Information processing device, information processing method, and information processing program

The information processing device uses deep learning to generate user vectors from convolved related information, addressing the lack of accuracy in conventional advertisement targeting by improving user interest prediction and advertisement distribution.

JP2024165584AActive Publication Date: 2024-11-28LY CORP
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
JP2023081886
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-17
Publication Date
2024-11-28
Estimated Expiration
2043-05-17

AI Technical Summary

Technical Problem

Conventional advertising distribution technologies lack the ability to provide highly accurate indicators for user interest prediction, leading to suboptimal targeting of advertisements.

Method used

An information processing device that utilizes deep learning to generate user vectors by individually convolving related information, such as click operations and user attributes, to improve the accuracy of user interest prediction and advertisement targeting.

Benefits of technology

Enhances the provision of better information by generating user vectors that more accurately reflect user interests, enabling more effective advertisement distribution.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024165584000001_ABST
    Figure 2024165584000001_ABST
Patent Text Reader

Abstract

To provide an information processing device capable of providing better information, an information processing method, and an information processing program.SOLUTION: An information processing device comprises an identification unit, a generation unit, and a provision unit. The identification unit identifies a plurality of pieces of related information related to an action intentionally taken by a user for an object on a Web. The generation unit generates a user vector on the object on the basis of a partial vector generated by individually convolving each of the plurality of pieces of related information in deep learning. The provision unit provides information based on the generated user vector.SELECTED DRAWING: Figure 3
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, various indices have been used in advertisement delivery via the Internet. For example, a technique is known in which various indices such as CTR (Click Through Rate) and CVR (Conversion Rate) are predicted, and users to whom advertisements are to be delivered are selected based on the prediction results (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2011-116345 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the prior art leaves room for improvement in terms of providing better information based on highly accurate indicators.

[0005] The present application has been made in consideration of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that are capable of providing better information. [Means for solving the problem]

[0006] The information processing device according to the present application includes an identification unit, a generation unit, and a provision unit. The identification unit identifies a plurality of pieces of related information related to an action that a user intentionally performed on an object on the web. The generation unit generates a user vector related to the object based on a partial vector generated by individually convolving the plurality of pieces of related information in deep learning. The provision unit provides information based on the generated user vector. Effect of the Invention

[0007] According to one aspect of the embodiment, it is possible to provide better information. [Brief description of the drawings]

[0008] [Figure 1A] FIG. 1A is a diagram showing a process executed by an information processing device according to an embodiment. [Figure 1B] FIG. 1B is a diagram showing a process executed by the information processing device according to the embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of user information. [Diagram 5] FIG. 5 is a diagram showing an example of advertisement information. [Figure 6] FIG. 6 is a diagram illustrating an example of advertiser information. [Figure 7] FIG. 7 is a flowchart showing the processing procedure executed by the information processing device according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments. In addition, the same parts in the following embodiments are given the same reference numerals, and duplicated descriptions are omitted.

[0010] (Embodiment) First, the process executed by the information processing device according to the embodiment will be described with reference to Figs. 1A and 1B. Figs. 1A and 1B are diagrams showing the process executed by the information processing device according to the embodiment. Note that Fig. 1A shows an example of the operation of an information processing system S including an information processing device 1 according to the embodiment. Below, a case is shown in which the information processing system S targets advertising content (also simply called "advertisement") and performs various information processing related to the advertisement. Note that the target is not limited to advertisements, and may be any content to which the processing described below can be applied.

[0011] As shown in FIG. 1A, an information processing system S according to the embodiment includes an information processing device 1, a distribution server 50, a user terminal 100, and an advertiser terminal 200.

[0012] In FIG. 1A, an information processing system S according to an embodiment identifies multiple pieces of related information related to actions intentionally taken by a user toward a target (advertisement) on the web, generates a user vector related to the target based on partial vectors generated by individually convolving the multiple pieces of related information in deep learning, and provides information based on the generated user vector.

[0013] Specifically, first, the advertiser terminal 200 performs a process of requesting distribution of the advertiser's advertisement (step S1). For example, the advertiser terminal 200 requests the distribution server 20 to distribute the advertisement in response to the operation of the advertiser, and the distribution server 50 adds the advertiser's advertisement to the distribution target to the user terminal 100 in response to the request from the advertiser terminal 200.

[0014] Next, the user terminal 100 transmits an advertisement distribution request in response to a user operation when the user uses the content distribution service provided by the distribution server 50 (step S2). For example, when the user uses the search service provided by the distribution server 50 and clicks on advertisement content displayed on a search screen (query input screen or search result screen), the user terminal 100 transmits a distribution request for the clicked advertisement.

