Information processing system, information processing method, and information processing program

Abstract

This invention provides an information processing system, information processing method, information processing program, and AI agent that can efficiently collect information used by an AI agent. [Solution] In the information processing system 10, the AI ​​agent includes an information generation means that generates characteristic information representing the purpose and function of an information source based on information collected from the information source, and stores the characteristic information in a storage means in association with the information source; an activation trigger analysis means that analyzes a given activation trigger; and a processing execution means that executes a specific process for the activation trigger based on the analysis results of the activation trigger. When the processing execution means executes the specific process, it determines whether at least a part of the analysis results of the activation trigger is related to the characteristic information, and if the two are related, it selects the information source based on the characteristic information and executes the specific process using the information obtained from the selected information source.

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing method, an information processing program using an AI agent, and an AI agent.

Background Art

[0002] Conventionally, by constructing an agent system, the server-side agent can detect information that the user is likely to want next in the first communication with the user-side agent, without the agents communicating with each other, and can cache information that will be requested in advance, enabling a content providing system that can instantaneously display the required information one after another has been proposed (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, although the above Patent Document 1 discloses a technical idea of detecting information that the user is likely to want next, there is no specific description about the implementation method, and in the system described in the same document, it is difficult for an agent to efficiently collect information.

[0005] In view of such circumstances, the present invention provides an information processing system, an information processing method, an information processing program that can efficiently collect information used by an AI agent and can increase the execution speed of processing by the AI agent. And, information processing progr Mu to be provided.

Means for Solving the Problems

[0006] The information processing system according to the present invention is an information processing system comprising an AI agent and a plurality of information sources, wherein the AI ​​agent, based on the information collected from the information sources, processes the objectives of the information sources. or Information generation means for generating characteristic information representing a function and storing the characteristic information in a storage means in association with the information source; activation trigger analysis means for analyzing a given activation trigger; and processing execution means for executing a specific process for the activation trigger based on the analysis results of the activation trigger. , an information gathering means for collecting evaluation information including evaluations, reviews, and comments regarding the aforementioned information source, The processing execution means, when executing the specific processing, determines whether at least a part of the analysis result of the trigger is related to the characteristic information, and if they are related, selects the information source based on the characteristic information and executes the specific processing using the information obtained from the selected information source. death , When the processing execution means selects the information source based on the characteristic information, it selects the information source taking into consideration the evaluation information. This is an information processing system characterized by the following:

[0007] Furthermore, the information processing method according to the present invention is an information processing method that is performed using an AI agent and a plurality of information sources, wherein the AI ​​agent performs the purpose of the information sources based on the information collected from the information sources. or The process includes an information generation step of generating characteristic information representing a function and storing the characteristic information in a storage means in association with the information source; an activation trigger analysis step of analyzing a given activation trigger; and a processing execution step of performing a specific process for the activation trigger based on the analysis results of the activation trigger. The process involves an information gathering step of collecting evaluation information, including evaluations, reviews, and comments, for the aforementioned information source, and The processing execution step, when executing the specific processing, determines whether at least a portion of the analysis results of the trigger is related to the characteristic information, and if they are related, selects the information source based on the characteristic information, and executes the specific processing using the information obtained from the selected information source. death , The processing execution step, when selecting the information source based on the characteristic information, selects the information source taking into consideration the evaluation information. This is an information processing method characterized by the following features.

[0008] Furthermore, the information processing program according to the present invention is A IA program for an information processing system comprising an agent and multiple information sources, wherein the AI ​​agent, which is a computer, processes the information collected from the information sources for the purpose of the information sources. or Information generation means for generating characteristic information representing a function and storing the characteristic information in a storage means in association with the information source; activation trigger analysis means for analyzing a given activation trigger; and processing execution means for executing a specific process for the activation trigger based on the analysis results of the activation trigger. It functions as an information gathering means for collecting evaluation information, including evaluations, word-of-mouth, and comments, regarding the aforementioned information source. When executing the specific process, the processing execution means determines whether at least a part of the analysis result of the trigger is related to the characteristic information, and if they are related, selects the information source based on the characteristic information and executes the specific process using the information obtained from the selected information source. death , When the processing execution means selects the information source based on the characteristic information, it selects the information source taking into consideration the evaluation information. This is an information processing program characterized by the following: [Effects of the Invention]

