Information processing device, method, program

Abstract

The goal is to provide technology that makes it easier for users to access content containing useful information. [Solution] The memory unit stores information about the search words specified by each user to search for content, and browsing behavior information, which is the content of each user's browsing behavior when they view content based on the search results corresponding to the search words, in association with each other. The program causes one or more computer processors to perform the following steps: receive a search word specification from a first user to search for content; identify content to recommend to the first user based on the browsing behavior information in the memory unit relating to the search words that are the same as or similar to the search words specified in the receiving step; and present the content identified in the identification step to the first user.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing apparatus, method, and program. [Background Art]

[0002] There are services that provide e-books for browsable access. In such services, there exist technologies for making it easier for users to search for e-books that they wish to browse.

[0003] Patent Document 1 below describes a technology for extracting e-books browsed by many users for each theme (keyword). Specifically, Patent Document 1 describes that an e-book management device stores a user's browsing time for each page constituting an e-book, aggregates, for each keyword included in the e-book, the browsing time of pages of the e-book that include said keyword, and calculates a keyword characteristic score for each e-book based on the aggregated browsing time of each keyword. [Prior Art Literature] [Patent Literature]

[0004] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2012-068971 [Summary of the Invention] [Problem to be Solved by the Invention]

[0005] The technology described above generates feature scores for keywords within pages and page viewing time in ebook searches, making it possible to understand the number of times each keyword appears on pages viewed by many users for each ebook. However, even if frequently appearing keywords are used as the theme of an ebook, the keywords corresponding to the theme do not necessarily directly relate to the content the user wants to know. In the example in Patent Document 1, there are cases where the keywords "mobile phone" and "smartphone" both have high scores for different books, and users cannot ascertain the differences in the content of each ebook. Therefore, even starting from the theme, it may not be easy for the user to find the ebook they want. For this reason, there is a need for technology that recommends content that corresponds to what the user wants.

[0006] The purpose of this disclosure is to provide technology that makes it easier for users to access content containing useful information. [Means for solving the problem]

[0007] According to one embodiment, a program is provided for operating a computer having one or more computer processors. In the memory unit, information on search words specified by each user to search for content is stored in association with browsing behavior information, which is the content of each user's browsing behavior when they view content based on the search results corresponding to the search words. The program causes one or more computer processors to perform the following steps: receiving a search word specification from a first user to search for content; identifying content to recommend to the first user based on the browsing behavior information in the memory unit relating to search words that are the same as or similar to the search word specified in the receiving step; and presenting the content identified in the identification step to the first user. [Effects of the Invention]

[0008] This disclosure makes it possible to make content containing useful information for users even easier to access. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 shows the configuration of System 1. [Figure 2] Figure 2 shows the configuration of server 20. [Figure 3] Figure 3 shows the configuration of terminal 10. [Figure 4] Figure 4 shows the data structure of the user database 211. [Figure 5] Figure 5 shows the data structure of the content database 212. [Figure 6] Figure 6 shows the data structure of the search and browsing history database 213. [Figure 7] Figure 7 shows the process flow for presenting recommended content to the user in response to their search actions. [Figure 8] Figure 8 shows the process flow for extracting supporting literature and generating answers in a question-answering system that responds to questions. [Figure 9] Figure 9 shows an example of an operation screen that accepts a content search operation and displays the content. [Figure 10] Figure 10 shows an example of the user interface for a system that generates answers to questions. [Modes for carrying out the invention]

[0010] The embodiments of this disclosure will be described below with reference to the drawings. In all the drawings illustrating the embodiments, common components are denoted by the same reference numerals, and repeated explanations are omitted. The following embodiments are not intended to unduly limit the content of this disclosure as described in the claims. Not all components shown in the embodiments are necessarily essential components of this disclosure. Also, each drawing is a schematic diagram and is not necessarily a strict illustration.

[0011] Furthermore, in the following description, "processor" refers to one or more processors. At least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may be another type of processor such as a GPU (Graphics Processing Unit). At least one processor may be single-core or multi-core.

[0012] Furthermore, at least one processor may be a broad-sense processor, such as a hardware circuit that performs some or all of the processing (e.g., an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit)).

[0013] Furthermore, in the following explanation, we may use expressions such as "xxx table" to describe information that yields an output for a given input. This information can be data with any structure, or it can be a learning model such as a neural network that generates an output for a given input. Therefore, "xxx table" can be referred to as "xxx information."

[0014] Furthermore, in the following explanation, the structure of each table is just an example; one table may be divided into two or more tables, or all or part of two or more tables may be a single table.

[0015] Further, in the following description, processing may sometimes be explained with a "program" as the subject. Since a program is executed by a processor to perform predetermined processing while appropriately using a storage unit and / or an interface unit or the like, the subject of the processing may be the processor (or a device such as a controller including the processor).

[0016] The program may be installed in a device such as a computer, or may be stored in, for example, a program distribution server or a computer-readable (e.g., non-transitory) recording medium. Further, in the following description, two or more programs may be implemented as a single program, and a single program may be implemented as two or more programs.

[0017] Further, in the following description, identification numbers are used as identification information for various objects, but types of identification information other than identification numbers (for example, identifiers including alphabetic characters and codes) may be employed.

[0018] Further, in the following description, reference signs (or common reference codes among reference signs) are used when elements of the same kind are described without distinction, and element identification numbers (or reference signs) are sometimes used when elements of the same kind are described with distinction.

[0019] Further, in the following description, control lines and information lines show those considered necessary for explanation, and not all control lines and information lines are necessarily shown in the product. All components may be mutually connected.

[0020] <Schematic of Embodiment> Embodiments are described below.

[0021] <First Embodiment> <1.1 Configuration Diagram of the Entire System> Figure 1 is a diagram showing the configuration of a system 1.

[0022] System 1, shown in Figure 1, includes a server 20 for content viewing services and a question answering system, a user terminal 10, a server 92 for business support system services, a server 93 for document review services, a server 95 for artificial intelligence (large-scale language model) services, a server 96 for document creation services, a server 97 for sales support system services, and a server 98 for messaging services. These devices communicate with each other via a network 80.

[0023] In the illustrated example, terminal 10 is shown as the terminal used by users of the service provided by server 20, but each user operates their own terminal.

[0024] Server 20 may be a device that provides services for concluding contracts electronically and services for managing document data concluded electronically. In System 1, the contract conclusion service provided by Server 20 and the document data management service may be provided by separate devices and separate service providers. For example, Server 20 may provide a document management service and, in addition to the data of electronically signed contracts, optically scan paper contracts with seals to extract information such as the contract period and whether the contract is automatically renewed, and manage this information along with the scanned contract data as management information. This would allow the server to notify the user when the contract period expires.

[0025] Server 20 may also be a server that provides services to support tasks such as submitting approval requests to organizations (business companies, etc.) that conduct business activities. For example, Server 20 provides a service to users that enables them to design a workflow for obtaining budget approval with multiple users.

[0026] Terminal 10 is a device operated by the user.

[0027] The business support system service server 92 provides users with tools that can be used for the organization's business operations. The business support system service server 92 provides users with a system for submitting approval requests as part of the organization's business operations. The business support system service server 92 may also communicate with server 20 to provide server 20 with data accumulated by the approval request service.

