WO2014073214A1 - パーソナル情報を分析する情報処理システム及びパーソナル情報分析方法 - Google Patents
パーソナル情報を分析する情報処理システム及びパーソナル情報分析方法 Download PDFInfo
- Publication number
- WO2014073214A1 WO2014073214A1 PCT/JP2013/006594 JP2013006594W WO2014073214A1 WO 2014073214 A1 WO2014073214 A1 WO 2014073214A1 JP 2013006594 W JP2013006594 W JP 2013006594W WO 2014073214 A1 WO2014073214 A1 WO 2014073214A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- recommendation
- recommendation rule
- user
- rule
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
- G06F21/6254—Protecting personal data, e.g. for financial or medical purposes by anonymising data, e.g. decorrelating personal data from the owner's identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
Definitions
- the present invention relates to an information processing system for analyzing personal information in consideration of privacy protection, a personal information analysis method, and a program therefor.
- providing personalized services by analyzing personal information (such as user behavior information) collected / stored on the terminal side and delivering personalized content to the users Is possible.
- Patent Document 1 discloses an example of information analysis technology.
- the trend evaluation technique described in Patent Literature 1 calculates the degree of change in co-occurrence probability between a keyword and a related word and the change in topic related to the keyword.
- the trend evaluation technique is a technique for calculating a trend score in consideration of the relative co-occurrence and the relative related word similarity obtained by this calculation.
- Non-Patent Document 1 discloses a technique for predicting an evaluation value of a certain user for a certain item.
- the evaluation value of a certain user (referred to as user 1) is unknown (unevaluated) for a certain item (referred to as item 1)
- the Slope One Scheme described in Non-Patent Document 1 is as follows. Estimate the evaluation value.
- Slope One Scheme obtains a difference d between an evaluation value for item 1 of another user (referred to as user 2) and an evaluation value for another item of user 2 (referred to as item 2).
- user 2 an evaluation value for item 1 of another user
- item 2 an evaluation value for another item of user 2
- the user average value dmu of the difference d corresponding to each user 2 is obtained.
- Slope One Scheme predicts an evaluation value for the item 1 of the user 1 based on the difference d (or the user average value dmu).
- the difference d (or user average value dmu) corresponding to each of the plurality of items 2 is obtained, the item average value dmi (or user average value dmu) of the difference d (or user average value dmu) is obtained.
- the evaluation value for the item 1 of the user 1 is predicted.
- dmui is a weighted average that takes into account the number of users 2 corresponding to each item 2.
- Slope One Scheme using this weighted average is called “Weighted Slope One Scheme”. Yes.
- Non-Patent Document 1 discloses Bi-Polar Slope One Scheme for evaluation with a distinction between likes and dislikes.
- Patent Document 2 discloses an example of a data integration system that conceals data and transfers and aggregates the concealed data.
- the data integration system described in Patent Document 2 is a distributed data integration system that performs a set operation on an element set stored in each of three or more nodes. These nodes are provided with means for concealing the element set stored by itself by character string disturbance or element number disturbance to generate and output concealed data.
- these nodes have means for outputting a union of the concealment data transmitted from other nodes and the concealment data generated by itself.
- the aggregation node among these nodes includes means for decoding the concealment data (the union of the concealment data) transmitted from other nodes.
- the aggregation node includes means for removing the influence of character string disturbance or element number disturbance from the element set obtained by decoding.
- the tabulation node includes means for performing a set operation on the element set from which the influence of the character string disturbance or the element number disturbance is removed.
- the data integration system disclosed in Patent Document 2 has the above-described configuration, and can perform data integration between distributed nodes in a state where an element set is not inferred from other nodes.
- Patent Document 2 for example, when personal information is transmitted from the user terminal to the server, it is difficult to guarantee the anonymity of the personal information on the user terminal side. was there.
- the server Various analyzes can be performed. As a result, there is a possibility that the personal information and the information specifying the user are associated with each other in the server. Therefore, there is a risk that privacy protection of the personal information will be insufficient.
- each node collects the concealed data that conceals the element set owned by itself and the concealed data received from other nodes while concealing them. This is because the origin of each element cannot be estimated by calculating and transferring.
- An object of the present invention is to provide an information processing system, a personal information analysis method, and a program therefor that solve the above-described problems.
- the information processing system includes information recommendation rule storage means for storing information recommendation rules indicating recommendation priorities of the recommendation information for recommendation information presented to the user, personal information of the user, and the information recommendation rule.
- information recommendation rule storage means for storing information recommendation rules indicating recommendation priorities of the recommendation information for recommendation information presented to the user, personal information of the user, and the information recommendation rule.
- the personal information analysis method of the present invention uses the information recommendation rule indicating the recommendation priority of the recommendation information and the user's personal information for the recommendation information presented to the user by the computer, and the information recommendation. Generate feedback information that is information for updating the user's personal information for the rule, anonymize the feedback information to generate and output anonymized feedback information, and use the anonymized feedback information
- the information recommendation rule is updated.
- the computer-readable non-transitory recording medium of the present invention uses the information recommendation rule indicating the recommendation priority of the recommendation information for the recommendation information presented to the user and the personal information of the user, Generate feedback information that is information for updating the user's personal information with respect to the information recommendation rule, anonymize the feedback information to generate and output anonymized feedback information, and use the anonymized feedback information And the program which makes a computer perform the process which updates the said information recommendation rule is recorded.
- the present invention has an effect that it is possible to guarantee the anonymity of personal information on the terminal side when personal information is transmitted from the terminal to the server.
- FIG. 1 is a block diagram showing a configuration of a personal information analysis system according to the first embodiment.
- FIG. 2 is a diagram illustrating an example of behavior information.
- FIG. 3 is a diagram illustrating an example of the information recommendation rule.
- FIG. 4 is a diagram illustrating an example of the analysis reflection information recommendation rule.
- FIG. 5 is a diagram illustrating an example of feedback information.
- FIG. 6 is a diagram illustrating an example of anonymized feedback information.
- FIG. 7 is a diagram illustrating an example of anonymized feedback information.
- FIG. 8 is a diagram illustrating an example of the information recommendation rule.
- FIG. 9 is a block diagram illustrating a hardware configuration of a computer that implements the personal information analysis system according to the first embodiment.
- FIG. 9 is a block diagram illustrating a hardware configuration of a computer that implements the personal information analysis system according to the first embodiment.
- FIG. 10 is a flowchart showing the operation of the personal information analysis system in the first embodiment.
- FIG. 11 is a flowchart showing the operation of the personal information analysis system in the first embodiment.
- FIG. 12 is a block diagram illustrating a configuration of an information recommendation system according to the second embodiment.
- FIG. 13 is a flowchart showing the operation of the information recommendation system in the second embodiment.
- FIG. 14 is a flowchart showing the operation of the information recommendation system in the second embodiment.
- FIG. 15 is a diagram illustrating an example of an information recommendation system according to the third embodiment.
- FIG. 16 is a block diagram illustrating a configuration of an information recommendation system according to the fourth embodiment.
- FIG. 17 is a diagram illustrating an example of an evaluation value.
- FIG. 18 is a diagram illustrating an example of the information recommendation rule.
- FIG. 19 is a diagram illustrating an example of feedback information.
- FIG. 20 is a diagram illustrating an example of anonymized feedback information.
- FIG. 21 is a diagram illustrating an example of anonymized feedback information.
- FIG. 22 is a diagram illustrating an example of the information recommendation rule.
- FIG. 23 is a flowchart showing the operation of the information recommendation system in the fourth embodiment.
- FIG. 24 is a block diagram illustrating a configuration of an information recommendation system according to the fifth embodiment.
- FIG. 25 is a diagram illustrating an example of an information recommendation system according to the sixth embodiment.
- FIG. 1 is a block diagram showing a configuration of a personal information analysis system 100 according to the first embodiment of the present invention.
- a personal information analysis system 100 includes a plurality of anonymized feedback information generation units 110 (only one is shown as a representative), an information recommendation rule update unit 140, and an information recommendation rule DB. (Data Base) 150.
- the information recommendation rule DB is also called information recommendation rule storage means.
- the constituent elements shown in FIG. 1 may be constituent elements in hardware units or constituent elements divided into functional units of the computer apparatus.
- the components shown in FIG. 1 will be described as components divided into functional units of the computer apparatus.
- the feedback information indicates information for updating the personal information with respect to the information recommendation rule.
- the information recommendation rule is a rule for determining recommendation information to be presented to the user.
- the recommendation information is information for recommending a product or the like.
- the information recommendation rule is information indicating the correlation between elements (for example, products) recommended by the recommendation information.
