Information processing system, method for processing information, and program
The information processing system dynamically adjusts website layouts based on user data to enhance engagement and satisfaction, addressing the static layout issue in existing technologies and improving user interaction metrics.
Patent Information
- Application Number
- JP2025038706
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-03-11
- Filing Date
- 2025-03-11
- Publication Date
- 2025-09-25
AI Technical Summary
Existing technologies fail to adapt the layout of websites based on user information, leading to reduced user interest and potential customer engagement.
An information processing system that includes a management server to acquire and manage user characteristic information, change the layout of websites based on user data, and output the adapted web pages to user terminals, utilizing machine learning models to optimize layout patterns for user segments.
Enhances user engagement and satisfaction by adapting website layouts to individual user preferences, increasing website access and conversion rates, and improving advertising effectiveness.
Smart Images

Figure 2025138620000001_ABST
Abstract
Description
[Technical Field]
[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]
[0002] In modern society, where the amount of information users are exposed to is constantly increasing, there is a demand for providing users with information optimized to their individual needs. Particularly in the web industry, where a vast amount of information about users exists, such as user access logs and behavioral data, appropriate processing of this vast amount of information can enable the presentation of content highly relevant to users, rapid access to information desired by users, and the suggestion of suitable content at the appropriate time. This can increase user satisfaction. In this technical field, for example, a technology is known that changes the content and advertisements displayed on websites accessed by users according to the user's interests and preferences inferred from information about the user (see, for example, Patent Document 1). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Application Publication No. 2018-190263 Summary of the Invention [Problem to be solved by the invention]
[0004] However, there is no known technology that changes the layout of a website accessed by a user depending on information about that user. As a result, the layout of the website accessed by a user is constant, which causes the user to lose interest in the web page and reduce the number of potential customers.
[0005] The present invention has been made in view of the above circumstances, and has as its object to make the layout of a website accessed by a user suited to that user. [Means for solving the problem]
[0006] In order to achieve the above object, one aspect of the present invention is to a user management means for acquiring and managing user characteristic information including at least one of attribute information relating to a user's attributes and behavioral information relating to the user's behavior on a website; a layout change means for changing the layout of a web page constituting a website accessed by the user in accordance with the user characteristic information of the user; an output unit for outputting the web page after the layout change to an information processing device operated by the user; The information processing system includes:
[0007] An information processing method and a program corresponding to the information processing system according to one aspect of the present invention are also provided as an information processing method and a program corresponding to the information processing system according to one aspect of the present invention. [Effects of the Invention]
[0008] According to the present invention, the layout of a website accessed by a user can be adapted to suit that user. [Brief explanation of the drawings]
[0009] [Figure 1] 1 is a diagram illustrating an example of the overall configuration of an information processing system according to an embodiment of the present invention. [Figure 2] 2 is a block diagram showing an example of a hardware configuration of a management server that constitutes the information processing system of FIG. 1. FIG. [Figure 3] FIG. 2 is a functional block diagram illustrating an example of a functional configuration of a management server. [Figure 4] 10 is a flowchart illustrating an example of a processing flow of a management server. [Figure 5] FIG. 10 is a diagram illustrating a specific example of this service. [Figure 6] FIG. 10 illustrates an example of segment-based batch processing and testing of layout changes. [Figure 7] FIG. 10 illustrates an example of segment-based batch processing and testing of layout changes. DETAILED DESCRIPTION OF THE INVENTION
[0010] Hereinafter, this embodiment will be described with reference to the drawings. <Information Processing System S> FIG. 1 is a diagram showing an example of the overall configuration of an information processing system S according to one embodiment of the present invention. An information processing system S according to one embodiment of the present invention is an information processing system applied to a service (hereinafter referred to as "this service") that automatically changes the layout of a website accessed by a user so that it suits the user. Examples of something that suits the user include something that reflects the user's tastes and preferences, or more specifically, something that suits the user's tastes and preferences by using the user's favorite colors and shapes.
[0011] In this embodiment, "layout" is a concept that includes the overall structure of a website, the structure of each webpage, and the presentation of content on the website or within the webpage. Specifically, the overall structure of a website includes the page hierarchy and the transition structure between pages, the webpage configuration includes the placement, presence or absence, and size of content blocks, and the presentation of content includes the font and size of characters, the size of images, color usage, and the presence or absence of animation.