[0015] Next, the distribution server 50 distributes the requested advertisement to the user terminal 100 in response to the distribution request from the user terminal 100 (step S3). In addition, the distribution server 50 acquires various information when distributing the advertisement and provides it to the information processing device 1 (step S4). Details of the information provided to the information processing device 1 will be described later with reference to FIG. 1B.

[0016] Next, the information processing device 1 generates a user vector related to the target based on the information acquired from the distribution server 50 (step S5). The user vector is, for example, a vector indicating the presence or absence of interest in the target advertisement and the degree of interest. In other words, the user vector is a vector indicating what kind of advertisement (advertised product or service) the user is interested in.

[0017] First, the information processing device 1 identifies a plurality of pieces of related information related to an intentional action performed by a user on an advertisement on the web. Specifically, the information processing device 1 determines whether or not a click operation to select a displayed advertisement is an intentional action. For example, when a click operation is performed on the center position of an area in which an advertisement is displayed, the information processing device 1 identifies the click operation as an intentional action. Furthermore, when a click operation is performed after a certain period of time during which a distributed advertisement is viewed (displayed) has elapsed, the information processing device 1 identifies the click operation as an intentional action. Furthermore, when a click operation is performed immediately (within a predetermined period of time) after an advertisement is distributed (displayed), the information processing device 1 identifies the click operation as not an intentional action (the advertisement was selected by mistake). Then, when the information processing device 1 determines that the action was intentional, it identifies related information related to the action. Related information includes, for example, identification information of the site linked to the advertisement selected by the user, information entered by the user when selecting the advertisement (search keywords in the case of a search service), audience category (classification information based on user information, classified by interests, concerns, attributes, and life events), the category of the advertisement selected by the user, and the title (product name, catch phrase, etc.).

[0018] Next, the information processing device 1 generates the user vector based on the identified multiple pieces of related information. Here, a method for generating a user vector will be described in detail with reference to Fig. 1B. Fig. 1B shows a model of a convolutional neural network (CNN), which is an example of deep learning.

[0019] 1B, the information processing device 1 generates a user vector using a deep learning model. Specifically, the information processing device 1 generates the user vector by aggregating a partial vector generated based on a plurality of pieces of related information input to the input layer and a stationary vector generated based on a plurality of pieces of stationary information input to the input layer.

[0020] First, a method for generating a partial vector will be described. A partial vector is generated by inputting multiple pieces of related information to the input layer. FIG. 1B shows an example in which related information, such as an audience category (ac_list), a search keyword (search_kw), an advertisement category (ad_categories), an advertisement title (ad_title), and an advertisement site ID (site_id), are input to the input layer. Note that the related information shown in FIG. 1B is just an example, and any information that changes in response to the above-mentioned action (click operation) can be applied.

[0021] The information processing device 1 generates a partial vector by convolving a plurality of pieces of related information in the CNN. Specifically, the information processing device 1 generates a partial vector (vec) by aggregating each piece of data (dence_3, dence_5, dence_7, dence_9, dence_11) in the intermediate layer generated by individually convolving a plurality of pieces of related information. Note that the partial vector is preferably expressed as a non-negative sparse vector. This makes it possible to prevent the values ​​of each piece of data in the intermediate layer corresponding to each piece of related information from being canceled by the aggregation.

[0022] In addition, while FIG. 1B shows an example of generating a partial vector based on a click operation on one advertisement, for example, the information processing device 1 may generate a partial vector for each action on multiple different advertisements and generate a partial vector that aggregates the partial vectors for each action.

[0023] Next, a method for generating a stationary vector will be described. A stationary vector is generated by inputting a plurality of pieces of stationary information to the input layer. The stationary information is stationary information of a user or advertisement. FIG. 1B shows an example in which a DS resource record (ds), gender (gender), advertisement format (media_adformat), Internet network line (network), OS (Operating System) type (os_type), advertisement style (adstyle), age (age), user's location area (area), and device type (device) of the user terminal 100 are input to the input layer (Input Layer). Note that the stationary information shown in FIG. 1B is an example, and any information that is stationary information of a user or advertisement can be applied.

[0024] The information processing device 1 generates a stationary vector by convolving a plurality of pieces of stationary information. Specifically, the information processing device 1 generates a stationary vector by convolving a plurality of pieces of stationary information into one value in the intermediate layer.

