Information processing system, information processing method and program
The information processing system addresses the challenge of aligning AI utilization with business operations by placing an AI-enabled UI on browsers, enabling efficient data organization and operational alignment.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-01-31
- Publication Date
- 2026-03-06
AI Technical Summary
Conventional technologies fail to effectively implement AI utilization measures tailored to a company's specific business operations.
An information processing system that includes a UI setting means for placing an AI-enabled UI on a browser, registering a target website, setting operators and processes, and executing these processes through an interactive system.
Enables companies to implement effective AI utilization measures aligned with their business operations, enhancing operational efficiency and data organization.
Smart Images

Figure 0007825297000001 
Figure 0007825297000002 
Figure 0007825297000003
Abstract
Description
[Technical Field]
[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]
[0002] In recent years, there have been a number of cases where companies have utilized interactive systems (see, for example, Patent Document 1) in their business activities, in which an AI receives a prompt and responds accordingly (hereinafter referred to as "AI utilization"). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Patent No. 7081099 Summary of the Invention [Problem to be solved by the invention]
[0004] However, while companies are being required to implement effective measures to utilize AI in line with their own business operations, conventional technologies, including those described in Patent Document 1, are unable to fully meet this demand.
[0005] The present invention was made in light of these circumstances, and aims to provide technology that enables companies to implement effective AI utilization measures in line with their own business operations. [Means for solving the problem]
[0006] In order to achieve the above object, an information processing system according to one aspect of the present invention comprises: a UI setting means for setting a predetermined UI (User Interface) for executing a predetermined process related to a part of a predetermined website where another system is executed using an interactive system; another system execution means for displaying the target of the predetermined website on a predetermined browser and executing the other system; a UI functioning means for placing the predetermined UI on the target in the predetermined browser and making the predetermined UI function; Equipped with The UI setting means a registration means for registering the target of the predetermined website; an operator setting means for setting an operator to be placed at a first position of the target in the predetermined browser; a predetermined process setting means for setting the predetermined process to be executed when the operator is operated; and The UI functionalization means a control placement means for placing the control at the first position of the target in the predetermined browser; an operation receiving means for receiving an operation on the operator in the predetermined browser; a predetermined processing execution means for executing the predetermined processing when the operation on the operator is accepted as a trigger; It has.
[0007] An information processing method and a program according to one aspect of the present invention are a method and a program corresponding to an information processing system according to one aspect of the present invention. [Effects of the Invention]
[0008] According to the present invention, companies will be able to implement effective measures to utilize AI in line with their own business operations. [Brief explanation of the drawings]
[0009] [Figure 1] 1 is a diagram showing an overview of a service to which an information processing system of the present invention is applied; [Figure 2] 1 is a diagram showing an overview of a service to which an information processing system of the present invention is applied; [Figure 3] FIG. 3 is a diagram showing an example of the configuration of an information processing system that realizes the provision of the present service shown in FIGS. 1 and 2, that is, an embodiment of the information processing system of the present invention. [Figure 4] 4 is a block diagram showing an example of a hardware configuration of an administrator terminal in the information processing system of FIG. 3. FIG. [Figure 5] 5 is a functional block diagram showing an example of the functional configuration of the administrator terminal and the user terminal of FIG. 4 that constitute the information processing system of FIG. 3. FIG. [Figure 6] 6 is a flowchart illustrating a flow of an example of processing of an administrator terminal having the functional configuration of FIG. 5; [Figure 7] 6 is a flowchart illustrating a flow of an example of processing of an administrator terminal having the functional configuration of FIG. 5; [Figure 8] 6 is a flowchart illustrating a flow of an example of processing of a user terminal having the functional configuration of FIG. 5; [Figure 9] 6 is a flowchart illustrating a flow of an example of processing of a user terminal having the functional configuration of FIG. 5; [Figure 10] 10 is a diagram showing an example of a screen of the administrator terminal of FIG. 3 when the button installation process of step S2 of FIG. 1 and FIG. 6 is executed. FIG. [Figure 11] 1 and 6 is executed, and is a diagram showing an example of a screen of the administrator terminal of FIG. 3 when the policy setting process of step S3 of FIG. 6 is executed, and is a diagram showing an example of a screen of a UI that generates a flowchart by connecting each step that constitutes a specified process. [Figure 12] 1 and 6. FIG. 10 is a diagram showing an example of a screen of the administrator terminal of FIG. 3 when step S3A of the policy setting process of step S3 of FIG. [Figure 13] 1 and 6. FIG. 10 is a diagram showing an example of a screen of the administrator terminal of FIG. 3 when step S3B of the policy setting process of step S3 of FIG. [Figure 14] 1 and 6. FIG. 10 is a diagram showing an example of a screen of the administrator terminal of FIG. 3 when step S3C of the policy setting process of step S3 of FIG. [Figure 15] 1 and 6 is executed, and is a diagram showing an example of a screen of the administrator terminal of FIG. 3 when the policy setting process of step S3 of FIG. 6 is executed, which is a different screen example from FIG. 11 of a UI that generates a flowchart by connecting each step that constitutes a specified process. [Figure 16]FIG. 8 is a diagram showing an example of a UI in which a component (this service extension UI) set by an administrator terminal having the functional configuration of FIG. 5 in accordance with the flowcharts of FIG. 6 and FIG. 7 is linked with a sidebar. [Figure 17] FIG. 8 is a diagram showing an example of a UI in which a component (this service extension UI) set by an administrator terminal having the functional configuration of FIG. 5 in accordance with the flowcharts of FIG. 6 and FIG. 7 is linked with a sidebar. [Figure 18] FIG. 8 is a diagram showing an example of a UI in which a component (this service extension UI) set by an administrator terminal having the functional configuration of FIG. 5 in accordance with the flowcharts of FIG. 6 and FIG. 7 is linked with a sidebar. DETAILED DESCRIPTION OF THE INVENTION
[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
[0011] First, with reference to FIG. 1, an overview of a service (hereinafter referred to as "this service") to which an embodiment of an information processing system of the present invention (see FIG. 3 described later) is applied will be described. 1 and 2 are diagrams showing an outline of the present service to which the information processing system of the present invention is applied.
[0012] This service provides user companies with tools (software programs) that enable them to implement measures to utilize AI, and allows user companies to use these tools to implement effective measures to utilize AI in line with their own business operations. Hereinafter, the person (department) in the user company who will take the lead in implementing the measures will be referred to as the "Service Administrator SU." The Service Administrator SU is usually the IT department. On the other hand, the person (department) receiving the measures is called the "Service User SR." The Service User SR is each business department. That is, the provider ST of this service provides the tools of this service to the user company and also provides operational support for this service to the user company. The service operator SU of the user company will develop measures to utilize AI using the tools of this service for the service user SR. The service user SR of the user company will implement measures to utilize AI using the tools of this service.