[0012] Furthermore, the concept of "content" encompasses not only the information that constitutes a website or webpage, but also the definition of the area in which that information is displayed. Specifically, in addition to content such as text, still images, and moving images provided on a website or webpage, the definition of the area in which advertisements are placed, for example, is also subject to layout as content. In this way, the placement of advertisements for external products or services that are different from the webpages covered by this service is also subject to layout changes. For example, in the case of advertising content, the advertising provider, the advertising target (products or services), and the type and content of the advertisement (display advertising, listing advertising, video advertising, etc.) are also forms of expression that can be changed using layout.
[0013] However, in this embodiment, a layout in which only the presentation style of advertisements introducing external products or services different from those of the target webpage is different but the rest of the layout is the same is not treated as a different layout. In other words, a layout in which only the presentation style of advertisements introducing external products or services different from those of the target webpage is different is treated as the same layout. On the other hand, if the target website or webpage is for a specific product or service, it goes without saying that a change in the presentation style of at least a part of that website or webpage is treated as a change in layout.
[0014] Note that "a layout suited to the user" refers to, for example, a layout that matches the user's tastes and preferences, a layout that matches the system environment the user is in, etc. In addition, as will be specifically described later, if the target website or web page is for a specific product or service, it refers to a layout that is expected to lead the user to purchase the product or service.
[0015] The information processing system S is configured by connecting a management server 1, user terminals 2-1 to 2-n (n is an integer value equal to or greater than 1), and a web server 3 via a network N. The network N is, for example, the Internet, a LAN (Local Area Network), or a VPN (Virtual Private Network). Hereinafter, when there is no need to explain each of the user terminals 2-1 to 2-n individually, they will be collectively referred to as "user terminals 2."
[0016] [Management Server 1] The management server 1 is an information processing device that serves as a server that manages the entire information processing system S. The management server 1 is managed, for example, by the provider of this service. The management server 1 is capable of executing a predetermined application program that makes the information processing system S available. The management server 1 acquires various types of information transmitted from a user terminal 2 operated by a user and various types of information transmitted from a web server 3 that provides a website, and is capable of executing various processes. The management server 1 also transmits various types of information to each of the user terminal 2 and the web server 3, and is capable of executing various processes.
[0017] For example, the management server 1 acquires and manages information relating to the characteristics of users (hereinafter referred to as "user characteristic information"). The user characteristic information includes, for example, information relating to the attributes of the user (hereinafter referred to as "attribute information"), information relating to the user's behavior on a website (hereinafter referred to as "behavior information"), and information relating to the user terminal 2 operated by the user (hereinafter referred to as "terminal information"). The management server 1 stores and manages the acquired user characteristic information in a predetermined database. Specific examples of user characteristic information will be described later.
[0018] When a user accesses a website provided by the web server 3, the management server 1 changes the layout of the website according to the user's user characteristic information and outputs the changed website to the user terminal 2. As a result, the website with a layout adapted to the user is output to the user terminal 2, and the following effects can be expected, for example: Namely, an increase in the number of website accesses can be expected. Furthermore, for example, an improvement in user engagement, which is an index showing whether users are actively using a website, and an improvement in the conversion rate (CVR), which is an index showing the percentage of users who achieve a final result on a website, can be expected. In other words, an improvement in advertising effectiveness can also be expected. As a result, for search engines that refer to user access status, etc., this can also contribute to search engine optimization (SEO).
[0019] Furthermore, the management server 1 can change the layout of a website accessed by a user to a layout that corresponds to the layout pattern corresponding to the segment to which the user belongs. A "segment" is a unit used to classify multiple users based on user characteristic information, and is managed by the management server 1. The management server 1 sets m pieces of information (m is an integer value of 1 or more) of the acquired user characteristic information as m axes, and there are r options per axis. m pcs(r m is the number of options on the m axis, each of which is an integer value of 2 or more. Therefore, the number of segments managed by the management server 1 may be several hundred to several thousand, or even more. Note that by treating two or more combinations corresponding to different axes and different options as one segment, the number of segments can be reduced by r m It may be a number less than the total product of m.
[0020] For example, assume that the user characteristic information includes segments based on two axes: information A with two options (A1 and A2) and information B with three options (B1, B2, and B3). In this case, users are classified into one of nine segments: A1-B1, A1-B2, A1-B3, A2-B1, A2-B2, A2-B3, A3-B1, A3-B2, and A3-B3. As a specific example, if information A is the type of device and information B is the language setting, A1 may be a smartphone, A2 may be a personal computer, B1 may be Japanese, B2 may be English, and B3 may be Chinese. In this way, the number of segments is determined by the number of information items and the number of options for each information item. The number of information items and the number of options for each information item can be designed taking into account the number of segments and information processing resources. In addition, each piece of information is not limited to the content of the individual piece of information (for example, "Japanese" as a language setting) itself being an option; for example, a numerical value can be set as the content of each piece of information, and options can be selected that are divided by one or more thresholds corresponding to that numerical value.