[0025] Then, the information processing device 1 generates a user vector based on the generated stationary vector and the partial vector. Specifically, the information processing device 1 generates a user vector, which is a value of the output layer, by aggregating the stationary vector and the partial vector.

[0026] Return to FIG. 1A. As shown in FIG. 1A, the information processing device 1 provides information based on the generated user vector to the distribution server 50 and the advertiser terminal 200 (step S6). For example, the distribution server 50 selects an advertisement to be distributed to the user (displayed on a search screen) based on the acquired user vector. In addition, the information processing device 1 may estimate, for example, based on the user vector, whether or not the user will perform a click operation to intentionally select an advertisement, and provide the estimation result (probability of performing a click operation, or whether or not to perform a click operation) to the distribution server 50.

[0027] In this manner, in the above-described embodiment, by generating a user vector based on a partial vector generated by convolving a plurality of pieces of related information individually, each piece of related information is less likely to be mixed and buried in the intermediate layer in deep learning, and therefore, a user vector (partial vector) that better reflects the feature amount of each piece of related information can be generated. That is, according to the information processing device 1 according to the embodiment, better information can be provided using a highly accurate index (user vector).

[0028] Next, a configuration example of an information processing system S according to an embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing a configuration example of an information processing system S according to an embodiment. As shown in Fig. 2, in the information processing system S according to the embodiment, an information processing device 1, a distribution server 50, a user terminal 100, and an advertiser terminal 200 are connected to a network N by wire or wirelessly. The network N is, for example, a network such as the Internet, a WAN (Wide Area Network), or a LAN (Local Area Network).

[0029] The information processing device 1 is a server device that executes an information processing method according to an embodiment. The information processing device 1 identifies a plurality of pieces of related information related to an action that a user intentionally performed on a target (advertisement) on the web, generates a user vector related to the target based on a partial vector generated by individually convolving the plurality of pieces of related information in deep learning, and provides information based on the generated user vector.

[0030] In addition, the information processing device 1 is an information processing device that cooperates with the distribution server 50, the user terminal 100, and the advertiser terminal 200, and provides the distribution server 50, the user terminal 100, and the advertiser terminal 200 with API (Application Programming Interface) services for various applications (hereinafter, apps), etc., and various data, and is realized by a server device, a cloud system, etc.

[0031] The information processing device 1 may be an information processing device that provides some kind of Web service online to the distribution server 50, the user terminal 100, and the advertiser terminal 200. For example, the information processing device 1 may provide services such as Internet connection, search service, SNS (Social Networking Service), electronic commerce (EC), electronic payment, online games, online banking, online trading, hotel and ticket reservations, video and music distribution, news, maps, route search, route guidance, line information, operation information, and weather forecasts as Web services. In reality, the information processing device 1 may cooperate with various servers that provide the above-mentioned Web services, and may mediate the Web services or be responsible for processing the Web services.

[0032] The distribution server 50 is a server device that distributes various contents such as advertisements to users. The distribution server 50 receives requests for content distribution from requesters (advertisers and service providers) and distributes the requested content to users.

[0033] The user terminal 100 is a terminal device owned by a user. The user terminal 100 may be any type of terminal device, such as a smartphone, a desktop PC, a notebook PC, or a tablet PC. The user terminal 100 transmits various information to the information processing device 1, the distribution server 50, or the like, and receives information provided by the information processing device 1, the distribution server 50, or the like.

[0034] The advertiser terminal 200 is a terminal device used by an advertiser who is a requester for the distribution of an advertisement. For example, the advertiser terminal 200 may be any type of terminal device, such as a smartphone, a desktop PC, a notebook PC, or a tablet PC. The advertiser terminal 200 submits an advertisement to a device that distributes advertisements (advertising distribution device), such as the distribution server 50, in accordance with the advertiser's operation.

[0035] Next, a configuration example of the information processing device 1 will be described with reference to FIG.

[0036] Fig. 3 is a diagram showing an example of the configuration of an information processing device 1 according to an embodiment. As shown in Fig. 3, the information processing device 1 has a communication unit 2, a control unit 3, and a storage unit 4. The control unit 3 includes an acquisition unit 31, an identification unit 32, a generation unit 33, and a provision unit 34. The storage unit 4 stores user information 41, advertisement information 42, and advertiser information 43.

[0037] The communication unit 2 is realized by, for example, a network interface card (NIC), etc. The communication unit 2 is connected to a network by wire or wirelessly.

