Information processing method, program, and information processing device

Abstract

The present invention addresses the problem of improving work efficiency of an analyst by generating data easy for the analyst to use on the basis of data on analysis of a user action by web pages. In order to solve the problem, this information processing method is executed by an information processing device to: acquire analysis data having items including parameters related events related to a user action on a web page, and the events; generate, for each event, event data including attributes and parameters of the event on the basis of the analysis data; aggregate the parameters for the event data on the basis of a predetermined rule associated with the corresponding event; generate aggregated data on the basis of the event data including the aggregated parameters; and output the aggregated data.

Description

Technical Field

[0001] The disclosed technology relates to an information processing method, a program, and an information processing apparatus. Background Art

[0002] Conventionally, systems for analyzing user behavior on web pages are known. For example, there is a technology in which a content provider system interacts with a network of websites to provide behavior-based content to users, a website operator adds a widget to a selected web page of the site, the widget reports user-generated events to the content provider system, and the content provider system analyzes the reported events to detect behavioral relevance of specific websites, web pages, products and other types of items (see Patent Document 1). Prior Art Literature Patent Literature

[0003] Patent Document 1 Japanese National Publication of International Patent Application No. 2011-508925 Summary of the Invention Problems to be Solved by the Invention

[0004] Here, regarding analysis of user behavior on web pages, there are services that provide analysis data. For example, in GA4 (Google Analytics (Registered Trademark) 4) and the like, data is analyzed in event units with events related to user behavior on web pages as the axis of measurement, and analysis data is provided. However, although events and parameters are associated in the provided data, the data structure is extremely difficult to use because multiple events are mixed in the same file, and furthermore, there are multiple parameters even within the same event.

[0005] Therefore, the disclosure technology aims to improve the efficiency of analysts' work by generating data that is easy for analysts to use, based on analysis data of user behavior on web pages. [Means for solving the problem]

[0006] An information processing method in one aspect of the disclosure involves an information processing device acquiring analytical data having items including each event relating to user behavior on a web page and each parameter relating to said event; generating event data including event attributes and parameters for each event based on the analytical data; aggregating parameters from the event data based on predetermined rules associated with the corresponding event; generating aggregated data based on the event data including the aggregated parameters; and outputting the aggregated data. [Effects of the Invention]

[0007] According to disclosure technology, it is possible to improve the efficiency of analysts' work by generating data that is easy for analysts to use based on analysis data of user behavior on web pages. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows an example of the configuration of an information processing system according to one embodiment. [Figure 2] Block diagram showing an example of a server according to one embodiment. [Figure 3] A block diagram showing an example of a user device according to one embodiment. [Figure 4] This figure shows an example of analysis data according to one embodiment. [Figure 5] This figure shows an example of generating event data based on simplified analysis data according to one embodiment. [Figure 6] This figure shows an example of an event list according to one embodiment. [Figure 7]This figure shows an example of event data according to one embodiment. [Figure 8] This figure shows an example of aggregated data according to one embodiment. [Figure 9] This figure shows an example of the event aggregation data according to one embodiment. [Figure 10] This flowchart shows an example of server-related processing according to one embodiment. [Modes for carrying out the invention]

[0009] Preferred embodiments of the present disclosure will be described with reference to the attached drawings. In each drawing, components denoted by the same reference numerals have the same or similar components.

[0010] [Embodiment] <System Configuration> Figure 1 is a diagram showing an example of the configuration of an information processing system 1 according to one embodiment of the disclosure. As shown in Figure 1, the information processing system 1 includes a server 10 and one or more user devices 20A, 20B, 20C. The server 10 and one or more user devices 20 can send and receive data from each other via a network N. The server 10 may be composed of multiple processing units (including a database). The number of user devices 20A, 20B, 20C may be arbitrary, and if they are not individually distinguished, they are referred to as user devices 20.

[0011] Server 10 acquires analysis data from user device 20 via upload or other means, generates data that is easy for analysts to analyze based on the analysis data, and outputs the generated data to user device 20. The analysis data includes, for example, reports from GA4. Server 10 may consist of a server or database on the cloud.

[0012] The user device 20 is, for example, an information processing device (or processing terminal) used for analyzing user behavior on a web page provided by a user. As the user device 20, for example, a personal computer, a tablet terminal, a mobile terminal such as a smartphone, or the like is used.