[0021] The management server 1 associates one or more layout patterns with one segment and manages them. That is, the management server 1 stores and manages the combination of a segment and one or more layout patterns associated with that segment as information about the segment (hereinafter referred to as "segment information") in a predetermined database. Therefore, if there are nine segments as described above, the management server 1 generates one or more layout patterns suitable for each of the nine segments and manages them in association with each of the nine segments.
[0022] By classifying users into segments, the management server 1 can manage web page layout patterns on a segment-by-segment basis rather than on a user-by-user basis. For example, suppose 10 users are classified into a certain segment, and only one layout pattern is associated with that segment. In this case, the management server 1 applies that layout pattern to all 10 users at once and changes the layout of the web page based on the applied layout pattern. This reduces the load on the management server 1 that processes the layout changes. As a result, it is possible to suppress a decrease in processing speed, a delay in response, etc.
[0023] The management server 1 continuously acquires the user characteristic information to update the user characteristic information as needed. Then, each time the management server 1 updates the user characteristic information, it classifies users into segments based on the user characteristic information. Here, in order to make layout changes that better suit the user, it is preferable to classify users into segments based on the latest user characteristic information. For this reason, it is preferable that the intervals at which the user characteristic information is acquired are short, and it is most preferable that it be acquired in real time.
[0024] In this way, by classifying users into segments each time user characteristic information is updated, it becomes possible to change the layout to suit the user more. However, depending on the content of the acquired user information, layout changes may occur frequently. In such cases, users who access the website may become confused about how to operate it.
[0025] In response to this, the management server 1 uses a predetermined machine learning model to change the layout of a website accessed by a user. Such a machine learning model may, for example, be capable of outputting a layout pattern based on input user characteristic information. Hereinafter, such a machine learning model will be referred to as a "layout optimization model." For example, the layout optimization model may, when inputting user characteristic information serving as an explanatory variable, attempt to change the layout of a website accessed by a user and output a layout pattern that optimizes a predetermined objective variable. In this case, the user characteristic information serving as an explanatory variable may, for example, be the number of clicks, conversion rate, number of page views, number of sessions, average session time, and page visit time.
[0026] According to the layout optimization model, in the early stages when learning has not yet progressed, the accumulation of learning data is insufficient, and therefore the above-mentioned frequent layout changes may occur. However, as the accumulation of learning data progresses and learning of the layout optimization model progresses, layout patterns that are less satisfying to users are gradually eliminated, and the accuracy converges so that layout patterns that are more satisfying to users are output. As a result, even if the frequency of user characteristic information is increased, frequent layout changes are suppressed.
[0027] Furthermore, the management server 1 enables the layout of a web page accessed by a user operating the user terminal 2 to be changed to a layout corresponding to a layout pattern corresponding to a segment different from the user's segment. By performing such layout changes at predetermined timing, it becomes easier to grasp the effect of the layout change. That is, by comparing the effect of a layout change according to a layout pattern corresponding to a segment with that of a layout change according to a layout pattern corresponding to a segment, it becomes easier to grasp the effect of a layout change according to a layout pattern corresponding to the user's segment. Note that the timing of the change to a layout according to a layout pattern corresponding to a segment is not particularly limited, and may be performed, for example, at a timing that is difficult for the user to predict (e.g., randomly).
[0028] Furthermore, the management server 1 can change the layout pattern corresponding to the user's segment to a layout pattern that is slightly modified, rather than changing the layout to a layout pattern corresponding to another segment. This makes it possible to search for a layout pattern that will maximize user satisfaction. The configuration and processing of the management server 1 will be described in detail later.
[0029] [User terminal 2] The user terminal 2 is an information processing device operated by a user who uses the service to use the information processing system S. The user terminal 2 is configured, for example, as a smartphone, tablet terminal, or personal computer. The user terminal 2 is capable of executing a predetermined application program that enables the use of the service.
[0030] The user terminal 2 is capable of performing various processes based on various information transmitted from the management server 1 and from the outside, and various information input by user operation. The user terminal 2 is also capable of transmitting various information to the management server 1 and from the outside. For example, the user terminal 2 accesses a website provided on the network N by the web server 3 and displays the web pages that make up the website on a display. The configuration and processing of the user terminal 2 will be described in detail later.
[0031] The above-described processing by each of the management server 1 and the user terminal 2 that constitute the information processing system S is one example. In addition, since it is sufficient for the information processing system S as a whole to have the function of realizing the above-described processing, some or all of the functions of realizing the above-described processing may be shared or cooperated within the information processing system S.