[0013] Here, an AI utilization measure is a unit that adds AI functions to the screens of third-party systems that user companies use in their business. Note that hereafter, AI utilization measures will be abbreviated to simply "measures." The third-party system is configured as a website managed by a third party. That is, the service operator SU starts a browser on the operator terminal 2 and uses the browser to access the URL of the website to use the third-party system. Similarly, the service user SR starts a browser on the user terminal 3 and uses the browser to access the URL of the website to use the third-party system. Therefore, measures to utilize AI can be said to be a unit for adding AI functions to the browser of a terminal that uses a third-party system (here, the operator terminal 2 or the user terminal 3).
[0014] The tools of this service include the "Administration Screen" and "Editor Extension" used by the service operator SU, and the "Player Extension" used by the service user SR. Normally, the "Player Extension" is forcibly installed by the Service Administrator SU into the browsers of the Service Users SR (all employees). The "Administration Screen" is a tool that provides regular web services and plays the role of an administration console. Specifically, for example, the "Administration Screen" allows you to create, edit, and control the publication of measures, as well as control users. The "editor extension" is a browser extension application software (hereinafter referred to as "extension app" as appropriate), and is a tool for setting measures and checking playback for the target third-party system. The player extension is a browser extension application and a tool that executes the actual measures on the target third-party system.
[0015] In this way, the tools of this Service do not improve third-party systems, but rather implement measures for those systems. In other words, implementing measures for third-party systems means placing (overlapping) an AI-enabled UI (User Interface) on the browser as an extension for the browser that uses the third-party system, and making it function. Note that this "AI-enabled UI" that is placed on the browser and functions on the third-party system is hereinafter referred to as the "Service-extended UI."
[0016] Hereinafter, an embodiment of the present invention will be described based on the following example. In other words, the third-party system is assumed to be a predetermined recruitment management tool, and the measure adopted is to add a function for summarizing messages within the recruitment management tool.
[0017] More specifically, in this example, the following problem is set by the service administrator SU. In other words, recruitment management tools have a timeline that allows user companies to share the history of the selection process, including the content of conversations with applicants and their impressions during interviews and meetings. However, with a wide variety of topics and many participants, it can be difficult to grasp the main points. The task is set to be one in which it is believed that organizing the main points and efficiently understanding the content will be beneficial for everyone involved in the selection process (SRs who use this service).
[0018] Also, for example, in this case, it is assumed that the following solution is proposed by the service operator SU. Therefore, as a measure, we will adopt a feature that adds a timeline summary to the recruitment management tool (candidate page). Selection criteria for each job type are prepared in advance as prompt templates, and the job type being applied for is identified from within the screen (browser), an appropriate prompt template is obtained, and the entire internal conversation is summarized. Have the reader organize the information they want to know from the following three perspectives: perspective 1 is the issue of concern; perspective 2 is what has been determined as the next action; and perspective 3 is the hiring manager's task. The solution is to install a button (this service's extended UI where the button is placed) that can execute this summary prompt with one click on the recruitment management tool screen (browser).
[0019] Here, the prompt template prepared in advance by the service administrator SU is as follows, and is also shown in FIG. "The following is a chat conversation between an internal recruiter and a candidate for {job type: variable 1}. Summarize this content as follows: 1st point: concerns, 2nd point: what has been determined as the next action, 3rd point: tasks of the recruiter Please categorize them into the following three categories. 1. How to read summary text (format) A message is a single block consisting of the sender, date, and text. Also, if someone has a name preceded by an @ symbol, it means they are being mentioned in the text, not the person who made the comment. 2. Please separate the tasks of the recruiter into individual tasks and provide specific descriptions for each. Below is the entire message: {Entire message: variable 2}" Here, {〇〇:variable △} indicates the location where the variable is replaced.
[0020] As shown in FIG. 1, the service administrator SU uses the tools of the service on the administrator terminal 2 to register measures to deal with such cases.
[0021] Specifically, in step S1, the service administrator SU registers the third-party system in the server 1 managed by the service provider ST before registering the measure. Here, registration of a third-party system includes not only registration of the URL of the third-party system's website, but also registration of a page on the website that indicates the scope of the policy implementation (in the example of Figure 1, the candidate page).
[0022] In step S2, the service administrator SU sets an operator (a button in the example of FIG. 1) to be placed at a predetermined position on the candidate page in the browser. Note that the predetermined position can be freely set by the service administrator SU.
[0023] In step S3, the service administrator SU sets up a predetermined process related to the candidate page using AI (in this example, a summary of the timeline of the candidate page), which is executed when the operator is operated.
[0024] Specifically, in this example, the predetermined processing is assumed to be composed of the following first to third steps. In this example, step S3 is performed by a process S3A for setting the first step, a process S3B for setting the second step, and a process S3C for setting the third step.
[0025] The first step is a step (hereinafter referred to as the "variable acquisition step") in which the variables to be substituted (input) for the substitution locations written as {〇〇: variable △} in the prompt template are acquired from the candidate page. Therefore, in step S3A, the variable acquisition step is set. For example, the prompt template in this example has {job title: variable 1}. On the candidate page, the information about the job title acquired as variable 1 is in the area where "job title applied for" is written. The location of this area is fixed on the candidate page (the browser on which it is displayed). Therefore, in step S3A, the "process of acquiring information about the area in that location on the candidate page as job title (variable 1)" is set. Similarly, for example, the prompt template in this example has {entire message: variable 2}. In the candidate page, the information on the entire message obtained as variable 2 is written in the timeline. The position of this timeline is fixed in the candidate page (the browser on which it is displayed). Therefore, in step S3A, the setting is made for "processing to obtain the information on the timeline of the candidate page as the entire message (variable 2)."
[0026] The second step is a step (hereinafter referred to as the "GPT step") in which variables (acquired in the variable acquisition step) are substituted into a prompt template to construct a prompt, and the prompt is sent to the AI system 4 (see Figure 2). Therefore, in step S3B, the GPT step is set.
[0027] The third step is a step of acquiring the answer from the AI system 4 to the prompt sent in the GPT step and displaying it on the candidate page on the browser (hereinafter referred to as the "AI answer display step"). Therefore, in step S3C, the AI answer display step is set.
[0028] In other words, it can be understood that the service extension UI (measure) having the following first and second functions is set and registered in the server 1 in steps S2 and S3. The first function is a function for placing an operator (a button in the example of FIG. 1) at a predetermined position on the candidate page in the browser. The second function is a function that, when the operator (button) is operated, causes a predetermined process to be executed, which is made up of a variable acquisition step, a GPT step, and an AI answer display step.
[0029] A detailed example of the service operator SU's registration of the third-party system (candidate page of the recruitment management tool) in step S1 and the configuration of the measures (service extension UI) in steps S2 and S3 will be described later with reference to the flowcharts in Figures 6 and 7.
[0030] After the service operator SU has registered the third-party system (candidate page of the recruitment management tool) in step S1 and set up the measures (extended UI of this service) in steps S2 and S3 in this way, the service operator SU will preview the measures (extended UI of this service) as appropriate to confirm the settings, and after confirmation, will publish the measures (extended UI of this service). With this release, service users SR will be able to use the tools of this service on user terminal 3, as shown in Figure 2, to use the measures (this service's extended UI) on the screen of a third-party system (the candidate page of the recruitment management tool) in a browser.
