendation apparatus of protection user privacy information of the present invention.
Embodiment
In order to illustrate more clearly of the present invention, the present invention is done further with reference to preferred embodiments and drawings
It is bright.Similar part is indicated with identical reference in accompanying drawing.It will be appreciated by those skilled in the art that institute is specific below
The content of description is illustrative and be not restrictive, and should not be limited the scope of the invention with this.
In a specific embodiment, Fig. 1 shows the knot of the recommendation method of protection user privacy information of the present invention
Structure block diagram, user terminal are arranged on display terminal, and commending system is arranged on server end, and secret protection module is independently arranged, Fig. 2
The flow chart of the recommendation method of protection user privacy information of the present invention, a kind of recommendation side for protecting user privacy information are shown
Method, specific method include：
Step S101：Secret protection module reads user's history behavioral data A from user terminal；It is described in forward direction operation
Secret protection module reads user's history behavioral data from front end user end.Forward direction Operation Definition is secret protection module from user
User's history behavioral data is read at end, and commending system is transferred to after data conversion；Reverse operating is in opposite direction, is defined as privacy guarantor
Protect module and read recommending data from commending system, user terminal is transferred to after data conversion.
Step S103：The secret protection module is changed the user's history behavioral data A, and by after conversion
DataIt is sent to commending system；The interest preference of non-warping user i.e. while fuzzy user DI, by user's history behavior
Part in data on user DI is obscured.
Step S105：The secret protection module is received after the privacy inference module of the commending system is inferred
Recommending data B；I.e. in reverse operating, secret protection module receives the recommending data of commending system.
Step S107：The secret protection module is modified to the recommending data B, and by revised recommending dataThe user terminal is sent to, so far, reverse operating is completed.
In another specific embodiment, so that video website user gender information protects as an example, illustrate this recommendation method,
When secret protection module carries out data conversion to the user's history behavioral data A, according to the user's history behavioral data
The sex characteristic of middle video, the dominant video of opposite sex is selected, the characteristic tendency parameter of the video can be by based on instruction
Practice collection data acquisition, i.e., for a female user, to add the video of male's tendency, vice versa.
In another specific embodiment, by taking video website age of user information protection as an example, when secret protection module
It is special according to the age of video in the user's history behavioral data when carrying out data conversion to the user's history behavioral data A
Property, the dominant video of all ages and classes is selected, the characteristic tendency parameter of the video can be by obtaining, i.e., based on training set data
For an adult human user, the video of old or children tendency is added, vice versa.
In another specific embodiment, the secret protection module is by the average score of the video of the opposite characteristic
As the virtual marking value of the video of selected addition, i.e., in forward direction operation, by the user DI's such as the other class of reflexive or anti-age class
Virtual marking value of the average score as the video of selected addition.
In another specific embodiment, the secret protection module enters line number to the user's history behavioral data A
During according to conversion, select given user video interested and/or the more popular video of selection being added to user's history behavior
Record in A.
In another specific embodiment, the secret protection module is repaiied the video that the commending system is recommended
Just, to meeting the transmission of video of the user's history behavior to user terminal.The addition that will be selected due to original commending system
Virtual marking value recorded as the historical behavior of user, will not repeat recommendations, and the addition video height of these selections accords with
Sharing the interest preference at family needs to recommend user, so these records are added to recommendation by secret protection module in reverse operating
System is delivered to recommended by client to user in exporting.
Fig. 3 shows the block diagram of the recommendation apparatus of protection user privacy information of the present invention, one kind protection privacy of user letter
The recommendation apparatus of breath, including user terminal, secret protection module and commending system, wherein user terminal are operated in secret protection module
Front end, commending system are operated in the rear end of secret protection module, and user terminal is arranged on display terminal, and commending system is arranged on clothes
Business device end, secret protection module are independently arranged, and the device includes：Read data module：Be configured to the secret protection module from
The user terminal reads user's history behavioral data A；Data conversion module：The secret protection module is configured to by the user
Historical behavior data A is changed, and by the data after conversionIt is sent to the commending system；Data reception module：Configuration
The recommending data B after the privacy inference module of the commending system is inferred is received for the secret protection module；Data
Correcting module：The secret protection module is configured to be modified the recommending data B, and by revised recommending data
It is sent to the user terminal.
