WO2023095456A1 - レコメンド装置 - Google Patents

レコメンド装置 Download PDF

Info

Publication number
WO2023095456A1
WO2023095456A1 PCT/JP2022/037344 JP2022037344W WO2023095456A1 WO 2023095456 A1 WO2023095456 A1 WO 2023095456A1 JP 2022037344 W JP2022037344 W JP 2022037344W WO 2023095456 A1 WO2023095456 A1 WO 2023095456A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
line
content
sight
trajectory
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2022/037344
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
邦宏 相場
素平 小野
航 明石
翔 前沖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NTT Docomo Inc
Original Assignee
NTT Docomo Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NTT Docomo Inc filed Critical NTT Docomo Inc
Priority to JP2023563538A priority Critical patent/JP7634111B2/ja
Priority to US18/712,778 priority patent/US12481359B2/en
Publication of WO2023095456A1 publication Critical patent/WO2023095456A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Recommending goods or services
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G06F3/013—Eye tracking input arrangements
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements

Definitions

  • One aspect of the present disclosure relates to a recommendation device that recommends content to users.
  • a recommendation system that recommends products, etc. according to the user to the user is known.
  • Such a recommendation system extracts information related to the user's interest using, for example, a log of user clicks or page transitions related to product selection. Then, the recommendation system sorts products using information about the user's interests, and recommends the sorted products to the user.
  • Patent Literature 1 an image including a face is presented to a user, the bias of the user's line of sight in the image is calculated based on line-of-sight information regarding the movement of the user's line of sight, and recommended information determined based on the line-of-sight bias. is disclosed to the user.
  • Logs of user clicks or page transitions related to product selection may be affected by erroneous operations. Therefore, it may not be possible to recommend content that fully reflects the user's preferences based on these pieces of information.
  • the algorithm that makes recommendations simply using the movement of the line of sight as described in Patent Document 1, when the movement of the line of sight differs for each product, such as online shopping, what is the user's gaze focused on? It is difficult to discriminate whether or not the content has been used, and as a result, it may not be possible to appropriately discriminate the user's taste, and it may not be possible to recommend content that fully reflects the user's taste.
  • one aspect of the present disclosure aims to provide a recommendation device capable of recommending content that matches the user's taste.
  • a recommendation device includes an acquisition unit that acquires a line-of-sight image that visualizes the line-of-sight trajectory of a user who browses content displayed on a user terminal, and extracts a feature vector that indicates the feature amount of the line-of-sight image. a generation unit that generates a correspondence relationship between the content and the trajectory of the line of sight of the user as a user context based on the feature vector; A calculation unit and an output unit that outputs a recommendation result of content selected based on the score.
  • the line-of-sight image is converted into a feature quantity, thereby extracting a feature vector indicating the feature quantity of the line-of-sight trajectory of the user browsing the content. Then, based on the feature vector, a correspondence relationship between the content and the trajectory of the user's line of sight is generated as a user context. Furthermore, the score of each content is calculated based on such user context, and a recommendation result is output. Instead of determining what the user was gazing at (for example, what information the user was gazing at, such as content information such as price or product details), the trajectory of the line of sight is visualized and each content is identified.
  • a recommendation device capable of appropriately grasping the preferences of each user and recommending content that matches the preferences of the users.
  • FIG. 10 is a diagram illustrating generation of user context; It is a figure explaining the outline of the recommendation based on a line-of-sight vector.
  • 4 is a flowchart showing processing executed by a recommendation device; It is a figure which shows the hardware constitutions of a recommendation apparatus.
  • FIG. 1 is a diagram showing the functional configuration of the recommendation device 10 according to this embodiment.
  • the recommendation device 10 is a device that recommends content according to each user's preference to the user (that is, delivers the content to the user's user terminal 30).
  • a content is, for example, any tangible or intangible that is traded for a fee or for free, and is a concept that includes the provision of goods and services.
  • the recommendation device 10 learns the user's preference based on a line-of-sight image obtained by imaging the trajectory of the line of sight of the user browsing the content displayed on the user terminal 30 .