[0032] For example, some or all of the functions of the management server 1 may be functions of other information processing devices (e.g., user terminal 2, web server 3) in the information processing system S. Specifically, for example, the web server 3 may function as the management server 1. Also, some or all of the functions of other information processing devices in the information processing system S may be functions of the management server 1. Furthermore, some or all of the functions of the management server 1 may be transferred to other servers (not shown). This promotes processing in the information processing system S as a whole and also enables processes to complement each other.
[0033] <Hardware configuration> [Hardware configuration of Management Server 1] FIG. 2 is a block diagram showing an example of the hardware configuration of the management server 1 that constitutes the information processing system S of FIG. The management server 1 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an output unit 16, an input unit 17, a memory unit 18, a communication unit 19, and a drive 20.
[0034] The CPU 11 executes various processes in accordance with a program recorded in the ROM 12 or a program loaded from the storage unit 18 into the RAM 13. The RAM 13 also stores data and the like required for the CPU 11 to execute various processes as appropriate. The CPU 11, the ROM 12, and the RAM 13 are interconnected via a bus 14. An input / output interface 15 is also connected to this bus 14. The management server 1 may include a QPU (Quantum Processing Unit) in addition to (or instead of) the CPU 11.
[0035] The input / output interface 15 is connected to an output unit 16, an input unit 17, a storage unit 18, a communication unit 19, and a drive 20. The output unit 16 is composed of a display, a speaker, etc., and outputs various types of information as images and sounds. The input unit 17 is composed of a keyboard, a mouse, a touch panel, etc., and accepts input of various types of information. The storage unit 18 is composed of a hard disk, a DRAM (Dynamic Random Access Memory), etc., and stores various types of data. The communication unit 19 communicates with other devices via the above-mentioned network N, which is composed of the Internet, etc.
[0036] Removable media 21, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is appropriately attached to the drive 20. Programs read from the removable media 21 by the drive 20 are installed in the storage unit 18 as needed. The removable media 21 can also store various data stored in the storage unit 18 in the same way as the storage unit 18.
[0037] [Hardware configuration of user terminal 2] Although not shown, the user terminal 2 has the same hardware configuration as the management server 1 shown in Fig. 2. That is, the user terminal 2 has a CPU, ROM, RAM, bus, input / output interface, output unit, input unit, memory unit, communication unit, drive, and removable media, which correspond to the CPU 11, ROM 12, RAM 13, bus 14, input / output interface 15, output unit 16, input unit 17, memory unit 18, communication unit 19, drive 20, and removable media 21, respectively, in Fig. 2. The output unit of the user terminal 2 functions as part of the output means constituting the present invention.
[0038] <Functional configuration of management server 1> FIG. 3 is a functional block diagram showing an example of the functional configuration of the management server 1. As shown in FIG. In operation, the CPU 11 of the management server 1 functions as an information acquisition unit 31, an information management unit 32 functioning as a user management unit and a segment management unit, and a layout modification unit 33 functioning as a layout modification unit. The CPU 11 also functions as a learning unit 34 functioning as a learning unit, and a transmission control unit 35 functioning as an output unit.
[0039] Various databases are provided in the storage unit 18 of the management server 1. For example, a user DB 41 that stores user characteristic information, a segment DB 42 that stores segment information, a site DB 43 that stores website information, and the like are provided.
[0040] The information acquisition unit 31 acquires various types of information and stores it in a database in the storage unit 18. For example, the information acquisition unit 31 acquires user characteristic information and stores it in the user DB 41. The user characteristic information may be provided from the user terminal 2 or from the web server 3. Alternatively, the user characteristic information may be provided from other external sources. Furthermore, the timing at which the information acquisition unit 31 acquires the user characteristic information is not particularly limited. For example, the user characteristic information may be acquired at predetermined intervals (for example, every 24 hours).
[0041] The content of the user characteristic information acquired by the information acquisition unit 31 depends on the various services the user uses by operating the user terminal 2. For example, when the user uses a service that requires a login operation, attribute information such as name, age, date of birth, gender, place of residence, and interests may be acquired. Furthermore, when the user uses a service that does not require a login operation, attribute information such as language setting, behavioral information such as the time and region when the website was accessed, access route, number of page views (PV), number of sessions, average session time, bounce rate, exit rate, time on page, click-through rate (CTR), conversion rate (CVR), search keywords used at the time of access, information recorded in cookies saved in the browser at the time of access (behavioral history, number of visits, etc.), and device information such as type (smartphone, tablet, personal computer, etc.), OS (operating system), type and version of browser used, place of residence, and interests may be acquired.