- the information indicating the correlation is the co-occurrence rate or the number of co-occurrence of product names based on the co-occurrence of product names referred to by the users. That is, the information recommendation rule indicates the degree that each recommended information should be presented or not (also referred to as recommendation priority).
- the anonymized feedback information generation unit 110 analyzes personal information, reflects it in the information recommendation rule, and generates an analysis reflected information recommendation rule. Next, the anonymized feedback information generation unit 110 extracts the difference between the generated analysis reflection information recommendation rule and the information recommendation rule, and generates feedback information.
- the anonymized feedback information generation unit 110 anonymizes the generated feedback information and generates anonymized feedback information.
- the anonymized feedback information generation unit 110 outputs the anonymized feedback information.
- the anonymized feedback information generation unit 110 applies a random number to the feedback information (adds an error) to generate the anonymized feedback information.
- the anonymized feedback information generation unit 110 may replace the individual values included in the feedback information and generate the anonymized feedback information.
- FIG. 2 is a diagram illustrating an example of behavior information which is one of personal information.
- the behavior information is reference information indicating that the user has referred to product data, for example.
- the behavior information is, for example, the position information of the user based on the position of the user terminal, purchase information that is information related to the product purchased by the user, and the like. Regardless of the example described above, the behavior information may be any available information related to the user's behavior.
- FIG. 3 is a diagram illustrating an example of the recommendation information rule.
- the information recommendation rule indicates, for example, the correlation between a certain product and another product by the number of co-occurrence.
- the correlation between “product A” and “product C” is “10”. This is because there is a case where there is a user who referred to both data of “product A” and data of “product C” (that is, “product A” and “product C” co-occurred) in the past. Indicates that there were times.
- the correlation may be the number of times when “product A” and “product C” co-occur instead of the number of times when such a user exists.
- the correlation may be a co-occurrence rate with the number of users providing behavior information as a parameter and the value of the parameter.
- the recommendation information rule indicates that the greater the correlation value, the greater the degree that it is better to present “recommendation information of the product corresponding to the value”.
- FIG. 4 is a diagram illustrating an example of the analysis reflection information recommendation rule when the anonymization feedback information generation unit 110 reflects the behavior information illustrated in FIG. 2 with respect to the information recommendation rule illustrated in FIG.
- the analysis reflection information recommendation rule shown in FIG. 4 is reflected in the information recommendation rule shown in FIG. 3 with “refer to product A”, “refer to product B” and “refer to product D” in the behavior information shown in FIG. Information. That is, the analysis reflection information recommendation rule shown in FIG. 4 is “product A” and “product B”, “product A” and “product D”, and “product B” compared to the information recommendation rule shown in FIG. And the number of co-occurrence with “Product D” is increased by “1”. 2 is not reflected in the analysis reflection information recommendation rule shown in FIG. 4 because there is no element corresponding to the information recommendation rule shown in FIG. .
- FIG. 5 is a diagram illustrating an example of feedback information when the anonymized feedback information generation unit 110 extracts a difference between the analysis reflection information recommendation rule illustrated in FIG. 4 and the information recommendation rule illustrated in FIG.
- the feedback information shown in FIG. 5 is information indicating the difference between the information recommendation rule shown in FIG. 3 and the analysis reflection information recommendation rule shown in FIG. That is, the feedback information shown in FIG. 5 is for updating the information recommendation rule shown in FIG. 3 with the action information shown in FIG. 2 “refer to product A”, “refer to product B”, and “refer to product D”. Information.
- FIG. 6 is a diagram illustrating an example of anonymized feedback information when the anonymized feedback information generation unit 110 anonymizes the feedback information illustrated in FIG. 5.
- the anonymized feedback information shown in FIG. 6 is anonymized information by applying a random number with an expected value of 0 to each value of the feedback information shown in FIG.
- the number of co-occurrence of “product A” and “product B” changes from “1” to “0”
- the number of co-occurrence of “product A” and “product C”. Has changed from “0” to “1”.
- the number of co-occurrence of “product A” and “product D” changes from “1” to “0”
- the number of co-occurrence of “product C” and “product D” changes from “0” to “1”. is doing.
- FIG. 7 is a diagram illustrating an example of anonymized feedback information of a user different from the user corresponding to the anonymized feedback information illustrated in FIG.
- FIG. 8 is a diagram showing an information recommendation rule updated by synthesizing the anonymized feedback information shown in FIGS. 6 and 7 with the information recommendation rule shown in FIG. As shown in FIG. 8, the anonymized feedback information shown in FIGS. 6 and 7 is combined with the information recommendation rule shown in FIG.
- FIG. 9 is a diagram illustrating a hardware configuration of a computer 700 that realizes the personal information analysis system 100 according to the present embodiment.
- the computer 700 includes a CPU (Central Processing Unit) 701, a storage unit 702, a storage device 703, an input unit 704, an output unit 705, and a communication unit 706. Furthermore, the computer 700 includes a recording medium (or storage medium) 707 supplied from the outside.
- the recording medium 707 may be a non-volatile recording medium that stores information non-temporarily.
- the CPU 701 controls the overall operation of the computer 700 by operating an operating system (not shown).
- the CPU 701 reads a program and data from a recording medium 707 mounted on the storage device 703, for example, and writes the read program and data to the storage unit 702.
- the program is, for example, a program that causes the computer 700 to execute operations of flowcharts shown in FIGS.
- the CPU 701 executes various processes as the anonymized feedback information generation unit 110 and the information recommendation rule update unit 140 shown in FIG. 1 according to the read program and based on the read data.
- each of the anonymized feedback information generation unit 110 and the information recommendation rule update unit 140 illustrated in FIG. 1 may be processed in each of different computers 700.
- the CPU 701 may download a program or data to the storage unit 702 from an external computer (not shown) connected to a communication network (not shown).
- the storage unit 702 stores programs and data (for example, data as shown in FIGS. 3, 4, 5, and 6).
- the storage unit 702 may include an information recommendation rule DB 150.
- the storage device 703 is, for example, an optical disk, a flexible disk, a magnetic optical disk, an external hard disk, and a semiconductor memory, and includes a recording medium 707.
- the storage device 703 (recording medium 707) stores the program in a computer-readable manner.
- the storage device 703 may store data (for example, data as shown in FIGS. 3, 4, 5, and 6).
- the storage device 703 may include an information recommendation rule DB 150.
- the input unit 704 is realized by, for example, a mouse, a keyboard, a built-in key button, and the like, and is used for an input operation.
- the input unit 704 is not limited to a mouse, a keyboard, and a built-in key button, and may be a touch panel, an accelerometer, a gyro sensor, a camera, or the like.
- the output unit 705 is realized by a display, for example, and is used for confirming the output.
- the communication unit 706 realizes an interface among the anonymized feedback information generation unit 110, the information recommendation rule update unit 140, and the information recommendation rule DB 150.
- the communication unit 706 may be included as part of the anonymized feedback information generation unit 110, the information recommendation rule update unit 140, and the information recommendation rule DB 150.
- the functional unit block of the personal information analysis system 100 shown in FIG. 1 is realized by the computer 700 having the hardware configuration shown in FIG.
- the means for realizing each unit included in the computer 700 is not limited to the above.
- the computer 700 may be realized by one physically coupled device, or may be realized by two or more physically separated devices connected by wire or wirelessly and by a plurality of these devices. .
- the recording medium 707 in which the above-described program code is recorded may be supplied to the computer 700, and the CPU 701 may read and execute the program code stored in the recording medium 707.
- the CPU 701 may store the code of the program stored in the recording medium 707 in the storage unit 702, the storage device 703, or both. That is, the present embodiment includes an embodiment of a recording medium 707 that stores a program (software) executed by the computer 700 (CPU 701) temporarily or non-temporarily.
- FIG. 10 is a flowchart showing the operation of the anonymized feedback information generation unit 110 of this embodiment. Note that the processing according to this flowchart may be executed based on the above-described program control by the CPU. Further, the step name of the process is described by a symbol as in S601.
- the anonymized feedback information generation unit 110 acquires an information recommendation rule from the information recommendation rule DB 150 (S601).
- the anonymized feedback information generation unit 110 analyzes the behavior information (personal information), reflects it in the acquired information recommendation rule, and generates an analysis reflection information recommendation rule (S602).
- the anonymized feedback information generation unit 110 extracts the difference between the generated analysis reflection information recommendation rule and the acquired information recommendation rule before update, and generates feedback information (S603).
- the anonymized feedback information generation unit 110 anonymizes the generated feedback information to generate anonymized feedback information (S604).