  • the recommendation device 10 selects content to be recommended to the user so that content that meets the user's taste is targeted for distribution.
  • the recommendation system 1 includes a recommendation device 10 and a user terminal 30.
  • the user terminal 30 is a communication terminal having a communication function, such as a smart phone, a tablet terminal, or a personal computer.
  • the user terminal 30 is communicably connected to the recommendation device 10 via a network.
  • the user terminal 30 has a function of displaying various screens, a function of detecting the trajectory of the user's line of sight, a function of transmitting various types of information to the recommendation device 10, and a function of receiving distribution of recommended content from the recommendation device 10. , and the ability to display the content.
  • the recommendation system 1 actually includes a plurality of user terminals 30 for each user.
  • the user terminal 30 displays a product detail screen for browsing products that are content.
  • the user terminal 30 detects the trajectory of the line of sight of the user browsing the content displayed on the user terminal 30 .
  • a method for detecting the trajectory of the line of sight is not limited.
  • the user terminal 30 may detect the trajectory of the user's viewpoint using the method of corneal reflection (PCCR).
  • PCCR corneal reflection
  • the user terminal 30 may include an infrared emitting device and an infrared camera as hardware configuration.
  • the user terminal 30 transmits information indicating the detected trajectory of the user's line of sight to the recommendation device 10 . Further, the user terminal 30 may transmit information indicating the user's purchase history regarding the content displayed on the user terminal 30 to the recommendation device 10 . Furthermore, the user terminal 30 may transmit user demographic data to the recommendation device 10 . Examples of demographic data include, but are not limited to, age, gender, place of residence, family structure, and occupation. Demographic data can be represented, for example, as numerical values or assigned codes (gender code, residence code, family structure code, occupation code, etc.). Furthermore, the user terminal 30 may transmit the user's content metadata to the recommendation device 10 .
  • the content metadata is metadata of the content that the user browsed last (immediately before). Content metadata includes, for example, class, genre, presence/absence of campaign, etc., but is not limited to these. Content metadata can be represented, for example, as a numerical value or assigned code (price range code, genre code, campaign code, etc.).
  • FIG. 2 is a diagram showing an example of a product detail screen G for browsing products.
  • the product detail screen G is, for example, a web page for online shopping.
  • the product detail screen G may be provided to the user terminal 30 by, for example, the recommendation device 10, or may be provided to the user terminal 30 by another external system.
  • Various types of information about the content are displayed on the product detail screen G.
  • FIG. In one example, the product detail screen G displays a product image C1, a product price C2, a detailed text C3, and additional information C4 relating to a hamburger.
  • the user terminal 30 detects the trajectory of the user's line of sight, for example, each time the product detail screen G is accessed. Also, the user terminal 30 may measure the browsing time of the content. The browsing time of the content may be the display time of the product detail screen G, for example.
  • FIG. 3 is a diagram illustrating an example of the line-of-sight trajectory V.
  • the trajectory V of the line of sight is the trajectory of the user's line of sight with respect to the content displayed on the product detail screen G.
  • the trajectory V of the line of sight is the trajectory of the user's line of sight with respect to the content detected when the product detail screen G is accessed for the first time.
  • the line of sight trajectory V is represented by a solid black line.
  • line-of-sight trajectory V indicates that line-of-sight moves in the order of product image C1, product price C2, detailed sentence C3, additional information C4, and detailed sentence C3.
  • the user terminal 30 transmits information indicating the detected line-of-sight trajectory V to the recommendation device 10 .
  • the information indicating the line-of-sight trajectory V has the browsing time of the content.
  • the recommendation device 10 receives information indicating the trajectory V of the line of sight.
  • the recommendation device 10 includes a storage unit 2, a line-of-sight image generation unit 11, an acquisition unit 12, an extraction unit 13, a generation unit 14, a calculation unit 15, and an output unit 16.
  • the storage unit 2 stores demographic data 21 and content metadata 22 of each user.
  • the recommendation device 10 stores the demographic data and content metadata of each user received from the user terminal 30 of each user in the storage unit 2 .