[0010] Information processing system, information processing method, according to the present invention And, Information processing program Mu Therefore, it is possible to efficiently collect information used by AI agents and achieve the excellent effect of increasing the execution speed of processing by AI agents. [Brief explanation of the drawing]

[0011] [Figure 1] This is a schematic diagram showing an overview of the information processing system 10 according to this embodiment. [Figure 2] This is a system configuration diagram showing an example of the configuration of the information processing system 10 according to this embodiment. [Figure 3] This figure shows a specific example of processing performed by the information processing system 10 according to this embodiment. [Modes for carrying out the invention]

[0012] The following describes an information processing system 10 according to an embodiment of the present invention with reference to the drawings.

[0013] <Overview of the System> First, the overview of the information processing system 10 according to this embodiment will be described using FIG. 1. FIG. 1 is a schematic diagram showing the overview of the information processing system 10 according to this embodiment.

[0014] The information processing system 10 is an information processing system configured to include an AI agent 12 and a plurality of information sources 14 (information sources 14a, 14b,...). The AI agent 12 generates characteristic information representing the purpose and function of the information source 14 based on the information collected from the information source 14, associates the characteristic information with the information source 14, and stores it in a storage means (storage device 26). The information generation means 12a, a trigger analysis means 12b that analyzes a given trigger, and a processing execution means 12c that executes a specific process based on the analysis result of the trigger. When executing a specific process, the processing execution means 12c determines whether at least a part of the analysis result of the trigger is related to the characteristic information. When the two are related, the information source 14 is selected based on the characteristic information, and the specific process is executed using the information obtained from the selected information source 14. It is an information processing system characterized by this.

[0015] According to the information processing system according to this embodiment, the information used by the AI agent can be efficiently collected, and the execution speed of the processing by the AI agent can be increased.

[0016] Here, the "AI agent" is a system that operates as an agent of a human, has the ability to learn and judge itself, and is a system that integrates various AI technologies for complex problem solving.

[0017] The AI agent executes a process based on a trigger given from the outside (for example, a question (prompt) by a user, a signal input from a sensor), or executes a process based on a trigger given from the inside (for example, activation by an internal scheduler, occurrence of an abnormality).

[0018] For example, when a question (prompt) is given as an external activation trigger (event), tasks such as searching for an answer to the question or generating an answer are executed, and the answer to the question is output. Also, for example, when a task (prompt) is given as an external activation trigger (event), tasks such as searching for a solution to the task or generating a solution are executed, and the solution to the task is output.

[0019] Also, a "prompt" refers to an instruction or question given by a user to the system, and includes, for example, an AI prompt given to a generative AI, a command prompt for giving an instruction by a command sentence (command), etc.

[0020] Various processes executed by an AI agent can also be executed by an "agent-based AI".

[0021] Here, an "agent-based AI" refers to a system in which multiple AI agents operate in cooperation. An agent-based AI is for solving complex problems that cannot be solved by a single AI agent. Each AI agent plays a specialized role and exchanges information with each other to output an answer to a question or a solution to a task.

[0022] An "information source" refers to the source or origin of information. Examples of "information sources" include websites, application software (hereinafter sometimes referred to as "apps"), SaaS (Software as a Service), databases, data warehouses, storage services, search engines, etc.

[0023] "Characteristic information" refers to information that describes the purpose and function of an information source. Examples of "characteristic information" include information provision (news, stocks, company official websites and apps, blogs that share hobbies or expertise, etc.), buying and selling of goods (e-commerce, hotel and ticket reservations, etc.), interaction and dialogue (SNS, bulletin boards, chat, video conferencing, etc.), service provision (storage, translation, games, etc.), declaration advertising (event announcements, product promotions, etc.), provision of specialized information and services (medical, education, real estate, etc.), development support (cloud IDE, code management, etc.), sales support (advertising management support, SNS management support, etc.), and business support (accounting, human resources, attendance, customer management, etc.).