[0028] The document review service server 93 accepts document data such as contracts and term sheets that define contract terms, and provides users with information on whether each clause is advantageous or disadvantageous to the company, whether there are any missing clauses, and the importance of the review items, thereby supporting the review of the document data. The document review service server 93 provides the above review support service using rule-based or pre-trained models. As a rule-based approach, for example, it may be possible to perform rule-based reviews of document data by associating specific wording or expressions with pre-defined information on whether the conditions are advantageous or disadvantageous, and explanations. Alternatively, for example, it may be possible to provide the above review service by generating a pre-trained model that responds with review results to document data input, using data from expert reviews of contracts, term sheets, etc., as training data. Furthermore, the document review service server 93 can also summarize the contents of contracts and generate review comments using a large-scale language model, and provide the results to the user. For example, the document review service server 93 may prompt the large-scale language model service server 95 with the document data to be reviewed (such as contract data) and information indicating the review criteria, and instruct the server 95 to perform the review according to the review criteria. By receiving the output of the large-scale language model service server 95, the server 93 may generate review comments for the document data. The document review service server 93 may also communicate with server 20 to provide the server 20 with data accumulated by the document review service.

[0029] Server 95 of the Large-Scale Language Model Service is a server that executes language processing tasks using language models built through learning processes including artificial intelligence (AI). An LLM (Large Language Model) is a model that has been pre-trained on large amounts of data (such as text data), for example, a large amount of web content on the internet, or a large amount of data stored in a designated database, and can perform various language processing tasks by being given a task.

[0030] The AI ​​service server 95 (sometimes referred to as the "large-scale language model service server 95") accepts prompt input in the form of text, images, audio, etc., and generates and responds with answers to those prompts. Examples of LLMs include GPT-3, GPT-4, and GPT-4o developed by OpenAI, and Gemini developed by Google.

[0031] The document creation service server 96 provides a service for managing document data such as meeting minutes in organizations conducting business activities. Server 96 can issue URLs (Uniform Resource Locators) for accessing document data, and for example, if the user account of a user of the document creation service has access rights to the document data, the document data can be accessed via the URL. The document creation service server 96 may also be linked with a server that provides a schedule management service with calendar functionality, so that user accounts are common to both services. For example, having a user account may allow access to both the schedule management service and the document creation service. In this case, if document data from the document creation service is associated with a schedule, access rights to that document data may be set for users participating in the schedule.

[0032] The document creation service server 96 may communicate with server 20 to provide server 20 with data accumulated by the document creation service.

[0033] The sales support system service server 97 provides services to support sales activities. For example, the sales support system service server 97 provides the following to the user: • For each sales project, manage information such as the client, transaction details (amount, goods), transaction history (memos, meeting minutes, etc.), and responsible person (our company, the other party, etc.). • Provide analysis results of sales performance (such as trends in closing rates) for each sales team. The server 97 of the sales support system service may communicate with the server 20 to provide the server 20 with the data accumulated by the sales support system service.

[0034] The messaging service server 98 provides users with a service that allows them to send and receive various types of messages, such as text and files, between users. The service provided by the messaging service server 98 may be an SNS-type service in which an unspecified number of users can participate. In an SNS, users may be able to view posts from other users even if they do not follow them, or they may be able to view posts by following other users. Accounts may also be issued in association with information issued after identity verification, such as a phone number. Furthermore, it may be a service in which members of an organization can participate, or it may provide email sending and receiving functionality. Furthermore, users may send and receive messages one-on-one, or multiple users may form a group (sometimes called a channel) to send and receive messages. Each user may be able to post replies to each user's post in a thread format.

[0035] The messaging service server 98 may issue a unique URL for each message posted by each user, allowing other services to access each user's posts via that URL.

[0036] In this embodiment, each device (terminal device, server, etc.) can also be considered as an information processing device. That is, the collection of each device can be considered as a single "information processing device," and System 1 may be formed as a collection of multiple devices. The way in which the multiple functions required to realize System 1 according to this embodiment are distributed to one or more hardware can be appropriately determined in view of the processing capacity of each hardware and / or the specifications required for System 1.

[0037] Terminal 10 can be implemented, for example, as follows: • Handheld mobile devices such as smartphones and tablets • Stationary PCs (Personal Computers), Laptop PCs • Wearable devices worn by the user (watch-type, glasses-type, etc.) Terminal 10 includes a communication interface (IF) 12, an input device 13, an output device 14, memory 15, storage 16, and a processor 19.

[0038] The communication interface 12 is an interface for inputting and outputting signals so that terminal 10 can communicate with an external device.

[0039] The input device 13 is a device for receiving input operations from the user (for example, a touch panel, touchpad, pointing device such as a mouse, keyboard, etc.).

[0040] The output device 14 is a device (such as a display or speaker) for presenting information to the user.

[0041] Memory 15 is for temporarily storing programs and data processed by programs, etc., and is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0042] Storage 16 is for storing data, and can be, for example, flash memory or an HDD (Hard Disk Drive).

[0043] The processor 19 is hardware for executing the instruction set described in the program, and consists of an arithmetic unit, registers, peripheral circuits, etc.

[0044] The server 20 includes a communication interface 22, an input / output interface 23, memory 25, storage 26, and a processor 29.

[0045] Communication IF22 is an interface for inputting and outputting signals so that the server 20 can communicate with external devices.

[0046] Input / Output IF23 functions as an interface between an input device for receiving user input operations and an output device for presenting information to the user.

[0047] Memory 25 is for temporarily storing programs and data processed by programs, etc., and is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0048] Storage 26 is for storing data, and can be, for example, flash memory or an HDD (Hard Disk Drive).

[0049] The processor 29 is hardware for executing the instruction set described in the program, and consists of an arithmetic unit, registers, peripheral circuits, etc.

[0050] <1.2 Functional Configuration of Server 20> Figure 2 shows the configuration of server 20. As shown in Figure 2, server 20 functions as a communication unit 201, a storage unit 202, and a control unit 203.

[0051] The communications unit 201 performs processing to enable the server 20 to communicate with external devices.

[0052] The storage unit 202 stores various databases such as a user database 211, a content database 212, a search and browsing history database 213, and pricing plan information 214. The storage unit 202 may also store various databases in the contract conclusion and document management service, such as a database for managing the progress of contract conclusion between parties and a document management database for managing concluded contracts.

[0053] User database 211 is a database for managing users.

[0054] The user database 211 contains information necessary for using the services provided by server 20, such as the user's name and contact information. Further details will be provided later.

[0055] The content database 212 is a database that manages each piece of content that is available for viewing in the content viewing service provided by server 20. Further details will be provided later.

[0056] The search and browsing history database 213 is a database that manages the history of content searched by each user in the content browsing service, and content selected and viewed based on the search results. Further details will be provided later.

[0057] Pricing plan information 214 is information about the pricing plan for the content viewing service. For example, by paying a regular fee, users can access content available on the content viewing service. Pricing plans may include free plans (where the range of content that can be viewed, the viewing period, and the number of views are limited) and paid plans (where the range of content that can be viewed, the viewing period, and the number of views are determined according to the amount of the pricing plan, and may also allow unlimited viewing).

[0058] Server 20 may also maintain a database that manages the contract conclusion process performed by the electronic contract service provided by Server 20, and a database that manages document data (including information that manages document data concluded by the electronic contract service provided by Server 20).