  • the recommendation device 10 may store, in the storage unit 2 , information indicating the trajectory of the line of sight received from the user terminal 30 and information indicating the user's purchase record regarding the content displayed on the user terminal 30 .
  • the line-of-sight image generation unit 11 generates a line-of-sight image that visualizes the trajectory of the user's line of sight. For example, the line-of-sight image generation unit 11 generates a line-of-sight image that visualizes the line-of-sight trajectory V based on information indicating the line-of-sight trajectory V received from the user terminal 30, for example. The line-of-sight image generation unit 11 outputs the generated line-of-sight image to the acquisition unit 12 .
  • the acquisition unit 12 acquires a line-of-sight image that is an image of the trajectory of the line of sight of the user browsing the content displayed on the user terminal 30 .
  • the acquisition unit 12 acquires a line-of-sight image in which the line-of-sight trajectory V is imaged by the line-of-sight image generation unit 11 .
  • the acquisition unit 12 acquires the browsing time of content and user demographic data. For example, the acquisition unit 12 acquires the browsing time during which the user browsed the content based on the information indicating the line-of-sight trajectory V received from the user terminal 30, for example. The acquisition unit 12 also acquires demographic data of each user stored in the storage unit 2 .
  • the extraction unit 13 extracts a feature vector (line-of-sight vector) indicating the feature amount of the line-of-sight image. For example, the extraction unit 13 generates numerical data obtained by converting the line-of-sight image into a feature quantity. Then, the extraction unit 13 extracts the first principal component as a line-of-sight vector by performing principal component analysis on the numerical data.
  • a feature vector line-of-sight vector
  • FIG. 4 is a diagram for explaining an example of a line-of-sight image converted into a feature quantity.
  • the line-of-sight image VP shown in FIG. 4 is a line-of-sight image obtained by imaging the trajectory V of the line of sight.
  • the extraction unit 13 extracts the feature amount of the line-of-sight image VP and generates two-dimensional or three-dimensional numerical data.
  • the extraction unit 13 divides the line-of-sight image VP into 6 ⁇ 6 regions, and acquires the feature amount in each divided region. Then, the extraction unit 13 generates numerical data VA in a two-dimensional array having 6 rows ⁇ 6 columns of elements corresponding to the feature amounts in each region.
  • the numerical value of each element of the numerical data VA indicates how much the user viewed which part of the content. For example, the higher the numerical value of the element of the numerical data VA, the higher the density of the line-of-sight trajectory V in the line-of-sight image VP. Also, the lower the numerical value of the element of the numerical data VA, the lower the density of the line-of-sight trajectory V in the line-of-sight image VP.
  • the numerical value of each element of the numerical data VA does not consider (determine) the position of the information on the content. More specifically, the numerical value of each element of the numerical data VA does not consider (discriminate) the positions of the product image C1, product price C2, detailed text C3, incidental information C4, etc. on the product detail screen G1.
  • FIG. 5 is a diagram illustrating extraction of a line-of-sight vector.
  • the extraction unit 13 extracts the first principal component as the line-of-sight vector by performing principal component analysis on the numerical data VA.
  • the extraction unit 13 extracts the acquired first principal component as the line-of-sight vector V t,a .
  • t is the number of trials (number of visits) and a is the content.
  • the line-of-sight vector extracted in this manner may differ for each trajectory of the user's line of sight, each visit, or each content. That is, the line-of-sight vector V t,a can be said to be the line-of-sight vector of "a certain visit to a certain content by a certain user".
  • the generation unit 14 generates the correspondence relationship between the content and the line-of-sight locus of the user as a user context based on the line-of-sight vector, which is a feature vector. For example, the generation unit 14 generates the correspondence relationship between the content and the trajectory of the user's line of sight as the user context based on the feature vector, browsing time, and demographic data.
  • FIG. 6 is a diagram illustrating generation of user context.
  • the acquisition unit 12 further acquires content metadata C t,a , demographic data U t,a , and browsing time T t,a .
  • t is the number of trials (visits), and a is the content.
  • the generation unit 14 generates the user context z t,a based on the line-of-sight vector V t,a , the content metadata C t,a , the demographic data U t,a , and the browsing time T t ,a. .
  • the line-of-sight vector V t,a has [v_1, v_2, .
  • the content metadata C t,a has [1,4,1] as elements.
  • Each element in the content metadata Ct ,a indicates a price range code, a genre code, and a campaign code, respectively.