[0024] "Characteristic information" may be further subdivided information. For example, "Information provision" could be a major category, and the content of "Information provision" (e.g., news, stocks, hobbies, specialized knowledge, etc.) could be subdivided into smaller categories, or the target audience of "Information provision" (e.g., men, women, young people, middle-aged and elderly people, Japanese people, foreigners, etc.) could be subdivided into smaller categories.

[0025] Furthermore, the system includes information gathering means for collecting evaluation information, including ratings, reviews, and comments, for information source 14, and the processing execution means 12c may select information source 14 considering evaluation information when selecting information source 14 based on characteristic information.

[0026] With this configuration, it is possible to select the appropriate information source from among multiple information sources based on evaluation information, thereby improving the accuracy of processing by the AI ​​agent.

[0027] Furthermore, the information sources may include websites, and the information generation means 12a may generate characteristic information of a website based on tags obtained from the website.

[0028] This configuration improves the accuracy of the characteristic information of the source websites, and by selecting information sources that are highly relevant to the analysis results of the trigger, the accuracy of processing by the AI ​​agent can be improved.

[0029] Here, "tags" include HTML tags, conversion tags, and tool control tags. HTML tags are tags made up of HTML (Hyper Text Markup Language), the programming language that makes up websites. Conversion tags are tags used to count actions that lead to purchases or inquiries. By using them in web advertising such as listing ads, it is possible to accurately grasp the number of conversions. Tool control tags are tags that are embedded in HTML and used in conjunction with tools. When a user accesses a website with tool control tags embedded, it is possible to check user information, traffic sources, and where users left the site.

[0030] Furthermore, the information generation means 12a may generate characteristic information of the website based on the information collected by the website.

[0031] This configuration improves the accuracy of the characteristic information of the source websites, and by selecting information sources that are highly relevant to the analysis results of the trigger, the accuracy of processing by the AI ​​agent can be improved.

[0032] Here, "information collected by a website" includes, for example, personal information, browser and OS type and version, location information, browsing history, IP address, network type, browsing history and ad click history, purchase history and point usage status, etc.

[0033] Furthermore, the information source may include application software, and the information generation means 12a may generate characteristic information of the application software based on the information collected by the application software.

[0034] With this configuration, the accuracy of the characteristic information of the application software that serves as the information source can be improved, and by selecting information sources that have a high correlation with the analysis results of the trigger for activation, the accuracy of processing by the AI ​​agent can be improved.

[0035] Here, "information collected by application software" includes, for example, personal information, OS type and version, location information, movement history, IP address, network type, in-app operation history, browsing history and ad click history, purchase history and point usage status, etc.

[0036] <Example of system configuration> Next, an example of the configuration of the information processing system 10 according to this embodiment will be described using Figure 2. Figure 2 is a system configuration diagram showing an example of the configuration of the information processing system 10 according to this embodiment.

[0037] The information processing system 10 can be configured, for example, to include a system terminal 12 that controls the entire system, and a plurality of information sources 14 and external terminals 16 that are connected to the system terminal 12 via a network NW so that they can communicate with each other.

[0038] System terminal 12 is a terminal that constitutes the AI ​​agent and controls the entire information processing system 10, and is composed of conventionally known servers, personal computers, etc. In this example, system terminal 12 is composed of one server, but it may be composed of multiple servers, personal computers, etc. The hardware configuration of system terminal 12 and the programs that system terminal 12 executes will be described later.

[0039] Multiple information sources 14 are comprised of information sources A14a, information sources B14b, and so on.

[0040] Information source A14a is a web server that provides a website. The content of a website is not particularly limited, but examples include: sites intended for information provision (news, stocks, company official websites, blogs that share hobbies or expertise, etc.), sites for buying and selling goods (e-commerce, hotel and ticket reservations, etc.), sites for interaction and communication (SNS, bulletin boards, chat, video conferencing, etc.), sites intended for service provision (storage, translation, games, etc.), sites for declaration advertising (event announcements, product promotions, etc.), sites intended for providing specialized information or services (medical, education, real estate, etc.), sites intended for development support (cloud IDE, code management, etc.), sites intended for sales support (advertising operation support, SNS operation support, etc.), and sites intended for business support (accounting, human resources, attendance, customer management, etc.).