[0042] Furthermore, the information acquisition unit 31 acquires information about the website provided by the web server 3. The website information includes information about the web pages that make up the website. The web page information includes information required to generate the web page. The information required to generate the web page includes, for example, information about the layout of the web page, information about the content posted on the web page, etc.
[0043] The information management unit 32 manages various types of information stored in the database of the storage unit 18. For example, the information management unit 32 manages user characteristic information stored in the user DB 41. Specifically, the information management unit 32 classifies users into segments based on the user characteristic information and manages the users. The method for classifying users into segments is not particularly limited. The information management unit 32 classifies users into segments using, for example, the following method. That is, the information management unit 32 may classify users into segments using a classification algorithm in machine learning or a clustering method. Examples of classification algorithms in machine learning include decision trees, logistic regression, random forests, SVMs (support vector machines), and neural networks. Examples of clustering methods include k-means, DBSCAN, and mathematical optimization including annealing. The information management unit 32 enables regular classification of users into segments based on the user characteristic information acquired by the information acquisition unit 31 by batch processing at predetermined intervals (for example, every 24 hours). Furthermore, the information management unit 32 manages, as user characteristic information, layouts that have already been output to the user terminal 2 operated by the user.
[0044] The information management unit 32 also manages segment information stored in the segment DB 42. The information management unit 32 also manages website information stored in the site DB 43. Specifically, the information management unit 32 manages multiple layout patterns defined for each website as website information. The layout patterns include content arrangement (e.g., columns), colors (e.g., warm colors, cool colors), etc. The number of layout patterns is not particularly limited and may range from several hundred to several thousand, or even more.
[0045] The layout modification unit 33 modifies the layout of a website accessed by a user operating the user terminal 2 in accordance with the user characteristic information of the user. For example, the management server 1 modifies the layout of a website accessed by a user to a layout in accordance with a layout pattern corresponding to the user's segment. The layout modification unit 33 uses a layout optimization model to enable modification of the layout of a website accessed by a user.
[0046] When changing the layout of a website using the layout optimization model, the layout modification unit 33 takes into consideration, for example, the following: website layout (arrangement, size, shape, number, etc. of content blocks), color scheme, text font, dynamic content (content, speed, etc.), loading speed, selection of web page on which content is to be placed (top page, article page, etc.), time of day when the user accessed the website, region from which the user is accessing the website, type of user terminal 2 (smartphone, personal computer, etc.), personal information and interests of the user, etc.
[0047] Furthermore, if the layout pattern of an output layout that has been output to a user included in the user characteristic information differs from the layout pattern corresponding to the user's segment, the layout change unit 33 changes the layout to the output layout instead of the layout pattern corresponding to the user's segment. This allows a suitable layout pattern to be adopted for each segment, while users who have already accessed the site can continue to view the site in the same layout as they viewed previously without changing the layout.
[0048] Furthermore, if the layout pattern of an output layout that has been output to a user included in the user characteristic information differs from the layout pattern corresponding to the user's segment, the layout change unit 33 changes the layout to a layout pattern similar to the output layout, rather than the layout pattern corresponding to the user's segment. This allows a layout pattern suitable for each segment to be adopted, while users who have already accessed the site can continue to view the site in a layout similar to the one they viewed previously, without any major changes to the layout.
[0049] Furthermore, when the layout pattern of an output layout that has been output to a user included in the user characteristic information is identical to a layout pattern corresponding to the user's segment, the layout modification unit 33 can change the layout to a layout pattern corresponding to a segment different from the user's segment. The layout modification unit 33 performs such layout modification at a predetermined timing (for example, randomly). Furthermore, the layout modification unit 33 can change the layout to a similar layout pattern that is slightly modified from the layout pattern corresponding to the user's segment. This allows the user to view a changed layout, which makes them understand that there has been an update and allows them to view with a fresh feeling.
[0050] The learning unit 34 trains the layout optimization model. The learning data for training the layout optimization model includes, for example, changes in the number of clicks, conversion rate, number of page views, number of sessions, average session time, and page visit time before and after a layout change, as well as a history of changes in the number of clicks, conversion rate, number of page views, number of sessions, average session time, and page visit time in the history of layout changes. Therefore, as the learning of the layout optimization model progresses, layout patterns that provide low user satisfaction are gradually eliminated, and accuracy is converged so that layout patterns that provide higher user satisfaction are output.