[0031] Specifically, in step S11, the service extension UI is placed in the third-party system (candidate page) in the browser of the user terminal 3. In other words, the operator (button in the example of FIG. 2) of the service extension UI is placed in the predetermined position set in step S2 of FIG. 1 in the third-party system (candidate page).
[0032] In step S12, the service user SR operates an operator (a button in the example of FIG. 2) placed at a predetermined position on the candidate page in the browser. Then, in step S13, the predetermined processing set in step S3 of FIG. 1 is automatically executed.
[0033] That is, in step S13A, the user terminal 3 executes the processing of the variable acquisition step. Specifically, for example, the user terminal 3 acquires information on the "Applied for Job Type" area of the candidate page as the job type (variable 1). Furthermore, for example, the user terminal 3 acquires information on the "timeline" of the candidate page as the entire message (variable 2).
[0034] In step S13B, the user terminal 3 executes the processing of the CPT step. Specifically, for example, in the prompt template shown in Figure 1, the user terminal 3 constructs a prompt by substituting information from the "Applied for job" area on the candidate page as variable 1 for {Job type: Variable 1}, and substituting information from the "Timeline" area on the candidate page as variable 2 for {Entire message: Variable 2}. The user terminal 3 transmits the prompt to the AI system 4 via the server 1.
[0035] In step S13C, the user terminal 3 executes the process of the AI answer display step. Specifically, for example, the user terminal 3 acquires the response from the AI system 4 to the prompt sent in step S13B and displays it on the candidate page on the browser.
[0036] A detailed example of the use of the measures (present service extension UI) in steps S11 to S13 by the present service user SR will be described later with reference to the flowcharts of FIGS.
[0037] Next, with reference to FIG. 3, the configuration of an information processing system that realizes the provision of the above-described service, that is, an embodiment of the information processing system of the present invention, will be described. FIG. 3 is a diagram showing an example of the configuration of an information processing system that realizes the provision of the present service shown in FIGS. 1 and 2, that is, an embodiment of the information processing system of the present invention.
[0038] The information processing system shown in FIG. 3 is configured to include a server 1, an operator terminal 2 and a user terminal 3 of a user company, an AI system 4, and a third-party system server 5. The server 1, the operator terminal 2, the user terminal 3, the AI system 4, and the third-party system server 5 are connected to one another via a network such as the Internet.
[0039] The server 1 is an information processing device managed by the service provider ST of this service (Figs. 1 and 2). The server 1 executes various processes to realize this service while communicating appropriately with the operator terminal 2 and user terminal 3 of the user company, and the AI system 4. When providing this service, the server 1 does not need to communicate directly with the third-party system server 5.
[0040] The operator terminal 2 is an information processing device managed by the service operator SU of the user company, and is composed of a smartphone, tablet, personal computer, etc., and communicates with the server 1 and the third-party system server 5 as appropriate, while executing the ``management screen'' and ``editor extension'' tools of this service.
[0041] The user terminal 3 is an information processing device managed by the user UR of the user company's service, and is composed of a smartphone, tablet, personal computer, etc., and executes the ``player extension'' tool of this service while communicating with the server 1 and the third-party system server 5 as appropriate.
[0042] The AI system 4 is a server or the like that operates AI that is utilized in measures implemented by user companies. In this example, it is assumed that LLM (Large Language Models) is adopted as the AI model. The third-party system server 5 is a server that manages a third-party system (website) used in the business of a user company.
[0043] FIG. 4 is a block diagram showing an example of a hardware configuration of the operator terminal in the information processing system shown in FIG.
[0044] The operator terminal 2 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an input unit 16, an output unit 17, a memory unit 18, a communication unit 19, and a drive 20.
[0045] The CPU 11 executes various processes according to a program recorded in the ROM 12 or a program loaded from the storage unit 18 into the RAM 13 . The RAM 13 also stores data and the like necessary for the CPU 11 to execute various processes.
[0046] The CPU 11, ROM 12, and RAM 13 are connected to one another via a bus 14. An input / output interface 15 is also connected to this bus 14. An input unit 16, an output unit 17, a storage unit 18, a communication unit 19, and a drive 20 are connected to the input / output interface 15.
[0047] The input unit 16 is configured with, for example, a keyboard and is used to input various information. The output unit 17 is configured with a display such as a liquid crystal display, a speaker, etc., and outputs various information as images and sounds. The storage unit 18 is configured with a DRAM (Dynamic Random Access Memory) or the like, and stores various data. The communication unit 19 communicates with other devices (for example, the server 1 and the third-party system server 5 in FIG. 3) via a network N including the Internet.
[0048] Removable media 30, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is appropriately attached to the drive 20. A program read from the removable media 30 by the drive 20 is installed in the storage unit 18 as needed. Furthermore, the removable medium 30 can also store various data stored in the storage unit 18 in the same manner as the storage unit 18.
[0049] Although not shown, the server 1 and the user terminal 3 also have the hardware configuration shown in FIG.
[0050] Various processes for providing the service of Figures 1 and 2 can be executed by cooperation between various hardware (Figure 4) and various software that constitute the information processing system of Figure 3, including server 1, operator terminal 2, and user terminal 3.
[0051] FIG. 5 is a functional block diagram showing an example of the functional configuration of the administrator terminal and the user terminal of FIG. 4 in the information processing system of FIG.
[0052] As shown in FIG. 5, in the administrator terminal 2, an extended UI setting unit 51, an extended UI provisional execution unit 52, and an extended UI publishing unit 53 function.
[0053] The extended UI setting unit 51 sets the extended UI of this service (measures utilizing AI) and registers the setting contents in the server 1. As described above with reference to Figures 1 and 2, this service extension UI is a UI for executing predetermined processing related to a part of a predetermined website on which a third-party system is executed (a page of the predetermined website that indicates the scope of execution of a measure, for example, the candidate page in the example of Figure 1) using an interactive system (here, AI system 4). This service extension UI functions by being placed in a browser for the target (candidate page) of the third-party system.
[0054] The extended UI setting unit 51 includes a third-party system registration unit 511 , an operator setting unit 512 , and a process setting unit 513 .
[0055] The third-party system registration unit 511 registers the target (candidate page) of a predetermined website of the third-party system in the server 1.
[0056] The operator setting unit 512 sets an operator (for example, a button) to be placed in the first position of the target (candidate page) in a predetermined browser.
[0057] The predetermined process setting unit 513 sets a predetermined process that is executed when an operator (for example, a button) is operated as a trigger.
[0058] Here, when a prompt for the AI system 4 is constructed by inputting specified information as variables into a prompt template including variables, the specified processing setting unit 513 sets the following first to third steps as steps constituting the specified processing. The first step is a step of obtaining information at the second location of the target in the predetermined browser as a variable, for example, the variable obtaining step described above with reference to FIGS. The second step is to construct a prompt by inputting the variables obtained in the first step into a prompt template and send the prompt to the AI system 4, for example, the GPT step described above using Figures 1 and 2. The third step is a step of obtaining the response of the AI system 4 to the prompt and presenting it in a predetermined browser, for example, the AI response display step described above with reference to FIGS.