[0038] The control unit 3 is a controller, and is realized by, for example, a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM or the like as a working area. The control unit 3 is also a controller, and may be realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit).

[0039] The storage unit 4 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0040] User information 41 is information related to a user. Fig. 4 is a diagram showing an example of user information 41. As shown in Fig. 4, user information 41 includes items such as "user ID", "attribute information", "action information", and "vector information".

[0041] "User ID" is identification information that identifies a user. "Attribute information" is information about the attributes of a user. Attribute information includes, for example, psychographic attributes and demographic attributes. "Behavior information" is information about an intentional behavior performed by a user toward a target on the web. Behavior information includes, for example, the related information and steady-state information described above. "Vector information" is information about the user vector described above, and is generated by the generation unit 33 described later.

[0042] The advertisement information 42 is information related to advertisements submitted by advertisers. Fig. 5 is a diagram showing an example of the advertisement information 42. As shown in Fig. 5, the advertisement information 42 includes items such as "advertisement ID", "advertiser ID", and "advertisement information".

[0043] "Advertising ID" is identification information that identifies an advertisement. "Advertiser ID" is identification information that identifies an advertiser. "Advertising Information" is information about an advertisement, including information about the content of the advertisement (overall design, images, text, etc.) and information about the product or service being advertised.

[0044] The advertiser information 43 is information related to an advertiser. Fig. 6 is a diagram showing an example of the advertiser information 43. As shown in Fig. 6, the advertiser information 43 includes items such as "advertiser ID" and "advertiser information".

[0045] The "advertiser ID" is identification information for identifying an advertiser. The "advertiser information" is information related to the advertiser, including the name of the advertiser, the category of the product or service being sold, and the like.

[0046] Next, each function (acquisition unit 31, identification unit 32, generation unit 33, and provision unit 34) of the control unit 3 of the information processing device 1 will be described.

[0047] The acquisition unit 31 acquires various information from the distribution server 50. Specifically, the acquisition unit 31 acquires related information related to the behavior of the user to whom the advertisement was distributed, and the above-mentioned stationary information.

[0048] The identification unit 32 identifies a plurality of pieces of related information related to an intentional action performed by a user on an advertisement on the web. Specifically, the identification unit 32 determines whether or not a click operation to select a displayed advertisement is an intentional action. For example, when a click operation is performed on the center position of an area in which an advertisement is displayed, the identification unit 32 identifies the click operation as an intentional action. Furthermore, when a click operation is performed after a certain period of time during which a delivered advertisement is viewed (displayed) has elapsed, the identification unit 32 identifies the click operation as an intentional action. Furthermore, when a click operation is performed immediately (within a predetermined period) after an advertisement is delivered (displayed), the identification unit 32 identifies the click operation as not an intentional action (the advertisement was selected by mistake). When the identification unit 32 determines that the action was intentional, the identification unit 32 identifies related information related to the action. Related information includes, for example, identification information of the site linked to the advertisement selected by the user, information entered by the user when selecting the advertisement (search keywords in the case of a search service), audience category (classification information based on user information, classified by interests, concerns, attributes, and life events), the category of the advertisement selected by the user, and the title (product name, catch phrase, etc.).

[0049] The generation unit 33 generates a user vector related to the advertisement based on a partial vector generated by convolving a plurality of pieces of related information individually in deep learning. Specifically, the generation unit 33 generates the user vector by aggregating the partial vector generated based on the related information and the stationary vector generated based on the stationary information.

[0050] The providing unit 34 provides information based on the generated user vector to the distribution server 50 and the advertiser terminal 200. For example, the distribution server 50 selects an advertisement to be distributed to the user (displayed on a search screen) based on the user vector acquired from the providing unit 34. In addition, the providing unit 34 may estimate, for example, based on the user vector, whether or not the user will perform a click operation to intentionally select an advertisement, and provide the estimation result (the probability of performing a click operation, or whether or not a click operation will be performed) to the distribution server 50.

[0051] Next, a processing procedure of the processing executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the processing procedure of the processing executed by the information processing device 1 according to the embodiment.

[0052] 7, the control unit 3 first acquires various information related to the user to whom the advertisement was distributed from the distribution server 50 (step S101). Specifically, the control unit 3 acquires the above-mentioned related information and steady-state information.

[0053] Next, the control unit 3 identifies an intentional action (for example, a click operation) performed on the delivered advertisement and a plurality of pieces of related information related to the action (step S102).