  • the demographic data U t,a has [29,1,20] as elements.
  • Each element in demographic data U t,a indicates age, gender code, and place of residence code, respectively.
  • the viewing time T t,a has as a component [20] indicating the viewing time in seconds.
  • the generation unit 14 combines the line-of-sight vector V t,a , the content metadata C t,a , the demographic data U t,a , and the browsing time T t,a to generate the user context z t,a Generate.
  • the generation unit 14 may generate the user context z t,a based only on the line-of-sight vector V t,a .
  • the generation unit 14 generates a user context z t,a based on one or more of a line-of-sight vector V t,a , content metadata C t,a , demographic data U t,a , and viewing time T t ,a. may be generated.
  • the calculation unit 15 calculates the score of each of a plurality of contents of recommendation candidates using the user context. For example, the calculation unit 15 calculates the content score pt,a by the following equation (1) to which the contextual bandit algorithm is applied.
  • t is the number of trials (number of visits), and a is the content (corresponding to arm in the ContextualBandit algorithm).
  • ( ⁇ a ) ⁇ is a term (utilization term) whose value is updated by learning from feedback of past user behavior as to what kind of score each content should be assigned to the user context.
  • ⁇ s t,a is a term (search term) that is updated along with the update of ( ⁇ a ) ⁇ and represents the uncertainty of the score (the degree to be searched) for each content.
  • the number of ( ⁇ a ) ⁇ and the number of ⁇ s t,a exist corresponding to the number of contents.
  • the Contextual Bandit Algorithm calculates a score by performing a search without correct data, and learns the user context in the process of calculating the score.
  • the calculation unit 15 learns the user context as, for example, "a user who makes such a line-of-sight movement for this content”. Note that when the user context includes content metadata, a model is created that learns the preferences of “the user who browsed content with such characteristics just before and made such eye movement”.
  • Correct answer data may be used for the Contextual Bandit algorithm.
  • the acquisition unit 12 further acquires correct answer data indicating the user's purchase record of the content displayed on the user terminal. Then, the calculation unit 15 learns the user context zt,a using the correct answer data in calculating the score.
  • the output unit 16 outputs a recommendation result of content selected based on the score. For example, the output unit 16 selects one or a plurality of contents from a plurality of contents in descending order of the score pt ,a , and transmits the recommendation result of the selected contents to the user terminal 30 .
  • FIG. 7 is a diagram for explaining an overview of recommendations based on line-of-sight vectors.
  • the generation unit 14 combines the line-of-sight vector V t,a , the content metadata C t,a , the demographic data U t,a , and the browsing time T t,a to generate the user context z t,a Generate.
  • the calculation unit 15 calculates a score for each of a plurality of contents as recommendation candidates using the user context.
  • the calculation unit 15 also learns the user context zt,a in calculating the score using the learning model E (for example, the Contextual Bandit algorithm).
  • the output unit 16 selects one or a plurality of contents in descending order of score from a plurality of contents, and transmits the recommendation result of the selected contents to the user terminal 30 .
  • the user terminal 30 displays the received recommendation result.
  • the user terminal 30 detects the trajectory of the user's line of sight (step S1).
  • the user terminal 30 detects the trajectory V of the user's line of sight with respect to the content while the product detail screen G shown in FIG. 3 is being displayed.
  • the user terminal 30 transmits information indicating the detected line-of-sight trajectory V to the recommendation device 10 .
  • the acquisition unit 12 acquires a line-of-sight image that is an image of the trajectory of the line of sight of the user browsing the content displayed on the user terminal 30 (step S2). For example, the acquisition unit 12 acquires the line-of-sight image VP in which the line-of-sight trajectory V is imaged by the line-of-sight image generation unit 11 .
  • the acquisition unit 12 acquires the viewing time for viewing the content (step S3). For example, the acquisition unit 12 acquires the browsing time T t,a during which the user browsed the content based on the information indicating the line-of-sight trajectory V received from the user terminal 30, for example.
  • the acquisition unit 12 acquires user demographic data (step S4).
  • the acquisition unit 12 acquires user demographic data U t,a stored in the storage unit 2 .
  • the acquisition unit 12 acquires the user's content metadata (step S5).
  • the acquisition unit 12 acquires the user's content metadata Ct,a stored in the storage unit 2 .