[0059] The extended UI virtual execution unit 52 places (superimposes) the extended UI of this service on the target (candidate page) of the third-party system in a specified browser to perform a preview for confirmation of the extended UI of this service (measures utilizing AI) set by the extended UI setting unit 51. That is, the extended UI provisional execution unit 52 has the same functions as a third-party system execution unit 61 and an extended UI execution unit 62 of the user terminal 3, which will be described later.
[0060] The extended UI publishing unit 53 publishes the extended UI of this service (measures using AI).
[0061] By this publication, the third-party system execution unit 61 and the extended UI execution unit 62 function in the user terminal 3.
[0062] The third-party system execution unit 61 accesses the URL of a specified website of the third-party system server 5 using a specified browser, displays the target of the third-party system (candidate page) in the specified browser, and executes the third-party system (recruitment management tool).
[0063] The extended UI execution unit 62 places the extended UI of this service on the target (candidate page) of the third-party system in a predetermined browser, and makes the extended UI of this service function. The extended UI execution unit 62 includes an extended UI placement unit 621 , an operator reception unit 622 , and a process execution unit 623 .
[0064] The extended UI placement unit 621 places the service extended UI on the target (candidate page) of the third-party system in the predetermined browser. That is, the extended UI placement unit 621 places an operator (e.g., a button) in the predetermined browser at the first position of the target (candidate page) of the third-party system.
[0065] The operator receiving unit 622 receives an operation on an operator in a predetermined browser.
[0066] The predetermined process execution unit 623 executes the predetermined process when an operation on the operator is accepted as a trigger. Specifically, for example, the predetermined process execution unit 623 executes the above-mentioned first step (e.g., variable acquisition step), the above-mentioned second step (e.g., GPT step), and the above-mentioned third step (e.g., AI answer display step) in sequence, thereby executing the predetermined process.
[0067] Next, a processing example of the administrator terminal 2 and the user terminal 3 having the functional configuration of FIG. 5 will be described. 6 and 7 are flowcharts illustrating an example of the flow of processing performed by the administrator terminal having the functional configuration of FIG. Steps S1 to S3 shown in FIGS. 6 and 7 correspond to the steps in FIG.
[0068] The extended UI setting unit 51 of the operator terminal 2 logs in using the management screen, one of the tools of this service, in a specified browser, and performs system registration, policy page registration, and policy registration as third-party system registration in step S1 of Figure 1. Although not shown in the figure, when a user logs in to the login screen of the management screen in a specified browser, the top page of the management screen is displayed. The top page of the management screen lists a list of third-party systems that have already been configured. When a user selects a configured third-party system, the user is taken to the top page (not shown) of the selected third-party system, and an analysis screen is displayed that allows the user to visualize the effects of measures being implemented within the selected third-party system. If the recruitment management tool described in Figure 1 is not present in the list of third-party systems on the management screen, click the Add button (not shown) on the top page. As a result, a new system registration screen (not shown) is displayed on the predetermined browser. When the title of the third-party system (for example, the title "Recruitment Management Tool") and the URL of the third-party system are entered on the new system registration screen, the third-party system registration unit 511 registers the title of the third-party system (for example, the title "Recruitment Management Tool") and the URL of the third-party system on server 1 as the system registration.
[0069] After registering the system (before registering the policy), the third-party system registration unit 511 registers a policy page to limit the scope of the policy. Here, there are no particular limitations on the pages that can be registered, and multiple pages can be registered, but for the sake of convenience, only the candidate page described in Figure 1 will be registered. Specifically, for example, the third-party system registration unit 511 registers the URL of the page on which the measure should be implemented (in this example, the candidate page of the recruitment management tool) on server 1, and can also make detailed settings such as the display status of specific elements on the screen and register the settings on server 1. In the example of Figure 1, a button is placed as an operator on the candidate page, so the following content is also registered: "Page title: Candidate page" and "Page conditions: URL contains "https: / / *** / candidacies / id / "."
[0070] After registering the policy page, the third-party system registration unit 511 registers the policy name of each individual policy (present service extension UI) for the policy page (candidate page in this example) as a policy registration. Although it is possible to register multiple measures on the measure page, it is assumed here that only the measure described in Fig. 1 (timeline summary by clicking a button) is registered. Therefore, the third-party system registration unit 511 registers the measure name "timeline summary" in the server 1.
[0071] Once the policy registration is complete, the policy setting process begins immediately. The setup process takes place in a specific browser on the third-party system to be installed, so in this example you will automatically be redirected to the candidate page of the recruitment management tool. In addition, the extended UI setting unit 53 activates an editor extension from among the tools of this service, and executes the policy setting process using the editor extension. In this example, the setting process shown in Figure 1 is performed, so the process of step S2, that is, the process of placing a button as an operator on the screen (of the candidate page in a specified browser), is executed. Note that the process of step S2 will be referred to as the "button placement process" hereinafter. Next, the process of step S3 is executed, that is, the process of setting a predetermined process that is executed when the operator is operated (the predetermined process that is executed when the button is clicked). Note that the process of step S3 will be referred to as the "measure setting process" hereinafter.
[0072] Specifically, first, as the button setting process in step S2, the operator setting section 512 executes the following process using the editor extension. That is, the operator setting unit 512 acquires the position where the button is to be placed (the predetermined position in the description of FIG. 1) within the screen of the candidate page in the predetermined browser as shown in FIG. 10. Specifically, for example, the operator setting unit 512 acquires element information of the button installation location (the predetermined position in the description of FIG. 1) from the HTML of the candidate page. The operator setting unit 512 sets the text in the button, fine-tuning the position, color, etc. Specifically, for example, the operator setting unit 512 inserts a button into the HTML of the candidate page and adjusts the text, color, etc. Figure 10 shows an example of the screen of the operator terminal of Figure 3 when the button installation process of step S2 in Figures 1 and 6 is executed. On the screen of Figure 10, a box with the text "Timeline Summary & Confirm Next Action" inserted in it indicates the button to be set to be placed at that position. In this way, the service administrator SU can adjust the button design and text on the actual page (the candidate page in this example). Being able to check the design on the actual page is very efficient in terms of work.
[0073] When the button setting process in step S2 is completed, the process setting unit 513 performs the action setting process in step S3 using the editor extension. As described above with reference to FIG. 1, the policy setting process in step S3 is made up of a process S3A for setting a variable acquisition step, a process S3B for setting a GPT step, and a response display step. Therefore, the process setting unit 513 can set the policy setting process of step S3 in the form of a flowchart as shown in Fig. 11. The reason why the policy setting process of step S3 is performed using a UI that uses a flowchart in this way is that a flowchart makes it possible to visualize each process and also allows for high editing efficiency. Figure 11 shows an example of a screen on the operator terminal of Figure 3 when the policy setting process of step S3 in Figures 1 and 6 is executed, and shows an example of a UI screen that connects each step that makes up the specified processing to generate a flowchart. There are several setting menus in the flowchart. In this example, a "variableization step" that changes the elements on the screen to variables, a "GPT step" that sends a prompt to the AI, and a "popup step" that displays the response from the prompt are used.