- the anonymization feedback information generation unit 110 transmits the generated anonymization feedback information to the information recommendation rule update unit 140 (S605). For example, when the anonymization feedback information generation unit 110 is requested by the information recommendation rule update unit 140 for anonymization feedback information, the anonymization feedback information generation unit 110 transmits the anonymization feedback information in response to the request. Note that the anonymized feedback information generation unit 110 may transmit the anonymized feedback information at a predetermined time or a predetermined time interval.
- FIG. 11 is a flowchart showing the operation of the information recommendation rule update unit 140 of this embodiment. Note that the processing according to this flowchart may be executed based on the above-described program control by the CPU.
- the information recommendation rule update unit 140 receives anonymized feedback information from the anonymized feedback information generation unit 110 (S611). For example, the information recommendation rule update unit 140 requests the anonymized feedback information generation unit 110 for anonymized feedback information, and receives the anonymized feedback information transmitted as a response thereto. Note that the information recommendation rule update unit 140 may passively receive anonymization feedback information from the anonymization feedback information generation unit 110.
- the information recommendation rule update unit 140 updates the information recommendation rule stored in the information recommendation rule DB 150 using the received anonymized feedback information (S612).
- the effect of the present embodiment described above is that when the personal information is transmitted from the user terminal to the server, the anonymity of the personal information can be guaranteed on the user terminal side.
- the anonymized feedback information generation unit 110 generates anonymized feedback information
- the information recommendation rule update unit 140 updates the information recommendation rule based on the anonymized feedback information.
- FIG. 12 is a block diagram showing a configuration of an information recommendation system 200 according to the second embodiment of the present invention.
- the information recommendation system 200 in this embodiment includes a plurality of user terminals 202 (only one is shown as a representative) and an information distribution server 203.
- the user terminal 202 and the information distribution server 203 are connected via a network (not shown).
- the user terminal 202 includes an anonymized feedback information generation unit 210, an information recommendation rule DB 252, a behavior information DB 260, an anonymization feedback information transmission unit 271, an information recommendation rule reception unit 272, a recommendation information reception unit 273, an information recommendation unit 276, and a user interface. 277 and a behavior information collection unit 278.
- the anonymized feedback information generation unit 210 generates feedback information using the behavior information stored in the behavior information DB 260 and the information recommendation rules stored in the information recommendation rule DB 252. Further, the anonymized feedback information generation unit 210 anonymizes the generated feedback information to generate anonymized feedback information and outputs it.
- the information recommendation rule DB 252 stores recommended information rules received from the information recommendation rule receiving unit 272 as shown in FIG.
- the behavior information DB 260 stores behavior information received from the behavior information collection unit 278 as shown in FIG.
- the anonymized feedback information transmitting unit 271 transmits the anonymized feedback information generated by the anonymized feedback information generating unit 210 as illustrated in FIG.
- the information recommendation rule receiving unit 272 receives the information recommendation rule from the information distribution server 203 and records it in the information recommendation rule DB 252.
- the recommendation information receiving unit 273 receives the recommendation information from the information distribution server 203 and outputs it to the information recommendation unit 276.
- the information recommendation unit 276 uses the information recommendation rule stored in the information recommendation rule DB 252 and the behavior information stored in the behavior information DB 260 to notify the user of the recommendation information received from the recommendation information reception unit 273. Determine recommended information to present. Then, the information recommendation unit 276 outputs the determined recommendation information to the user interface 277.
- the information recommendation unit 276 receives recommendation information for recommending each of “product A”, “product B”, “product C”, and “product D” from the recommendation information receiving unit 273.
- the information recommendation unit 276 determines recommendation information to be output to the user interface 277 with reference to the information recommendation rule stored in the information recommendation rule DB 252.
- the information recommendation rule DB 252 stores the information recommendation rule shown in FIG.
- the behavior information DB 260 stores the behavior information shown in FIG.
- the information recommendation unit 276 shares the behavior information “reference to product A” with the other product in the “product A” line of the information recommendation rule shown in FIG. Extract the number of occurrences. Similarly, the information recommendation unit 276 extracts the number of co-occurrence with respect to other products in the “product B” row and the “product D” row.
- the information recommendation unit 276 adds the extracted number of co-occurrence for each product, and the degree of interest of the user for each of “product A”, “product B”, “product C”, and “product D”. Are calculated as “1”, “7”, “12”, and “6”.
- the information recommendation unit 276 excludes “product A”, “product B”, and “product D” that have already been referred to by the user, selects information that recommends “product C”, and outputs it to the user interface 277. To do. For example, the information recommendation unit 276 selects all the products whose interest levels are other than “0” from the remaining products excluding the already-referenced products. Note that the information recommendation unit 276 may select a product with the highest degree of interest from the remaining products excluding already-referenced products. Further, the information recommendation unit 276 may select a product having an interest level equal to or greater than a predetermined value from the remaining products excluding the already-referenced products. In addition, the information recommendation unit 276 may select a predetermined number of products in descending order of interest from the remaining products excluding already-referenced products.
- the user interface 277 outputs the recommendation information received from the information recommendation unit 276 to the output unit of the user terminal 202 (for example, the output unit 705 shown in FIG. 9).
- the user interface 277 outputs the user behavior information acquired from the input means of the user terminal 202 (for example, the input unit 704 shown in FIG. 9) to the behavior information collection unit 278.
- the behavior information collection unit 278 records the behavior information of the user received from the user interface 277 and means (not shown) (for example, a GPS (Global Positioning System) receiver not shown) of the user terminal 202 in the behavior information DB 260.
- means for example, a GPS (Global Positioning System) receiver not shown
- the information distribution server 203 includes an information recommendation rule update unit 240, an information recommendation rule DB 253, an anonymized feedback information reception unit 281, an information recommendation rule provision unit 282, a recommendation information transmission unit 283, and a recommendation information DB 285.
- the information recommendation rule update unit 240 updates the information recommendation rule stored in the information recommendation rule DB 253 using the anonymization feedback information received from the anonymization feedback information reception unit 281.
- the information recommendation rule DB 253 stores information recommendation rules.
- the anonymized feedback information receiving unit 281 receives anonymized feedback information from the user terminal 202 and outputs it to the information recommendation rule update unit 240.
- the information recommendation rule providing unit 282 reads the information recommendation rule stored in the information recommendation rule DB 253 and transmits it to the user terminal 202. For example, when the information recommendation rule update unit 240 updates the information recommendation rule DB 253, the information recommendation rule provision unit 282 reads out the information recommendation rule and transmits it to the user terminal 202. The information recommendation rule providing unit 282 may read the information recommendation rule and transmit it to the user terminal 202 when the information recommendation rule is requested from the user terminal 202.
- the recommendation information transmission unit 283 reads the recommendation information stored in the recommendation information DB 285 and transmits it to the user terminal 202.
- the recommendation information DB 285 stores recommendation information.
- FIG. 13 is a flowchart showing an operation in which the information recommendation system 200 updates the information recommendation rule.
- the user interface 277 of the user terminal 202 outputs the user behavior information to the behavior information collection unit 278 (S621).
- the behavior information collection unit 278 records the received behavior information in the behavior information DB 260 (S622).
- the anonymized feedback information generation unit 210 generates and outputs anonymized feedback information using the information recommendation rule stored in the information recommendation rule DB 252 and the behavior information stored in the behavior information DB 260. (S623).
- the anonymized feedback information transmitting unit 271 transmits the anonymized feedback information generated by the anonymized feedback information generating unit 210 to the information distribution server 203 (S624).
- the anonymized feedback information receiving unit 281 of the information distribution server 203 receives the anonymized feedback information and outputs it to the information recommendation rule update unit 240 (S625).
- the information recommendation rule update unit 240 updates the information recommendation rule stored in the information recommendation rule DB 253 based on the received anonymized feedback information (S626).
- the information recommendation rule update unit 240 may execute this step in response to reception of anonymized feedback information from all other user terminals 202 (not shown). Further, the information recommendation rule update unit 240 may execute this step in response to reception of one or more arbitrary numbers of anonymized feedback information. Alternatively, the information recommendation rule update unit 240 may execute this step at a predetermined time or a predetermined time interval.
- the information recommendation rule providing unit 282 transmits the information recommendation rule stored in the information recommendation rule DB 253 to the user terminal 202 (S627).
- the information recommendation rule receiving unit 272 of the user terminal 202 receives the information recommendation rule and records it in the information recommendation rule DB 252. (S628).
- FIG. 14 is a flowchart showing an operation in which the information recommendation system 200 presents recommendation information to the user.