[0059] The control unit 203 is realized when the processor 29 reads a program stored in the memory unit 202 and executes instructions contained in the program. By operating according to the program, the control unit 203 performs the functions shown as the reception control module 2041, the transmission control module 2042, the user management module 2043, the content registration module 2044, the content search processing module 2045, the content viewing processing module 2046, and the LLM utilization module 2047.

[0060] The receive control module 2041 controls the process by which the server 20 receives signals from external devices according to a communication protocol.

[0061] The transmission control module 2042 controls the process by which the server 20 transmits signals to external devices according to a communication protocol.

[0062] The user management module 2043 is a module for managing information for each user using System 1. Specifically, the user management module 2043 accepts registration of each user's information and updates the user database 211.

[0063] The content registration module 2044 controls the process of registering information about content to be viewed in the content viewing service and updating the content database 212.

[0064] The content search processing module 2045 controls the process of searching for content and responding with search results in the content browsing service, by referring to the search browsing history database 213, the content database 212, etc., in response to an operation to search for content.

[0065] The content viewing processing module 2046 controls the process in the content viewing service that allows users to view content, records the user's actions during viewing, and updates various databases such as the search and viewing history database 213.

[0066] The LLM utilization module 2047 is a program module that performs processing related to the use of LLM, such as generating prompts to send to the server 95 of the large-scale language model service, sending the generated prompts as instructions to the server 95 of the large-scale language model service, receiving the results output by the server 95 of the large-scale language model service in response to the instructions (prompts), and performing processing using the received results.

[0067] Server 20 may have a contract signing processing module that controls the process by which the parties approve document data as part of the process of concluding a contract by electronic contract. Specifically, the contract signing processing module notifies each user who approves the document data and updates the database in response to the operation of approving the document data.

[0068] Server 20 may have a document management module that controls the process of managing document data by referring to a document management database. Specifically, the document management module notifies the user, based on the contract period information set in the document data, whether to renew the contract upon the expiration of the contract period, and updates the document management database in response to user actions (such as renewing).

[0069] Server 20 may have an approval processing module that receives an operation from a user to submit an approval request and controls the process by which approvers approve the request. Specifically, the approval processing module notifies each user who approves the request and updates the database of approval requests in response to the operation to approve the request.

[0070] Server 20 may have a review processing module that records reviews of document data to be reviewed (for example, each clause of a contract to be reviewed) and updates a database that manages the review history. The review processing module communicates with the document review service server 93 and sends the document data to be reviewed, causing Server 93 to perform the review process. The module receives the results and updates the database that manages the review history. The review processing module also accepts operations from users to review document data (for example, operations to input comments in association with the entire contract or each clause of the contract) and updates the database that manages the review history.

[0071] <1.3 Configuration of Terminal 10> Figure 3 shows the configuration of terminal 10.

[0072] As shown in Figure 3, terminal 10 includes multiple antennas (antenna 111, antenna 112), communication units corresponding to each antenna (first communication unit 120, second communication unit 121), an input device 130 (including a touch-sensitive device 131), a display 132, an audio processing unit 140, a microphone 141, a speaker 142, a position information sensor 150, a camera 160, a motion sensor 170, a storage unit 180, and a control unit 190. Terminal 10 also has functions and configurations not specifically shown in Figure 3 (for example, a battery for maintaining power, a power supply circuit for controlling the supply of power from the battery to each circuit, etc.). As shown in Figure 3, each block included in terminal 10 is electrically connected by a bus or the like.

[0073] Antenna 111 radiates signals emitted by terminal 10 as radio waves. Antenna 111 also receives radio waves from space and provides the received signals to first communication unit 120.

[0074] Antenna 112 radiates signals emitted by terminal 10 as radio waves. Antenna 112 also receives radio waves from space and provides the received signals to the second communication unit 121.

[0075] The first communication unit 120 performs modulation and demodulation processing, etc., for the terminal 10 to transmit and receive signals via the antenna 111 in order to communicate with other wireless devices. The second communication unit 121 also performs modulation and demodulation processing, etc., for the terminal 10 to transmit and receive signals via the antenna 112 in order to communicate with other wireless devices. The first communication unit 120 and the second communication unit 121 are a communication module that includes a tuner, an RSSI (Received Signal Strength Indicator) calculation circuit, a CRC (Cyclic Redundancy Check) calculation circuit, a high-frequency circuit, etc. The first communication unit 120 and the second communication unit 121 perform modulation and demodulation, frequency conversion, etc., of the wireless signals transmitted and received by the terminal 10, and provide the received signal to the control unit 190.

[0076] The input device 130 has a mechanism for receiving user input operations. Specifically, the input device 130 is configured as a touchscreen and includes a touch-sensitive device 131. The touch-sensitive device 131 receives user input operations of the terminal 10. The touch-sensitive device 131 detects the user's contact position with the touch panel, for example, by using a capacitive touch panel. The touch-sensitive device 131 outputs a signal indicating the user's contact position detected by the touch panel to the control unit 190 as an input operation.

[0077] The display 132 displays data such as images, videos, and text in accordance with the control of the control unit 190. The display 132 is implemented by, for example, an LCD or an organic EL display.

[0078] The audio processing unit 140 modulates and demodulates the audio signal. The audio processing unit 140 modulates the signal received from the microphone 141 and provides the modulated signal to the control unit 190. The audio processing unit 140 also provides the audio signal to the speaker 142. The audio processing unit 140 is implemented, for example, by an audio processing processor. The microphone 141 receives an audio input and provides the audio signal corresponding to that audio input to the audio processing unit 140. The speaker 142 converts the audio signal received from the audio processing unit 140 into sound and outputs the sound to the outside of the terminal 10.

[0079] The location information sensor 150 is a sensor that detects the location of the terminal 10, and is, for example, a GPS (Global Positioning System) module. A GPS module is a receiving device used in a satellite positioning system. In a satellite positioning system, signals are received from at least three or four satellites, and the current location of the terminal 10, which is equipped with a GPS module, is detected based on the received signals.

[0080] Camera 160 is a device that receives light using a photodetector and outputs it as an image. Camera 160 is, for example, a depth camera that can detect the distance from camera 160 to the object being photographed.

[0081] The motion sensor 170 includes an acceleration sensor, an angular velocity sensor, etc., and detects the movement of the terminal 10.

[0082] The storage unit 180 is composed of, for example, flash memory and stores data and programs used by the terminal 10. The various types of information stored in the storage unit 180 will be described later.

[0083] The control unit 190 controls the operation of the terminal 10 by reading the program stored in the memory unit 180 and executing the instructions contained in the program. The control unit 190 is, for example, an application processor. By operating according to the program, the control unit 190 performs the functions of an operation reception unit 191, a transmission / reception unit 192, a data processing unit 193, a notification control unit 194, and a memory control unit 195.

[0084] The operation reception unit 191 processes input operations from the user to an input device such as a touch-sensitive device 131. Based on the coordinate information of the touch-sensitive device 131 where the user's finger or the like has made contact, the operation reception unit 191 determines the type of operation, such as whether the user's operation is a flick operation, a tap operation, or a drag (swipe) operation.

[0085] The transmitting / receiving unit 192 performs processing to enable the terminal 10 to send and receive data with an external device such as a server 20 in accordance with a communication protocol.

