TW201626805A - Method and system for privacy-preserving recommendations - Google Patents

Abstract

Various examples of systems and methods for providing recommendations that can be tailored to a user while preserving the privacy of the users personal information are disclosed. In various embodiments, user information can be encrypted such that the recommendation service cannot decrypt the user information, yet the recommendation service can analyze the user information to predict user ratings for content items. The predicted user ratings can remain obscured from the recommendation service by encryption, yet can provide the basis for recommendations tailored to the user. In particular, encrypted comparison information of predicted user ratings can be sent to the user, and the user can decrypt the comparison and send result information to the recommender to determine recommendations.

Description

Method and system for privacy protection advice [Cross Reference]

The present application claims priority to U.S. Provisional Application Serial No. 62/051,135, filed on Sep.

The present invention is generally directed to a suggestion system and, more particularly, the present invention relates to privacy protection recommendations.

Home entertainment systems, which include television and media centers, interface with the Internet and provide access to a large number of available content sources, such as video, movies, television shows, music, and the like. This expansion of the number of available sources requires a new strategy to navigate one of the media interfaces associated with such systems and to enable access to specific portions of media content consumed by the user.

In terms of this expansion, there is a tendency to provide personalized content to a user who has set up a profile containing personal information. This personal information can describe the user and his or her interests. In addition, this personal information may also provide information about the content sources available to that particular user. Such content sources may be one of a source of content (eg, in a media repository on a regional network) and a third party source of content (eg, a fee-based service or a pay-per-view system).

The present invention discloses that a suggestor provides advice to a user and makes specific user information And various examples of systems and methods for recommending information confidentiality. In various embodiments, the user information can be encrypted, for example, using the user's public encryption key, such that the suggestor cannot decrypt the user information, but can operate the encrypted user information to produce a usable Determine the user's encrypted comparison information for the user's suggestion. In this way, for example, the user information can be kept secret, because the user information can be kept encrypted by the user when the recommender uses the user information to determine the suggestion.

In this regard, the user encrypted comparison information can be provided to the user for decryption, and the user can provide the decrypted result to the recommender for use in determining the suggestion. The comparison information can include a comparison of the suggested indicators. For example, the comparison can be a difference between two suggested indicators, such as a predictive rating of two content items. In this way, the specific recommender information can be concealed for the user because, for example, although the user can obtain one of the differences between the two predicted ratings, the user cannot obtain the same. Predict the value of the rating itself.

100‧‧‧ system

102‧‧‧Content source

104‧‧‧Broadcasting Union Manager

106‧‧‧Transport network

107‧‧‧User System

108‧‧‧ Receiving device

110‧‧‧Content Manager

112‧‧‧Communication network

113‧‧‧Internet

114‧‧‧Display device

116‧‧‧ Input device

117‧‧‧Recommended system

118‧‧‧Recommended engine

120‧‧‧Database

200‧‧‧Receiver/recommended system/user system

202‧‧‧Input signal receiver

204‧‧‧Input Stream Processor

206‧‧‧Optical processor

208‧‧‧ audio interface

210‧‧‧Video Processor

212‧‧‧Storage devices/non-transitory computer readable media

214‧‧‧Controller/Processor

216‧‧‧User interface

218‧‧‧Display interface

220‧‧‧Control memory

300‧‧‧Input device/touch panel device/touch panel/touch screen device

400‧‧‧ Input device

402‧‧‧12 button alphanumeric keypad

404‧‧‧Navigating section

406‧‧‧ function button

408‧‧‧Programmable dedicated button

410‧‧‧display screen

500‧‧‧Privacy Protection Recommendation System

501‧‧‧User System

504‧‧‧Recommended system

511‧‧‧Communication

514‧‧‧Communication

517‧‧‧Communication

521‧‧‧Communication

601‧‧‧Get user information

602‧‧‧Encrypting user information using encryption

603‧‧‧Providing user encrypted user information to the recommender

701‧‧‧Decision to provide advice

702‧‧‧Determining the comparison information of the first user encryption based on the user information encrypted by the user

703‧‧‧Providing user-encrypted comparison information to users

704‧‧‧Get results information from users

705‧‧‧Comparative information based on the result information to determine the second user's encryption

706‧‧‧ Providing the second user encrypted comparison information to the user

707‧‧‧Continue to receive the result information, determine the comparison information encrypted by the second user, and provide the second user encrypted comparison information to the user

708‧‧‧Determining the proposed content item

709‧‧‧Provides recommendations to users

801‧‧‧Compare information from the recommender to obtain user encryption

802‧‧‧ Decrypt the user's encrypted comparison information to determine the result information

803‧‧‧Providing results information to the proponent

901‧‧‧Get a rating on the content project

902‧‧‧Encryption for encryption using encryption

903‧‧‧Send rating information to the proponent

1001‧‧‧Get rating information

1002‧‧‧Search user encryption rating based on corresponding content item ID

1003‧‧‧Storage user encryption rating based on search

1101‧‧‧Users

1104‧‧‧Recommended engine

1107‧‧‧Recommended Information Library

1111‧‧‧Communication

1114‧‧‧Information structure

1201‧‧‧ User profile encrypted by user i

1202‧‧‧Initial content item index j

1203‧‧‧Determine whether there is a user-encrypted rating for the j-th content item or whether the content item j has been identified as a k-content item

1204‧‧‧Increase j

1205‧‧‧Get the user-encrypted modified profile vector for content item j

1206‧‧‧ make versus Multiply

1207‧‧‧Encrypt the predictive rating of the user's encryption using the proponent's private key

1208‧‧‧Determining whether the user's encrypted prediction rating is the first one after the initialization j

1209‧‧‧Comparative information for determining the first user encryption

1210‧‧‧Compare information for user encryption And the user encryption prediction rating corresponding to the suggester encryption And sent to the user

1211‧‧‧Receive result information from users

1212‧‧‧Determining whether the content item j is the final content item

1213‧‧‧Determining the content item corresponding to the last received result information

1214‧‧‧Send information about content items to users

1215‧‧‧Determining whether the k-good item is the last to be determined

1216‧‧‧End of the program

1 is a block diagram of one example of a system for transmitting video content in accordance with various embodiments.

2 is a block diagram of one example of an arithmetic system, such as a video converter/digital video recorder (DVR), gateway, etc., in accordance with various embodiments.

3 illustrates an example of a touch panel input device in accordance with various embodiments.

4 illustrates another example of an input device in accordance with various embodiments.

5 is a block diagram of one example of a privacy protection suggestion system in accordance with various embodiments.

6 illustrates an example of one of the methods that can be performed by a user system in accordance with various embodiments.

7 illustrates an example of one of the methods that can be performed by a suggested system in accordance with various embodiments.

8 illustrates an example of one of the methods that can be performed by a user system in accordance with various embodiments.

9 illustrates another example of a method that can be performed by a user system in accordance with various embodiments.

10 illustrates an example of one of the methods that can be performed by a suggested system in accordance with various embodiments.

11 is a diagram showing an example of one of the embodiments of the method of FIG. 10 in accordance with various embodiments.

12 illustrates an example of one method of determining a suggestion using a user-encrypted user profile in accordance with various embodiments.

The drawings are intended to illustrate the concepts of the present invention and are not necessarily the only possible configuration for the present invention.