[0013] The user device 20 acquires analysis data from a service that analyzes user behavior on a web page, for example, GA4. The user device 20, for example, accesses a web page provided by the server 10 using a web browser, and uploads the analysis data using this web page. The user device 20 downloads and acquires aggregated data processed to facilitate analysis of user behavior from the server 10.

[0014] According to the information processing system 1 described above, by generating data that is easy for an analyst to use based on analysis data of user behavior on a web page, the work efficiency of the analyst can be improved. Hereinafter, each configuration and the like of the information processing system 1 capable of executing the above-described processing will be described in detail.

[0015] <Configuration> <<Server>> Figure 2 is a block diagram showing an example of the server 10 according to an embodiment of the present disclosure. For example, the server 10 includes one or more processors (CPU: Central Processing Unit) 110, one or more network communication interfaces 120, a memory 130, and one or more communication buses 170 for interconnecting these components.

[0016] The server 10 may optionally include a user interface 150. The user interface 150 includes a display, an input device (such as a keyboard and / or mouse, or any other pointing device, etc.), and the like.

[0017] The memory 130 is, for example, a high-speed random access memory such as DRAM, SRAM, or other random access solid-state storage devices, and may also be a non-volatile memory such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state storage devices, and may be a computer-readable non-transitory recording medium.

[0018] The memory 130 stores data used by the information processing system 1. For example, the memory 130 stores various types of data such as analysis data, event lists, event data, and aggregated data. Details of each data will be described later with reference to FIGS. 4 to 10.

[0019] As another example of the memory 130, it may be one or more storage devices (e.g., a database) provided separately from the processor 110. In one embodiment, the memory 130 stores programs, modules and data structures, or subsets thereof, executed by the processor 110.

[0020] The processor 110 constitutes a control unit 112 by executing programs stored in the memory 130, and the control unit 112 constitutes an acquisition unit 113, a first generation unit 114, an aggregation unit 115, a second generation unit 116, and an output unit 117.

[0021] The control unit 112 controls processing for generating aggregated data that facilitates analysis of user behavior based on the analysis data. For example, the control unit 112 performs login to a service that generates aggregated data, and performs billing processing for system usage.

[0022] The acquisition unit 113 acquires analytical data that includes items containing each event related to user behavior on a web page, and each parameter related to that event. For example, the acquisition unit 113 acquires analytical data from GA4. In the analytical data, multiple events are mixed together, and each event contains multiple attributes and parameters corresponding to these attributes in an unorganized manner. In addition, the analytical data may have a structure in which tables are nested within tables, or the definition of items may be insufficient (strings, percentages, numbers, etc. may be included without distinction). The analytical data will be described later using Figure 4.

[0023] Events include, for example, scrolling, file downloads, clicks, page views, session start, and user-defined attributes (dimensions).

[0024] The first generation unit 114 generates event data for each event, including event attributes and parameters, based on the analysis data acquired by the acquisition unit 113. For example, the first generation unit 114 classifies events using their event names and generates event data for each event. The event data will be described later using Figure 5 or Figure 7.

[0025] The aggregation unit 115 aggregates parameters for each event data generated by the first generation unit 114 based on predetermined rules associated with the corresponding event. For example, the aggregation unit 115 acquires predetermined event data, analyzes the data contained in the event data, converts the data format to make it easier for the user (analyst) to analyze, or extracts attributes and parameters to reorganize the data structure.

[0026] The prescribed rules are associated with each event and define how parameters should be handled. For example, if a parameter is a number, numerical arithmetic operations are defined; if a parameter is a character, string processing is defined.

[0027] The second generation unit 116 generates aggregated data based on event data including parameters aggregated by the aggregation unit 115. For example, the second generation unit 116 may generate aggregated data in a data format (one record per row) where each attribute of the event is represented by a column item. The aggregated data will be described later, for example, using Figures 8-9.

[0028] The output unit 117 outputs aggregated data. For example, if the user device 20 requests a download, the output unit 117 outputs the aggregated data to the user device 20. The aggregated data has one file format that allows for data editing or analysis, such as CSV or Excel.

[0029] Through the above process, it is possible to improve the efficiency of analysts' work by generating data that is easy for analysts to use based on analysis data of user behavior on web pages.

[0030] The first generation unit 114 may also include classifying each event according to the registered event list. The event list is stored in memory 130 and may include events specified by the user (analyst) or events extracted from analysis data.