[0086] The data processing unit 193 performs calculations on the data received as input by the terminal 10 according to the program and outputs the calculation results to memory or other locations.

[0087] The notification control unit 194 performs the following processes: displaying the display image on the display 132, outputting sound to the speaker 142, and generating vibrations.

[0088] The memory control unit 195 controls the storage of data to the memory unit 180.

[0089] The various types of information stored by the memory unit 180 will now be explained. In a given scenario, the memory unit 180 stores various types of information, such as user information 181.

[0090] User information 181 is information about a user who uses the services of server 20. User information 181 includes, for example, the user's name.

[0091] <2 Data Structure> Figure 4 shows the data structure of the user database 211. The user database 211 includes the fields "User ID", "Name", "Field", "Position", "Occupation", "Email Address", "Phone Number", "Registration Date and Time", "Account Status", and "Pricing Plan".

[0092] The "User ID" field is information that identifies each user.

[0093] The "Name" field contains information about the user's name, nickname, or other designation.

[0094] The "Field" field contains information about the user's areas of expertise and areas of interest.

[0095] More specifically, the "Field" item includes attributes of the user's area of ​​expertise, such as back-office operations like legal affairs, accounting, and bookkeeping, development operations including engineers and designers, and more detailed expertise within legal affairs, such as corporate law and business law.

[0096] The "Job Title" field contains information about the user's job title within their organization.

[0097] The "Occupation" field contains information about the user's occupation.

[0098] The "Email Address" field contains the user's email address information, which will be used for contact purposes.

[0099] The "Phone Number" field contains the user's contact phone number information.

[0100] The "Registration Date and Time" field contains information about when the user registered with the system and had an account issued.

[0101] The "Account Status" field contains information about the status of the user account.

[0102] More specifically, the "Account Status" item refers to the state of the account, including active, suspended, frozen, etc.

[0103] The item "Pricing Plan" contains information about the pricing plans used by users for the content viewing service provided by Server 20.

[0104] More specifically, the "Pricing Plan" item includes plans that specify whether or not there is a fee (free, paid, etc.), the scope of content that can be viewed, and the amount of content that can be viewed (for example, there may be restrictions on the number of pieces of content or the amount of information that can be viewed within a certain period, such as monthly).

[0105] Figure 5 shows the data structure of the content database 212. The content database 212 includes the following items: "Content ID", "Book Title", "Author", "Publisher", "Year of Publication", "Genre", "Keywords", "Availability Status", "Average Rating", and "Summary".

[0106] The "Content ID" field is information that identifies each piece of content.

[0107] The "Book Title" field contains information about the name of the ebook, if the content is an ebook.

[0108] The "Author" field contains information about the name of the author of the content (such as an e-book).

[0109] The "Publisher" field contains information about the name of the publisher of the content (such as ebooks).

[0110] The "Publication Year" field indicates the timing of the content (e-book)'s publication.

[0111] The "Field" item contains information about the attributes of the content (e-book), such as its category and genre.

[0112] The "Keywords" field contains information about keywords related to the content.

[0113] More specifically, the "Keywords" item includes keywords used for searching, etc., that have been assigned to the content.

[0114] The "Availability Status" field provides information about the status of content availability.

[0115] More specifically, the "Availability Status" item includes information about whether the content is available or not, such as "Available" or "Discontinued."

[0116] The "Rating Value" item contains information about the user's evaluation results.

[0117] More specifically, the item "Evaluation Value" includes information on evaluation values ​​calculated by weighting each user's evaluation.

[0118] The "Summary" item contains information summarizing the content.

[0119] More specifically, the item "Summary" includes information on a summary of the content set by the publisher or other party, or a summary generated based on the content.

[0120] Figure 6 shows the data structure of the search and browsing history database 213. The search and browsing history database 213 includes the following items: "History ID", "User ID", "Search Date and Time", "Search Term", "Content ID", "Browsing Start Date and Time", "Browsing End Date and Time", "Browsing Time", "Number of Pages Viewed", "Pages with the Most Time Spent", "Bookmarked", "Highlighted", "Highlighted Sections", "Comments", and "Browsing Device".

[0121] The "History ID" field is information that identifies each search and content browsing history.

[0122] The "User ID" field is information that identifies the user who performed the action of viewing the content.

[0123] The item "User ID" may be associated with the item "User ID" in user database 211.

[0124] The "Search Date and Time" field contains information about when the user performed the search.

[0125] The "Search Term" field contains information about the search keywords entered by the user.

[0126] The "Content ID" field is information that identifies the content viewed by the user based on search results derived from their search terms.

[0127] The item "Content ID" may be associated with the item "Content ID" in content database 212.

[0128] The "Viewing Start Date and Time" field contains information about when the user began viewing the content.

[0129] The "Viewing End Date and Time" field indicates the moment when the user finished viewing the content.

[0130] The "Viewing Time" item represents the total time a user spent viewing content.

[0131] More specifically, the "Viewing Time" item stores information about the time a user viewed content, such as the time the content was displayed in a viewer, in units of hours or minutes.

[0132] The item "Number of pages viewed" is information about the number of pages viewed by the user when the content is an e-book.

[0133] The item "Pages with the longest dwell time" refers to information about the parts of the content (e.g., page numbers) that users spent the most time viewing, based on the viewing time of each part of the content (e.g., each page) when the content is an ebook.

[0134] The item "Bookmarked" indicates whether or not the content has been bookmarked.

[0135] More specifically, the item "Bookmarked" includes information on whether or not the entire content has been bookmarked.

[0136] The item "Highlight Presence / Absence" is a flag indicating whether or not there are highlighted sections within the content.

[0137] The "Highlighted Section" field contains information about the areas (such as text content) that the user has highlighted within the content.

[0138] More specifically, the "Highlighted Sections" item contains information about the sections that have been highlighted, based on the user's selection of content.

[0139] The "Comments" item contains information about comments that users have left on the content.

[0140] More specifically, the "Comments" category includes comments made by users on the entire content, as well as comments made in relation to specific parts of the content (for example, highlighted sections).

[0141] The "Viewing Device" field contains information about the attributes of the device used to view the content.

[0142] More specifically, the item "Viewing Device" includes information such as smartphone, tablet, laptop PC, viewer type, and viewer version.

[0143] <3 operations> Figure 7 illustrates the process flow for presenting recommended content to users in response to their search operations. This process allows users to quickly access content that best suits their search intent and attributes. Furthermore, by accumulating and analyzing user browsing behavior data, the overall recommendation accuracy of the system can be continuously improved.

[0144] The process is outlined below. • Acquisition and utilization of user attributes (device): User attribute information such as field of study and occupation can be used to extract recommended content and personalize it for the user. If user attribute information is not registered, the user may be prompted to enter it, and if it is already registered, the user may be asked to confirm that it is up-to-date. • Content extraction and browsing behavior analysis: Extracts content related to search terms and infers user interests based on browsing behavior data derived from search results. Prioritizing data from users with similar attributes further improves the accuracy of recommendations. • Calculation of recommendation score: Content is scored by comprehensively evaluating various browsing behavior data, such as viewing time and number of bookmarks. For example, content that has been viewed for a long time or that has been bookmarked by many users will receive a high score. • Recommended Content: Users are shown not only the title and thumbnail of content, but also previews of particularly popular pages (those with long viewing times, frequently viewed, etc.) and excerpts of comments from other users. This helps them choose what content to view. • Collection and updating of browsing behavior data: New user browsing behavior data is collected in real time, and the database is updated on the server side. This allows content recommendations to always be based on the latest browsing behavior data. The details of the process are explained below.