[0054] Next, the control unit 3 generates a user vector related to the advertisement based on a partial vector generated by individually convoluting a plurality of pieces of related information in deep learning (step S103).

[0055] Next, the control unit 3 generates information based on the generated user vector and provides it to the distribution server 50 and the advertiser terminal 200 (step S104), and ends the process.

[0056] 〔others〕 In addition, among the processes described in the above embodiments, some of the processes described as being performed automatically can be performed manually. Alternatively, all or some of the processes described as being performed manually can be performed automatically using a known method. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0057] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0058] 3 may be held in a storage server or the like instead of being held by each device. In this case, each device obtains various pieces of information by accessing the storage server.

[0059] [Hardware configuration] The information processing device 1 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 8. Fig. 8 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which a calculation device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.

[0060] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050 and programs read from the input device 1020, and executes various processes. The primary storage device 1040 is a memory device, such as a RAM, that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), a HDD (Hard Disk Drive), a flash memory, or the like.

[0061] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor or a printer, and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (registered trademark) (High Definition Multimedia Interface). The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, and scanner, and is realized by a USB, for example.

[0062] The input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. The input device 1020 may also be an external storage medium such as a USB memory.

[0063] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0064] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0065] For example, when the computer 1000 functions as the information processing device 1, the arithmetic unit 1030 of the computer 1000 realizes the functions of the control unit 3 by executing a program loaded onto the primary storage device 1040.

[0066] 〔effect〕 As described above, the information processing device 1 according to the embodiment includes the identification unit 32, the generation unit 33, and the provision unit 34. The identification unit 32 identifies a plurality of pieces of related information related to an action intentionally performed by a user on a target on the web. The generation unit 33 generates a user vector related to the target based on a partial vector generated by individually convolving the plurality of pieces of related information in deep learning. The provision unit 34 provides information based on the generated user vector. With such a configuration, better information can be provided.

[0067] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0068] 〔others〕 In addition, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0069] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0070] Furthermore, the processes described in the above-described embodiments can be appropriately combined as long as the process contents are not contradictory.

[0071] Moreover, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, the control unit 3 can be read as control means or a control circuit. [Explanation of symbols]

[0072] 1. Information processing device 2. Communications Department 3. Control Unit 4 Storage section 31 Acquisition Department 32 Specific part 33 Generation part 34 Providing Department 41 User Information 42 Advertising Information 43 Advertiser Information 50 Distribution Server 100 user terminals 200 Advertiser Terminal S Information Processing System

Claims

1. An identification unit that identifies a plurality of pieces of related information related to an action intentionally performed by a user on a target on the web; A generation unit that generates a user vector related to the target based on a partial vector generated by individually convolving the plurality of related information in deep learning; A providing unit that provides information based on the generated user vector; An information processing device comprising:

2. The generation unit is The partial vector is generated by aggregating each data of the intermediate layer generated by convoluting each of the plurality of related information individually. The information processing device according to claim 1 .

3. The identification unit is Further identifying stationary information, which is stationary information of the user or the subject; The generation unit is The user vector is generated based on a stationary vector generated by convolving the stationary information and the partial vector. The information processing device according to claim 2 .

4. The related information is The information varies depending on the action. The information processing device according to claim 1 .

5. The providing unit is Based on the user vector, it is estimated whether the user will perform the action on the target, and the estimation result is provided as the information. The information processing device according to claim 1 .

6. The generation unit is generating a user vector for each of the actions on the different targets, and generating an aggregated user vector by aggregating the generated user vectors; The providing unit is Providing information based on the aggregate user vector The information processing device according to claim 1 .

7. The generation unit is Generate the subvector of the non-negative sparse vector representation The information processing device according to claim 1 .

8. The said act is A click operation on the target The information processing device according to claim 1 .

9. 1. A computer-implemented information processing method, comprising: identifying a plurality of pieces of relevant information related to an intentional action taken by a user on a target on the web; A generation step of generating a user vector related to the target based on a partial vector generated by individually convolving the plurality of related information in deep learning; A providing step of providing information based on the generated user vector; An information processing method comprising:

10. identifying a plurality of pieces of relevant information related to an intentional action taken by a user on a web target; A generation step of generating a user vector related to the target based on a partial vector generated by convolving each of the plurality of related information individually in deep learning; A provision step of providing information based on the generated user vector; An information processing program that causes a computer to execute the above.

Citation Information

Patent Citations

  • Information processing apparatus, information processing method, and information processing program

    JP2022144341A

  • Electronic shift operation device of vehicle

    JP2011116345A