[0031] Through the above process, the event list allows analysts to efficiently extract the events they want to analyze.

[0032] Furthermore, the first generation unit 114 may include a list generation unit that generates an event list based on pre-set events. The first generation unit 114 may determine whether each event included in the analysis data acquired by the acquisition unit 113 is included in the event list. If the first generation unit 114 determines that there is a predetermined event that is not included in the event list, it may also include registering the predetermined event in the event list.

[0033] The pre-configured events may include events that are included in the analysis data by default. Furthermore, users can freely configure the events to be analyzed regarding the acquisition of analysis data. Events configured by the user are not included in the default event list. Even in this case, the first generation unit 114 can identify user-specific events configured by the user by comparing them with each event included in the event list, and therefore can register these unique events in the event list.

[0034] Alternatively, the first generation unit 114 may generate an event list based on analysis data that includes events pre-configured by the user behavior analysis service. In this case, there are no events included in the initial event list, but the first generation unit 114 may extract events included in the analysis data one by one and register these events in the event list.

[0035] Through the above process, the event list is automatically generated, making it possible to register new events included in the analysis data to the event list without burdening the user.

[0036] Furthermore, the first generation unit 114 may set events that should not be registered in the event list. For example, the first generation unit 114 determines whether an event extracted from the analysis data corresponds to an event that cannot be registered, and if it is an event that cannot be registered, it does not register it in the event list. This allows users to exclude events that are unnecessary for analysis from the analysis target, making it possible to analyze events efficiently.

[0037] If multiple events indicate the same scroll event, the prescribed rule may include obtaining the maximum value from among multiple numerical values ​​included in multiple parameters corresponding to the multiple events.

[0038] For example, if there are identical scroll events (e.g., same user, same page, same session, etc.) in the scroll event data, the aggregation unit 115 obtains the maximum value of the scroll rate (percentage of scrolling relative to the total page) included in the parameter and merges the identical scroll events. Note that in some cases the parameter is simply a number, in which case the aggregation unit 115 may determine the unit of the numerical value of the parameter based on the meaning of the event included in the event data (e.g., column name).

[0039] By performing the above process, if there are multiple identical scroll events, only the maximum scroll rate is retained, thereby reducing the amount of data and improving the efficiency of analysis.

[0040] If multiple events indicate the same download event, the prescribed rule may include obtaining the sum of multiple numerical values ​​contained in multiple parameters corresponding to the multiple events.

[0041] For example, the aggregation unit 115, when it finds identical download events in the download event data, obtains the total number of downloads included in the parameters and merges the identical download events. For example, the aggregation unit 115 calculates the total number of downloads for each file that can be downloaded from the same web page.

[0042] Through the above processing, if there are multiple download events for each file from the same web page, the total number of downloads for each file is aggregated, and only the total value is retained in the aggregated data, thereby reducing the amount of data and improving the efficiency of analysis. The aggregation unit 115 can also aggregate the number of downloads for the same file. For example, the aggregation unit 115 may identify the downloaded file using the file name and the URL indicating the file's storage location, and count the number of downloads for each file. The aggregation unit 115 may also aggregate user behavior on application screens rather than web pages. For example, event data on application screens may be used as the primary key, and parameters may be aggregated for each event.

[0043] If multiple events containing strings as parameters refer to the same event, the prescribed rule may include concatenating (or merging) the multiple strings contained in the multiple parameters corresponding to the multiple events according to a prescribed criterion. The prescribed criterion may be, for example, concatenating the multiple strings using commas.

[0044] For example, the aggregation unit 115, when it finds identical events (e.g., same user, same page, same session, etc.) in the event data of a dimension set by the user, concatenates the strings contained in each parameter (e.g., user input values, etc.) and integrates the events of the same dimension.

[0045] Through the above process, when there are multiple events of the same dimension, the amount of data can be reduced and the efficiency of analysis can be improved by concatenating the parameter strings.

[0046] The aggregated data may include aggregated data for each event, or aggregated data that combines the aggregated data for each event. That is, the second generation unit 116 generates aggregated data for each event and / or aggregated data as aggregated data. For example, the second generation unit 116 may first generate aggregated data for each event and then generate aggregated data as needed, or it may generate aggregated data as a requirement. The aggregated data may be in a data format where, for example, there is one record (one row) per page view, and each event is represented by a column item.

[0047] Through the above process, it becomes possible to configure the generation of aggregated data for each user, thereby increasing the variety of outputs available to users.