[0145] In step S711, terminal 10 receives an operation from the user to enter a search term on the content search operation screen. Terminal 10 sends the entered search term to the content search processing module 2045 of server 20. Terminal 10 may also obtain user attribute information (field, position, occupation, etc.) from the user. For example, when a user uses the system for the first time, or when the user has not registered an account, the terminal 10 may prompt the user to enter attribute information. Terminal 10 sends the obtained user attribute information to the content search processing module 2045 of server 20.

[0146] Server 20 stores information about the search terms specified by each user to search for content in the search history database 213 of the storage unit 202, associating it with browsing behavior information, which is the content of each user's browsing actions when they viewed content based on the search results corresponding to the search terms.

[0147] More specifically, the search and browsing history database 213 in the memory unit 202 is configured to store, as browsing behavior information, at least one of the following: the time each user spends viewing content based on search results, the amount of information viewed, the number of times the content is viewed, the time spent on each part of the content, the range selected by the user within the content, whether or not bookmarks were added to each unit when the content is divided into units of predetermined amounts of information, and whether or not comments were added to the content.

[0148] More specifically, the search and browsing history database 213 of the memory unit 202 is configured to store browsing behavior information, which includes the browsing history of each user within the content, specifically the details of their browsing actions for each part of the content (for example, the time spent viewing each page of an ebook, whether or not they highlighted each page, whether or not they added comments associated with each page, etc.). The search and browsing history database 213 of the memory unit 202 is configured to store information about the time each user spent on each part of the content as browsing behavior information. The search and browsing history database 213 of the memory unit 202 is configured to store information indicating that each user selected a part of the content (such as highlighting text) as browsing behavior information.

[0149] In step S721, the content search processing module 2045 of the server 20 receives a search term from the first user who is searching for content. Based on the received search term, the content search processing module 2045 extracts content related to the search term from the content database 212. The content search processing module 2045 of the server 20 may also extract content from the content database 212 by analyzing the search term and the user's attribute information.

[0150] In step S722, the content search processing module 2045 of the server 20 refers to the search and browsing history database 213 and obtains information on other users' browsing behavior (viewing time, number of views, number of bookmarks, page dwell time, etc.) for the extracted content. Based on each user's browsing behavior information for the content and the relevance of the content to the search words, it calculates a score for recommending each piece of content to the user. For example, the score may be calculated by prioritizing the recommendation of content that is similar to the user's search words and associated with the search words in the search and browsing history database 213 (i.e., content that the user has previously viewed from search results based on the search words). Here, the content search processing module 2045 may also prioritize the analysis of browsing behavior data for each piece of content accumulated for users with similar attributes to the user who performed the search, based on the user's attribute information. For example, it may prioritize the recommendation of content that has been viewed from search results in the past by users with similar attributes using similar search words and that has browsing behavior information such as a long viewing time.

[0151] In this way, the content search processing module 2045 identifies content to recommend to the first user based on the browsing behavior information of each user stored in the search browsing history database 213 of the storage unit 202, which pertains to search words that are the same as or similar to the search words specified by the user in step S711.

[0152] Here, the content search processing module 2045 may identify recommended content based on information about the extent to which each user views content, as browsing behavior information.

[0153] More specifically, the content search processing module 2045 may identify recommended content based on browsing behavior information, including at least one of the following: the time each user spends viewing content based on search results, the amount of information viewed, the number of times the content is viewed, the time spent on each part of the content, the range selected by the user within the content, whether or not bookmarks were added to each unit when the content is divided into units of predetermined information amounts, and whether or not comments were added to the content. For example, it may prioritize recommending content that is frequently viewed and viewed for extended periods of time.

[0154] Furthermore, the content search processing module 2045 may prioritize identifying content viewed by users with specific attributes. The content search processing module 2045 may refer to the attributes of a first user searching for content and prioritize identifying content viewed by users with similar attributes to the first user, as users with specific attributes. Here, the content search processing module 2045 may prioritize identifying content viewed by users whose field, job title, or occupation is specific, as users with specific attributes.

[0155] The content search processing module 2045 may identify parts of the content to recommend based on each user's browsing behavior for each part of the content (for example, parts that are frequently viewed, parts that are viewed for a long time, parts that have been highlighted, etc.). For example, the content search processing module 2045 may identify parts of the content to recommend based on information about the time spent on each part. In this way, the content search processing module 2045 may identify parts of the content to recommend to the user based on information about parts of the content that each user has selected, such as by highlighting, in the search browsing history database 213.

[0156] In step S723, the content search processing module 2045 of the server 20 creates a list of content to recommend to the user according to the calculated recommendation score and sends it to the user on terminal 10.

[0157] Thus, the content search processing module 2045 presents the content identified in the identification step to the first user. When presenting the identified content, the content search processing module 2045 may present a portion of the identified recommended content (for example, a section with a long viewing time, a section that is frequently viewed, a section that is highlighted, etc.). The content search processing module 2045 may present the user with a portion of the recommended content and information representing the entirety of that recommended content. For multiple recommended content items, the content search processing module 2045 may present a portion identified in each piece of content and information representing the entirety of each piece of content.

[0158] In step S712, terminal 10 displays the received list of recommended content to the user. Here, terminal 10 also presents an overview of each content item, as well as excerpts of pages that are viewed frequently.

[0159] In step S713, terminal 10 accepts an operation from the user to select content of interest and starts viewing the selected content. Terminal 10 collects the user's viewing behavior (viewing time, page navigation, bookmarks, highlights, comments, etc.) in real time while the content is being viewed.

[0160] The content viewing processing module 2046 of server 20 presents the content to the user via a viewer or the like, in response to the user's operation to view the content.

[0161] In step S724, the content search processing module 2045 of the server 20 saves the received user browsing behavior data to the search browsing history database 213 and updates the data. The updated data in the search browsing history database 213 will be reflected in subsequent recommendation processes and used to improve the accuracy of the recommendation algorithm.

[0162] Figure 8 shows the process flow for extracting supporting literature and generating answers in a question-answering system that responds to questions. This process allows for the provision of more accurate and reliable answers to user questions by utilizing data on other users' content viewing behavior.

[0163] The process is outlined below. • Question analysis and keyword extraction: Analyze questions received from users using natural language processing to identify key keywords and understand the user's intent. • Use of similar search terms: Search for past content browsing service search terms similar to the question and utilize relevant browsing behavior information. • Content extraction based on browsing behavior: Prioritizing the extraction of content frequently viewed by other users or sections that showed high interest. This allows for the provision of information that is generally considered useful. • Prompt and answer generation: Combine the extracted content and question to generate prompts to input into the language model. The prompts also include instructions for answer generation so that the language model can produce appropriate answers. • Updating browsing behavior data: Continuously collecting new user questions and browsing behavior after answering questions (such as the locations and duration of content viewed when viewing the content that forms the basis of the answer) and updating the database can improve the overall accuracy and personalization of the system. The details of the process are explained below.

[0164] In step S811, terminal 10 receives a question input operation from the user on a question input operation screen. Terminal 10 sends the question entered by the user to server 20.