[0051] The transmission control unit 35 controls the transmission of various types of information via the communication unit 19. Specifically, the transmission control unit 35 controls the transmission of various types of information to the user terminal 2, the web server 3, and the outside. For example, the transmission control unit 35 controls the transmission of control information to the user terminal 2 for outputting the web page after the layout change on the display of the user terminal 2 or the like.
[0052] <Processing flow of Management Server 1> FIG. 4 is a flowchart showing an example of the processing flow of the management server 1. The management server 1 defines and manages web page layout patterns for each website (step S1). When the management server 1 acquires user characteristic information (YES in step S2), it classifies users into predetermined segments based on the user characteristic information and manages them (step S3). On the other hand, when the management server 1 has not acquired user characteristic information (NO in step S2), the management server 1 repeats the determination process of step S1.
[0053] The management server 1 associates layout patterns with segments and manages them (step S4). When the user accesses a website (YES in step S5), the management server 1 outputs a web page after changing the layout according to the layout pattern corresponding to the user's segment (step S6). On the other hand, if the user is not accessing the website (NO in step S5), the management server 1 repeats the determination process of step S5.
[0054] <Example> [Examples of web page layout changes] 5A to 5C are diagrams showing a specific example of this service. FIG. 5(A) shows the layout L of web page W before the layout change. "A" to "E" that make up layout L are contents. FIG. 5(B) shows the layout L1 of web page W that is displayed on user terminal 2-1 when user U1 who uses this service accesses web page W. FIG. 5(C) shows the layout L2 of web page W that is displayed on user terminal 2-2 when user U2 who uses this service accesses web page W.
[0055] As shown in FIG. 5(B), user U1 is classified into segment G1. When user U1 accesses web page W, the web page W is changed to a layout L1 corresponding to a layout pattern corresponding to segment G1 among multiple layout patterns defined in the web page W, and the changed web page W is displayed on user terminal 2-1. Also, as shown in FIG. 5(C), user U2 is classified into segment G2. When user U2 accesses web page W, the web page W is changed to a layout L2 corresponding to a layout pattern corresponding to segment G2, and the changed web page W is displayed on user terminal 2-2.
[0056] 6 and 7 show examples of segment-based batch processing and testing of layout changes. As shown in FIG. 6, as of the daytime on January 16th, among users U1 to U3 using the service, user U1 is classified into segment G1, user U2 is classified into segment G2, and user U3 is classified into segment G3. In this case, when user U1 accesses web page W, layout L1, which is a layout corresponding to segment G1 among the multiple layout patterns defined in web page W, is displayed on user terminal 2-1. When user U2 accesses web page W, layout L2, which is a layout corresponding to segment G2 among the multiple layout patterns defined in web page W, is displayed on user terminal 2-2. When user U3 accesses web page W, layout L3, which is a layout corresponding to segment G3 among the multiple layout patterns defined in web page W, is displayed on user terminal 2-3.
[0057] Now, suppose the following batch processing was performed during the night of January 16th. That is, user characteristic information for each of users U1 to U3 was acquired, and user U1 was classified into segment G2, user U2 into segment G1, and user U3 was classified into segment G3. In this case, when user U1 accesses web page W during the daytime on the following day, January 17th, layout L2, which is a layout corresponding to the layout pattern corresponding to segment G2, is displayed on user terminal 2-1. That is, the layout of web page W has changed before and after the batch processing.
[0058] Furthermore, when user U2 accesses web page W, layout L1, which is a layout corresponding to the layout pattern corresponding to segment G1 among the multiple layout patterns defined in web page W, is displayed on user terminal 2-2. In other words, the layout of web page W has changed before and after batch processing. In contrast, when user U3 accesses web page W, layout L3, which is a layout corresponding to the layout pattern corresponding to segment G3 among the multiple layout patterns defined in web page W, is displayed on user terminal 2-3. In other words, the layout of web page W has not changed before and after batch processing.
[0059] In the batch processing performed during the night of January 17th, no segment changes were made, so no layout changes were made. However, the following layout change test was performed based on the daytime usage status on January 17th derived from the user characteristic information. That is, as shown in FIG. 7, user U1 is classified into segment G2, but as a layout change test, layout L2 corresponding to the layout pattern corresponding to segment G2 was slightly changed to layout L2-1. Also, user U2 is classified into segment G1, but as a layout change test, layout L1 corresponding to the layout pattern corresponding to segment G1 was slightly changed to layout L1-1. In contrast, layout change tests were not performed for user U3.
[0060] In this case, when user U1 accesses web page W during the day on the following day, January 18th, a layout L2-1 different from yesterday (January 17th) is displayed on user terminal 2-1. When user U2 accesses web page W, a layout L1-1 different from yesterday is displayed on user terminal 2-2. In contrast, when user U3 accesses web page W, a layout L3 similar to yesterday is displayed on user terminal 2-3.