[0048] Furthermore, the first generation unit 114 may also include identifying individual events based on identification information that includes a user ID (for example, user_pseudo_id shown in Figure 4) and a session ID included in the parameters (for example, ga_session_id shown in Figure 4). By using this identification information as a primary key, the first generation unit 114 can extract events as separate events even if the user ID is the same, if the session ID is different. This also makes it possible to analyze user behavior on a session-by-session basis.

[0049] User device Figure 3 is a block diagram showing an example of a user device 20 according to one embodiment of the disclosure. For example, the user device 20 includes one or more processors (CPUs) 210, one or more network communication interfaces 220, memory 230, and one or more communication buses 270 for interconnecting these components.

[0050] The user interface 250 includes a display 251 and an input device (such as a keyboard and / or mouse, or any other pointing device) 252.

[0051] Memory 230 is, for example, a high-speed random-access memory such as DRAM, SRAM, or other random-access solid-state memory, and may also be a non-volatile memory such as one or more magnetic disk memory devices, optical disk memory devices, flash memory devices, or other non-volatile solid-state memory devices, or a computer-readable non-temporary recording medium.

[0052] Memory 230 stores data used by the information processing system 1. For example, memory 230 stores analytical data for analyzing user behavior on web pages.

[0053] Another example of memory 230 may be one or more storage devices located remotely from the processor 210. In one embodiment, memory 230 stores programs, modules, and data structures, or subsets thereof, executed by the processor 210.

[0054] The processor 210 configures the client application 212 by executing a program stored in memory 230. The client application 212 includes, for example, a web browser and an email application. The web browser can access web pages provided by the server 10.

[0055] Furthermore, the processor 210 can enjoy the services provided by the server 10 by executing a program stored in the memory 230. The processor 210 also has an output unit 213, an acquisition unit 214, and a display control unit 215 for executing the processing of the disclosed technology.

[0056] The output unit 213 outputs the analysis data stored in the memory 230 to the server 10 via the network communication interface 220. For example, the output unit 213 uploads the analysis data using a web page provided by the server 10.

[0057] The acquisition unit 214 acquires aggregated data generated by the server 10 based on the outputted analysis data from the server 10 via the network communication interface 220.

[0058] The display control unit 215 controls the screen displayed on the display 251. For example, it controls the display screen to show aggregated data.

[0059] In summary, the user device 20 displays aggregated data generated by the server 10, and by analyzing this data, the user can efficiently analyze user behavior on web pages.

[0060] <Examples of each data> Next, some of the data used in the disclosed technology will be explained with reference to Figures 4 to 10.

[0061] Figure 4 shows an example of analysis data according to one embodiment. The example shown in Figure 4 is analysis data in JSON format obtainable by GA4. The analysis data shown in Figure 4 includes "event date", "event timestamp", "event_name", "event_params", "event_bundle_sequence_id", "user_pseudo_id", etc. In addition, the analysis data may be directly connected to a data storage service on the cloud using an API or the like, and that data may be analyzed. Furthermore, when uploading and downloading analysis data, instead of a single file, a single file compressed from multiple files may be processed.

[0062] "event date" indicates the date and time the event occurred, "event timestamp" indicates the time the event occurred, "event_name" indicates the name of the event, "event_params" contains the event parameters, "event_bundle_sequence_id" indicates an ID used to group events that occurred at the same time into one, and "user_pseudo_id" indicates the user ID.

[0063] Furthermore, "event_params" includes a "key" that indicates the event's attributes and a "value" that corresponds to that "key". There are two types of "value": a string "string_value" and a number "int_value".

[0064] As shown in Figure 4, "event_name" contains multiple parameters within "scroll," for example, the values ​​(numbers or strings) of parameters corresponding to each key, resulting in a disorganized, complex data structure and a data format that is difficult to analyze.

[0065] Figure 5 shows an example of event data generation based on simplified analysis data according to one embodiment. The simplified analysis data on the left in Figure 5 includes "pagescroll" and "filedownload" in "event_name," and each event has multiple keys (attributes) and parameter values ​​corresponding to each key.

[0066] The first generation unit 114 generates event data for the pagescroll (pagaview) event (top right table) and the filedownload event (bottom right table) shown in Figure 5, based on the simplified analysis data on the left shown in Figure 5. For example, the first generation unit 114 dynamically creates and executes SQL statements using the column names for each "key" stored in the columns of the simplified analysis data. The first generation unit 114 refers to integer or string values ​​that contain values ​​as data to be inserted into the event data.