[0165] The content viewed in the content viewing service provided by Server 20 is used as the basis for the answers in the system that generates responses to questions.

[0166] In step S821, the content search processing module 2045 of the server 20 analyzes the question received from the user's terminal 10 and extracts keywords and intent. For example, the content search processing module 2045 may perform processes such as vectorizing the content of the question entered by the user or breaking it down into words, and use this as information for searching for content.

[0167] In step S822, the content search processing module 2045 of the server 20 searches the search browsing history database 213 for search terms similar to the content of the question. For example, it may extract search terms from the content of the question and compare them with the search terms stored in the search browsing history database 213. The content search processing module 2045 refers to the search browsing history database 213 and obtains content browsing behavior information associated with search terms similar to the entered question.

[0168] In step S823, the content search processing module 2045 of server 20 extracts relevant content in order of priority based on browsing behavior information (browsing time, number of pages viewed, number of bookmarks, time spent on the site, etc.). For example, it prioritizes content that is frequently viewed, has been viewed for a long time, or has been bookmarked. From the extracted content, the content search processing module 2045 identifies a particular part (page or chapter, etc.) that has been viewed frequently.

[0169] The content search processing module 2045 extracts content from the content database 212 that serves as the basis for the answer, based on the content of the question entered by the user. The content search processing module 2045 determines the priority of content extraction (for example, frequently viewed, viewed for a long time, etc.) based on the browsing behavior information associated with each piece of content and extracts the content accordingly.

[0170] In this way, the content search processing module 2045 compares the content of the question entered by the user with the search word information in the search and browsing history database 213 of the storage unit 202, and extracts content that serves as the basis for the answer based on browsing behavior information corresponding to search words similar to the content of the question.

[0171] In step S824, the content search processing module 2045 of the server 20 generates a prompt that includes a question and a portion of the identified content, and includes instructions to refer to the content and generate an answer.

[0172] Thus, the content search processing module 2045 generates a prompt that includes the content of a question entered into the system and the content extracted in step S823, and which includes an instruction that, in relation to the content of the question, refers to the extracted content to generate an answer.

[0173] In step S825, the content search processing module 2045 of the server 20 inputs the generated prompt to an information processing system that performs language processing (for example, a language model such as the server 95 of the large-scale language model service), and obtains the answer generated by the information processing system. In this way, the content search processing module 2045 provides the information processing system that performs language processing with the prompt generated in step S824, causing it to generate an answer corresponding to the prompt.

[0174] In step S826, the content search processing module 2045 of the server 20 sends the generated response to the terminal 10.

[0175] In step S812, terminal 10 presents the response received from server 20 to the user. Terminal 10 may also accept the user to enter additional questions or provide feedback as needed.

[0176] In step S813, terminal 10 records the user's question history and answer viewing behavior (viewing time, number of rereads, etc.). Terminal 10 sends the recorded data to server 20.

[0177] In step S827, the content search processing module 2045 of the server 20 stores the received user browsing behavior data in the search browsing history database 213. The updated data in the search browsing history database 213 may be used to inform content extraction and priority setting when generating future responses.

[0178] <4 Screen Examples> Figure 9 shows an example of an operation screen that accepts a content search operation and displays the content.

[0179] The operation screen 900 is an operation screen that accepts the operation to search for content and displays the content.

[0180] The operation screen 900 corresponds to each process in Figure 7.

[0181] The user information display area 902 is the area that displays the logged-in username, user attributes, notifications, and other information.

[0182] The search keyword specification unit 904 is an operating component that receives keyword specifications from the user for searching for content.

[0183] The search operation unit 906 is an operating component that accepts an operation to perform a search using the entered keyword.

[0184] The category designation unit 908 is an operating member that accepts the designation of a content category.

[0185] In the illustrated example, the category specification section 908 accepts the category of the ebook's content. For example, it accepts category specifications such as law (and may further accept the specification of more subdivided categories such as corporate law or specific jurisdictions), business, technology, and literature, in a dropdown or checkbox format.

[0186] The user attribute specification unit 910 is an operating member that accepts the specification of user attribute information.

[0187] In the illustrated example, the user attribute specification unit 910 accepts operations to set or edit user attributes such as the user's field, occupation, and position.

[0188] The search results display area 912 is the area that displays a list of content that matches or is related to the entered search keywords.

[0189] In the illustrated example, the search results display area 912 displays a list of ebook content, showing content information such as title, author, and publisher, and accepting the user's selection of content.

[0190] The recommended content display area 914 is an area that displays a list of recommended content based on the user's search keywords and attribute information.

[0191] In the illustrated example, the recommended content display area 914 displays not only the title of the content, but also a preview of part of the content and rating information.

[0192] The content details display area 916 is the area that displays detailed information about the selected content.

[0193] In the illustrated example, the content details display area 916 displays the content title, author, summary, etc.

[0194] The detailed viewing operation unit 918 is an operation component that accepts operations to transition to a page that displays detailed information about each content item.

[0195] In the illustrated example, the detailed viewing operation unit 918 displays a viewer for viewing content specified by the user, in response to the user's operation.

[0196] The favorites addition operation unit 920 is an operation component that accepts the operation to add content of interest to the favorites list.

[0197] The filtering condition specification unit 922 is an operating member that accepts the specification of filtering conditions for narrowing down search results, such as the year of publication and the author's name.

[0198] The reset operation unit 924 is an operating component that accepts operations to return the search conditions and filter selections to their initial state.

[0199] The browsing history reference operation unit 926 is an operation component that accepts operations to access the user's own past content browsing history page.

[0200] Figure 10 shows an example of the user interface for a system that generates answers to questions.

[0201] Operation screen 1000 is the operation screen for a system that generates answers to questions.

[0202] The operation screen 1000 corresponds to each process in Figure 8.

[0203] The question content specification unit 1002 is an operating member that receives the user's specification of the question content.

[0204] In the illustrated example, the question content specification section 1002 is provided as a free text input field, supporting multiple lines of input and allowing for the description of detailed questions. The system may also accept questions from the user via voice input. The system may also output voice guidance ("Do you have any questions?" etc.) to accept the input of questions, or it may output voice guidance while displaying an avatar.

[0205] The question transmission operation unit 1004 is an operation component that accepts an operation to confirm a question entered by the user and send it to the server 20.

[0206] The question category designation unit 1006 is an operating member that accepts the designation of a question category.

[0207] In the illustrated example, the question category specification section 1006 accepts selections of categories such as technology, health, and law (and may also allow selection of more subdivided categories such as corporate law and specific jurisdictions) via a dropdown or checkbox format. The information of the specified category is used to improve the accuracy of searching for content that forms the basis for generating answers to the question.

[0208] The file upload operation unit 1008 is an operation component that accepts requests to upload documents and images related to the question.

[0209] In the illustrated example, the file upload operation unit 1008 supports the attachment of multiple files.

[0210] The clear operation unit 1010 is an operating component that accepts operations to reset the entered question content and selected options.

[0211] The answer display area 1012 is the area for displaying the generated answers.

[0212] In the illustrated example, the response display area 1012 displays the system's response in text format, highlighting important points with bold text or similar methods.

[0213] The conversation history display area 1014 is an area that displays the history of past questions and answers between the user and the system.