  • the extraction unit 13 extracts a feature vector (line-of-sight vector) indicating the feature amount of the line-of-sight image (step S6). For example, the extraction unit 13 generates numerical data obtained by converting the line-of-sight image into a feature quantity. Then, the extraction unit 13 extracts the first principal component as a line-of-sight vector by performing principal component analysis on the numerical data. In one example, the extraction unit 13 generates numerical data VA obtained by converting the line-of-sight image VP into a feature quantity (see FIG. 4). Further, the extracting unit 13 extracts the first principal component as the line-of-sight vector V t,a by performing principal component analysis on the numerical data VA (see FIG. 5).
  • a feature vector line-of-sight vector
  • the generation unit 14 Based on the line-of-sight vector, which is a feature vector, the generation unit 14 generates a correspondence relationship between the content and the trajectory of the user's line of sight as a user context (step S7). For example, the generation unit 14 combines the line-of-sight vector V t,a , the content metadata C t,a , the demographic data U t,a , and the browsing time T t,a to generate the user context z t,a Generate.
  • the calculation unit 15 uses the user context to calculate the score of each of the plurality of contents that are the recommendation candidates (step S8). In one example, the calculation unit 15 calculates the score pt,a of the content using Equation (1). The calculation unit 15 also learns the user context z t ,a in the process of calculating the score pt ,a .
  • the acquisition unit 12 may further acquire correct answer data indicating the user's purchase record of the content displayed on the user terminal 30.
  • the calculation unit 15 may learn the user context using the correct answer data in calculating the score.
  • the output unit 16 outputs the recommendation result of the content selected based on the score (step S9). For example, the output unit 16 selects one or a plurality of contents from a plurality of contents in descending order of the score pt ,a , and transmits the recommendation result of the selected contents to the user terminal 30 .
  • the recommendation device 10 includes an acquisition unit 12 that acquires a line-of-sight image that is an image of the line-of-sight trajectory of a user browsing content displayed on a user terminal 30, and a feature vector that indicates the feature amount of the line-of-sight image.
  • an extraction unit 13 for extraction a generation unit 14 for generating a correspondence relationship between the content and the trajectory of the line of sight of the user as a user context based on the feature vector, and a score for each of a plurality of content of recommendation candidates using the user context.
  • an output unit 16 for outputting a recommendation result of content selected based on the score.
  • the line-of-sight image is converted into a feature quantity, thereby extracting a feature vector indicating the feature quantity of the line-of-sight trajectory of the user browsing the content. Then, based on the feature vector, a correspondence relationship between the content and the trajectory of the user's line of sight is generated as a user context. Furthermore, the score of each content is calculated based on such user context, and a recommendation result is output. Instead of determining what the user was gazing at (for example, what information the user was gazing at, such as content information such as price or product details), the trajectory of the line of sight is visualized and each content is identified. By calculating the score, it becomes possible to grasp the user's preferences abstractly on a behavioral basis.
  • the processing of the recommendation device 10 can be said to be reinforcement learning based on the line of sight trajectory.
  • Such reinforcement learning can be learned on the premise that a different line-of-sight trajectory occurs for each content, so it is easier to capture individuality than an algorithm that simply uses line-of-sight.
  • the recommendation device 10 can deal with the problem of not knowing what line of sight trajectory leads to what user's preference.
  • the acquisition unit 12 further acquires content metadata, which is meta information about the content last viewed by the user, the viewing time of the content, and demographic data of the user.
  • the generation unit 14 generates, as a user context, the correspondence relationship between the content and the trajectory of the user's line of sight, based on the feature vector, content metadata, demographic data, and browsing time.
  • User context reflects content metadata, demographic data, and viewing time in addition to feature vectors. Then, the score of each content is calculated based on such user context, and a recommendation result is output. Reflecting the user's characteristics in the recommendation results makes it easier for content that meets the user's tastes to appear in the recommendation results.
  • the acquisition unit 12 further acquires correct data indicating the user's purchase record of the content displayed on the user terminal 30 .
  • the calculation unit 15 learns the user context using the correct answer data in calculating the score. Correct data is reflected in the user context in addition to the feature vector. Then, the score of each content is calculated based on such user context, and a recommendation result is output. Reflecting the correct data in the recommendation result makes it easier for content that meets the user's taste to appear in the recommendation result.