Consumers of content (such as movies, television (TV), music, etc.) may have difficulty finding content that they may appreciate. Consumers can face browsing (for example) a large library of content and become overwhelmed and frustrated. Consumers may wish to obtain suggestions for content items (also referred to herein as "items") (eg, movies, television shows, songs, etc.) from a suggestor (such as a suggestion system, a suggestion service, etc.).

The proponent may formulate a proposal by analyzing the user information to determine the indicator (also referred to herein as a "recommendation indicator"), such as measurement of user preferences (eg, likes, dislikes, predictions, etc.). The indicator items can be used to determine recommendations that are appropriate for the user. For example, a proponent requires the user to provide rating information (such as a user's personal rating of various content items), and may analyze the user rating to predict the rating that the user will give to other content items. These predictive ratings can be used to advise users. For example, the proposer may determine a user's prediction rating for a plurality of content items (eg, all content items in the recommender's catalog), and classify the predictive ratings to determine the highest predictive rating. The content item and provide user information related to the content item with the highest forecast rating. For example, a suggestor may determine a k-content content item, where k is the number of ones selected by the recommender (eg, five best content items with five highest-predicted ratings), and the name of the k-good content item is provided for use. (as a suggestion).

The predictive rating is only one example of an indicator that can be used to determine a suggestion, and those skilled in the art will readily appreciate that there are many such suggested indicators that can be determined by analyzing user information. In fact, a large amount of resources in the industry and academia are devoted to analyzing user information (such as biographical information (such as age, gender, ethnicity, etc.), economic information (such as income levels, etc.), preference information (for example, use). What content items are consumed and how users evaluate content items, etc.) and predict what users will like. However, while many users expect accurate, personalized advice, some users do not want a proponent to know the user information that forms the basis of these recommendations. In other words, some users want to keep their user information confidential.

Similarly, a proponent may wish to keep certain information confidential. For example, if a proponent obtains a benefit each time a user requests a suggestion, the suggestor wants the user to periodically request a suggestion, ie, to return the business. Therefore, the recommender will limit the number of suggestions per request to a predetermined number k, so that when the k suggestions are completed, if the user wants more suggestions, another request is required. For example, each suggestion can only identify k content items that have the highest indication of user preferences, ie, k-good content items. In addition to limiting the number of suggestions, the proponent may wish to prevent the user from obtaining specific information that the recommender uses to determine the suggestion. Otherwise, the user can generate the suggestion himself and not have to pay the recommender for more suggestions.

The following disclosure includes various examples of a suggestor providing advice to a user and keeping certain user information and advisor information confidential. In various embodiments, the user information can be encrypted, for example, using the user's public encryption key, such that the suggestor cannot decrypt the user information, but can operate the encrypted user information to produce a usable decision User-encrypted comparison information for the user's suggestion. In this way, for example, the make The user information is kept confidential because the user information can be kept encrypted by the user when the recommender uses the user information to determine the suggestion.

In this regard, the user-encrypted comparison information can be provided to the user for decryption, and the user can provide the decrypted result to the recommender for use in determining the suggestion. The comparison information can include a comparison of suggested indicators. For example, the comparison can be a difference between two suggested indicators, such as a predictive rating of two content items. In this way, specific recommender information can be concealed to the user because, for example, although the user can obtain one of the differences between the two predicted ratings, the user cannot obtain the value of the predictive rating itself. Again, as explained in more detail below, additional steps can be taken to further conceal the information while still allowing for decision making.

1 is a block diagram showing one example of a system 100 for transmitting content and suggestions to a home or terminal user. The content is derived from a content source 102, such as a movie studio or production company. The content can be served in at least one of two forms. One form can be a broadcast form of one of the content. The broadcast content is provided to a broadcast affiliate manager 104, which is typically a national broadcast service such as the American Broadcasting Corporation (ABC), the National Broadcasting Corporation (NBC), the Columbia Broadcasting Corporation (CBS), and the like. The broadcast affiliate manager can collect and store content and can plan to deliver content over a transport network (which is shown as transport network 106). Transport network 106 may include satellite link transmissions from a national center to one or more regional or regional centers. Transport network 106 may also include regional content delivery using a zone delivery system, such as by wireless broadcast, satellite broadcast, or cable television broadcast. The zone delivery content is provided to one of the user's home user systems 107.

User system 107 can include a receiving device 108 that can receive and process content and perform other functions as described in greater detail below. It should be appreciated that the receiving device 108 can be, for example, a video converter, a digital video recorder (DVR), a gateway, a data modem, and the like. The receiving device 108 can act as an entry point or gateway to a home network system that includes additional devices configured as client or peer devices in the home network.

User system 107 can also include a display device 114. In some embodiments, display device 114 can be an external display coupled to one of receiving devices 108. In some embodiments, receiving device 108 and display device 114 can be part of a single device. Display device 114 can be, for example, a conventional 2-D display, an advanced 3D display, and the like. The user system 107 can also include an input device 116, such as a remote controller, a keyboard, a mouse, a touch panel, a touch screen, and the like. Input device 116 can be adapted to provide user control of receiving device 108 and/or display device 114. In some embodiments, input device 116 can be an external device that can be coupled to receiving device 108 via, for example, a wired connection, a signal transmission system such as infrared (IR), radio frequency (RF) communication, or the like. And may include standard protocols (such as Universal Serial Bus (USB), Infrared Data Association (IRDA) standards, Wi-Fi, Bluetooth, and the like), proprietary agreements, and the like. In some embodiments, receiving device 108 and input device 116 can be part of the same device. The operation of the input device 116 will be described in further detail below.

One of the second forms of content refers to special content. Special content may include, for example, paid viewing content, pay-per-view content, internet access, and other content not provided to broadcast affiliate managers (eg, movies, video games, other video elements, etc.). The special content may be content requested by the user, such as a web page, a movie download, and the like. The special content can be transferred to a content manager 110. The content manager 110 can be a service provider such as, for example, one of the Internet sites associated with a content provider, a broadcast service, or a delivery network service. The content manager 110 can also incorporate the internet content into the delivery system. The content manager 110 can communicate the content to the user's receiving device 108 over a communication network (e.g., communication network 112). Communication network 112 may include a high speed broadband internet type communication system. It is important to note that all or portions of the communication network 112 can also be used to communicate content from the broadcast affiliate manager 104 and all or portions of the delivery network 106 can be used to communicate content from the content manager 110. In some embodiments, the user can directly obtain content (such as a web page, etc.) from the Internet 113 via the communication network 112 without having to It is managed by the content manager 110.

Several adaptations for utilizing separate delivery of content may be possible. In one possible approach, special content is provided as a value-added item of broadcast content to provide alternative display, purchase and sale options, progressive materials, and the like. In another embodiment, the special content may completely replace some of the stylized content provided as broadcast content. Finally, the special content can be completely separated from the broadcast content, and only one of the media alternatives can be selected by the user. For example, special content may be a movie library that cannot be used as one of broadcast content.

Receiving device 108 can receive different types of content from one or both of transport network 106 and communication network 112. The receiving device 108 processes the content and provides a separation of the content based on user preferences and commands. The receiving device 108 can also include a storage device for recording and playing audio and video content, such as a hard disk drive or a CD player. Further details of the operation of the receiving device 108 and features associated with playing the stored content will be described below with respect to FIG. The processed content is provided to display device 114.