- the recommended information transmitting unit 283 of the information distribution server 203 transmits the recommended information read from the recommended information DB 285 to the user terminal 202 (S631).
- the recommendation information transmission unit 283 may execute this step at a predetermined time or a predetermined time interval.
- the recommendation information receiving unit 273 of the user terminal 202 receives the recommendation information and outputs it to the information recommendation unit 276 (S632).
- the information recommendation unit 276 uses the information recommendation rule stored in the information recommendation rule DB 252 and the behavior information stored in the behavior information DB 260, and uses the recommendation information received from the recommendation information reception unit 273. Recommendation information to be presented to the user is determined (S633).
- the information recommendation unit 276 outputs the determined recommendation information to the user interface 277 (S634).
- the user interface 277 notifies the user of the received recommendation information (S635).
- the user interface 277 notifies the user of recommendation information via the output unit 705 illustrated in FIG.
- the user interface 277 may notify the user of recommendation information by any means (not shown).
- the effect of the present embodiment described above is that information can be recommended based on the optimum information recommendation rule in addition to the effect of the first embodiment.
- the information recommendation rule providing unit 282 transmits the information recommendation rule stored in the information recommendation rule DB 253, and the information recommendation rule receiving unit 272 records the information recommendation rule in the information recommendation rule DB 252.
- the information recommendation unit 276 selects information to be recommended to the user based on the information recommendation rule stored in the information recommendation rule DB 252.
- FIG. 15 is a block diagram showing a configuration of an information recommendation system 300 according to the third embodiment of the present invention.
- the information recommendation system 300 in this embodiment includes a plurality of user terminals 302 (only one is shown as a representative), an information distribution server 203, and a personal information analysis server 304.
- the user terminal 302, the information distribution server 203, and the personal information analysis server 304 are connected to each other via a network (not shown).
- the personal information analysis server 304 is, for example, a server operated by a third party authorized by security, and the privacy information held by the personal information analysis server 304 is not leaked.
- the user terminal 302 includes an information recommendation rule DB 252, a behavior information DB 260, an information recommendation rule reception unit 272, a recommendation information reception unit 273, a behavior information transmission unit 274, an information recommendation unit 276, a user interface 277, and a behavior information collection unit 278.
- the behavior information transmission unit 274 transmits the behavior information read from the behavior information DB 260 to the personal information analysis server 304.
- the personal information analysis server 304 includes an anonymized feedback information generating unit 310, an information recommendation rule DB 350, an action information DB 360, an anonymized feedback information transmitting unit 371, an information recommendation rule receiving unit 372, and an action information receiving unit 374.
- the anonymized feedback information generation unit 310 generates feedback information using the behavior information stored in the behavior information DB 360 and the information recommendation rules stored in the information recommendation rule DB 350. Further, the anonymized feedback information generation unit 310 anonymizes the generated feedback information to generate anonymized feedback information and outputs it.
- the information recommendation rule DB 350 stores recommendation information rules received from the information recommendation rule receiving unit 372 as shown in FIG.
- the behavior information DB 360 stores the behavior information received from the behavior information receiving unit 374 as shown in FIG.
- the anonymized feedback information transmitting unit 371 transmits the anonymized feedback information generated by the anonymized feedback information generating unit 310 to the information distribution server 203.
- the information recommendation rule receiving unit 372 receives the information recommendation rule from the information distribution server 203 and records it in the behavior information DB 360.
- the behavior information receiving unit 374 records the received user behavior information in the behavior information DB 360.
- the effect of the present embodiment described above is that the load on the user terminal 302 can be reduced in addition to the effect of the second embodiment.
- the user terminal 302 does not include the anonymized feedback information generation unit 210, and the personal information analysis server 304 includes the anonymization feedback information generation unit 310.
- FIG. 16 is a block diagram showing a configuration of a personal information analysis system 400 according to the fourth embodiment of the present invention.
- the personal information analysis system 400 includes a plurality of anonymized feedback information generation units 410 (only one is shown as a representative), an information recommendation rule update unit 440, and an information recommendation rule DB 150. Including.
- FIG. 16 may be hardware components or components divided into functional units of the computer apparatus.
- the components shown in FIG. 16 will be described as components divided into functional units of the computer apparatus.
- the information recommendation rule is information indicating the evaluation of the element recommended by the recommendation information (for example, the average of the evaluation values at which each of the plurality of users has evaluated the product, and the number of users who have been evaluated).
- the anonymized feedback information generation unit 410 refers to the information recommendation rule, analyzes the personal information, and generates feedback information.
- the anonymized feedback information generation unit 410 anonymizes the generated feedback information and generates anonymized feedback information. Next, the anonymized feedback information generation unit 410 outputs the anonymized feedback information.
- FIG. 17 is a diagram illustrating an example of an evaluation value that is one of personal information.
- the evaluation value shown in FIG. 17 indicates that the larger the value, the better the user's evaluation for each product.
- the evaluation value “X” assigned to the product C in FIG. 17 indicates that it has not been evaluated (there is no evaluation value).
- the evaluation value is input by, for example, a user via an input unit (for example, input unit 704 shown in FIG. 9) of a user terminal (not shown) including the personal information analysis system 400.
- the evaluation value may be generated by an evaluation value generation unit (not shown) of the personal information analysis system 400 based on the behavior information shown in FIG. Regardless of the above example, the evaluation value need not be an integer.
- the evaluation value may be information indicating a positive evaluation (good evaluation) when the value is positive and a negative evaluation (bad evaluation) when the value is negative.
- the personal information analysis system 400 may process positive evaluation and negative evaluation separately.
- FIG. 18 is a diagram illustrating an example of the recommendation information rule.
- the information recommendation rule is, for example, an average of evaluation value differences between a certain product and another product, and the number of differences between the evaluation values (the number of users who provided the difference in evaluation values) is there.
- the correlation between “product A” and “product C” is “1.9, 10”. This indicates that the average of the difference between the evaluation values of “product A” and “product C” is “1.9”, and the number of users who evaluated both of them is “10”.
- the recommendation information rule indicates that the greater the average of the difference between the evaluation values, the greater the degree that it is better to present the recommendation information of the product corresponding to the average.
- FIG. 19 is a diagram illustrating an example of feedback information generated by the anonymized feedback information generation unit 410 by analyzing the evaluation value illustrated in FIG. 17 with reference to the information recommendation rule illustrated in FIG.
- the feedback information shown in FIG. 19 is information indicating a difference in evaluation value between products targeted by the information recommendation rule shown in FIG. 18 in the evaluation value shown in FIG.
- “X” in FIG. 19 indicates that the evaluation value difference is invalid (there is no effective evaluation value difference) (the same applies hereinafter). That is, the feedback information shown in FIG. 19 reflects the difference in evaluation value between “product A”, “product B”, “product C”, and “product D” of the evaluation values shown in FIG.
- the information recommendation rule shown in FIG. 18 is updated. It should be noted that the evaluation value “product E” shown in FIG. 17 is not reflected in the feedback information shown in FIG. 19 because there is no element corresponding to the information recommendation rule shown in FIG.
- FIG. 20 is a diagram illustrating an example of the anonymized feedback information when the anonymized feedback information generation unit 410 anonymizes the feedback information illustrated in FIG. 19.
- the difference between the evaluation values of “product B” with respect to “product A” is “0” to “0”.
- the difference in the evaluation value of “product A” with respect to “product B” is changed from “ ⁇ 1” to “0”.
- the difference in evaluation value of “product D” with respect to “product A” changes from “0” to “1”
- the difference in evaluation value of “product A” with respect to “product D” changes from “0” to “ ⁇ 1”. Is changing.
- FIG. 21 is a diagram illustrating an example of anonymized feedback information of a user different from the user corresponding to the anonymized feedback information illustrated in FIG.
- FIG. 22 is a diagram showing an information recommendation rule updated by synthesizing the anonymized feedback information shown in FIGS. 20 and 21 with the information recommendation rule shown in FIG.
- the difference in evaluation values between “product A”, “product B”, “product C”, and “product D” in the anonymized feedback information shown in FIGS. This is reflected in 18 information recommendation rules.
- the number of users who have provided the difference in evaluation value is updated from “10” to “12”.
- each of the anonymization feedback information generation part 410 and the information recommendation rule update part 440 shown in FIG. 16 may be processed in each of the different computers 700.
- FIG. 23 is a flowchart showing the operation of the anonymized feedback information generation unit 410 of this embodiment. Note that the processing according to this flowchart may be executed based on the above-described program control by the CPU.
- the anonymized feedback information generation unit 410 acquires an information recommendation rule from the information recommendation rule DB 150 (S641).