[0074] In the example of FIG. 11, in order to execute the process S3A, a "variableization step" corresponding to the variable acquisition step is arranged as the first step in the flowchart. Therefore, when the variable menu in the first step (variableization step) of the flowchart in FIG. 11 is clicked, the screen shown in FIG. 12 is displayed and step S3A is executed. FIG. 12 shows an example of a screen of the administrator terminal of FIG. 3 when step S3A of the policy setting process of step S3 of FIGS. 1 and 6 is executed. As a process S3A for setting a variable acquisition step (a step for creating a variable for variable 1), the process setting unit 513 supplements the area (position) of "Applied for Job Type" to be set as variable 1, which fleshes out the current prompt, from the screen (the screen of the candidate page in a specified browser) as shown in Fig. 12. In the example of Fig. 12, when the service administrator SU clicks on the area displayed as "01 Senior Account Executive Producer" in the screen information and enters "Applied for Job Type Variable 1" as the variable name, the process setting unit 513 supplements the area of "Applied for Job Type" to be set as variable 1 from the screen of Fig. 12 based on the clicked position and the input content. Here, when the service administrator SU presses the "Confirm button" in the area below "Variable Settings" on the screen in Fig. 12, the processing setting unit 513 acquires only the position information of the clicked area (element) and stores it on the server 1 side so as not to acquire the actual display content unnecessarily. This is to avoid sending confidential information unnecessarily to the server 1 (service provider ST). That is, the position information of the area (element) is a selector in HTML, etc., and has almost no confidentiality.
[0075] When the service operator SU presses the "Confirm button" on the screen in Figure 12, the setting of the variableization step for setting the area (position) of "Applied for job type" as variable 1 is completed, and the screen transitions to the flowchart portion (not shown), and one step is added to the flowchart. In the example of Figure 1, the content of the timeline (the message to be summarized) needs to be variable 2, so although not shown, another variableization step is added to the flowchart. In this case, too, when the variable menu in the flowchart is clicked, a screen similar to that in Figure 12 is displayed, although not shown. Therefore, although not shown in the figure, the process setting unit 513 supplements the area (position) of the "timeline" to be used as variable 2, which is the fleshing out of this prompt, from the screen (the candidate page screen in the specified browser) as step S3A for setting the variable acquisition step (variableization step for variable 2). At this time, the variable name of variable 2 is set to "Entire message variable 2."
[0076] Although not shown in the figure, when the service operator SU presses the "Confirm button," the setting of the variableization step for setting the "timeline" area (position) as variable 2 is completed (process S3A is completed), and although not shown in the figure, the screen transitions to the flowchart portion, where a GPT step is added after the two variableization steps for variable 1 and variable 2. In this way, after two variableization steps for variable 1 and variable 2 are registered in step S3A, step S3B is performed to construct a prompt using these variables 1 and 2, i.e., step S3B is performed to set up the GPT step. When the GPT step menu in the flowchart is clicked, the screen shown in Figure 13 will be displayed. FIG. 13 shows an example of a screen of the administrator terminal of FIG. 3 when step S3B of the policy setting process of step S3 of FIGS. 1 and 6 is executed.
[0077] In step S3B of setting the GPT step, the process setting unit 513 registers a prompt template using the screen of Fig. 13. Specifically, for example, the process setting unit 513 registers the prompt template shown in Fig. 1, in which "Variable 1: Job type applied for" and "Variable 2: Entire message," which are converted into variables in the immediately preceding variable acquisition step, are entered in the relevant places. In addition, a variable name is registered that will receive the response (answer) from the AI that received the prompt template at runtime. Here, the variable name is set to "Response from GPT".
[0078] When the service operator SU presses the "Confirm button" on the screen in Figure 13, process S3B of setting the GPT step is completed, and although not shown, the screen transitions to the flowchart portion, and in the flowchart, two variableization steps for variable 1 and variable 2, and a pop-up step is added after the GPT step. Therefore, when the pop-up menu in the flowchart is clicked to execute step S3C, that is, to execute the setting of the pop-up step adopted as the AI answer display step, the screen in FIG. 14 is displayed. FIG. 14 shows an example of a screen of the administrator terminal of FIG. 3 when step S3C of the policy setting process of step S3 of FIGS. 1 and 6 is executed.
[0079] In step S3C of setting the AI answer display step, the process setting unit 513 inputs only {Response from GPT} into the message using the screen in Fig. 14. This is because the pop-up step adopted as the AI answer display step simply displays the response (answer) received by the GPT step executed before it.
[0080] When the service administrator SU presses the "Confirm button" on the screen of Figure 14, process S3C is completed, that is, when the entire policy setting step S3 is completed, the screen transitions to the flowchart portion shown in Figure 15. Figure 15 shows an example of a screen displayed on the operator terminal of Figure 3 when the policy setting process of step S3 in Figures 1 and 6 is executed, and shows a different example of a screen from Figure 11, which shows a UI that generates a flowchart by connecting together the steps that make up the specified processing. Comparing the screen in Figure 15 with Figure 11, it can be seen that the flowchart for executing the predetermined process is complete. That is, from the top, the variableization step for variable 1, the variableization step for variable 2, the GPT step, and the pop-up step are connected together, and finally, the flowchart with the message "Complete" is displayed on the screen in Figure 15.
[0081] Here, the service operator SU can use the preview function to test whether the actual processing works properly. Specifically, for example, when the preview on the screen of Figure 15 is clicked, the extended UI temporary execution unit 52 executes three steps that constitute the specified processing as the preview shown in Figure 7, namely, a variable acquisition step (two variableization steps for variable 1 and variable 2), a GPT step, and an AI answer display step (pop-up step).
[0082] In the variable acquisition steps (two variableization steps for variable 1 and variable 2), actual values are acquired from the position information of the on-screen elements of the candidate page in the specified browser. That is, for variable 1, information (actual value) of the "job type applied for" area (on-screen element) of the candidate page is acquired. For variable 2, information (actual value) of the "timeline" (on-screen element) of the candidate page is acquired.
[0083] In the GPT step, a prompt is constructed using the prompt template shown in Figure 1 and the actual values obtained as variables 1 and 2 in the variable acquisition step, and the prompt is sent to the AI system 4 via server 1.
[0084] In the pop-up step, an answer (response) is obtained from the AI system 4 that received the prompt actually sent in the GPT step, and a pop-up display (result display) is displayed on the candidate page screen in a specified browser.
[0085] If, as a result of executing such a preview function, the service operator SU determines that there are no problems with the measures (service extension UI) set in steps S2 and S3, the operator can issue an instruction to save the contents of the measures (service extension UI) on a screen not shown. By this instruction, the contents (the set values in steps S2 and S3) of the measure (this service extension UI) are additionally saved in the server 1.