In the example of FIG. 1, content manager 110 also controls a suggestion system 117 that can include a suggestion engine 118 and a repository 120. The suggestion system 117 can process encrypted suggestion information that can be used to provide recommendations to the user, as will be described in more detail below. Although in this example, the suggestion system 117 is controlled by the content manager 110, it should be appreciated that in some embodiments, the suggestion system may be operated by other entities, such as a separate suggestion service provider whose primary service is providing advice.

2 includes a block diagram of one example of an arithmetic system, such as a receiving device 200. The receiving device 200 can operate similar to the receiving device 108 described in FIG. 1, and can be included as a gateway device, a data machine, a video converter, a personal computer, a television, a tablet, a smart phone, and the like. section. The receiving device 200 can also be incorporated into other systems that include an audio device or a display device. Receiving device 200 can be, for example, a video converter coupled to an external display device (e.g., a television), a personal computer coupled to a display device (e.g., a computer monitor), and the like. In some embodiments, the receiving device 200 can An integrated display device is included, such as a portable device such as a tablet computer, a smart phone, and the like.

In the receiving device 200 shown in FIG. 2, content is received by an input signal receiver 202. Input signal receiver 202 can include, for example, a receiver circuit for receiving, demodulating, and decoding through a number of possible networks (which include wireless networks, cable networks, satellite networks, Ethernet, Signal provided by one of the fiber optic network and the telephone line network). The desired input signal can be obtained based on user input provided through a user interface 216. For example, the user input can include a search term and the input signal received by the input signal receiver 202 can include the search results. The user interface 216 can be coupled to an input device (such as the input device 116) and can receive corresponding user input (eg, a keystroke, a button press, a touch input (such as a gesture), an audio input (such as Voice input), etc.) and process the corresponding user input. The user interface 216 can be adapted to interface to a cellular phone, a tablet computer, a mouse, a remote controller, and the like.

The decoded output signal is provided to an input stream processor 204. The input stream processor 204 performs final signal selection and processing and includes separating the video content of the content stream from the audio content. The audio content is provided to an audio processor 206 for conversion from a received format, such as a compressed digital signal, to an analog waveform signal. The analog waveform signal is provided to an audio interface 208 and further to a display device or audio amplifier. In some embodiments, the audio interface 208 can use a high definition multimedia interface (HDMI) cable, an audio interface (such as via a Sony/Philips Digital Interconnect Format (SPDIF)), etc. And so on to provide a digital signal to an audio output device or display device. The audio interface can also include an amplifier for driving one or more sets of speakers. The audio processor 206 also performs any conversion required to store the audio signals.

The video output from the input stream processor 204 is provided to a video processor 210. The video signal can be in one of several formats. The video processor 210 provides one of the video content conversions as needed based on the input signal format. Video processor 210 also performs storage of video signals Any conversion required.

A storage device 212 stores the audio content and video content received at the input location. The storage device 212 allows for subsequent capture and playback of content under control of a controller 214 and also based on commands received from the user interface 216 (eg, navigation commands such as fast forward (FF) and reverse (RW)). . The storage device 212 can be, for example, a hard disk drive, one or more large-capacity integrated electronic memories (such as static RAM (SRAM) or dynamic RAM (DRAM)), an interchangeable optical disk storage system (such as a compact disk ( CD) or digital video disc (DVD) machine, etc.

The converted video signal from video processor 210 (which originates from input or storage device 212) is provided to display interface 218. The display interface 218 provides the display signal further to one of the display devices described above, such as the display device 114. The controller 214 is interconnected to a plurality of components of the device 200 via a bus, including an input stream processor 204, an audio processor 206, a video processor 210, a storage device 212, and a user interface 216. The controller 214 manages a conversion program for converting the input stream signal to a signal stored on the storage device or for display. Controller 214 also manages the capture and playback of stored content. Additionally, as will be described below, controller 214 can receive rating information entered by a user and can perform encryption of the user rating information, as will be described in more detail below.

Controller 214 is further coupled to control memory 220 (e.g., volatile or non-volatile memory, including RAM, SRAM, DRAM, ROM, Programmable ROM (PROM)) for storing information and instruction codes for controller 214. , flash memory, electronically programmable ROM (EPROM), electronically erasable programmable ROM (EEPROM), etc.). Control memory 220 can store instructions from controller 214. Control memory 220 can also store an elemental library, such as graphical elements containing content. The database may be stored as a pattern of one of the graphical elements, such as a graphical element containing content, various graphical elements for generating a display interface 218 that may display a user interface, and the like. In some embodiments, the memory can store the graphical elements in the identified or grouped memory locations and use an access or location table to identify the memory locations of the various portions of the information associated with the graphical elements. Set. Additional details related to the storage of graphical elements are described below. Moreover, embodiments of control memory 220 can include several possible embodiments, such as a single memory device, one or more memory circuits communicatively coupled or coupled together to form a common or common memory, and the like. In addition, the memory can be included in other circuitry in a larger circuit, such as part of a busbar communication circuit.

3 and 4 illustrate two examples of input devices 300 and 400, such as input device 116. Input devices 300 and 400 can be coupled to a user interface, such as user interface 216. Input devices 300 and 400 can be used to initiate and/or select various functions available to a user associated with the acquisition, consumption, access, and/or modification of content, such as multimedia content, broadcast content, internet content, and the like. . Input devices 300 and 400 may also allow a user to enter rating information and suggestion requests, as will be described in more detail below.

FIG. 3 illustrates an example of a touch panel input device 300. The control panel device 300 can be accessed, for example, via the user interface 216 of the receiving device 200 of FIG. The touch panel device 300 allows a receiving device or a video converter to be operated based on hand movements (or gestures) and actions that are translated into commands by a video converter or other control device through the panel. This is accomplished by controller 214 generating a touch screen user interface that includes at least one user selectable image element capable of initiating at least one operational command. The touch screen user interface can be pushed to the touch screen device 300 via the user interface 216. In some embodiments, the touch screen user interface generated by controller 214 can be accessed via one of the web servers on one of user interfaces 216. Touch panel 300 can act as a navigation tool to navigate a grid display as described above for search results. In some embodiments, the touch panel 300 can act as a display device to allow a user to more directly interact with the navigation through the content display. The touch panel 300 can also include a camera component and/or at least one audio sensing component.

In some embodiments, the touch panel 300 employs a gesture sensing controller or touch screen that implements several different types of user interactions. Input from the controller is used to define the hand Potential, and gestures then define specific context commands. The configuration of the sensor may allow for the movement of a user's finger on a touch screen to be defined and may even allow for the definition of the controller itself to move in one dimension or two dimensions. A combination of two-dimensional motion (such as a diagonal line), and roll, pitch, and scroll can be used to define any three-dimensional motion, such as a swing. The gesture is interpreted in conjunction with the context and the recognition gesture is moved by the definition made by the user. Only simple one-dimensional motion or gestures can be tolerated due to the complexity of the sensor system. For example, one of the sensors simply moving to the right or moving to the left (as shown in the figure) can produce a fast forward or reverse function. In addition, multiple sensors can be included and placed at different locations on the touch screen. For example, one of the horizontal sensors moving to the left and moving to the right can be placed at one point and used to increase/decrease the volume, while one of the vertical sensors for moving up and down can be placed on In a different point and used to change channels. In this way, a specific gesture map can be used. For example, the touch screen device 300 can recognize an alphanumeric input track that can be automatically converted to alphanumeric text that can be displayed on one of the touch screen devices 300 or output to a main display device via the display interface 218.