[0067] The first generation unit 114 can generate a portion of the event table using, for example, the following SQL statement. CREATE TABLE pagescroll ( (common column), key1, key2 ) CREATE TABLE filedownload( (common column), key1, key2, key3 )

[0068] Through the above process, even if an event contains multiple attributes and parameters (numerical or string) for those attributes, the data can be restructured into a format that makes it easy to analyze each attribute as a column item.

[0069] Figure 6 shows an example of an event list according to one embodiment. Figure 6 includes some of the events provided by GA4. For example, "click", "file_download", and "scroll" are included in the event list.

[0070] The first generation unit 114 may include a new event (e.g., a custom dimension) set by the user in the event list if the analysis data includes such a new event.

[0071] An example of generating aggregated data will be explained using Figures 7 to 9. Figure 7 shows an example of event data according to one embodiment. The content of "value" in the simplified event data shown in Figure 7 can vary depending on the event, including only numerical values, a mix of alphanumeric characters, and so on.

[0072] Figure 7(A) shows an example of simplified event data for pagescroll. Two events are extracted for pageA, where the PV (pageview) is the same as "pageA". In this case, the aggregation unit 115 obtains the maximum value as a predetermined rule for identical scroll events, so it obtains 90% of 50% and 90%, and aggregates the two scroll events for pageA as events with a scroll rate of 90% of the maximum value.

[0073] Figure 7(B) shows an example of simplified event data for filedownload. Two events are extracted for pageA, where the PV (pageview) is the same as that of pageA. In this case, the aggregation unit 115 calculates a total value according to a predetermined rule for identical file download events, so it calculates a total of "3" ("2" times + "1" time) and aggregates the two download events for pageA as events with a total value of "3".

[0074] Figure 7(C) shows an example of simplified event data for custom dimension A. Two events are extracted for page A, where the PV (pageview) is the same as "page A". In this case, the aggregation unit 115, following a predetermined rule for identical events in custom dimension A, concatenates strings, so it concatenates "ABC" and "nbv" and aggregates the two custom dimension A events for page A as an event with the string "ABC,nbv".

[0075] Figure 8 shows an example of aggregated data according to one embodiment. For example, the aggregated data shown in Figure 8 is data that combines aggregated data for each event. The aggregated data has aggregated values ​​for page scrolls, file downloads, and custom dimension A, based on page views.

[0076] For example, "pageA" contains page scroll "0.9", file download "3 times", and custom dimension A "ABC, nbv". "pageB" contains page scroll "1". Note that the parameter values ​​included in the analysis data are assumed to be numerical only, in which case the unit of the numerical value is specified as "%" based on the event data "scroll" (column name), and the event aggregate data is generated with "0.9" and "1" representing 90% and 100% respectively.

[0077] Figure 9 shows an example of event aggregation data according to one embodiment. Figure 9(A) shows the aggregation data for scroll events, where the event data shown in Figure 7(A) is aggregated on a page view basis. For example, in "pageA", the scroll parameter values ​​are grouped together at the maximum scroll rate of "90%".

[0078] Figure 9(B) shows aggregated data for file download events, where the event data shown in Figure 7(B) is aggregated on a page view basis. For example, in "pageA," the value of the download count parameter is aggregated to a total value of "3 (=2+1)."

[0079] Figure 9(C) shows aggregated event data for a custom dimension, where the event data shown in Figure 7(C) is aggregated on a pageview basis. For example, "pageA" is created by concatenating the strings contained in the parameter values ​​of each event with commas to form "ABC, nbv".

[0080] Regarding the aggregated data shown in Figure 8 or Figure 9, the output unit 117 only needs to output the file specified by the user. This allows the information processing system 1 to determine the billing amount based on the aggregated data output to the user device 20.

[0081] <Operation Description> Next, we will describe the various operations of the information processing system 1. Figure 10 is a flowchart showing an example of processing related to the server 10 according to one embodiment. The processing shown in Figure 10 is, for example, the processing that takes place after the user device 20 logs in to the service provided by the server 10.

[0082] In step S102, the acquisition unit 113 of the server 10 acquires analytical data having items that include each event related to user behavior on the web page and each parameter related to said event.