[0041] Information source 14b is a server that provides the application, and can be configured as, for example, SaaS (Software as a Service). The content of the application is not particularly limited, but examples include: applications for providing information (news, stocks, official company apps, blogs for sharing hobbies or expertise, etc.), applications for buying and selling goods (e-commerce, hotel and ticket reservations, etc.), applications for interaction and communication (SNS, bulletin boards, chat, video conferencing, etc.), applications for providing services (storage, translation, games, etc.), applications for declarative advertising (event announcements, product promotions, etc.), applications for providing specialized information or services (medical, education, real estate, etc.), applications for development support (cloud IDE, code management, etc.), sales support (advertising operation support, SNS operation support, etc.), and applications for business support (accounting, human resources, attendance, customer management, etc.).

[0042] Furthermore, one, several, or all of the multiple information sources 14 may be processing devices interconnected with the system terminal 12 via a local network (e.g., LAN or P2P). Therefore, for example, a website may be an intranet, and an application may be an application stored in the storage means of the system terminal 12 (e.g., storage device 26) or an application installed on a mobile terminal connected to the network NW (e.g., a tablet or smartphone).

[0043] External terminals 16 are terminals used by users of the information processing system 10 (individuals or specific groups of people (teams, departments, companies, etc.)), and consist of personal computers, tablets, smartphones, etc. The type of external terminal 16 is not particularly limited, but examples include smartphones, personal computers, and tablets used by individuals, and smartphones, personal computers, and tablets used by employees of companies, etc.

[0044] The network NW is a line that allows the system terminal 12, the information source 14, and the external terminal 16 to communicate with each other, and is typically composed of a WAN (Wide Area Network), also known as the Internet. The network NW may be wired or wireless, a LAN (Local Area Network), a dedicated line such as a VPN (Virtual Private Network), or a combination of these lines.

[0045] <System Terminal / Hardware Configuration Example> Next, we will describe an example of the hardware configuration of system terminal 12.

[0046] As shown in Figure 2, the system terminal 12 is configured to include, for example, a CPU 21, and a ROM 22, RAM 23, external storage drive 25, storage device 26, input device 27, display device 28, communication unit 29, etc., all connected to the CPU 21 via a bus.

[0047] The CPU 21 is a control means that controls the entire system terminal 12, and performs processes such as executing application programs and operating systems (OS) stored in ROM 22 and storage devices 26, and storing data and files necessary for program execution in RAM 23 and storage devices 26.

[0048] ROM22 is a storage means for storing basic I / O programs and various data, and is composed of, for example, PROM, flash memory, etc. RAM23 is a storage means for temporarily storing data, and is composed of, for example, SDRAM, DRAM, etc. External storage drive25 is a control means that can read and write data to recording media 24 such as magnetic tape, DVD, etc., and is composed of, for example, magnetic tape storage, DVD drive, etc.

[0049] The storage device 26 is a storage means for storing application programs, the OS, control programs, related programs, various information, etc., and is composed of, for example, a hard disk drive (HDD), a solid-state drive (SDD), etc. The input device 27 is for inputting commands (instructions), etc., to the system terminal 12, and is composed of, for example, a keyboard, a pointing device (mouse, etc.), a touch panel, etc.

[0050] The display device 28 displays commands input by the input device 27, the response output of the system terminal 12 to those commands, and various other displays, and is composed of, for example, a liquid crystal display, plasma display, organic EL, etc. The communication unit 29 is a control means that controls communication with the information source 14 and external terminals 16, etc. via the network NW, and is composed of, for example, a communication card, etc.

[0051] <System Terminal / Function> Next, we will explain the functions of the system terminal 12.

[0052] The storage device 26 of the system terminal 12 stores a program (information processing program) that causes the system terminal 12 to function as an information generation means 12a, a startup trigger analysis means 12b, and a processing execution means 12c.

[0053] <System terminal / function / information generation means> Next, the information generation means 12a will be described.

[0054] The information generation means 12a generates characteristic information representing the purpose and function of the information source 14 based on information collected from the information source 14, and stores the characteristic information in a storage means (storage device 26) in association with the information source 14. In this example, it consists of a program stored in the storage device 26 of the system terminal 12, and the storage device 26, etc.