In another specific embodiment, the device is in the secret protection module to the user's history behavioral data
When A carries out data conversion, according to the characteristic of video in the user's history behavioral data, select opposite characteristic is dominant to regard
Frequently, the characteristic tendency parameter of the video can be by being obtained based on training set data, and the characteristic of the video is united for user's population
Meter learns one or more contents in information, including sex, age.
In another specific embodiment, secret protection module the putting down the video of the opposite characteristic in the device
Virtual marking value of the marking as the video of selected addition.
In another specific embodiment, the secret protection module is arranged in the user terminal.In order to further
User DI is protected, secret protection module can be arranged in the user terminal, avoid user DI leakage.
In another specific embodiment, video that the secret protection module in the device recommends the commending system
It is modified, to meeting the transmission of video of the user's history behavior to user terminal.
Obviously, the above embodiment of the present invention is only intended to clearly illustrate example of the present invention, and is not pair
The restriction of embodiments of the present invention, for those of ordinary skill in the field, may be used also on the basis of the above description
To make other changes in different forms, all embodiments can not be exhaustive here, it is every to belong to this hair
Row of the obvious changes or variations that bright technical scheme is extended out still in protection scope of the present invention.
Claims (10)
- A kind of 1. recommendation method for protecting user privacy information, it is characterised in that this method includes：S101：Secret protection module reads user's history behavioral data A from user terminal；S103：The secret protection module is changed the user's history behavioral data A, and by the data after conversionHair Give commending system；S105：The secret protection module receives the recommending data after the privacy inference module of the commending system is inferred B；S107：The secret protection module is modified to the recommending data B, and by revised recommending dataIt is sent to The user terminal.
- 2. recommendation method according to claim 1, it is characterised in that the secret protection module is to the user's history row When carrying out data conversion for data A, according to the characteristic of video in the user's history behavioral data A, opposite characteristic is selected to be dominant The video of gesture, the characteristic tendency parameter of the video can be by being obtained based on training set data, and the characteristic of the video is user One or more contents in demographic information, including sex, age.
- 3. recommendation method according to claim 2, it is characterised in that the secret protection module is by the opposite characteristic Virtual marking value of the average score of video as the video of selected addition.
- 4. recommendation method according to claim 1, it is characterised in that the secret protection module is to the user's history row When carrying out data conversion for data A, given user video interested and/or the more popular video of selection is selected to be added to institute State in user's history behavioral data A.
- 5. method is recommended according to any one described in Claims 1-4, it is characterised in that the secret protection module is by institute The video for stating commending system recommendation is modified, to meeting the transmission of video of user's history behavior to user terminal.
- 6. a kind of recommendation apparatus for protecting user privacy information, it is characterised in that including user terminal, secret protection module and recommendation System, wherein user terminal are operated in the front end of secret protection module, and commending system is operated in the rear end of secret protection module, the dress Put including：Read data module：It is configured to the secret protection module and reads user's history behavioral data A from the user terminal；Data conversion module：It is configured to the secret protection module to be changed the user's history behavioral data A, and will turns Data after changingIt is sent to the commending system；Data reception module：The privacy inference module of the secret protection module reception through the commending system is configured to be pushed away The recommending data B having no progeny；Data correction module：It is configured to the secret protection module to be modified the recommending data B, and is pushed away revised Recommend dataIt is sent to the user terminal.
- 7. recommendation apparatus according to claim 6, it is characterised in that the secret protection module is to the user's history row When carrying out data conversion for data A, according to the characteristic of video in the user's history behavioral data, select opposite characteristic dominant Video, the video characteristic tendency parameter can be by being obtained based on training set data, the characteristic of the video is user people One or more contents in mouth demographic information, including sex, age.
- 8. recommendation apparatus according to claim 7, it is characterised in that the secret protection module is by the opposite characteristic Virtual marking value of the average score of video as the video of selected addition.
- 9. recommendation apparatus according to claim 6, it is characterised in that the secret protection module is arranged on the user terminal In.