[0214] In the illustrated example, the conversation history display area 1014 allows users to scroll through the conversation history and refer to past exchanges.

[0215] The evidence content display area 1016 is an area that displays the content that formed the basis of the answer, or a part of it (especially the part that is of high interest based on browsing behavior).

[0216] The related content recommendation display area 1018 is an area that displays recommended content (such as ebooks and articles) based on the user's questions and browsing history.

[0217] The follow-up question operation unit 1020 is an operating component that accepts operations to ask additional questions or inquire about details regarding the current answer.

[0218] In the illustrated example, the re-question operation unit 1020 accepts input of a new question in response to user actions.

[0219] The feedback operation unit 1022 is an operation component that accepts input from users to provide feedback on their satisfaction level and comments regarding the provided answers.

[0220] In the illustrated example, the feedback operation unit 1022 receives feedback input in response to user operations, and this feedback is used to improve the service.

[0221] <Variation> The matters described in the above embodiments may be combined in various ways. In the above embodiments, the content mainly described was an example of an e-book. Other types of content may also be used, such as audio content, video content, or document content.

[0222] (1) Extraction of content using content viewing history based on the question text in a system that generates answers to questions. A system that generates answers to questions will retain information about the question text and a history of viewing the content that forms the basis of the answer, and this information may be stored in a search and browsing history database 213. For example, the "search term" item in the search and browsing history database 213 may store information about the question text received as input in the process described in Figure 8 (or words obtained by analyzing the question text), and information about the viewed content may be managed in the "content ID" item, etc. This allows the content viewing service to extract content for search words based on the questions in the system that generates answers to questions and the viewing behavior of the content that forms the basis of the answer.

[0223] (2) When viewing content from the content preview, the viewer will display the portion shown in the preview. As explained in Figure 8 above, the system that generates answers to questions also presents the content that formed the basis for generating those answers. Depending on the user's interaction with a preview of a portion of the content, the content viewing service may display a content viewer and allow the user to view that portion. This makes it easier for the user to refer to the portion of the content that forms the basis of the answer to the question, and also makes it easier to refer to the text before and after that portion, thereby making it even easier for the user to understand what they wanted to know from the question.

[0224] (3) The basis for the answer in a system that generates an answer to a question. In the example above, as shown in Figure 8, when generating an answer to a question, data is extracted based on the content of the question, referring to the data that forms the basis of the answer, and a prompt is generated that includes the extracted data and the content of the question. The prompt may also include instructions to generate an answer to the question by referring to the extracted data.

[0225] Here, based on the content of the question, the scope of data referenced to support the answer may include data stored on server 92 of the business support system service, data stored on server 93 of the document review service, data stored on server 96 of the document creation service, data stored on server 97 of the sales support system service, and data stored on server 98 of the messaging service. Alternatively, data to support the answer may be extracted by referencing this data with data such as the search and browsing history database 213 in the content browsing service.

[0226] (4) Method for extracting content that serves as the basis for the answer When extracting content corresponding to search criteria entered by a user (search terms, question sentences like those in Figure 8), the priority of presenting content (processing in Figure 7) or the priority of content that serves as the basis for generating an answer to a question (processing in Figure 8) may be determined by referring to the user's past browsing behavior. Alternatively, when extracting content corresponding to search criteria entered by a user (search terms, question sentences like those in Figure 8), the priority of presenting content or the priority of content that serves as the basis for generating an answer to a question may be determined by referring to the user's past browsing behavior and according to the user's pricing plan information. For example, the browsing behavior of users on paid plans may be prioritized, or the browsing behavior of users on paid plans with fewer restrictions on the scope of content that can be viewed on the content viewing service (for example, unlimited access to content provided on the content viewing service through regular payments) may be prioritized when extracting content. Since users on paid plans are likely to have more opportunities to view content, it can be expected that the content extracted based on the browsing behavior of users on paid plans will also match the user's search criteria.

[0227] (Note) The details described in each of the above embodiments are noted below.

[0228] (Note 1) A program for operating a computer that has one or more computer processors and provides a service for viewing content including ebooks, In the memory unit, information about the search terms specified by each user to search for content is stored in association with browsing behavior information, which describes the content each user viewed based on the search results corresponding to the search terms. The program runs on one or more computer processors. The first step involves receiving a search term from the first user to specify for searching for content, A step to identify content to recommend to the first user based on browsing behavior information in the memory unit relating to search terms that are the same as or similar to the search terms specified in the acceptance step, A program that causes the first user to perform the steps of presenting the content identified in the identification step and then executing the following steps.

[0229] (Note 2) In the identification step, the program described in Appendix 1 identifies recommended content based on browsing behavior information, specifically the degree to which each user views content.

[0230] (Note 3) In the memory unit, as browsing behavior information, The viewing time of each user when viewing content based on search results, Amount of information viewed, Number of views, Time spent on each part of the content, In the content section, the range selected by the user, Whether or not a bookmark has been added to each unit when the content is divided into units of a predetermined amount of information. Whether or not a user has added a comment to the content. It is configured to store at least one of the following: In the identification step, as browsing behavior information, The viewing time of each user when viewing content based on search results, Amount of information viewed, Number of views, Time spent on each part of the content, In the content section, the range selected by the user, Whether or not a bookmark has been added to each unit when the content is divided into units of a predetermined amount of information. Whether or not a user has added a comment to the content. The program described in Appendix 2 identifies recommended content based on at least one of the following.

[0231] (Note 4) A program described in any of the appendices 2 to 3, which, in the identification step, prioritizes identifying content viewed by users with specific attributes.

[0232] (Note 5) The program described in Appendix 4, which, in the identification step, refers to the attributes of a first user and, as a user having specific attributes, prioritizes identifying content viewed by users with attributes similar to those of the first user.

[0233] (Note 6) A program as described in any of Appendix 4 to 5, which, in the identification step, prioritizes identifying content viewed by users whose field of study, job title, or occupation is specified as a user with specific attributes.

[0234] (Note 7) The memory unit is configured to store browsing behavior information, specifically the browsing history of each user within the content, and the details of their browsing actions for each component of the content. In the identification step, based on each user's browsing behavior for each part of the content, the parts of the content to recommend are identified. A program described in any of the appendices 1 to 6, which presents a portion of the specified recommended content in the step of presenting the specified content.

[0235] (Note 8) The memory unit is configured to store information about the time each user spends on each part of the content as browsing behavior information. The program described in Appendix 7 identifies the portion of content to recommend based on information about the time spent on each section during the identification step.

[0236] (Note 9) The program described in Appendix 8, which, in the steps of presentation, presents a portion of the recommended content and information representing the entirety of the recommended content.

[0237] (Note 10) The program described in Appendix 9 presents, in the steps of the presentation, a specific portion of each piece of recommended content and information representing the entirety of each piece of content.

[0238] (Note 11) The memory unit is configured to store information indicating that each user has selected a portion of the content as browsing behavior information. A program described in any of Appendix 7 to 10 that, in the identification step, identifies a portion of the content to recommend based on a portion of the information each user has selected about the content.

[0239] (Note 12) The content viewed in computer-provided services is used as the basis for answers in systems that generate responses to questions. The program is implemented on one or more computer processors, and further, A program described in any of Appendix 1 to 11, which performs a step of extracting content that serves as the basis for an answer based on the content of a question entered by a user in the system, and then performs a step of extracting content by determining the priority of extracting each piece of content based on browsing behavior information associated with each piece of content.