- the anonymized feedback information generation unit 410 analyzes the evaluation value with reference to the information recommendation rule, and generates feedback information (S643).
- the anonymized feedback information generation unit 410 anonymizes the generated feedback information to generate anonymized feedback information (S644).
- the anonymized feedback information generation unit 410 transmits the generated anonymized feedback information to the information recommendation rule update unit 440 (S645). For example, when the anonymization feedback information generation unit 410 is requested by the information recommendation rule update unit 440 for anonymization feedback information, the anonymization feedback information generation unit 410 transmits the anonymization feedback information in response to the request. Note that the anonymized feedback information generation unit 410 may transmit the anonymized feedback information at a predetermined time or at a predetermined time interval.
- the operation of the information recommendation rule update unit 440 is substantially the same as the operation of the information recommendation rule update unit 140 shown in FIG.
- the effects of the present embodiment described above can guarantee the anonymity of personal information on the user terminal side when transmitting personal information from the user terminal to the server. It is a point to become.
- the anonymized feedback information generation unit 410 generates anonymized feedback information
- the information recommendation rule update unit 440 updates the information recommendation rule based on the anonymized feedback information.
- FIG. 24 is a block diagram showing a configuration of an information recommendation system 500 according to the fifth embodiment of the present invention.
- the information recommendation system 500 in this embodiment includes a plurality of user terminals 502 (only one is shown as a representative) and an information distribution server 503.
- the user terminal 502 and the information distribution server 503 are connected via a network (not shown).
- the user terminal 502 includes an anonymized feedback information generation unit 510, an information recommendation rule DB 252, an evaluation value DB 560, an anonymization feedback information transmission unit 271, an information recommendation rule reception unit 272, a recommendation information reception unit 273, an information recommendation unit 576, and a user interface. 277 and an evaluation value collection unit 578.
- the anonymized feedback information generation unit 510 generates feedback information by using the evaluation value stored in the evaluation value DB 560 and the information recommendation rule stored in the information recommendation rule DB 252.
- the anonymized feedback information generation unit 510 anonymizes the generated feedback information to generate anonymized feedback information and outputs it.
- the information recommendation rule DB 252 stores recommendation information rules as shown in FIG. 18 received from the information recommendation rule receiving unit 272.
- the evaluation value DB 560 stores the evaluation value as shown in FIG. 17 received from the evaluation value collection unit 578.
- the anonymized feedback information transmitting unit 271 transmits the anonymized feedback information generated by the anonymized feedback information generating unit 510 as shown in FIG. 20 to the information distribution server 503.
- the information recommendation rule receiving unit 272 receives the information recommendation rule from the information distribution server 503 and records it in the information recommendation rule DB 252.
- the recommendation information receiving unit 273 receives the recommendation information from the information distribution server 503 and outputs it to the information recommendation unit 576.
- the information recommendation unit 576 uses the information recommendation rule stored in the information recommendation rule DB 252 and the evaluation value stored in the evaluation value DB 560, and uses the recommended information received from the recommendation information receiving unit 273, as a user. Recommendation information to be presented to is determined. Then, the information recommendation unit 576 outputs the determined recommendation information to the user interface 277.
- the information recommendation unit 576 receives information recommending each of “product A”, “product B”, “product C”, and “product D” from the recommendation information receiving unit 273.
- the information recommendation unit 576 determines recommendation information to be output to the user interface 277 with reference to the information recommendation rule stored in the information recommendation rule DB 252.
- the information recommendation rule DB 252 stores the information recommendation rule shown in FIG.
- the evaluation value DB 560 stores the evaluation values shown in FIG.
- the information recommendation unit 576 sets “4” as the evaluation value of “product A” stored in the evaluation value DB 560 and “product C” with respect to the evaluation value of “product A” indicated by the information recommendation rule.
- the information recommendation unit 576 sets “5” that is the evaluation value of “product B” stored in the evaluation value DB 560 and “product C” with respect to the evaluation value of “product B” indicated by the information recommendation rule.
- the addition value “4.8” with “ ⁇ 0.2”, which is the average value of the evaluation value differences, is calculated.
- the information recommendation unit 576 corresponds to the evaluation value “4” that is the evaluation value of “product D” stored in the evaluation value DB 560 and the evaluation value of “product D” indicated by the information recommendation rule.
- the information recommendation unit 576 uses the number of users who provided the difference in evaluation values shown in FIG. 22 to calculate the weighted average of the calculated addition values (hereinafter, this weighted average value is referred to as a recommendation evaluation value). ) Is calculated.
- the information recommendation unit 576 calculates the evaluation value for recommendation of “product C” that is not evaluated (the evaluation value is “X”) in the evaluation values shown in FIG.
- the information recommendation unit 576 selects information for recommending a product based on the calculated evaluation value for recommendation and outputs it to the user interface 277. For example, the information recommendation unit 576 selects information for recommending a product corresponding to “the highest recommendation evaluation value”. Further, the information recommendation unit 576 may select all pieces of information recommending products corresponding to the “evaluation value for recommendation greater than or equal to a predetermined value”. In addition, the information recommendation unit 576 may select “recommend a predetermined number of products in descending order of recommendation evaluation values” information.
- the information recommendation unit 576 may calculate a recommendation evaluation value for a product that is not yet evaluated (has a numerical value as the evaluation value) in the evaluation values shown in FIG.
- the user interface 277 outputs the recommendation information received from the information recommendation unit 576 to the output unit of the user terminal 502 (for example, the output unit 705 shown in FIG. 9).
- the user interface 277 outputs the user evaluation value acquired from the input means of the user terminal 502 (for example, the input unit 704 shown in FIG. 9) to the evaluation value collection unit 578.
- the evaluation value collection unit 578 records the user's evaluation value received from the user interface 277 and a means not shown (for example, a means for calculating an evaluation value from behavior information not shown of the user terminal 502) in the evaluation value DB 560.
- the information distribution server 503 includes an information recommendation rule update unit 540, an information recommendation rule DB 253, an anonymized feedback information reception unit 281, an information recommendation rule provision unit 282, a recommendation information transmission unit 283, and a recommendation information DB 285.
- the information recommendation rule update unit 540 updates the information recommendation rule stored in the information recommendation rule DB 253 using the anonymization feedback information received from the anonymization feedback information reception unit 281.
- the information recommendation rule DB 253 stores information recommendation rules.
- the anonymized feedback information receiving unit 281 receives anonymized feedback information from the user terminal 502 and outputs it to the information recommendation rule update unit 540.
- the information recommendation rule providing unit 282 reads out the information recommendation rule stored in the information recommendation rule DB 253 and transmits it to the user terminal 502. For example, when the information recommendation rule update unit 540 updates the information recommendation rule DB 253, the information recommendation rule provision unit 282 reads out the information recommendation rule and transmits it to the user terminal 502. The information recommendation rule providing unit 282 may read the information recommendation rule and transmit it to the user terminal 502 when the information recommendation rule is requested from the user terminal 502.
- the recommendation information transmission unit 283 reads the recommendation information stored in the recommendation information DB 285 and transmits it to the user terminal 502.
- the recommendation information DB 285 stores the recommendation information.
- the operation of updating the information recommendation rule by the information recommendation system 500 of the present embodiment is substantially the same as the operation shown in FIG.
- the operation of presenting the recommendation information to the user by the information recommendation system 500 of the present embodiment is substantially the same as the operation illustrated in FIG.
- the effect of the present embodiment described above is that information can be recommended based on the optimum information recommendation rule in addition to the effect of the fourth embodiment.
- the information recommendation rule providing unit 282 transmits the information recommendation rule stored in the information recommendation rule DB 253, and the information recommendation rule receiving unit 272 records the information recommendation rule in the information recommendation rule DB 252.
- the information recommendation unit 576 selects information to be recommended to the user based on the information recommendation rule stored in the information recommendation rule DB 252.
- FIG. 25 is a block diagram showing a configuration of an information recommendation system 600 according to the sixth embodiment of the present invention.
- the information recommendation system 600 in this embodiment includes a plurality of user terminals 602 (only one is shown as a representative), an information distribution server 503, and a personal information analysis server 604.
- the user terminal 602, the information distribution server 503, and the personal information analysis server 604 are connected to each other via a network (not shown).
- the personal information analysis server 604 is a server operated by, for example, a third party whose security has been authenticated. The privacy information held by the personal information analysis server 604 is not leaked.
- the user terminal 602 includes an information recommendation rule DB 252, an evaluation value DB 560, an information recommendation rule reception unit 272, a recommendation information reception unit 273, an evaluation value transmission unit 574, an information recommendation unit 576, a user interface 277, and an evaluation value collection unit 578.