FIG. 4 illustrates another example of an input device (input device 400). Input device 400 can, for example, be used to interact with a user interface that is generated by the system and output for display to a primary display device (eg, a television, monitor, etc.) via display interface 218. The input device of FIG. 4 can be formed as a remote control having a 12-button alphanumeric keypad 402 and a navigation section 404 including a directional navigation button and a selector button. Input device 400 can also include a set of function buttons 406 that, when selected, initiate a particular system function (e.g., menu, guide, DVR, etc.). In some embodiments, input device 400 can include a set of programmable dedicated buttons 408 that, when selected, can initiate a specially defined function associated with one of the particular applications executed by controller 214. The input device 400 can include a display screen 410 that can display information such as program information, menu information, navigation information, and the like. The depiction of the input device in FIG. 4 is merely an example, and it should be appreciated that various input devices can include enabling a user to interface with a user interface in accordance with various embodiments. Any number of buttons and/or button configurations that interact. Additionally, it should be noted that the user can interact with the system simultaneously and/or sequentially using either or both of the input devices depicted and described in FIGS. 3 and 4. Other input devices can be considered within the scope of the present invention.

In some embodiments, the user input device can include at least one of an audio sensor and a visual sensor. For example, the audio sensor can sense an audible command issued by a user and translate the audible commands into functions to be performed by the user. The visual sensor can sense the presence of the user and match the user information of the sensed user(s) to the stored visual data in the usage database 120 of FIG. Matching the visual data sensed by the visual sensor enables the system to automatically identify the presence of the user and retrieve any user profile information associated with the user. Additionally, the visual sensor can sense the presence of at least one user's body movement and translate the movements into control commands for controlling the operation of the system. In this embodiment, the system can have a set of pre-stored command gestures that, when sensed, enable the controller 214 to perform a particular feature or function of the system. An example of one type of gesture command may include: the user waving his hand in a right direction (which may initiate a fast forward command or a screen command) or waving his hand in a left direction (which may be based on The current situation starts with a reverse or previous screen command). This description of a body gesture that can be recognized by the system is merely exemplary and should not be considered as limiting. Rather, this description is intended to illustrate the general concept of body gesture control that can be recognized by the system, and those skilled in the art should readily appreciate that the controller can be programmed to specifically recognize any body gesture and allow the gesture and system to At least one executable function association.

FIG. 5 is a block diagram of one example of a privacy protection suggestion system 500 in accordance with various embodiments. System 500 can include a user system 501, such as one of a user's home, such as user system 107 shown in FIG. The user system 501 can include, for example, a video converter, a digital video recorder (DVR), a gateway, a data machine, etc., which can be received and processed via a communication network (such as the communication network 112). And transmitting the content, and the communication can be sent via the communication network, such as materials, information, messages, requests and many more. System 500 can also include a suggestion system 504, such as suggestion system 117 shown in FIG.

The user may wish to obtain suggestions for content items (such as movies, television shows, music, etc.) from the suggestion system 504. In general, the suggested service requires information about a user to determine what content the user might like. As described above, the proposed service can be analyzed by user information (such as biographical information (such as age, gender, ethnicity, etc.), economic information (such as income level, etc.), preference information (such as what content items the user consumes). And how users rate content items, etc.) and provide suggestions to predict what other content items a user might like. However, some users may not want to provide this information to a suggested service.

System 500 depicts an example in which user information can be concealed from the recommender while still allowing the recommender to analyze the user information and provide suggestions. User information may include, for example, ratings that the user has given to various content items (eg, star ratings that the user has given to various movies, etc.), and identification information of content items that the user has consumed (eg, use) Watching movies), viewing habits (such as what type of movie the user has watched recently or a movie that the user has watched in the evening, day, weekend, etc.) and/or other information (which can be used to determine the pair) Suggestions for content projects), as will be appreciated by those skilled in the art. The user system 501 can provide user information to the suggestion system 504 under an encryption that does not allow the suggestion system to decrypt user information, but allows the user system to decrypt the rating. For example, the user can encrypt the user information using the user's public encryption key.

In this regard, FIG. 6 illustrates an example of one of the methods that can be performed by a user system, such as user system 501. The user system can obtain (601) user information. For example, a user can view a movie on a display, such as display device 114, and the user system can determine various user information associated with the viewing. For example, the user system can determine the time and date the user viewed the movie, the type of the movie, and the like. The user system can encrypt (602) the user information using an encryption that does not allow for a suggestor (such as The system 504) decrypts the user information but allows the user system to decrypt the user information. In other words, the user system can generate a user information encrypted by the user. For example, the user system can encrypt the user information using one of the user's public encryption keys.

The user system can transmit, by, for example, one of the user information including the user encryption to the recommender, by storing the user information encrypted by the user in a storage medium accessible to one of the proposers, The user information encrypted by the user is provided (603) to the recommender.

FIG. 5 illustrates an example of providing user encrypted user information by including user encrypted user information in a communication 511 sent from the user system 501 to the suggestion system 504. In various embodiments, the user information encrypted by the user in communication 511 may include a single user encrypted information, such as a user encrypted identifier (ID) of one of the movies that the user has viewed. For example, each time a user views a movie, the user system 501 can automatically encrypt the movie ID and send the user-encrypted movie ID to the suggestion system 504 in a communication 511. In various embodiments, communication 511 may also include, for example, unencrypted information to allow the recommender to better utilize user encrypted user information. In various embodiments, for example, communication 511 can include encrypting a user of one of the movies that the user has rated, and also including the unencrypted ID of the movie. Providing an unencrypted movie ID corresponding to the user's encrypted rating may, for example, allow the recommender to retrieve and store the user encrypted rating in an efficient manner, as will be described in more detail below with respect to Figures 9-11.

In various embodiments, the user information encrypted by the user in the communication 511 may include a plurality of different pieces of information (such as a plurality of user-encrypted IDs of the viewed movies), and may also include a message that may correspond to the user's encrypted information. Encrypt information. For example, the user system 501 can store the movie ID of the movie that has been watched, periodically encrypt the movie ID, and send the movie ID in a single communication 511, such as the movie ID encrypted by the user.

When the user wishes to receive a suggestion, the user can input a request for one of the suggestions to the user system 501, and the user system can send a suggestion request as a communication 514. The suggestion system 504 is sent.

FIG. 7 illustrates an example of one of the methods that can be performed by a recommender, such as suggestion system 504. The proponent may decide (701) to provide a suggestion. For example, suggestion system 504 can determine to provide a suggestion to user system 501 in response to receiving the suggestion request in communication 514. The recommender may determine (702) the comparison information encrypted by the first user based on the user information encrypted by the user.

The comparison information can be a comparison of one or two or more suggestion items (such as a measure of user preferences (eg, likes, dislikes), estimated ratings, etc.). As described above, there are a number of such suggested indicators that can be determined based on user information and used to guide the user in selecting suggestions, as will be appreciated by those skilled in the art. The user-encrypted comparison information may be determined based on the user information encrypted by the user obtained by the recommender, and the user-encrypted comparison information may be determined when the user information remains encrypted.

In various embodiments, for example, the comparison information may include a difference between the predicted ratings of two content items (eg, item j and item j'):

among them: User i’s prediction of item j, and It is the user's prediction of the item j'.