[0083] In step S104, the first generation unit 114 of the server 10 determines whether there is a new event (e.g., event_name) in the acquired analysis data that is not included in the event list. If there is a new event (step S104-YES), the process proceeds to step S106; if there is no new event (step S104-NO), the process proceeds to step S108.

[0084] In step S106, the first generation unit 114 of the server 10 registers a new event in the event list and updates the event list.

[0085] In step S108, the first generation unit 114 of the server 10 generates an event table for each event identified based on the event list (for example, Figures 5 and 7). The event table reconstructs the values ​​of each key and its parameters included in the "event_params" of the analysis data into a single-column record, making it easier to analyze. For example, by using the user ID + session ID mentioned above as the primary key, the first generation unit 114 makes it possible to analyze events with different primary keys, even if they have the same page view, in more detail.

[0086] In step S110, the aggregation unit 115 of the server 10 aggregates the parameters of the same event (e.g., the same page view) for each event table based on predetermined rules associated with the corresponding event.

[0087] In step S112, the second generation unit 116 of the server 10 generates aggregated data based on the aggregated event data (for example, Figure 8 or Figure 9).

[0088] In step S114, the output unit 117 of the server 10 outputs the aggregated data generated by the second generation unit 116 to the user device 20.

[0089] Through the above process, it is possible to improve the efficiency of analysts' work by generating data that is easy for analysts to use based on analysis data of user behavior on web pages.

[0090] Although embodiments have been described in detail above, the invention is not limited to the embodiments described above, and various modifications and changes are possible within the scope of the claims, as shown below.

[0091] [Differentiation] For example, the disclosed technology may integrate the processing on the server side and the user device side as appropriate, or transfer processing to the other device, as long as it does not deviate from its gist. For example, when analytical data is input to an AI (Artificial Intelligence) machine learning model, it is not possible to properly train the model if the data remains unorganized. Therefore, the second generation unit 116 may generate the aggregated data described in the above embodiment as training data for training the machine learning model. As a result, the analytical data is reconstructed in a form that is easy to analyze, thereby improving the training efficiency of the learning model. Furthermore, the server 10 may generate training data for each holder of the analytical data, or it may generate training data by combining the analytical data for each holder's industry, or it may generate training data for all the analytical data together.

[0092] Specifically, when server 10 receives a request to acquire training data from a user device, it uses the user ID included in the acquisition request to use the past aggregated data of the owner as training data, and the industry ID to use the aggregated data associated with that industry ID as training data, and if all aggregated data is to be shown, it generates all aggregated data as training data. Server 10 may also determine the billing amount to be charged to the user according to the amount of aggregated data included in the training data.

[0093] The second generation unit 116 may input the aggregated data generated by the above-described process into a large-scale language model (LLM) or machine learning model along with the instructions, and perform further aggregation or analysis. For example, the LLM or machine learning model may be pre-loaded with data from a schema definition document that defines the structure of the analysis data within the database. This allows the LLM or machine learning model to understand the structure of the aggregated data, enabling it to perform analysis and aggregation based on the schema definition document.

[0094] Furthermore, the definitions of conversion and / or bounce rate are loaded into the large-scale language model or machine learning model. Since there are various definitions of conversion and bounce rate, data containing general definitions of conversion and / or bounce rate is loaded into the large-scale language model or machine learning model in order to use a uniform definition.

[0095] Furthermore, the second generation unit 116 may be equipped with a function to input prompts to a large-scale language model or machine learning model to identify pages or paths that contribute to sales, and to analyze the impact of those pages on purchases. The second generation unit 116 may also have a function to automatically generate graphs and tables based on the analysis results of aggregated data, and may be equipped with format and design rules for presenting information visually.

[0096] Furthermore, the second generation unit 116 may have a function to generate a lightweight file by integrating multiple JSON files and removing unnecessary data columns. The second generation unit 116 may also have a function to extract only the necessary data from a large dataset and perform analysis efficiently.