  • the extraction unit 13 divides the line-of-sight image and the information about the content (for example, the product image C1, the product price C2, the detailed sentence C3, the incidental information C4, etc.) into regions that are associated with each other, and the feature amount in each divided region. may be obtained.
  • the acquisition unit 12 may further acquire the location of information regarding content from the user terminal 30 .
  • the generation unit 14 generates a correspondence relationship between the content and the trajectory of the line of sight of the user as a user context, based on the feature vector, the content metadata, the demographic data, the browsing time, and the position of the information about the content. good.
  • the user context reflects the position of the information about the content.
  • the calculation unit 15 may further learn the user context in which the position of the information regarding the content is reflected in the calculation of the score.
  • the user terminal 30 transmits the detected line-of-sight trajectory V to the recommendation device 10 .
  • the recommendation device 10 receives a line-of-sight image in which the line-of-sight trajectory V is imaged.
  • each functional block may be implemented using one device physically or logically coupled, or directly or indirectly using two or more physically or logically separated devices (e.g. , wired, wireless, etc.) and may be implemented using these multiple devices.
  • a functional block may be implemented by combining software in the one device or the plurality of devices.
  • Functions include judging, determining, determining, calculating, calculating, processing, deriving, examining, searching, checking, receiving, transmitting, outputting, accessing, resolving, selecting, choosing, establishing, comparing, assuming, expecting, assuming, Broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, assigning, etc.
  • a functional block (component) that performs transmission is called a transmitting unit or transmitter. In either case, as described above, the implementation method is not particularly limited.
  • the recommendation device 10 may function as a computer that performs information processing of the present disclosure.
  • FIG. 9 is a diagram illustrating an example of a hardware configuration of the recommendation device 10 according to an embodiment of the present disclosure.
  • the recommendation device 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.
  • the hardware configuration of the user terminal 30 may be the one described here.
  • the term "apparatus” can be read as a circuit, device, unit, or the like.
  • the hardware configuration of the recommendation device 10 may be configured to include one or more of each device shown in the figure, or may be configured without including some of the devices.
  • Each function in the recommendation device 10 is performed by causing the processor 1001 to perform calculations, controlling communication by the communication device 1004, controlling communication by the communication device 1004, and controlling the and by controlling at least one of reading and writing of data in the storage 1003 .
  • the processor 1001 for example, operates an operating system and controls the entire computer.
  • the processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, registers, and the like.
  • CPU central processing unit
  • each function in the recommendation device 10 described above may be implemented by the processor 1001 .
  • the processor 1001 reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 to the memory 1002, and executes various processes according to them.
  • programs program codes
  • software modules software modules
  • data etc.
  • the program a program that causes a computer to execute at least part of the operations described in the above embodiments is used.
  • each function of the recommendation device 10 may be implemented by a control program stored in the memory 1002 and running on the processor 1001 .
  • FIG. Processor 1001 may be implemented by one or more chips.
  • the program may be transmitted from a network via an electric communication line.
  • the memory 1002 is a computer-readable recording medium, and is composed of at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. may be
  • ROM Read Only Memory
  • EPROM Erasable Programmable ROM
  • EEPROM Electrical Erasable Programmable ROM
  • RAM Random Access Memory
  • the memory 1002 may also be called a register, cache, main memory (main storage device), or the like.
  • the memory 1002 can store executable programs (program code), software modules, etc. for performing information processing according to an embodiment of the present disclosure.
  • the storage 1003 is a computer-readable recording medium, for example, an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disc, a magneto-optical disc (for example, a compact disc, a digital versatile disc, a Blu-ray disk), smart card, flash memory (eg, card, stick, key drive), floppy disk, magnetic strip, and/or the like.