Each predictive rating may be, for example, a predictor predicting that the user (eg, user i of the n users using the advisor's service) will be in the corresponding content item (eg, m content items in the list of recommenders) The item j (or j')) gives the rating.

The suggester can provide (703) the user encrypted comparison information to the user. Referring to FIG. 5, for example, suggestion system 504 can transmit user encrypted comparison information to user system 501 in a communication 517. The user can, for example, use a method (such as the method illustrated by FIG. 8) to process the user-encrypted comparison information and provide information related to the processing results to the recommender.

Figure 8 illustrates a method that can be performed by a user system, such as user system 501. An example. The user system can, for example, obtain (801) user-encrypted comparison information from the recommender. The user system can decrypt (802) the user-encrypted comparison information to determine the result information.

In various embodiments in which the comparison information may include a difference between two predictive ratings (eg, as shown in Equation 1 above), the user may obtain a value for the difference between the predicted ratings when decrypting the comparison information. However, it is worth noting that the user does not get the actual value. and . In other words, the user will not be able to determine how the proponent predicts how the user will rate item j and item j'. In this way, for example, specific recommender information can be hidden from the user. Moreover, in various embodiments, the comparison information does not include the identifier of the compared content item, thereby further limiting the information that the user can obtain from the decrypted comparison information.

The user system can provide (803) the result information to the recommender. Referring to FIG. 5, the user system 501 can send the resulting information to the suggestion system 504 in a communication 521.

In various embodiments, the result information can include information that decrypts the comparison information and/or based on the decrypted comparison information. One example of including the decryption comparison information (in this example, the difference between the two prediction ratings) included in the result information can be as follows: when the user system performs the decryption and obtains the result (ie, two prediction ratings) When the value of the difference is), the user system sends the value to the suggester as the result information. An example of information containing information based on decrypted comparison information may be as follows: When the user system performs decryption and obtains a result (ie, the value of the difference between the two predicted ratings), the user system determines whether the value is a positive number. (ie, the value > 0), and the user system sends the decision result to the suggester as the result information. In each of these examples, the suggestor may use the result information to determine the suggestion, as will be described in more detail below.

Referring again to Figure 7, the suggestor can obtain (704) results information from the user. The recommender can determine (705) the second user encrypted comparison information based on the result information. For example, if the comparison information includes a difference between two predictive ratings, the resulting information can be used to determine which predictive rating is higher than the other predicted rating. In particular, from the first example described above, if the resulting information contains The value of the suggestion can be determined when the value is positive And when the value is negative . Similarly, from the second example described above, if the result information includes whether the value of the difference is an indication of a positive number, then a similar manner can be determined in a similar manner.

The proponent can rotate the higher prediction rating for the next comparison. For example, if the suggestor decides from the result information Above , the suggestor can compare Predictive rating with another content item (eg item j"). In other words, the suggestor can decide versus A user encryption difference between. The comparison information of the second user encryption determined in 705 is based on the result information obtained from the user, as compared with the comparison information of the first user encryption determined in 702. The suggester may provide (706) the second user encrypted comparison information to the user, and may continue (707) receiving the result information, and determine the second user encrypted comparison information (for example, determining which prediction rating is higher) And a new comparison between the higher prediction rating and the prediction rating of another content item is generated), and the second user encrypted comparison information is provided to the user. For each iteration, the higher prediction rating is determined such that when all of the prediction ratings have been compared, the content item with the highest prediction rating can be identified. The suggestor can then determine (708) the suggested content item and provide (709) the suggestion (which is the best content item in this example) to the user.

In order to obtain the second-highest prediction rating, the proponent can repeat the procedure without including the best content item, and can identify the sub-optimal content item. Similarly, the recommender can repeat the process until the k-content item has been identified and provided as a recommendation to the user.

9 through 12 illustrate examples in accordance with various embodiments of the present invention. In particular, FIGS. 9-11 illustrate examples of obtaining and storing user encrypted ratings, etc., in accordance with various embodiments. Figure 12 depicts a more detailed example of one of the suggestions provided in accordance with various embodiments.

In this regard, FIG. 9 illustrates an example of one of the methods that can be performed by a user system, such as user system 501. The user system can obtain (901) a rating for one of the content items (such as a movie). For example, the user can view on a display such as display device 114 The movie, and then an input device, such as input device 116, is used to enter a rating for one of the movies. The user system may encrypt (902) the rating using an encryption that does not allow a recommender (such as suggestion system 504) to decrypt the rating, but allows the user system to decrypt the rating. In other words, the user system can generate a user encrypted rating. For example, the user system can encrypt the rating using one of the user systems' public keys. The user system can send (903) the rating information to the recommender. The rating information may include a user encrypted rating and an unencrypted identifier (ID) of the content item. The unencrypted content item ID may allow the recommender to identify content items corresponding to the user's encrypted rating. In this way, the recommender can determine which content item corresponds to the rating, but cannot determine one of the rating values.

FIG. 10 illustrates an example of one of the methods that can be performed by a recommender, such as suggestion system 504. The suggester can obtain (1001) rating information, that is, the user encrypted rating and the corresponding content item ID. The suggestion system may retrieve (1002) user encrypted ratings based on the corresponding content item ID and may store (1003) user encrypted ratings based on the search. For example, user encrypted ratings may be stored in a repository (such as the suggested information repository 120 shown in FIG. 1).

11 is a diagram of an exemplary embodiment of the method of FIG. 10 in accordance with various embodiments. The plurality of users 1101 can subscribe to one of the suggested systems for suggesting services. The suggestion system can include a suggestion engine 1104 and a suggested information repository 1107. Some users may choose a privacy protection option in which user information for such users may remain encrypted (as described above) and may require an additional fee. Other users are unable to interfere with the privacy of the user information of such users and may send unencrypted user information of such users, such as ratings. A matrix M can be stored as one of the data structures 1114 stored in the suggested information repository 1107. Matrix M can include user encryption ratings for users who choose privacy protection options And other users' unencrypted ratings (r _i,j ), where r is the user rating, i is a user index, j is a content item index, and Indicates the encryption of user i. That is, the columns of matrix M contain user-encrypted ratings or unencrypted ratings for a particular user, and the rows of matrix M contain unencrypted ratings of user-encrypted ratings or a particular content item. In other words, the columns of the matrix M can represent a user-encrypted use profile vector. Or an unencrypted user profile vector u _i , and each row of the matrix M may represent a content item profile v _j including a user encrypted rating and an unencrypted rating. Figure 11 shows a matrix M containing elements at some locations, and the position in the matrix M without an element is indicated by a short "-".

FIG. 11 also illustrates an example of one method for storing user encrypted rating and unencrypted rating in matrix M, in accordance with various embodiments. When one of the users 1101 votes for a content item, the user system can send a communication 1111 to the suggestion engine 1104. Each communication from a privacy-protected user may include user-encrypted rating information (such as a user encrypted rating and a corresponding unencrypted content item ID) and an unencrypted use of the user who can identify the communication. ID. Each communication from a non-private protected user may include unencrypted rating information (such as an unencrypted rating and a corresponding unencrypted content item ID) and an unencrypted user ID that identifies the user who sent the communication. . For example, a privacy protection user (1) may input a user rating of the content item (3) to the user system of the user (1), and the user system may encrypt and send the user rating. Includes a user (1) ID, a project (3) ID, and user encryption rating. Communication 1111. The suggestion engine 1104 can receive the communication 1111 from the user (1), determine the user index i based on the user ID (i = 1), and determine the content item index j based on the content item ID (j = 3). Next, it is recommended that the system can retrieve the included user encryption ratings. The search user encryption rating is stored, for example, in the third row of the first column of the matrix M.