[0086] In this way, when the contents of the measure (this service extension UI) are saved in the server 1, the screen of the operator terminal 2 transitions to the management screen (not shown in the figure). The previously set measure (this service extension UI) is registered on this management screen. However, at this point, the measure (this service extension UI) is still in a "private" state, and the measure (this service extension UI) is not placed on the actual screen of the user terminal 3, and the buttons used for the measure are not displayed. That is, although not shown in the figure, the service administrator SU presses a publish button (not shown) on the management screen at an appropriate time. Then, the extended UI publishing unit 53 communicates with the server 1 and makes the measure (the extended UI of the present service) public. As a result, the measure (the extended UI of the present service) is placed on the actual screen of the user terminal 3, and the buttons used in the measure are also displayed.
[0087] In other words, when the above-mentioned measure (this service extension UI) is made public, when a user terminal 3 on which the player extension, one of the tools of this service, is installed, accesses the relevant page (in this example, the candidate page), a new button will be displayed in a designated position on the relevant page, as shown in Figure 2. By clicking this button at the necessary time, service users (SRs, general employees, etc.) can automatically view the timeline summary in a pop-up window, as shown in Figure 2, without any further action being required.
[0088] The flow of such processing on the user terminal 3 side is shown in FIGS. 8 and 9 are flowcharts illustrating an example of the flow of processing performed by the user terminal 3 having the functional configuration of FIG. Steps S11 to S13 shown in FIGS. 8 and 9 correspond to the steps in FIG.
[0089] The third-party system execution unit 61 of the user terminal 3 displays the relevant page of the third-party system (the candidate page in this example) on a predetermined browser.
[0090] The extended UI execution unit 62 of the user terminal 3 executes system determination. That is, the extended UI execution unit 62 acquires a list of third-party systems from the server 1 and performs a comparison with the third-party systems. That is, the third-party system execution unit 61 determines whether the third-party system displayed in the specified browser corresponds to one included in the list. If it is determined that the third-party system does not correspond, the process ends with the system comparison. In this example, the candidate page of the recruitment management tool is displayed, and since the recruitment management tool is included in the list, the process moves to the next policy page determination.
[0091] The extended UI execution unit 62 acquires a list of policy pages of the third-party system from the server 1 and collates the page to determine whether it is a policy page. That is, the third-party system execution unit 61 determines whether the page displayed on the predetermined browser is a page included in the list (a page for which a policy exists). If it is determined that the page is not included in the list (a page for which a policy does not exist), the process ends with page collation. In this example, the candidate page of the recruitment management tool is displayed, and since the candidate page includes the measures (this service's extended UI) set up as described above (listed as such), the process proceeds to the button installation process in the next step S11.
[0092] In the button installation process of step S11, the extended UI placement unit 621 of the extended UI execution unit 62 acquires the action list and, for each action listed in the action list, places a button on the screen of the corresponding page of the third-party system in a predetermined position set for that action on the screen of the corresponding page of the third-party system in a predetermined browser. Here, if multiple actions are found, buttons for each of the multiple actions are installed simultaneously in parallel. In this example, although not shown, the button will be placed at the position set in Figure 10. Specifically, for example, the button is inserted into the HTML of the candidate page, and the text and color are adjusted.
[0093] In other words, when the service user SR presses the button, in step S12, the operator receiving unit 622 of the extended UI execution unit 62 receives the button pressing operation, and the process proceeds to step S13.
[0094] In step S13, the processing execution unit 623 of the extended UI execution unit 62 sequentially executes the three steps that make up the specified processing, namely, the variable acquisition step (two variableization steps for variable 1 and variable 2), the GPT step, and the AI answer display step (pop-up step), in that order.
[0095] The process execution unit 623 executes a variable acquisition step (two variableization steps for variable 1 and variable 2) in step S13A. Specifically, for example, actual values are acquired from the position information of the on-screen elements of the candidate page in the specified browser. That is, for variable 1, information (actual value) of the "Applied for Job Type" area (on-screen element) of the candidate page is acquired. For variable 2, information (actual value) of the "Timeline" (on-screen element) of the candidate page is acquired.
[0096] The processing execution unit 623 executes the GPT step in step S13B. Specifically, for example, a prompt is constructed using the prompt template shown in Figure 1 and the actual values acquired as variables 1 and 2 in the variable acquisition step, and the prompt is sent to the AI system 4 via the server 1.
[0097] The process execution unit 623 executes an AI answer display step (pop-up step) in step S13C. Specifically, for example, an answer (response) is acquired from the AI system 4 that received the prompt actually sent in the GPT step, and a pop-up display (result display) is performed on the candidate page screen in a predetermined browser.
[0098] The playback log in step S13 is transmitted to and saved in the server 1 and is used to create a report.
[0099] The processing example of the administrator terminal 2 having the functional configuration of FIG. 5 has been described above using the flowcharts of FIGS. 6 and 7 and the screen examples of FIGS. Also, an example of processing by the user terminal 3 having the functional configuration of FIG. 5 has been described using the flowcharts of FIGS.
[0100] By employing the administrator terminal 2 capable of executing the process examples of FIGS. 6 and 7, the following advantages can be enjoyed. 6 and 7, no communication takes place between the server 1 of the service provider ST and the third-party system server 5. The information required to install the button is obtained by obtaining the necessary information from the screen of the third-party system (in this example, the candidate page of the recruitment management tool) through an editor extension, one of the tools of this service. In addition, the information obtained through the editor extension is mainly limited to the URL of third-party systems and HTML information that makes up the layout on the screen, and no unnecessary information about the content is obtained.
[0101] Furthermore, by employing a user terminal 3 that can execute the processing examples of FIGS. 8 and 9, the following advantages can be enjoyed. In other words, the player extension, one of the tools of this service, incorporates a multi-stage process of determining which third-party system (which website) and which page to place the controls (buttons, etc.) on the screen (see system determination and action page determination in Figure 8). Once these checks are completed successfully and the button installation process begins, the location for the button is determined based on the element position information set in the editor extension (on the operator terminal 2 side), and the button is added to the screen of the relevant page (the candidate page in the example above) in the specified browser based on the design setting values registered in the editor extension (on the operator terminal 2 side). The button added on the screen is in a state of waiting to be clicked by the service user SR, and when clicked, the actual process (predetermined process of the set measure) is executed. In other words, the process of determining the system, page, and button placement is also the process of selecting the required prompt template. In addition, when the service user SR clicks a button to enter the execution process of the specified policy processing, information (variables) is obtained from the screen, and the prompt template is automatically rewritten using that information (variables) to create an optimized prompt, which is then automatically sent to AI System 4 (LLM).