  • Storage 1003 may also be called an auxiliary storage device.
  • a storage medium included in the recommendation device 10 may be, for example, a database including at least one of the memory 1002 and the storage 1003, a server, or other suitable medium.
  • the communication device 1004 is hardware (transmitting/receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also called a network device, a network controller, a network card, a communication module, or the like.
  • the input device 1005 is an input device (for example, keyboard, mouse, microphone, switch, button, sensor, etc.) that receives input from the outside.
  • the output device 1006 is an output device (eg, display, speaker, LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated (for example, a touch panel).
  • Each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information.
  • the bus 1007 may be configured using a single bus, or may be configured using different buses between devices.
  • the recommendation device 10 includes hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array).
  • DSP digital signal processor
  • ASIC Application Specific Integrated Circuit
  • PLD Physical Location Deposition
  • FPGA Field Programmable Gate Array
  • processor 1001 may be implemented using at least one of these pieces of hardware.
  • Input/output information may be stored in a specific location (for example, memory) or managed using a management table. Input/output information and the like can be overwritten, updated, or appended. The output information and the like may be deleted. The entered information and the like may be transmitted to another device.
  • the determination may be made by a value represented by one bit (0 or 1), by a true/false value (Boolean: true or false), or by numerical comparison (for example, a predetermined value).
  • notification of predetermined information is not limited to being performed explicitly, but may be performed implicitly (for example, not notifying the predetermined information). good too.
  • Software whether referred to as software, firmware, middleware, microcode, hardware description language or otherwise, includes instructions, instruction sets, code, code segments, program code, programs, subprograms, and software modules. , applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, and the like.
  • software, instructions, information, etc. may be transmitted and received via a transmission medium.
  • the software uses at least one of wired technology (coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), etc.) and wireless technology (infrared, microwave, etc.) to website, Wired and/or wireless technologies are included within the definition of transmission medium when sent from a server or other remote source.
  • wired technology coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), etc.
  • wireless technology infrared, microwave, etc.
  • system and “network” used in this disclosure are used interchangeably.
  • information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values from a predetermined value, or may be expressed using other corresponding information. may be represented.
  • determining and “determining” used in this disclosure may encompass a wide variety of actions.
  • “Judgement” and “determination” are, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (eg, lookup in a table, database, or other data structure);
  • "judgment” and “determination” are used for receiving (e.g., receiving information), transmitting (e.g., transmitting information), input, output, access (accessing) (for example, accessing data in memory) may include deeming that a "judgment” or “decision” has been made.
  • judgment and “decision” are considered to be “judgment” and “decision” by resolving, selecting, choosing, establishing, comparing, etc. can contain.
  • judgment and “decision” may include considering that some action is “judgment” and “decision”.
  • judgment (decision) may be read as “assuming”, “expecting”, “considering”, or the like.
  • connection means any direct or indirect connection or coupling between two or more elements, It can include the presence of one or more intermediate elements between two elements being “connected” or “coupled.” Couplings or connections between elements may be physical, logical, or a combination thereof. For example, “connection” may be read as "access”.
  • two elements are defined using at least one of one or more wires, cables, and printed electrical connections and, as some non-limiting and non-exhaustive examples, in the radio frequency domain. , electromagnetic energy having wavelengths in the microwave and optical (both visible and invisible) regions, and the like.
  • any reference to elements using the "first,” “second,” etc. designations used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, reference to a first and second element does not imply that only two elements can be employed or that the first element must precede the second element in any way.
  • a and B are different may mean “A and B are different from each other.”
  • the term may also mean that "A and B are different from C”.
  • Terms such as “separate,” “coupled,” etc. may also be interpreted in the same manner as “different.”