- Evaluation value transmission unit 574 transmits the evaluation value read from evaluation value DB 560 to personal information analysis server 604.
- the personal information analysis server 604 includes an anonymized feedback information generation unit 610, an information recommendation rule DB 650, an evaluation value DB 660, an anonymization feedback information transmission unit 671, an information recommendation rule reception unit 672, and an evaluation value reception unit 674.
- the anonymized feedback information generation unit 610 generates feedback information by using the evaluation value stored in the evaluation value DB 660 and the information recommendation rule stored in the information recommendation rule DB 650. Also, the anonymized feedback information generation unit 610 anonymizes the generated feedback information to generate anonymized feedback information and outputs it.
- the information recommendation rule DB 650 stores recommendation information rules as shown in FIG. 18 received from the information recommendation rule receiving unit 672.
- Evaluation value DB 660 stores the evaluation value as shown in FIG. 17 received from the evaluation value receiving unit 674.
- the anonymized feedback information transmitting unit 671 transmits the anonymized feedback information generated by the anonymized feedback information generating unit 610 to the information distribution server 503.
- the information recommendation rule receiving unit 672 receives the information recommendation rule from the information distribution server 503 and records it in the information recommendation rule DB 650.
- Evaluation value receiving unit 674 records the received evaluation value of the user in evaluation value DB 660.
- the effect of the present embodiment described above is that the load on the user terminal 602 can be reduced in addition to the effect of the fifth embodiment.
- the user terminal 602 does not include the anonymized feedback information generation unit 510, and the personal information analysis server 604 includes the anonymization feedback information generation unit 610.
- Each of the user terminal 202, the information distribution server 203, the user terminal 302, the personal information analysis server 304, the user terminal 502, the information distribution server 503, the user terminal 602, and the personal information analysis server 604 described above is a computer shown in FIG. 700.
- each component described in each of the above embodiments does not necessarily need to be an independent entity.
- each component may be realized as a module with a plurality of components.
- each component may be realized by a plurality of modules.
- Each component may be configured such that a certain component is a part of another component.
- Each component may be configured such that a part of a certain component overlaps a part of another component.
- each component and a module that realizes each component may be realized by hardware if necessary. Moreover, each component and the module which implement
- the program is provided by being recorded on a non-volatile computer-readable recording medium such as a magnetic disk or a semiconductor memory, and is read by the computer when the computer is started up.
- the read program causes the computer to function as a component in each of the above-described embodiments by controlling the operation of the computer.
- a plurality of operations are not limited to being executed at different timings. For example, another operation may occur during the execution of a certain operation, or the execution timing of a certain operation and another operation may partially or entirely overlap.
- each of the embodiments described above it is described that a certain operation becomes a trigger for another operation, but the description does not limit all relationships between the certain operation and other operations. For this reason, when each embodiment is implemented, the relationship between the plurality of operations can be changed within a range that does not hinder the contents.
- the specific description of each operation of each component does not limit each operation of each component. For this reason, each specific operation
- movement of each component may be changed in the range which does not cause trouble with respect to a functional, performance, and other characteristic in implementing each embodiment.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
図1は、本発明の第1の実施形態に係るパーソナル情報分析システム100の構成を示すブロック図である。
匿名化フィードバック情報生成部110は、パーソナル情報(例えば、ユーザの行動情報)と情報推薦ルールDB150が記憶している情報推薦ルールとを利用して、フィードバック情報を生成する。
図2は、パーソナル情報のひとつである行動情報の一例を示す図である。図2に示すように、その行動情報は、例えば、ユーザが商品のデータを参照したことを示す参照情報である。また、行動情報は、例えば、ユーザ端末の位置に基づくそのユーザの位置情報、そのユーザが購入した商品に関する情報である購買情報、等である。上述の例に係わらず、行動情報は、そのユーザの行動に係る、利用可能な任意の情報であってよい。
図3は、推薦情報ルールの一例を示す図である。図3に示すように、情報推薦ルールは、例えば、ある商品と他の商品との相関性を共起数で示す。図3において、例えば、「商品A」と「商品C」とのその相関性は、「10」である。これは、「商品A」のデータと「商品C」のデータとの両方を参照した(即ち、「商品A」と「商品C」とが共起した)ユーザが存在した場合が、過去に10回あったことを示す。尚、その相関性は、そのようなユーザが存在した場合の回数に替えて、「商品A」と「商品C」とが共起した場合の回数そのものであってもよい。また、その相関性は、行動情報を提供するユーザの数を母数とする共起率と、その母数の値であってもよい。
図4は、匿名化フィードバック情報生成部110が、図3に示す情報推薦ルールに対して、図2に示す行動情報を反映した場合の、分析反映情報推薦ルールの例を示す図である。
図5は、匿名化フィードバック情報生成部110が、図4に示す分析反映情報推薦ルールと図3に示す情報推薦ルールとの差分を抽出した場合の、フィードバック情報の例を示す図である。
図6は、匿名化フィードバック情報生成部110が、図5に示すフィードバック情報を匿名化した場合の、匿名化フィードバック情報の例を示す図である。
情報推薦ルール更新部140は、それらの匿名化フィードバック情報を利用して、情報推薦ルールDB150が記憶している情報推薦ルールを更新する。例えば、情報推薦ルール更新部140は、それらの匿名化フィードバック情報を、その情報推薦ルールに合成して更新する。
情報推薦ルールDB150は、推薦情報ルールを記憶する。
次に、本発明の第2の実施形態について図面を参照して詳細に説明する。以下、本実施形態の説明が不明確にならない範囲で、前述の説明と重複する内容については説明を省略する。
次に、本発明の第3の実施形態について図面を参照して詳細に説明する。以下、本実施形態の説明が不明確にならない範囲で、前述の説明と重複する内容については説明を省略する。
次に、本発明の第4の実施形態について図面を参照して詳細に説明する。以下、本実施形態の説明が不明確にならない範囲で、前述の説明と重複する内容については説明を省略する。
匿名化フィードバック情報生成部410は、パーソナル情報(例えば、評価値)と情報推薦ルールDB150が記憶している情報推薦ルールとを利用して、フィードバック情報を生成する。