[0102] Among the measures (service extension UI) described above, when a button is pressed, a predetermined process is performed by sending a predetermined prompt to the AI system 4 (LLM) and obtaining an answer to the prompt, and this process is repeated one or more times (interacting with the AI), which will be referred to as a "component." By installing this "component" in a third-party system (implementing measures), a company can achieve one of its three major missions: improving business efficiency. The three major missions here include improving business efficiency, employee training, and security. However, there was an issue in that simply installing the "component" alone did not necessarily improve the utilization rate of AI System 4 (LLM) by the SRs (employees) who use this service. To solve this issue from the perspective of employee training to improve work efficiency, the component can be integrated with the sidebar function. The sidebar function is a function that displays a chat interface in the sidebar, such as next to the screen of a third-party service in a specified browser, that allows users to interact with AI System 4 (LLM) in chat format. Specifically, for example, when the component's dialogue with AI System 4 (LLM) ends (in the above example, a summary of the timeline on the candidate page is displayed as the answer), if the service user SR instructs that they wish to continue the dialogue, the sidebar will be displayed and they will be able to continue the dialogue in chat format with AI System 4 (LLM). This chat format sidebar also displays the initial prompt from the component, allowing the service user SR to continue the dialogue appropriately, taking that prompt into consideration.
[0103] Figures 16 to 18 show an example of a UI that combines a component (this service extension UI) set up by an operator terminal having the functional configuration of Figure 5 according to the flowcharts of Figures 6 and 7 with a sidebar. As shown in the screen of FIG. 16, a component placed on a screen of a third-party system in a predetermined browser on the user terminal 3 (e.g., a page for creating documents, different from the candidate page described above) displays operators for executing one or more LLM functions (functions for executing predetermined processes for measures). In the example component of FIG. 16, a box labeled "What do you want to do?" displays a first menu item labeled "Create a draft structure for proposal documents" and a second menu item labeled "Create a draft structure for market reports." This first menu item is an example of an operator that triggers the execution of a predetermined process, which is to interact with the AI system 4 (LLM) to create a draft structure for proposal documents. The second menu item is also an example of an operator that triggers the execution of a predetermined process, which is to interact with the AI system 4 (LLM) to create a draft structure for market reports. Regardless of whether the first or second menu is selected, appropriate prompts are adjusted to return content appropriate to the task in the dialogue (predetermined processing) with the AI system 4 (LLM).
[0104] For example, when the first menu (operator) of a component is selected, an interaction occurs with the AI system 4 (LLM), and a proposed structure for the proposal document is displayed as a pop-up as an answer (response) from the AI system 4 (LLM), as shown in Figure 17. As shown in FIG. 17, this pop-up display screen has a button labeled "Talk more" in addition to a button to close the modal. If the service user SR wishes to continue the conversation with AI system 4 (LLM), he / she presses the button labeled "Talk more." This activates the sidebar function, and a chat interface that allows users to interact with the AI system 4 (LLM) in chat format is displayed next to the screen of the third-party service in a specified browser, as shown in Figure 18. This chat interface displays the history of interactions with the AI system 4 (LLM) up to now, as shown in FIG. The service user SR can then continue the conversation with the AI system 4 (LLM) using this chat interface. In addition, by looking at the history of this chat interface, SRs who use this service can see what prompts were actually sent to AI System 4 (LLM) and what answers were received from AI System 4 (LLM).
[0105] The value provided by the user interface that combines the components shown in FIGS. 16 to 18 with the sidebar function is as follows. That is, there is a function called "Conversation Starter" that serves as an opportunity to start a conversation with the LLM. The component is responsible for the role of that function. In other words, placing a component with that function on the screen of a third-party system in a specified browser (the screen used by the service user SR in their work) is equivalent to integrating that function into their work, which is expected to dramatically improve the utilization rate of the AI System 4 (LLM).
[0106] In other words, the user interface that combines the components shown in Figures 16 to 18 with the sidebar function serves as a gateway for users (SRs who use this service) to increase the utilization rate of the AI system 4 (LLM). In other words, the component can encourage the use of LLM in line with business operations (starting a dialogue with LLM with one click). Furthermore, you can seamlessly transition from the component to the sidebar function, allowing you to develop a conversation with the LLM (expand the contents of the component) on the spot. Furthermore, although not shown, it is also possible to switch from a sidebar chat interface to a full-screen chat interface, which can help users (SRs who use this service) to become accustomed to using chat.
[0107] Although one embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and modifications, improvements, etc. within the scope of achieving the object of the present invention are considered to be included in the present invention.
[0108] For example, in the above-mentioned service, the person interacting with the measure (the service's extended UI) is an LLM, but this is not limited to this and can be any of a variety of AI models, and ultimately any interactive system, not just AI, will suffice.
[0109] For example, in the above-described present service, a button is used as a trigger for starting execution of a predetermined process in the measure (present service extended UI), but this is not particularly limited to this, and any operator will suffice.
[0110] Furthermore, the system configuration shown in FIG. 3 and the hardware configurations of the administrator terminal 2 and the user terminal 3 shown in FIG. 4 are merely examples for achieving the object of the present invention, and are not particularly limited.
[0111] Furthermore, the functional block diagram shown in Fig. 5 is merely an example and is not particularly limited. That is, it is sufficient if the information processing system in Fig. 3 is provided with a function that can execute the various processes described above as a whole, and the functional blocks and databases used to realize this function are not particularly limited to the example in Fig. 5.
[0112] Furthermore, the locations of the functional blocks and databases are not limited to those shown in FIG. 5 and may be arbitrary. For example, at least some of the functional blocks and databases (for example, service provider databases) arranged on the administrator terminal 2 and user terminal 3 side may be provided in other information processing devices.
[0113] The above-described series of processes can be executed by hardware or software. Furthermore, one functional block may be configured as a single piece of hardware, a single piece of software, or a combination thereof.
[0114] When a series of processes is executed by software, the programs that make up the software are installed into a computer or the like from a network or a recording medium. The computer may be a computer built on dedicated hardware. The computer may also be a computer that can execute various functions by installing various programs, such as a service provider server, a general-purpose smartphone, or a personal computer.
[0115] The recording medium containing such a program may be composed not only of a removable medium (not shown) that is distributed separately from the device main body in order to provide the program to the user, but also of a recording medium that is provided to the user in a state that is pre-installed in the device main body.
[0116] In this specification, the steps describing the program to be recorded on the recording medium include not only processes that are performed in chronological order, but also processes that are not necessarily performed in chronological order but are performed in parallel or individually.