Similarly, FIG. 11 shows the communication 1111 resulting from the non-privacy-protected user (2) rating item (5), ie, [user (2) ID, item (5) ID, r], suggestion engine 1104 receives The communication 1111 retrieves r _2,5 and stores the communication 1111 in the fifth row and fifth row of the matrix M. Figure 11 also shows communications 1111 retrieved and stored from other users. In the example of Figure 11, the matrix M also contains other elements (such as , r _2,1 , r _2,4, etc.), which may, for example, be pre-existing ratings resulting from prior communications from the user 1101.

In various embodiments, matrix factorization (MF) can be used to analyze user encryption ratings. While remaining encrypted by the user to generate a user-encrypted prediction rating for other content items . For example, if the suggested service has n users (i=1...n) and can provide suggestions for m content items (j=1...m), the matrix M can be an n×m matrix with corresponding All user ratings elements received from such users. For many applications, the number of elements in matrix M is much smaller than the value of n x m. In other words, for many applications, most of the elements in matrix M are empty. Matrix factorization can be used to predict the value of an empty element of a particular user profile u _i and thus predict how the user will rate the content item that the user has not yet rated, while the user profile is Keep the user encrypted. In various embodiments, for example, an additional semantic preservation common key can be used for isomorphic encryption. (For example, the Paillier cryptography system), and a user-encrypted predicted user rating can be determined for each empty element (i, j) in a user-encrypted user profile. Each content item profile vector can be modified by removing (other user's) user encryption ratings to result in a modified content item profile vector _vj ' with only unencrypted ratings left. Then, the user's public key can be used to encrypt the modified content item profile vector to generate a user-encrypted modified content item profile vector. . User profile vector that can be encrypted by the user Modified content item profile encrypted with the user of content item j Multiply and determine the user's encryption prediction rating for content item j:

12 illustrates an example of one method of determining a suggestion using a user-encrypted user profile in accordance with various embodiments. A suggested system can obtain (1201) user i encrypted user profile . The content item index j can be initialized (1202), for example, by setting j=1. It is recommended that the system can determine (1203) whether there is an encrypted rating for the user of the jth content item. (ie, it is determined whether the user (i) has rated the content item (j)) or whether the content item j has been identified as a k-content item. If If the presence or content item j is already a good item, then j can be incremented (1204) (eg, incremented by 1) and the program can return to decision (1203) does it exist Or whether the content item j is a k-item item. On the other hand, if judged (1203) If it does not exist, it is recommended that the system obtain (1205) the user-encrypted modified profile vector of the content item j. And can make versus Multiply (1206) to obtain predictive ratings for user encryption , as in equation (2) above.

It is recommended that the system use the proponent's private key to encrypt the user's encrypted prediction rating (1207) to obtain a suggestor encryption user encryption prediction rating. ,among them Instructs the recommender to encrypt. The suggestion system can determine (1208) whether the predictive rating of the user encryption is the first one determined after initialization j. If the user's encrypted prediction rating is the first one, then the indication: the prediction rating for one of the other content items must be determined to have a comparison. In other words, if the user's encrypted prediction rating is the first one after the initialization j, it is suggested that the system cannot provide the user with comparison information or result information received from the user. Thus, the program returns to a prediction rating that increments j (1204) and determines another user encryption. In this case, once other prediction ratings are determined, the suggestion system determines (1209) the first user encrypted comparison information to obtain a comparison between the two user-encrypted prediction ratings by performing an operation "oper". A user encryption difference:

among them: The first prediction rating determined after j is initialized, and The second prediction rating determined after initialization of j.

The operation "oper" that can be used to satisfy equation (3) can depend on the particular encryption method used, as will be appreciated by those skilled in the art.

It is recommended that the system can encrypt the user's information. And the user encryption prediction rating corresponding to the suggester encryption and Send (1210) to the user in a predetermined format (eg, an array):

The user system can have predetermined instructions to decrypt the first element (ie, ), whether the value is positive, and the second element is when the value is positive (ie, ) return or make the third element when the value is not positive (ie, )return.

The suggestion system can receive (1211) the result information from the user and can determine (1212) whether the content item j is the last content item. If the content item j is not the last content item, then the suggestion system can proceed to increment j (1204) to determine the user encryption prediction rating of another content item to be compared. However, when (1206) the next user encrypted prediction rating is obtained and the decision (1207) corresponds to the recommender encryption user authentication prediction rating, the recommender system will determine (1208) that this is not the first after j initialization. One operation (1208). Therefore, the recommender system will proceed to determine (1209) the user-encrypted comparison information based on the result information received from the user. In particular, it is recommended that the system can decrypt the user's encrypted prediction rating of the received recommender's encryption to obtain the user's encrypted prediction rating, which we know is higher than the two prediction ratings previously sent to the user. By. The proponent system can use Equation 3 above to generate a comparison of the predicted rating of the return with one of the latest judgments:

among them: The forecast rating returned in the result information, and The forecast rating determined after receiving the result information.

The program may proceed in this manner, wherein each iteration identifies the current highest user encryption prediction rating until the suggestion system determines (1212) that the result information of the comparison information of the last content item has been received, and the user encrypted prediction rating returned in the result information It is judged as the highest forecast rating. The recommender system can determine (1213) that the content item corresponding to the last received result information is a good item and can send (1214) the information of the content item to the user as a suggestion. In some embodiments, the k-goods can be saved in a list until all k-goods have been determined, and then the list can be sent to the user. It is recommended that the system determine whether the (1215)k good is the last to be determined (eg, whether k is equal to the construction of each proposed request) The predetermined number of agenda items). If the k-item is the last, the program can end (1216). If the k-item is not the last, then in the next iteration it is suggested that the system can initialize j and start repeating the program to find the next best item in addition to the currently determined k-item.

In some embodiments, the recommender and the user do not compare only two items at a time, but can perform a network classification. In this way, for example, the user can obtain an entire catalog of content items categorized according to the preferences of the user.

In some embodiments, the suggester may appropriately select the random elements ρ and θ, and may prepare the user-encrypted comparison information as follows: And can be encrypted with the corresponding suggestor encryption user rating prediction and Send it to the user together. An example of an appropriate selection of one of the random elements ρ and θ can be: Located at All possible values In the message space. If the message space is a set of N remainders, the "negative number" is expressed as a number in the range [N/2, N). The suggester can send the information to the user in a predetermined format (eg, an array):

The user system can have predetermined instructions to decrypt the first element (ie, ), whether the value is positive. If the decrypted value is positive, the user can return the following to the suggester:

Or otherwise (if the value is not positive) the user can return:

Where K can be a ciphertext prepared by the user for one of the constants (such as zero (0)):

In some embodiments, the operation "oper" can be multiplication, and the suggestor encrypts It can be partially isomorphic with respect to multiplication.

In this way, for example, the information provided by the proposer to the user can be "randomized" by the random elements ρ and θ, and the information returned by the user to the recommender can be "randomized" by K.