[0061] After that, when batch processing is performed in the nighttime of January 18th, users U1 to U3 are classified into segments based on user characteristic information including usage during the daytime of January 18th. This derives the results of the layout change test. That is, as a result of the layout change test, the change in user U1's satisfaction with the layout change from layout L2 to layout L2-1 is derived. Also, the change in user U2's satisfaction with the layout change from layout L1 to layout L1-1 is derived.
[0062] If the layout change increases user U1's satisfaction, layout L2-1 is maintained (pattern 1). On the other hand, if the layout change decreases user U1's satisfaction, the layout is either changed back to the layout L2 before the test, or changed to layout L2-2, which is a slight modification of layout L2-1 (pattern 2). The same is true for user U2; if user U2's satisfaction increases, layout L1-1 is maintained (pattern 1), and if user U2's satisfaction decreases, layout L1-1 is either returned to the layout before the test, or changed to layout L1-2, which is a slight modification of layout L1-1 (pattern 2). By repeating this process every day, the accuracy of the layout optimization model converges.
[0063] <Advantageous Effects of the Present Embodiment> According to the above-described embodiment, the layout of a website accessed by a user can be adapted to suit the user.
[0064] <Other embodiments> Although one embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and modifications, improvements, etc. within the scope of achieving the object of the present invention are included in the present invention.
[0065] Furthermore, for example, the above-described series of processes can be executed by hardware or software. In other words, the above-described functional configuration is merely an example and is not particularly limited. In other words, it is sufficient for the information processing system to be provided with a function that can execute the above-described series of processes as a whole, and the type of functional block used to realize this function is not particularly limited to the above-described example.
[0066] The location of the functional blocks is not particularly limited and may be arbitrary. For example, the functional blocks of the management server 1 may be transferred to another device, or the functional blocks of another device may be transferred to a server. Furthermore, one functional block may be configured as a single piece of hardware, a single piece of software, or a combination of both.
[0067] When a series of processes is executed by software, the programs constituting the software are installed onto a computer or the like from a network or a recording medium. The computer may be a computer incorporated into dedicated hardware. The computer may also be a computer capable of executing various functions by installing various programs, such as a server, a general-purpose smartphone, or a personal computer.
[0068] The recording medium containing such a program may be configured as a removable medium (not shown) that is distributed separately from the device main body in order to provide the program to users, etc., or may be configured as a recording medium that is pre-installed in the device main body and provided to users, etc. Since the program can be distributed via a network, the recording medium may be installed in or accessible from a computer that is connected or connectable to the network.
[0069] In this specification, the steps describing the program recorded on the recording medium include not only processes that are performed in chronological order, but also processes that are not necessarily performed in chronological order but are performed in parallel or individually. Also, in this specification, the term "system" means an overall device composed of multiple devices or multiple means, etc.
[0070] In the above-described embodiments, the processing performed using a predetermined machine learning model can be realized using quantum computer technology. A quantum computer can execute the processing of optimization problems using a large number of parameters. That is, the use of a quantum computer enables the analysis of user attribute information and the consideration of segment and layout optimization to be performed at high speed. Even in such cases, at least a portion of the information processing of the above-described embodiments is expected to improve usability.
[0071] In other words, the information processing system to which the present invention is applied can take various forms having the following configurations. (1) That is, the information processing system S to which the present invention is applied is an information processing system that includes a user management means (e.g., information management unit 32 in FIG. 3) that acquires and manages user characteristic information including at least one of attribute information related to a user's attributes and behavioral information related to the user's behavior on a website, a layout modification means (e.g., layout modification unit 33 in FIG. 3) that modifies the layout of web pages that make up a website accessed by the user in accordance with the user characteristic information of the user, and an output means (e.g., transmission control unit 35 in FIG. 3) that outputs the web pages after the layout modification to an information processing device operated by the user.
[0072] (2) The system further includes a segment management means (e.g., information management unit 32 in FIG. 3) for associating and managing layout patterns of web pages for each predetermined segment, and the user management means classifies and manages users into the segments based on the user characteristic information of the users, and the layout change means can change the layout of the web pages constituting the website accessed by the users to a layout according to the layout pattern corresponding to the segment of the user.
[0073] (3) Furthermore, the user management means further manages the output layout that has been output to the information processing device operated by the user as the user characteristic information, and the layout change means can change the layout pattern corresponding to the segment of the user to the output layout or a layout of a layout pattern similar to the output layout if the layout pattern corresponding to the segment of the user is different from the layout pattern of the output layout.