[0240] (Note 13) The program described in Appendix 12 compares the content of a question entered by the user in the system with the search word information in the memory unit during the extraction step, and extracts content that serves as the basis for the answer based on browsing behavior information corresponding to search words similar to the content of the question.

[0241] (Note 14) The program is implemented on one or more computer processors, and further, The program described in Appendix 13, which includes a prompt containing the content of a question entered in the system and content extracted in an extraction step, and which causes the system to execute a step that generates a prompt containing an instruction that, in response to the content of the question, refers to the extracted content to generate an answer.

[0242] (Note 15) The program is implemented on one or more computer processors, and further, The program described in Appendix 14, which, by providing the prompt generated in the generation step to an information processing system that performs language processing, causes the system to execute a step that generates a response corresponding to the prompt.

[0243] (Note 16) A method for operating a computer that provides a service for viewing content including ebooks, comprising one or more computer processors, In the memory unit, information about the search terms specified by each user to search for content is stored in association with browsing behavior information, which describes the content each user viewed based on the search results corresponding to the search terms. The method involves one or more computer processors, The first step involves receiving a search term from the first user to specify for searching for content, A step to identify content to recommend to the first user based on browsing behavior information in the memory unit relating to search terms that are the same as or similar to the search terms specified in the acceptance step, A method for performing the following steps: presenting the content identified in the identification step to the first user.

[0244] (Note 17) An information processing device that provides a service for viewing content including ebooks, In the memory unit, information about the search terms specified by each user to search for content is stored in association with browsing behavior information, which describes the content each user viewed based on the search results corresponding to the search terms. The control unit of the information processing device, The first step involves receiving a search term from the first user to specify for searching for content, A step to identify content to recommend to the first user based on browsing behavior information in the memory unit relating to search terms that are the same as or similar to the search terms specified in the acceptance step, An information processing device that performs the steps of presenting the content identified in the identification step to the first user.

Claims

1. A program for operating a computer that has one or more computer processors and provides a service for viewing content including ebooks, In the memory unit, information of the search words specified by each user to search for the content is stored in association with browsing behavior information, which is the content of each user's browsing behavior when they viewed the content based on the search results corresponding to the search words. The program is configured on one or more computer processors. A step of receiving a search term from the first user to search for the aforementioned content, A step of identifying the content to recommend to the first user based on the browsing behavior information of the storage unit relating to search words that are the same as or similar to the search words specified in the receiving step, A program that causes the first user to perform the step of presenting the content identified in the identification step.

2. The program according to claim 1, wherein in the step of identifying, the program identifies the content to be recommended based on information regarding the degree to which each user views the content, as browsing behavior information.

3. In the aforementioned storage unit, the browsing behavior information is as follows: The viewing time when each user viewed the aforementioned content based on the search results, Amount of information viewed, Number of views, Time spent on each portion of the aforementioned content, The range selected by the user in the aforementioned content section, Whether or not a bookmark has been attached to each unit when the aforementioned content is divided into units of a predetermined amount of information, Whether or not a user has commented on the aforementioned content. It is configured to store at least one of the following: In the step of identifying the above, the browsing behavior information is, The viewing time when each user viewed the aforementioned content based on the search results, Amount of information viewed, Number of views, Time spent on each portion of the aforementioned content, The range selected by the user in the aforementioned content section, Whether or not a bookmark has been attached to each unit when the aforementioned content is divided into units of a predetermined amount of information, Whether or not a user has commented on the aforementioned content. The program according to claim 2, which identifies the recommended content based on at least one of the following.

4. The program according to claim 2, wherein in the step of identifying, it prioritizes identifying content viewed by users having specific attributes.

5. The program according to claim 4, wherein in the identifying step, the program refers to the attributes of the first user and, as a user having the identified attributes, prioritizes identifying content viewed by users having attributes similar to the attributes of the first user.

6. The program according to claim 4, wherein in the identifying step, the program prioritizes identifying content viewed by users who, as users having the identified attributes, are those whose field of work, job title, or occupation is identified as a specific user.

7. The memory unit is configured to store, as browsing behavior information, the content of the browsing behavior of each user in the content, as a history of what each user has viewed in the content. In the aforementioned identification step, based on the content of each user's browsing behavior for each part of the content, the portion of the content to be recommended is identified. The program according to claim 1, wherein in the step of presenting, the program presents a portion of the specified recommended content.

8. The memory unit is configured to store information about the time each user spends on each part of the content as browsing behavior information. The program according to claim 7, wherein in the identifying step, a portion of the recommended content is identified based on information regarding the time spent in each portion.

9. The program according to claim 8, wherein in the step of presenting, a portion of the recommended content and information representing the entirety of the recommended content are presented.

10. The program according to claim 9, wherein in the step of presenting the above, the program presents, for each of the recommended contents, a portion that is identified in each content and information that represents the whole of each content.

11. The memory unit is configured to store information indicating that each user has selected a portion of the content as browsing behavior information. The program according to claim 7, which, in the identifying step, identifies a portion of the recommended content based on a portion of the information selected by each user regarding the content.

12. The content viewed in the service provided by the aforementioned computer is used as the basis for the answer in a system that generates an answer to a question. The program further provides the one or more computer processors with: The program according to claim 1, which performs the step of extracting content that serves as the basis for an answer based on the content of a question entered by a user in the system, wherein the priority of extracting each content is determined based on the browsing behavior information associated with each content, and the program performs the step of extracting the content.

13. The program according to claim 12, wherein in the extraction step, the program compares the content of a question entered by a user in the system with the information of the search word in the storage unit, and extracts content that forms the basis of the answer based on the browsing behavior information corresponding to the search word that is similar to the content of the question.

14. The program further provides the one or more computer processors with: The program according to claim 13, which performs a step of generating a prompt that includes the content of a question input in the system and the content extracted in the extraction step, the prompt including an instruction that generates an answer in relation to the content of the question by referring to the extracted content.

15. The program further provides the one or more computer processors with: The program according to claim 14, wherein the program provides the prompt generated in the generation step to an information processing system that performs language processing, thereby causing the system to generate a response corresponding to the prompt.

16. A method for operating a computer that provides a service for viewing content including ebooks, comprising one or more computer processors, In the memory unit, information of the search words specified by each user to search for the content is stored in association with browsing behavior information, which is the content of each user's browsing behavior when they viewed the content based on the search results corresponding to the search words. The above method involves one or more computer processors, A step of receiving a search term from the first user to search for the aforementioned content, A step of identifying the content to recommend to the first user based on the browsing behavior information of the storage unit relating to search words that are the same as or similar to the search words specified in the receiving step, A method comprising the steps of: presenting the content identified in the identification step to the first user; and

17. An information processing device that provides a service for viewing content including ebooks, In the memory unit, information of the search words specified by each user to search for the content is stored in association with browsing behavior information, which is the content of each user's browsing behavior when they viewed the content based on the search results corresponding to the search words. The control unit of the information processing device, A step of receiving a search term from the first user to search for the aforementioned content, A step of identifying the content to recommend to the first user based on the browsing behavior information of the storage unit relating to search words that are the same as or similar to the search words specified in the receiving step, An information processing device that performs the steps of: presenting the content identified in the identification step to the first user;

Images