図17は、パーソナル情報のひとつである評価値の一例を示す図である。例えば、図17に示す評価値は、その値が大きいほど、商品のそれぞれに対するユーザの評価がよりよいことを示す。尚、図17において商品Cに付与されている評価値の「X」は、未評価(評価値が無いこと)を示している。評価値は、例えば、ユーザにより、パーソナル情報分析システム400を含むユーザ端末(不図示)の入力手段(例えば、図9に示す入力部704)を介して、入力される。また、評価値は、図2に示す行動情報に基づいて、パーソナル情報分析システム400の評価値生成手段(不図示)が生成するようにしてもよい。上述の例に係わらず、評価値は、整数である必要はない。
図18は、推薦情報ルールの一例を示す図である。図18に示すように、情報推薦ルールは、例えば、ある商品と他の商品との評価値の差の平均、及びそれらの評価値の差の数(評価値の差を提供したユーザ数)である。図18において、例えば、「商品A」と「商品C」との相関性は、「1.9、10」である。これは、「商品A」と「商品C」との評価値の差の平均が「1.9」で、それらの両方を評価したユーザの数が「10」であったことを示す。
図19は、匿名化フィードバック情報生成部410が、図18に示す情報推薦ルールを参照し、図17に示す評価値を分析して生成したフィードバック情報の一例を示す図である。
図20は、匿名化フィードバック情報生成部410が、図19に示すフィードバック情報を匿名化した場合の、匿名化フィードバック情報の例を示す図である。
情報推薦ルール更新部440は、それらの匿名化フィードバック情報を利用して、情報推薦ルールDB150が記憶している情報推薦ルールを更新する。例えば、情報推薦ルール更新部440は、それらの匿名化フィードバック情報を、その情報推薦ルールに合成して更新する。
情報推薦ルールDB150は、その推薦情報ルールを記憶する。
次に、本発明の第5の実施形態について図面を参照して詳細に説明する。以下、本実施形態の説明が不明確にならない範囲で、前述の説明と重複する内容については説明を省略する。
次に、本発明の第6の実施形態について図面を参照して詳細に説明する。以下、本実施形態の説明が不明確にならない範囲で、前述の説明と重複する内容については説明を省略する。
110 匿名化フィードバック情報生成部
140 情報推薦ルール更新部
150 情報推薦ルールDB
200 情報推薦システム
202 ユーザ端末
203 情報配信サーバ
210 匿名化フィードバック情報生成部
240 情報推薦ルール更新部
252 情報推薦ルールDB
253 情報推薦ルールDB
260 行動情報DB
271 匿名化フィードバック情報送信部
272 情報推薦ルール受信部
273 推薦情報受信部
274 行動情報送信部
276 情報推薦部
277 ユーザインタフェース
278 行動情報収集部
281 匿名化フィードバック情報受信部
282 情報推薦ルール提供部
283 推薦情報送信部
285 推薦情報DB
300 情報推薦システム
302 ユーザ端末
304 パーソナル情報分析サーバ
310 匿名化フィードバック情報生成部
350 情報推薦ルールDB
360 行動情報DB
371 匿名化フィードバック情報送信部
372 情報推薦ルール受信部
374 行動情報受信部
400 パーソナル情報分析システム
410 匿名化フィードバック情報生成部
440 情報推薦ルール更新部
500 情報推薦システム
502 ユーザ端末
503 情報配信サーバ
510 匿名化フィードバック情報生成部
540 情報推薦ルール更新部
560 評価値DB
574 評価値送信部
576 情報推薦部
578 評価値収集部
600 情報推薦システム
602 ユーザ端末
604 パーソナル情報分析サーバ
610 匿名化フィードバック情報生成部
650 情報推薦ルールDB
660 評価値DB
671 匿名化フィードバック情報送信部
672 情報推薦ルール受信部
674 評価値受信部
700 コンピュータ
701 CPU
702 記憶部
703 記憶装置
704 入力部
705 出力部
706 通信部
707 記録媒体
Claims (16)
- ユーザに提示する推薦情報について、前記推薦情報のそれぞれの推薦優先度を示す情報推薦ルールを記憶する情報推薦ルール記憶手段と、
前記ユーザのパーソナル情報と前記情報推薦ルールとを利用して、前記情報推薦ルールに対して前記ユーザのパーソナル情報を更新するための情報であるフィードバック情報を生成し、前記フィードバック情報を匿名化して匿名化フィードバック情報を生成し、出力する匿名化フィードバック情報生成手段と、
前記匿名化フィードバック情報を利用して、前記情報推薦ルールを更新する情報推薦ルール更新手段と、を含む
パーソナル情報分析システム。 - 前記パーソナル情報は、前記ユーザの行動情報であって、
前記匿名化フィードバック情報生成手段は、前記行動情報を分析して前記情報推薦ルールに反映し、反映前の前記情報推薦ルールに対する差分を抽出して、前記フィードバック情報を生成する
ことを特徴とする請求項1記載のパーソナル情報分析システム。 - 前記情報推薦ルールは前記推薦情報で推薦される要素同士の相関性を示す情報である
ことを特徴とする請求項1または2記載のパーソナル情報分析システム。 - 前記パーソナル情報は、前記ユーザの評価値であって、
前記匿名化フィードバック情報生成手段は、前記評価値間の差分に基づいて、前記フィードバック情報を生成する
ことを特徴とする請求項1記載のパーソナル情報分析システム。 - 前記情報推薦ルールは前記推薦情報で推薦される要素の評価値平均と評価数を示す情報である
ことを特徴とする請求項1または4記載のパーソナル情報分析システム。 - 前記情報推薦ルール更新手段は、複数の前記フィードバック情報を利用して前記情報推薦ルールを更新する
ことを特徴とする請求項1乃至5のいずれか1項に記載のパーソナル情報分析システム。 - 前記匿名化フィードバック情報生成手段は、前記フィードバック情報に誤差を与えて匿名化フィードバック情報を生成する
ことを特徴とする請求項1乃至6のいずれか1項に記載のパーソナル情報分析システム。 - 前記匿名化フィードバック情報生成手段は、前記フィードバック情報に含まれる個々の値を入れ替えて、匿名化フィードバック情報を生成する
ことを特徴とする請求項1乃至6のいずれか1項に記載のパーソナル情報分析システム。 - 請求項1乃至8のいずれか1項に記載の匿名化フィードバック情報生成手段を含む端末装置と、
請求項1乃至8のいずれか1項に記載の前記情報推薦ルール更新手段及び前記情報推薦ルール記憶手段を含む情報配信サーバと、を含む
パーソナル情報分析システム。 - 複数の端末装置から前記端末装置のパーソナル情報を取得する手段と、
請求項1乃至8のいずれか1項に記載の前記匿名化フィードバック情報生成手段と、を含むパーソナル情報分析サーバと、
請求項1乃至8のいずれか1項に記載の前記情報推薦ルール更新手段及び前記情報推薦ルール記憶手段を含む情報配信サーバと、を含む
パーソナル情報分析システム。 - 第1のコンピュータが、
ユーザに提示する推薦情報について、前記推薦情報のそれぞれの推薦優先度を示す情報推薦ルールと、前記ユーザのパーソナル情報とを利用して、前記情報推薦ルールに対して前記ユーザのパーソナル情報を更新するための情報であるフィードバック情報を生成し、
前記フィードバック情報を匿名化して匿名化フィードバック情報を生成し、出力し、
第2のコンピュータが、
前記匿名化フィードバック情報を利用して、前記情報推薦ルールを更新する
パーソナル情報分析方法。 - 第1のコンピュータが、
ユーザに提示する推薦情報について、前記推薦情報のそれぞれの推薦優先度を示す情報推薦ルールと、前記ユーザのパーソナル情報とを利用して、前記情報推薦ルールに対して前記ユーザのパーソナル情報を更新するための情報であるフィードバック情報を生成し、
前記フィードバック情報を匿名化して匿名化フィードバック情報を生成し、
前記匿名化フィードバック情報を利用して、前記情報推薦ルールを更新する第2のコンピュータに出力する
パーソナル情報分析方法。 - ユーザに提示する推薦情報について、前記推薦情報のそれぞれの推薦優先度を示す情報推薦ルールと、前記ユーザのパーソナル情報とを利用して、前記情報推薦ルールに対して前記ユーザのパーソナル情報を更新するための情報であるフィードバック情報を生成する処理と、
前記フィードバック情報を匿名化して匿名化フィードバック情報を生成する処理と、
前記匿名化フィードバック情報を利用して、前記情報推薦ルールを更新する第2のコンピュータに出力する処理と、を第1のコンピュータに実行させる
プログラムを記録したコンピュータ読み取り可能な非一時的記録媒体。 - ユーザに提示する推薦情報について、前記推薦情報のそれぞれの推薦優先度を示す情報推薦ルールと、前記ユーザのパーソナル情報とを利用して生成された、前記情報推薦ルールに対して前記ユーザのパーソナル情報を更新するための情報であるフィードバック情報が匿名化された匿名化フィードバック情報を利用して、前記情報推薦ルールを更新する処理をコンピュータに実行させる
プログラムを記録したコンピュータ読み取り可能な非一時的記録媒体。 - ユーザのパーソナル情報と前記ユーザに提示する推薦情報のそれぞれの推薦優先度を示す情報推薦ルールとを利用して、前記情報推薦ルールに対して前記ユーザのパーソナル情報を更新するための情報であるフィードバック情報を生成し、前記フィードバック情報を匿名化して匿名化フィードバック情報を生成する手段と、
前記匿名化フィードバック情報を、前記匿名化フィードバック情報を利用して前記情報推薦ルールを更新する情報推薦ルール更新手段に出力する手段と、を含む
端末装置。 - ユーザに提示する推薦情報について、前記推薦情報のそれぞれの推薦優先度を示す情報推薦ルールを記憶する情報推薦ルール記憶手段と、
前記ユーザのパーソナル情報と前記情報推薦ルールとを利用して生成された、前記情報推薦ルールに対して前記ユーザのパーソナル情報を更新するための情報であるフィードバック情報が、匿名化された匿名化フィードバック情報を利用して、前記情報推薦ルールを更新する情報推薦ルール更新手段と、を含む
情報配信サーバ。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP13853377.3A EP2919128A4 (en) | 2012-11-12 | 2013-11-08 | INFORMATION PROCESSING SYSTEM WITH ANALYSIS OF PERSONAL INFORMATION AND METHOD FOR ANALYZING PERSONAL INFORMATION |
US14/440,901 US20150286842A1 (en) | 2012-11-12 | 2013-11-08 | Information processing system that analyzes personal information, and method for analyzing personal information |
JP2014545581A JPWO2014073214A1 (ja) | 2012-11-12 | 2013-11-08 | パーソナル情報を分析する情報処理システム及びパーソナル情報分析方法 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2012248526 | 2012-11-12 | ||
JP2012-248526 | 2012-11-12 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014073214A1 true WO2014073214A1 (ja) | 2014-05-15 |
Family
ID=50684339
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2013/006594 WO2014073214A1 (ja) | 2012-11-12 | 2013-11-08 | パーソナル情報を分析する情報処理システム及びパーソナル情報分析方法 |
Country Status (4)
Country | Link |
---|---|
US (1) | US20150286842A1 (ja) |
EP (1) | EP2919128A4 (ja) |
JP (1) | JPWO2014073214A1 (ja) |
WO (1) | WO2014073214A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114365527A (zh) * | 2019-09-06 | 2022-04-15 | 三星电子株式会社 | 用于无线通信系统中的网络自动化的装置和方法 |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106649415B (zh) * | 2015-11-03 | 2019-12-20 | 广州市动景计算机科技有限公司 | 客户端数据检查更新方法及装置 |
US10932004B2 (en) * | 2017-01-24 | 2021-02-23 | Adobe Inc. | Recommending content based on group collaboration |
US11562143B2 (en) | 2017-06-30 | 2023-01-24 | Accenture Global Solutions Limited | Artificial intelligence (AI) based document processor |
US11003796B2 (en) * | 2017-06-30 | 2021-05-11 | Accenture Global Solutions Limited | Artificial intelligence based document processor |