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Human Computer Interaction (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
PCT/JP2022/037344 2021-11-29 2022-10-05 レコメンド装置 Ceased WO2023095456A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2023563538A JP7634111B2 (ja) 2021-11-29 2022-10-05 レコメンド装置
US18/712,778 US12481359B2 (en) 2021-11-29 2022-10-05 Recommendation device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-192950 2021-11-29
JP2021192950 2021-11-29

Publications (1)

Publication Number Publication Date
WO2023095456A1 true WO2023095456A1 (ja) 2023-06-01

Family

ID=86539239

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/037344 Ceased WO2023095456A1 (ja) 2021-11-29 2022-10-05 レコメンド装置

Country Status (3)

Country Link
US (1) US12481359B2 (https=)
JP (1) JP7634111B2 (https=)
WO (1) WO2023095456A1 (https=)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008072739A1 (ja) * 2006-12-15 2008-06-19 Visual Interactive Sensitivity Research Institute Co., Ltd. 視聴傾向管理装置、システム及びプログラム
US20190236680A1 (en) * 2018-01-29 2019-08-01 Selligent, Inc. Systems and Methods for Providing Personalized Online Content
JP2020123962A (ja) * 2016-06-30 2020-08-13 株式会社ソニー・インタラクティブエンタテインメント 注視追跡のための装置及び方法

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4947709B2 (ja) * 2007-02-23 2012-06-06 Ｋｄｄｉ株式会社 コンテンツ配信システム
US20130124344A1 (en) * 2011-11-14 2013-05-16 Venkateswarlu Kolluri Method and system for determining user likelihood to select an advertisement prior to display
JP2015046089A (ja) * 2013-08-29 2015-03-12 ソニー株式会社 情報処理装置および情報処理方法
GB2567164A (en) * 2017-10-04 2019-04-10 Continental Automotive Gmbh Display system in a vehicle
JP7253325B2 (ja) 2018-04-27 2023-04-06 株式会社 資生堂 情報処理装置、プログラム、及び、情報処理方法
JP2020091897A (ja) * 2020-02-25 2020-06-11 株式会社ドワンゴ 情報表示端末、情報送信方法、コンピュータプログラム

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008072739A1 (ja) * 2006-12-15 2008-06-19 Visual Interactive Sensitivity Research Institute Co., Ltd. 視聴傾向管理装置、システム及びプログラム
JP2020123962A (ja) * 2016-06-30 2020-08-13 株式会社ソニー・インタラクティブエンタテインメント 注視追跡のための装置及び方法
US20190236680A1 (en) * 2018-01-29 2019-08-01 Selligent, Inc. Systems and Methods for Providing Personalized Online Content

Also Published As

Publication number Publication date
US12481359B2 (en) 2025-11-25
JP7634111B2 (ja) 2025-02-20
US20250021158A1 (en) 2025-01-16
JPWO2023095456A1 (https=) 2023-06-01

Similar Documents

Publication Publication Date Title
WO2019245316A1 (en) System and method for generating aspect-enhanced explainable description-based recommendations
US20090216639A1 (en) Advertising selection and display based on electronic profile information
US20210232621A1 (en) Machine Learning for Digital Image Selection Across Object Variations
CN111292168B (zh) 数据处理方法、装置及设备
CN113806631B (zh) 一种推荐方法、训练方法、装置、设备及新闻推荐系统
CN111340605B (zh) 训练用户行为预测模型、用户行为预测的方法和装置
KR20030058660A (ko) 개인화 시스템에서 사용자의 컨텐트 선호도를 이용한협업필터링 학습방법
JP7728805B2 (ja) 情報処理装置
JP2022026683A (ja) レコメンド装置
JP7634111B2 (ja) レコメンド装置
JP7664413B2 (ja) レコメンド装置
JP7668803B2 (ja) 広告効果予測装置
JP7500583B2 (ja) 価格予測装置
JP7809798B2 (ja) 興味推定装置
JP7765607B2 (ja) レコメンドシステム
KR102865284B1 (ko) 전자 장치 및 그의 제어 방법
JP7663581B2 (ja) レコメンドシステム
US20240428289A1 (en) Region value evaluation system
JP7705861B2 (ja) レコメンドシステム
JP7682214B2 (ja) 情報処理装置
CN114021000B (zh) 商品推荐的方法及装置、存储介质、电子设备
TWI870874B (zh) 處理商品銷售註冊請求之方法及電子裝置
WO2025126492A1 (ja) 情報処理装置
JP7489255B2 (ja) 情報提供装置
JP2025158600A (ja) 装置及び方法

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: 22898241

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023563538

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 18712778

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22898241

Country of ref document: EP

Kind code of ref document: A1

WWG Wipo information: grant in national office

Ref document number: 18712778

Country of ref document: US