- 10. according to any one recommendation apparatus described in claim 6 to 9, it is characterised in that the secret protection module is by institute The video for stating commending system recommendation is modified, to meeting the transmission of video of user's history behavior to user terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710707636.3A CN107563217A (en) | 2017-08-17 | 2017-08-17 | A kind of recommendation method and apparatus for protecting user privacy information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710707636.3A CN107563217A (en) | 2017-08-17 | 2017-08-17 | A kind of recommendation method and apparatus for protecting user privacy information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107563217A true CN107563217A (en) | 2018-01-09 |
Family
ID=60975825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710707636.3A Pending CN107563217A (en) | 2017-08-17 | 2017-08-17 | A kind of recommendation method and apparatus for protecting user privacy information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107563217A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108628955A (en) * | 2018-04-10 | 2018-10-09 | 中国科学院计算技术研究所 | The personalized method for secret protection and system of commending system |
| CN109766955A (en) * | 2019-02-12 | 2019-05-17 | 深圳乐信软件技术有限公司 | Gender identification method, device, equipment and storage medium |
| CN112200132A (en) * | 2020-10-28 | 2021-01-08 | 支付宝(杭州)信息技术有限公司 | Data processing method, device and equipment based on privacy protection |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105138664A (en) * | 2015-09-02 | 2015-12-09 | 中国地质大学（武汉） | Big data recommendation method and system with privacy protection function |
| CN106134142A (en) * | 2013-02-08 | 2016-11-16 | 汤姆逊许可公司 | Resist the privacy of the inference attack of big data |
-
2017
- 2017-08-17 CN CN201710707636.3A patent/CN107563217A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106134142A (en) * | 2013-02-08 | 2016-11-16 | 汤姆逊许可公司 | Resist the privacy of the inference attack of big data |
| CN105138664A (en) * | 2015-09-02 | 2015-12-09 | 中国地质大学（武汉） | Big data recommendation method and system with privacy protection function |
Non-Patent Citations (1)
| Title |
|---|
| TINGTING FENG等: "Can User Gender and Recommendation Performance be Preserved Simultaneously?", 《2015 INTERNATIONAL CONFERENCE ON COMPUTING, NETWORKING AND COMMUNICATIONS (ICNC)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108628955A (en) * | 2018-04-10 | 2018-10-09 | 中国科学院计算技术研究所 | The personalized method for secret protection and system of commending system |
| CN109766955A (en) * | 2019-02-12 | 2019-05-17 | 深圳乐信软件技术有限公司 | Gender identification method, device, equipment and storage medium |
| CN112200132A (en) * | 2020-10-28 | 2021-01-08 | 支付宝(杭州)信息技术有限公司 | Data processing method, device and equipment based on privacy protection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ha et al. | Sport fans in a “smart sport”(SS) age: Drivers of smartphone use for sport consumption | |
| CN109495770B (en) | Live broadcast room recommendation method, device, equipment and medium | |
| CN107341679A (en) | Obtain the method and device of user's portrait | |
| CN107563217A (en) | A kind of recommendation method and apparatus for protecting user privacy information | |
| US8392431B1 (en) | System, method, and computer program for determining a level of importance of an entity | |
| US20140089067A1 (en) | User rewards from advertisers for content provided by users of a social networking service | |
| CN107016569A (en) | The targeted customer's account acquisition methods and device of a kind of networking products | |
| US8930392B1 (en) | Simulated annealing in recommendation systems | |
| KR101886738B1 (en) | Apparatus and user device for providing feedback effect to postings in social network services | |
| CN103678329A (en) | Recommendation method and device | |
| US10956611B2 (en) | Methods, systems, and media for data anonymization | |
| US9870579B2 (en) | Managing shareable content in a social network | |
| CN108241619A (en) | A kind of recommendation method based on the more interest of user | |
| CN103996143A (en) | Movie marking prediction method based on implicit bias and interest of friends | |
| CN103530428A (en) | Same-occupation type recommendation method based on developer practical skill similarity | |
| CN107103028A (en) | A kind of information processing method and device | |
| CN109241437A (en) | A kind of generation method, advertisement recognition method and the system of advertisement identification model | |
| CN110046736B (en) | Rights and interests recommending method, device and equipment | |
| US20120123899A1 (en) | Social network shopping system and method | |
| CN109033224A (en) | A kind of Risk Text recognition methods and device | |
| CN107547626A (en) | The sharing method and device of user's portrait | |
| US20170039627A1 (en) | Cigar Band Recognition Interface | |
| CN106254208B (en) | Social functions information sorting method and terminal | |
| CN107888793A (en) | Package recommendation method, apparatus and system | |
| Hafid et al. | The influence of brand equity toward Indonesian prepaid SIM card customers’ purchase decision |
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: 20180109 |