[0117] To sum up, the information processing device to which the present invention is applied is sufficient as long as it has the following configuration, and can take on a variety of different embodiments. That is, an information processing system to which the present invention is applied (for example, the information processing system of FIG. 3) is a UI setting unit (e.g., the extended UI setting unit 51 of the operator terminal 2 in FIG. 5) that sets a predetermined UI (User Interface) (e.g., the service extended UI in FIGS. 1 and 2) for executing a predetermined process related to a part of a predetermined website (e.g., a predetermined web page, e.g., a candidate page in the above example) on which another system (e.g., a third-party system, e.g., a recruitment management tool in the above example) is executed using an interactive system; Another system execution means (for example, the third-party system execution unit 61 of the user terminal 3 in FIG. 5) for displaying the target of the predetermined website on a predetermined browser and executing the other system; a UI functioning means (for example, the extended UI execution unit 62 of the user terminal 3 in FIG. 5) for arranging the predetermined UI on the target in the predetermined browser and making the predetermined UI function; Equipped with The UI setting means A registration means (for example, the third-party system registration unit 511 in FIG. 5) registers the target of the predetermined website (for example, executes step S1 in FIG. 1 and FIG. 6); an operator setting unit (e.g., the operator setting unit 512 in FIG. 5) that sets an operator (e.g., the button in FIGS. 1, 2, and 10) to be placed at the first position of the target in the predetermined browser (e.g., executes step S2 in FIGS. 1 and 7); A predetermined process setting means (for example, the process setting unit 513 in FIG. 5) sets the predetermined process to be executed when the operator is operated (for example, executes step S3 in FIGS. 1 and 7), and The UI functionalization means A control placement unit (for example, the extended UI placement unit 621 in FIG. 5) places the control at the first position of the target in the predetermined browser (for example, executes step S11 in FIGS. 2 and 8); An operation receiving unit (for example, the operator receiving unit 622 in FIG. 5) receives an operation on the operator in the predetermined browser (for example, executes step S12 in FIGS. 2 and 9), A predetermined processing execution unit (for example, the processing execution unit 623 in FIG. 5) executes the predetermined processing (for example, executes step S13 in FIGS. 2 and 9) when the operation on the operator is accepted as a trigger. having Any information processing system will suffice.
[0118] wherein a prompt for the interactive system is configured by inputting predetermined information as a variable into a prompt template including the variable (e.g., the prompt template shown in FIG. 1 ); The predetermined processing setting means As a step constituting the predetermined processing, a first step of acquiring information at a second location of the target in the predetermined browser as the variable (for example, the variable acquisition step (one or more variableization steps) described above); a second step (e.g., the GPT step described above) of constructing the prompt by inputting the variables obtained in the first step into the prompt template and sending the prompt to the interactive system; a third step (e.g., the AI response display step (pop-up step) described above) of obtaining an answer from the interactive system in response to the prompt and presenting the answer in the predetermined browser; (for example, by executing steps S3A to S3C in FIGS. 1 and 7), The predetermined processing execution means executes the predetermined processing by sequentially executing the first step, the second step, and the third step (for example, executes steps S13A to S13C in FIGS. 2 and 9 ); It is possible.
[0119] The UI functioning means may further include: After the predetermined process is executed, another UI (e.g., a chat interface in the sidebar of FIG. 18) is activated for further use of the interactive system. It is possible. [Explanation of symbols]
[0120] 1 Server, 2 Operator terminal, 3 User terminal, 4 AI system, 5 Third-party system server, 11 CPU, 12 ROM, 13 RAM, 14 Bus, 15 Input / output interface, 16 Input unit, 17 Output unit, 18 Storage unit, 19 Communication unit, 20 Drive, 30 Removable media, 51 Extended UI setting unit, 52 Extended UI virtual execution unit, 53 Extended UI publication unit, 61 Third-party system execution unit, 62 Extended UI execution unit, 511 Third-party system registration unit, 512 Operator setting unit, 513 Processing setting unit, 621 Extended UI placement unit, 622 Operator reception unit, 623 Processing execution unit
Claims
1. a UI setting means for setting a predetermined UI (User Interface) for executing a predetermined process related to a part of a predetermined website on which another system is executed using an interactive system; another system execution means for displaying the target of the predetermined website on a predetermined browser and executing the other system; a UI functioning means for arranging the predetermined UI on the target in the predetermined browser and making the predetermined UI function; Equipped with The UI setting means a registration means for registering the target of the predetermined website; an operator setting means for setting an operator to be placed at a first position of the target in the predetermined browser; a predetermined process setting means for setting the predetermined process to be executed when the operator is operated; and The UI functioning means includes: a control placement means for placing the control at the first position of the target in the predetermined browser; an operation receiving means for receiving an operation on the operator in the predetermined browser; a predetermined processing execution means for executing the predetermined processing when the operation on the operator is accepted as a trigger; having Information processing system.
2. a prompt for the interactive system is configured by inputting predetermined information as a variable for a prompt template including the variable; The predetermined processing setting means As a step constituting the predetermined processing, a first step of obtaining information at a second location of the object in the predetermined browser as the variable; a second step of constructing the prompt by inputting the variables acquired in the first step into the prompt template and sending the prompt to the interactive system; a third step of obtaining responses from the interactive system to the prompts and presenting the responses in the predetermined browser; Set the predetermined processing execution means executes the predetermined processing by sequentially executing the first step, the second step, and the third step, respectively. The information processing system according to claim 1 .
3. The UI functioning means includes: After the predetermined process is executed, a separate UI is activated for further use of the interactive system.
3. The information processing system according to claim 1 or 2.
4. An information processing method executed by an information processing system, a UI setting step of setting a predetermined UI (User Interface) for executing a predetermined process related to a part of a predetermined website on which another system is executed using an interactive system; an other system execution step of displaying the target of the predetermined web site on a predetermined browser and executing the other system; a UI functioning step of arranging the predetermined UI on the target in the predetermined browser and making the predetermined UI function; Including, The UI setting step includes: a registration step of registering the target of the predetermined website; a control setting step of setting a control to be placed at a first position of the target in the predetermined browser; a predetermined process setting step for setting the predetermined process to be executed in response to the operation of the operator; Including, The UI functionalization step includes: a control placement step of placing the control at the first position of the target in the predetermined browser; an operation receiving step of receiving an operation on the operator in the predetermined browser; a predetermined processing execution step of executing the predetermined processing in response to the acceptance of the operation on the operator; Including, Information processing methods.
5. On the computer, a UI setting step of setting a predetermined UI (User Interface) for executing a predetermined process related to a part of a predetermined website on which another system is executed using an interactive system; an other system execution step of displaying the target of the predetermined web site on a predetermined browser and executing the other system; a UI functioning step of arranging the predetermined UI on the target in the predetermined browser and making the predetermined UI function; Execute a control process including As the UI setting step, a registration step of registering the target of the predetermined website; a control setting step of setting a control to be placed at a first position of the target in the predetermined browser; a predetermined process setting step for setting the predetermined process to be executed in response to the operation of the operator; Execute a control process including As the UI functionalization step, a control placement step of placing the control at the first position of the target in the predetermined browser; an operation receiving step of receiving an operation on the operator in the predetermined browser; a predetermined processing execution step of executing the predetermined processing in response to the acceptance of the operation on the operator; Execute a control process including program.
Citation Information
Patent Citations
Operation assist system, operation assist method, and operation assist program
JP2017072872A
Information processing device, program and control method
JP7081099B2
Display control device, display control method, and display control program
WO2022102000A1
User interface extension system, user interface extension method, and user interface extension program
WO2022113315A1
Display control device, display control method, and display control program
WO2023238261A1