In some embodiments, a Paillier system can be used for user encryption. And one of the (Z/ N ² Z) ^x ElGamal systems can be used for suggester encryption . N can be an RSA type modulus, so: (for some random ρ (Z/ N Z)*)

(for some random r (Z/ N Z)*), and

Where ρ *=( ρ r) is the remainder of N, g is one of the highest order elements in (Z/ N ² Z), and y=g ^{x is} the remainder of N ² , where x is the ElGamal private decryption key . If (c ₁ , c ₂ )= ( K oper ),then:

In some embodiments, the recommender may apply a random arrangement to the catalog of content items. Therefore, the user can infer the highest rating of the permutation list (especially the full classification), ie, Π(j ₁ ), where J≠j ₁ (especially Π(j ₁ ), Π(j ₂ )...Π(j _m ), where for all p<q, ). If a fuzzy transmission of 1 (especially k in m) is used, then user i can obtain j ₁ = Π ^{-1 (} Π (j ₁ )) (especially j ₁ ... j _k ).

Those skilled in the art will appreciate that a computer (eg, a general purpose computer) can be executed by a computer readable medium (eg, a storage disk, memory, etc.) and executed by a computer processor. The methods described above are implemented with executable instructions (eg, software, firmware, etc.). Referring to FIG. 2, for example, a software implementing one or more of the methods shown in the flow table can be stored in storage device 212 and executed by controller 214. It will be appreciated that the various elements shown in the figures may be embodied in various forms of hardware, software, or combinations thereof. That is, the various components can be implemented as one or more suitable stylizations (which can include a process A combination of hardware and software on a general purpose device, memory, and input/output interface.

It should also be understood that, although various examples of various embodiments have been shown and described in detail herein, those skilled in the art can readily

All of the examples and conditional terms set forth herein are intended to be a teaching purpose to help the reader understand the principles of the present invention and the concepts contributed by the inventor to enhance the technology and should be construed as being not limited to such specific statements. Examples and conditions.

Furthermore, all statements herein reciting principles, aspects, and embodiments of the invention, as well as the specific embodiments of the invention are intended to In addition, regardless of the structure, such equivalents are intended to encompass both the presently known equivalents and future development equivalents (i.e., any development elements that perform the same function).

Thus, it will be understood by those skilled in the <RTIgt; </ RTI> <RTIgt; </ RTI> that the block diagram presented herein represents a conceptual diagram of an illustrative circuit embodying the principles of the invention. Similarly, it should be understood that any flow diagrams, flow diagrams, state transition diagrams, pseudocodes, and the like represent various programs that can be substantially represented in a computer readable medium and thus executed by a computer or processor, whether or not Show this computer or processor.

The functions of the various elements shown in the figures can be provided through the use of dedicated hardware and hardware capable of executing software associated with the appropriate software. When a function is provided by a processor, the functionality can be provided by a single dedicated processor, a single shared processor, or a plurality of individual processors (the portions of which can be shared). Furthermore, the explicit use of the terms "processor" or "controller" should not be construed as referring only to hardware capable of executing software, but may implicitly include, but is not limited to, digital signal processors ("DSP" Hardware) Read-only memory ("ROM"), random access memory ("RAM") and non-volatile memory for storing software.

Other hardware (known and/or custom) may also be included. Similarly, any of the switches shown in the figures are conceptual only. Through the operation of program logic, through dedicated logic, through The interaction of program control and dedicated logic, or even the manual implementation of such hardware functions, may be selected by the implementer, as more specifically understood from the context.

In the context of the present invention, any element expressed as "a member for performing a specified function" is intended to cover any means of performing the function, including, for example, a combination of circuit elements that perform the function, The software (which thus comprises a firmware, a microcode or the like) in any form in combination with appropriate circuitry for performing the software to perform the function. The invention as defined by the scope of the patent application has the fact that the functionality provided by the various stated components is combined and put together in the manner claimed in the claims. Accordingly, any component that provides such functionality is considered equivalent to the components shown herein.

200‧‧‧Receiver/recommended system/user system

202‧‧‧Input signal receiver

204‧‧‧Input Stream Processor

206‧‧‧Optical processor

208‧‧‧ audio interface

210‧‧‧Video Processor

212‧‧‧Storage devices/non-transitory computer readable media

214‧‧‧Controller/Processor

216‧‧‧User interface

218‧‧‧Display interface

220‧‧‧Control memory

Claims (42)