[0074] (4) The layout modification means can also modify the layout of web pages constituting a website accessed by the user using a machine learning model that outputs a layout pattern of a web page based on the input user characteristic information.
[0075] (5) Furthermore, when the user characteristic information serving as an explanatory variable is input to the machine learning model, the machine learning model may attempt to change the layout of web pages constituting a website accessed by the user, and output a web page layout pattern that optimizes a predetermined objective variable.
[0076] (6) The objective variable may include one or more of the number of clicks, conversion rate, number of page views, number of sessions, average session time, and time spent on page.
[0077] (7) The system may further include a learning means for causing the machine learning model to learn using the user characteristic information of the user acquired after the layout change as learning data.
[0078] Furthermore, the information processing method to which the present invention is applied can take various forms having the following configurations. (8) In other words, an information processing method to which the present invention is applicable is an information processing method executed by an information processing system, which includes the steps of acquiring and managing user characteristic information including at least one of attribute information regarding a user's attributes and behavioral information regarding the user's behavior on a website, changing the layout of web pages constituting a website accessed by the user in accordance with the user characteristic information of the user, and outputting the web pages after the layout change to an information processing device operated by the user.
[0079] Furthermore, the program to which the present invention is applied can take various forms having the following configurations. (9) In other words, the program to which the present invention is applicable is a program that causes a computer of an information processing system to execute control processing including the steps of acquiring and managing user characteristic information including at least one of attribute information regarding a user's attributes and behavioral information regarding the user's behavior on a website, changing the layout of web pages that make up a website accessed by the user in accordance with the user characteristic information of the user, and outputting the web pages after the layout change to an information processing device operated by the user. [Explanation of symbols]
[0080] 1: Management server, 2: User terminal, 3: Web server, 11: CPU, 16: Output unit, 17: Input unit, 18: Memory unit, 19: Communication unit, 31: Information acquisition unit, 32: Information management unit, 33: Layout change unit, 34: Learning unit, 35: Transmission control unit, S: Information processing system, N: Network
Claims
1. a user management means for acquiring and managing user characteristic information including at least one of attribute information relating to a user's attributes and behavioral information relating to the user's behavior on a website; a layout change means for changing the layout of the web pages constituting the website accessed by the user in accordance with the user characteristic information of the user; an output unit for outputting the web page after the layout change to an information processing device operated by the user; An information processing system comprising:
2. The method further comprises a segment management means for managing a layout pattern of the web page in association with each predetermined segment, the user management means classifies and manages the users into the segments based on the user characteristic information of the users; the layout change means changes the layout of the web pages constituting the website accessed by the user to a layout according to a layout pattern corresponding to the segment of the user; The information processing system according to claim 1 .
3. The user management means further manages, as the user characteristic information, an output layout that has been output to the information processing device operated by the user; When a layout pattern corresponding to the segment of the user is different from a layout pattern of the output layout, the layout change means changes the layout to a layout of the output layout or a layout pattern similar to the output layout. The information processing system according to claim 2 .
4. the layout modification means modifies the layout of the web pages constituting the website accessed by the user using a machine learning model that outputs a layout pattern of the web pages based on the input user characteristic information. The information processing system according to any one of claims 1 to 3.
5. the machine learning model, when inputting the user characteristic information serving as an explanatory variable, attempts to change the layout of web pages constituting a website accessed by the user, and outputs a layout pattern of the web pages that optimizes a predetermined objective variable; The information processing system according to claim 4 .
6. The objective variable includes one or more of the number of clicks, the conversion rate, the number of page views, the number of sessions, the average session time, and the time spent on a page. The information processing system according to claim 5 .
7. a learning means for causing the machine learning model to perform learning using the user characteristic information of the user acquired after the layout change as learning data; The information processing system according to claim 4 , further comprising:
8. An information processing method executed by an information processing system, acquiring and managing user characteristic information including at least one of attribute information relating to a user's attributes and behavioral information relating to the user's behavior on a website; changing the layout of a web page constituting a website accessed by the user in accordance with the user characteristic information of the user; outputting the web page after the layout change to an information processing device operated by the user; An information processing method including:
9. To the computer of the information processing system, acquiring and managing user characteristic information including at least one of attribute information relating to a user's attributes and behavioral information relating to the user's behavior on a website; changing the layout of a web page constituting a website accessed by the user in accordance with the user characteristic information of the user; outputting the web page after the layout change to an information processing device operated by the user; A program that executes control processing including:
Citation Information
Patent Citations
Display advertisement code generation device, display advertisement code generation method, and display advertisement code generation program
JP2018190263A