[0097] The second generation unit 116 may, for example, input prompts to the large-scale language model that include instructions to aggregate the period, number of page views, number of sessions, and number of users along with the aggregated data, and obtain the aggregated results. Alternatively, after aggregation, the second generation unit 116 may input additional prompts to the large-scale language model, such as those shown below, and obtain the analysis results. List the content and pages that visitors view most frequently before making a sale or conversion. Also, analyze the impact those pages have on purchasing decisions. Identify the blog posts, product description pages, or FAQ pages that visitors frequently view before making a purchase or conversion, and analyze how these pages impact sales. Analyze the pages with high viewing time and click-through rates, and in particular, analyze which pages visitors go through before converting or making a purchase. The above is merely one example and is not limited to the above example. [Explanation of symbols]

[0098] 1...Information processing system, 10...Server, 20...User device, 110...Processor, 130...Memory, 112...Control unit, 113...Acquisition unit, 114...First generation unit, 115...Aggregation unit, 116...Second generation unit, 117...Output unit, 210...Processor, 212...Client application, 213...Output unit, 214...Acquisition unit, 215...Display control unit

Claims

1. Information processing device, To obtain analytical data provided by a service that analyzes user behavior on a web page or application, which includes items containing each event related to user behavior on a web page or application, and each parameter related to each event. Based on pre-configured events, generate an event list in which each event is registered. To determine whether each event included in the aforementioned analysis data is included in the aforementioned event list, If it is determined that there is a predetermined event not included in the aforementioned event list, the predetermined event shall be registered in the aforementioned event list. Based on the aforementioned analysis data, event data is generated that includes event attributes and parameters for each event, and is classified according to the registered event based on the aforementioned event list. The event data is processed based on predetermined rules associated with the corresponding event, and parameters corresponding to the attributes of the event are processed accordingly. An information processing method that performs the following.

2. Processing the aforementioned parameters means The information processing method according to claim 1, further comprising aggregating parameters corresponding to the attributes of the aforementioned event.

3. The aforementioned information processing device To generate aggregated data based on the event data after aggregation, The information processing method according to claim 2, further comprising outputting the aggregated data.

4. The information processing method according to any one of claims 1 to 3, wherein, when multiple events indicate the same scroll event, the predetermined rule includes obtaining the maximum value from among multiple numerical values ​​included in multiple parameters corresponding to the multiple events.

5. The information processing method according to any one of claims 1 to 3, wherein, when multiple events indicate the same download event, the predetermined rule includes obtaining the sum of multiple numerical values ​​included in multiple parameters corresponding to the multiple events.

6. The information processing method according to any one of claims 1 to 3, wherein, when multiple events containing strings as parameters indicate the same event, the predetermined rule includes concatenating multiple strings contained in multiple parameters corresponding to the multiple events according to a predetermined criterion.

7. The information processing method according to claim 3, wherein the aggregated data includes event aggregated data for each event, or comprehensive aggregated data which is a compilation of the event aggregated data.

8. Generating the aforementioned event data means The information processing method according to claim 1, comprising identifying individual events based on identification information including a user ID and a session ID included in the parameters.

9. The information processing method according to claim 3, further comprising inputting a prompt to a large-scale language model that has read schema definition data of the analysis data, which includes instructions to aggregate the aggregate data and at least one of the period, number of page views, number of sessions, and number of users, and obtaining the aggregation results.

10. In an information processing device, To obtain analytical data provided by a service that analyzes user behavior on a web page or application, which includes items containing each event related to user behavior on a web page or application, and each parameter related to each event. Based on pre-configured events, generate an event list in which each event is registered. To determine whether each event included in the aforementioned analysis data is included in the aforementioned event list, If it is determined that there is a predetermined event not included in the aforementioned event list, the predetermined event shall be registered in the aforementioned event list. Based on the aforementioned analysis data, event data is generated that includes event attributes and parameters for each event, and is classified according to the registered event based on the aforementioned event list. The event data is processed based on predetermined rules associated with the corresponding event, and parameters corresponding to the attributes of the event are processed accordingly. A program that executes the command.

11. An information processing apparatus comprising one or more processors, The one or more processors described above To obtain analytical data provided by a service that analyzes user behavior on a web page or application, which includes items containing each event related to user behavior on a web page or application, and each parameter related to each event. Based on pre-configured events, generate an event list in which each event is registered. To determine whether each event included in the aforementioned analysis data is included in the aforementioned event list, If it is determined that there is a predetermined event not included in the aforementioned event list, the predetermined event shall be registered in the aforementioned event list. Based on the aforementioned analysis data, event data is generated that includes event attributes and parameters for each event, and is classified according to the registered event based on the aforementioned event list. The event data is processed based on predetermined rules associated with the corresponding event, and parameters corresponding to the attributes of the event are processed accordingly. An information processing device that performs the following actions.

Images