A suggestion system (200) comprising: a processor (214); and a memory (220) storing instructions that are configured to cause the processor to: obtain user information encrypted by a user, One of the user systems can decrypt the user encryption, but the suggestion system cannot decrypt the user encryption; and the first information is determined based on the user information encrypted by the user without decrypting the user information encrypted by the user. The user-encrypted comparison information, wherein the first user-encrypted comparison information includes a first comparison of one of the suggestion items of the content item of the suggestion system; and the first user-encrypted comparison information is provided to the user system Obtaining first result information from the user system, wherein the first result information includes an indication of one of the results of the first comparison; and based on the first result information without decrypting the user information encrypted by the user And determining, by the second user, the comparison information encrypted, wherein the comparison information encrypted by the second user includes a second comparison of one of the suggestion items of the content item Providing the second user encrypted comparison information to the user system; obtaining second result information from the user system, wherein the second result information includes an indication of one of the results of the second comparison; and based on the A suggestion is determined by comparing the indications of the results of the second comparison. The suggestion system of claim 1, wherein the user information encrypted by the user comprises a user encrypted rating of one of the content items. The suggestion system of claim 1, wherein the first comparison comprises comparing one of the first content items to one of the second content items and one of the second content items. The suggestion system of claim 3, wherein the second comparison comprises comparing one of the third content items to a predicted rating and one of the first content item or the one of the second content items. A suggested system of claim 1, wherein the first comparison comprises a difference between values of the two suggested indicators. The suggestion system of claim 5, wherein the first result information includes an indication of which of the two suggested indicators has a higher value. The suggestion system of claim 6, wherein the second comparison includes the higher value suggestion indicator compared to one of the other suggestion indicators. A non-transitory computer readable medium (212) storing computer executable instructions executable to perform one of a plurality of content items for providing a content item in a suggestion system In one method, the method includes: obtaining user information encrypted by a user, wherein a user system can decrypt the user encryption, but the suggestion system cannot decrypt the user encryption; without decrypting the user information encrypted by the user The first user encrypted comparison information is determined based on the user information encrypted by the user, wherein the first user encrypted comparison information includes a first comparison of one of the suggestion items of the content item; The user encrypted comparison information is provided to the user system; the first result information is obtained from the user system, wherein the first result information includes an indication of one of the results of the first comparison; and the user encryption is not required to be decrypted In the case of user information, based on the first result information, determining comparison information encrypted by the second user, wherein the second Comparison encrypts information contains suggestions for the contents of the instruction is one of the projects of the second comparator; Providing the second user encrypted comparison information to the user system; obtaining second result information from the user system, wherein the second result information includes an indication of one of the results of the second comparison; and based on the A suggestion is determined by comparing the indications of the results of the second comparison. The computer readable medium of claim 8, wherein the user information encrypted by the user comprises a user encrypted rating of one of the content items. The computer readable medium of claim 8, wherein the first comparison comprises comparing one of the first content items to one of the second content items and one of the second content items. The computer readable medium of claim 10, wherein the second comparison comprises comparing one of the third content items to a predicted rating of the first content item or the second content item. The computer readable medium of claim 8, wherein the first comparison comprises a difference between values of the two suggested indicators. The computer readable medium of claim 12, wherein the first result information includes an indication of which of the two suggested indicators has a higher value. The computer readable medium of claim 13, wherein the second comparison includes the higher value suggestion indicator compared to one of the other suggested indicators. A method for providing one of a plurality of content items in a suggestion system, the method comprising: obtaining user encrypted user information, wherein a user system is capable of decrypting the user encryption, but It is recommended that the system cannot decrypt the user encryption; and the first user encrypted comparison information is determined based on the user information encrypted by the user without decrypting the user information encrypted by the user, wherein the first user encrypts the information. The comparison information includes a first comparison of one of the suggested indicators of the content item; Providing the first user encrypted comparison information to the user system; obtaining first result information from the user system, wherein the first result information includes an indication of one of the results of the first comparison; Comparing the user information encrypted by the user, determining, according to the first result information, comparison information encrypted by the second user, wherein the second user encrypted comparison information includes a second comparison of one of the suggestion items of the content item; Providing the second user encrypted comparison information to the user system; obtaining second result information from the user system, wherein the second result information includes an indication of one of the results of the second comparison; and based on the A suggestion is determined by comparing the indications of the results of the second comparison. The method of claim 15, wherein the user information encrypted by the user comprises a user encrypted rating of one of the content items. The method of claim 15, wherein the first comparison comprises comparing one of the first content items to one of the second content items and one of the second content items. The method of claim 17, wherein the second comparison comprises comparing one of the third content items, the predicted rating, and the one of the first content item or the second content item. The method of claim 15, wherein the first comparison comprises a difference between values of the two suggested indicators. The method of claim 19, wherein the first result information includes an indication of which of the two suggested indicators has a higher value. The method of claim 20, wherein the second comparison comprises the higher value suggestion indicator compared to one of the other suggestion indicators. A user system (200) comprising: a processor (214); a memory (220) storing instructions that are configured to cause the processor to: obtain user information; encrypt the user information using a user encryption, wherein the user system can decrypt the use Encrypted, but a suggested system cannot decrypt the user encryption; the user information encrypted by the user is provided to the suggestion system; the first user encrypted comparison information is obtained from the suggestion system, and the first user encrypts The comparison information is based on the user information encrypted by the user, wherein the first user encrypted comparison information includes a first comparison of one of the suggestion items of the content item of the suggestion system; and the first user encrypted comparison information is decrypted. The first result information is determined, wherein the first result information includes an indication of one of the results of the first comparison; the first result information is provided to the suggestion system; and the second user encrypted comparison information is obtained from the suggestion system The comparison information encrypted by the second user is based on the result information, wherein the comparison information encrypted by the second user includes the content item a second comparison of the suggested indications; decrypting the second user encrypted comparison information to determine the second result information, wherein the second result information includes one of the results of the second comparison; the second result Information is provided to the suggestion system; and a recommendation is obtained from the suggestion system, wherein the suggestion is based on the first comparison and the indication of the results of the second comparison. The user system of claim 22, wherein the user information encrypted by the user comprises a user encrypted rating of one of the content items. The user system of claim 22, wherein the first comparison comprises comparing one of the first content items to one of the second content items and one of the second content items. The user system of claim 24, wherein the second comparison comprises comparing one of the third content items to a predicted rating and one of the first content item or the one of the second content items. The user system of claim 22, wherein the first comparison comprises a difference between values of the two suggested indicators. The user system of claim 26, wherein the first result information includes an indication of which of the two suggested indicators has a higher value. The user system of claim 27, wherein the second comparison comprises the higher value suggestion indicator compared to one of the other suggestion indicators. A non-transitory computer readable medium (212) storing computer executable instructions executable to perform one of a plurality of content items suggested for obtaining a plurality of content items in a suggestion system In one method, the method includes: obtaining user information; encrypting the user information by using a user encryption, wherein a user system can decrypt the user encryption, but a suggestion system cannot decrypt the user encryption; The user information encrypted by the user is provided to the suggestion system; the first user encrypted comparison information is obtained from the suggestion system, and the first user encrypted comparison information is based on the user information encrypted by the user, wherein the first a user-encrypted comparison information includes a first comparison of one of the suggestion items of the content item of the suggestion system; decrypting the first user-encrypted comparison information to determine the first result information, wherein the first result information includes the first Comparing one of the results to one of the results; providing the first result information to the suggestion system; obtaining a second from the suggestion system Comparison with encrypts information, the encrypted information of the second user based on the comparison result information, wherein the second user encryption The comparison information includes a second comparison of one of the suggestion items of the content item; decrypting the second user encrypted comparison information to determine the second result information, wherein the second result information includes one of the results of the second comparison Providing the second result information to the suggestion system; and obtaining a suggestion from the suggestion system, wherein the suggestion is based on the first comparison and the indication of the results of the second comparison. The computer readable medium of claim 29, wherein the user information encrypted by the user comprises a user encrypted rating of one of the content items. The computer readable medium of claim 29, wherein the first comparison comprises comparing one of the first content items to one of the second content items and one of the second content items. The computer readable medium of claim 31, wherein the second comparison comprises comparing one of the third content items to a predicted rating of the first content item or the second content item. The computer readable medium of claim 29, wherein the first comparison comprises a difference between values of the two suggested indicators. The computer readable medium of claim 33, wherein the first result information includes an indication of which of the two suggested indicators has a higher value. The computer readable medium of claim 34, wherein the second comparison includes the higher value suggestion indicator compared to one of the other suggested indicators. A method for obtaining one of a plurality of content items in a suggestion system, the method comprising: obtaining user information; encrypting the user information using a user encryption, wherein the user system The user encryption can be decrypted, but a suggestion system cannot decrypt the user encryption; the user information encrypted by the user is provided to the suggestion system; The first user encrypted comparison information is obtained based on the user information encrypted by the user, wherein the first user encrypted comparison information includes the content of the suggestion system. a first comparison of one of the suggested items of the item; decrypting the first user encrypted comparison information to determine the first result information, wherein the first result information includes an indication of one of the results of the first comparison; The result information is provided to the suggestion system; the second user encrypted comparison information is obtained from the suggestion system, and the second user encrypted comparison information is based on the result information, wherein the second user encrypted comparison information includes the content item a second comparison of the suggested indications; decrypting the second user encrypted comparison information to determine the second result information, wherein the second result information includes one of the results of the second comparison; the second result Information is provided to the suggestion system; and a recommendation is obtained from the suggestion system, wherein the recommendation is based on the first comparison and the second comparison Such results of such instructions. The method of claim 36, wherein the user information encrypted by the user comprises a user encrypted rating of one of the content items. The method of claim 36, wherein the first comparison comprises comparing one of the first content items to one of the second content items and one of the second content items. The method of claim 38, wherein the second comparison comprises comparing one of the third content items, the predicted rating, and the one of the first content item or the second content item. The method of claim 36, wherein the first comparison comprises a difference between values of the two suggested indicators. The method of claim 40, wherein the first result information includes an indication of which of the two suggested indicators has a higher value. The method of claim 41, wherein the second comparison comprises the higher value suggestion indicator compared to one of the other suggestion indicators.