ES2913424T3 (es) * | 2017-09-18 | 2022-06-02 | Huawei Tech Co Ltd | Procedimiento de recomendación y terminal |
US10521608B2 (en) * | 2018-01-09 | 2019-12-31 | Accenture Global Solutions Limited | Automated secure identification of personal information |
US11126736B2 (en) * | 2018-03-12 | 2021-09-21 | Microsoft Technology Licensing, Llc | Protecting storage by detecting unrecommended access |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007043322A (ja) | 2005-08-01 | 2007-02-15 | Canon Inc | 撮像装置及びその制御方法及びプログラム及び記憶媒体 |
JP2010166228A (ja) | 2009-01-14 | 2010-07-29 | Nec Corp | 分散型秘匿化データ統合装置、分散型秘匿化データ統合方法および分散型秘匿化データ統合用プログラム |
JP2011039909A (ja) * | 2009-08-17 | 2011-02-24 | Albert:Kk | 提示情報の最適化方法及びシステム |
JP2012118878A (ja) * | 2010-12-02 | 2012-06-21 | Ntt Docomo Inc | リコメンドシステム及びリコメンド方法 |
JP2012155409A (ja) * | 2011-01-24 | 2012-08-16 | Ntt Docomo Inc | 評価値推定システム及び評価値推定方法 |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020162017A1 (en) * | 2000-07-14 | 2002-10-31 | Stephen Sorkin | System and method for analyzing logfiles |
US7949883B2 (en) * | 2004-06-08 | 2011-05-24 | Hrl Laboratories, Llc | Cryptographic CPU architecture with random instruction masking to thwart differential power analysis |
GB2430771A (en) * | 2005-09-30 | 2007-04-04 | Motorola Inc | Content access rights management |
US20070172058A1 (en) * | 2006-01-25 | 2007-07-26 | Tomokazu Sada | Data transmitting apparatus and data receiving apparatus |
US20110178943A1 (en) * | 2009-12-17 | 2011-07-21 | New Jersey Institute Of Technology | Systems and Methods For Anonymity Protection |
US8849734B2 (en) * | 2010-06-29 | 2014-09-30 | Mcafee Inc. | System, method, and computer program product for updating an algorithm |
JP5593245B2 (ja) * | 2011-01-31 | 2014-09-17 | インターナショナル・ビジネス・マシーンズ・コーポレーション | 移動物に関連するトレース・データの開示を制御する方法、並びにそのコンピュータ及びコンピュータ・プログラム |
FR2973906B1 (fr) * | 2011-04-05 | 2015-07-31 | Alcatel Lucent | Procede de parametrage de regles de diffusion de donnees personnelles |
-
2013
- 2013-11-08 EP EP13853377.3A patent/EP2919128A4/en not_active Withdrawn
- 2013-11-08 WO PCT/JP2013/006594 patent/WO2014073214A1/ja active Application Filing
- 2013-11-08 JP JP2014545581A patent/JPWO2014073214A1/ja active Pending
- 2013-11-08 US US14/440,901 patent/US20150286842A1/en not_active Abandoned
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007043322A (ja) | 2005-08-01 | 2007-02-15 | Canon Inc | 撮像装置及びその制御方法及びプログラム及び記憶媒体 |
JP2010166228A (ja) | 2009-01-14 | 2010-07-29 | Nec Corp | 分散型秘匿化データ統合装置、分散型秘匿化データ統合方法および分散型秘匿化データ統合用プログラム |
JP2011039909A (ja) * | 2009-08-17 | 2011-02-24 | Albert:Kk | 提示情報の最適化方法及びシステム |
JP2012118878A (ja) * | 2010-12-02 | 2012-06-21 | Ntt Docomo Inc | リコメンドシステム及びリコメンド方法 |
JP2012155409A (ja) * | 2011-01-24 | 2012-08-16 | Ntt Docomo Inc | 評価値推定システム及び評価値推定方法 |
Non-Patent Citations (3)
Title |
---|
D. LEMIRE; A. MACLACHLAN: "Slope One Predictors for Online Rating-Based Collaborative Filtering", SIAM DATA MINING (SDM'05), NEWPORT BEACH, 21 April 2005 (2005-04-21) |
See also references of EP2919128A4 |
SHOGO HACHIYA ET AL.: "Information Recommendation Modeling Method for Privacy Preservation", IEICE TECHNICAL REPORT, vol. 109, no. 448, 25 February 2010 (2010-02-25), pages 517 - 522, XP008179237 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114365527A (zh) * | 2019-09-06 | 2022-04-15 | 三星电子株式会社 | 用于无线通信系统中的网络自动化的装置和方法 |
Also Published As
Publication number | Publication date |
---|---|
EP2919128A4 (en) | 2016-07-20 |
JPWO2014073214A1 (ja) | 2016-09-08 |
EP2919128A1 (en) | 2015-09-16 |
US20150286842A1 (en) | 2015-10-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2014073214A1 (ja) | パーソナル情報を分析する情報処理システム及びパーソナル情報分析方法 | |
US10862843B2 (en) | Computerized system and method for modifying a message to apply security features to the message's content | |
AU2019201885B2 (en) | Client-side integration framework of services | |
US11228653B2 (en) | Terminal, cloud apparatus, driving method of terminal, method for processing cooperative data, computer readable recording medium | |
KR101247859B1 (ko) | 컴퓨팅 디바이스들 간의 동적 콘텐츠 프리퍼런스 및 동작 공유 | |
CN110771126B (zh) | 用于用户设备事件的匹配与归因的系统 | |
KR20180043392A (ko) | 어플리케이션들을 추천하는 방법 | |
US11100568B2 (en) | System and method for creating and analyzing a low-dimensional representation of webpage sequences | |
US20150215383A1 (en) | Methods for Exchanging Data Amongst Mobile Applications Using Superlinks | |
KR102271786B1 (ko) | 개인 데몬의 훈련 가속화 | |
US20130304686A1 (en) | Methods and systems for personalizing user experience based on attitude prediction | |
CN106255970B (zh) | 本地个人守护程序 | |
WO2019231627A2 (en) | Privatized apriori algorithm for sequential data discovery | |
JP7252748B2 (ja) | 情報推薦方法及びコンピュータシステム | |
US10248802B2 (en) | Digital rights management using geographic and temporal traits | |
EP3133502A1 (en) | Terminal device, cloud device, method for driving terminal device, method for cooperatively processing data and computer readable recording medium | |
CN113396411A (zh) | 用于增强的主机分类的系统和方法 | |
JP6698707B2 (ja) | バイナリ併合装置、その方法及び該コンピュータプログラム | |
US10049231B2 (en) | Method and system for obfuscating the properties of a web browser | |
JP2008176782A (ja) | 関心事を反映して抽出した情報提供方法及びシステム | |
KR20140113879A (ko) | 광고 메커니즘을 구비한 정보 전달 시스템 및 그 작동 방법 | |
JP6983705B2 (ja) | 端末装置、端末制御方法および端末制御プログラム | |
WO2014136422A1 (ja) | 匿名化処理を行う情報処理装置及び匿名化方法 | |
CN114945918A (zh) | 隐私保护的虚拟电子邮件系统 | |
US20200257825A1 (en) | Customized display of filtered social media content using a private dislike button |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13853377 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14440901 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2014545581 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REEP | Request for entry into the european phase |
Ref document number: 2013853377 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2013853377 Country of ref document: EP |