[0055] The information generation means 12a crawls through a plurality of information sources 14 (information source A14a, information source B14b, ...) at predetermined intervals, generates characteristic information representing the purpose and function of the information source 14 based on the information obtained from the information source 14, and stores the characteristic information in the storage device 26 in association with the information source 14.

[0056] As mentioned above, an "information source" refers to the source or origin of information. Examples of information sources include websites, application software (sometimes referred to as "apps"), SaaS (Software as a Service), databases, data warehouses, storage services, and search engines.

[0057] "Characteristic information" refers to information that describes the purpose and function of an information source. Examples of "characteristic information" include information provision (news, stocks, company official websites and apps, blogs that share hobbies or expertise, etc.), buying and selling of goods (e-commerce, hotel and ticket reservations, etc.), interaction and dialogue (SNS, bulletin boards, chat, video conferencing, etc.), service provision (storage, translation, games, etc.), declaration advertising (event announcements, product promotions, etc.), provision of specialized information and services (medical, education, real estate, etc.), development support (cloud IDE, code management, etc.), sales support (advertising management support, SNS management support, etc.), and business support (accounting, human resources, attendance, customer management, etc.).

[0058] "Characteristic information" may be further subdivided information. For example, "Information provision" could be a major category, and the content of "Information provision" (e.g., news, stocks, hobbies, specialized knowledge, etc.) could be subdivided into smaller categories, or the target audience of "Information provision" (e.g., men, women, young people, middle-aged and elderly people, Japanese people, foreigners, etc.) could be subdivided into smaller categories.

[0059] For example, the information generation means 12a crawls information source A14a, which consists of a web server, at predetermined intervals. If the website provided by information source A14a is an e-commerce site, it generates "buying and selling of goods (e-commerce site)" as one of the characteristic information of information source A14a, as shown in Figure 3(a), and stores this characteristic information (buying and selling of goods (e-commerce site)) in the storage device 26, associating it with an identifier that identifies information source A14a (for example, the ID of information source A14a).

[0060] If the website provided by information source A14a is a news distribution site, the information generation means 12a generates "information provision (news)" as one of the characteristic information of information source A14a, as shown in Figure 3(b), and stores this characteristic information (information provision (news)) in the storage device 26, associating it with an identifier that identifies information source A14a (for example, the ID of information source A14a).

[0061] If the website provided by information source A14a is a promotional site for a certain product (for example, cosmetics), then the information generation means 12a generates "advertisement (cosmetics)" as one of the characteristic information of information source A14a, as shown in Figure 3(c), and stores this characteristic information (advertisement) in the storage device 26, associating it with an identifier that identifies information source A14a (for example, the ID of information source A14a).

[0062] Furthermore, the information generation means 12a generates characteristic information of the website based on tags obtained from the website and information collected by the website.

[0063] Here, "tags" include HTML tags, conversion tags, and tool control tags. "Information collected by the website" includes, for example, personal information, browser and OS type and version, location information, visit history, IP address, network type, page and ad click history, purchase history, and point usage status.

[0064] For example, if the information generation means 12a obtains personal information (age, gender) from tags obtained from a website provided by information source A14a, which consists of a web server, or from information collected by the website, it stores the characteristic information (personal information (age, gender)) in the storage device 26, as shown in Figures 3(a) to (c), in association with an identifier that identifies information source A14a (for example, the ID of information source A14a).

[0065] Furthermore, the information generation means 12a crawls the information source B14b, which consists of SaaS, at predetermined intervals. If the application provided by information source B14b is an accounting and bookkeeping service, it generates "Business support (accounting and bookkeeping)" as one of the characteristic information of information source B14b, as shown in Figure 3(d), and stores this characteristic information (business support (accounting and bookkeeping)) in the storage device 26, associating it with an identifier that identifies information source B14b (for example, the ID of information source B14b).

[0066] Furthermore, if the application provided by information source B14b is a bulletin board, the information generation means 12a generates "interaction dialogue (bulletin board)" as one of the characteristic information of information source B14b, as shown in Figure 3(e), and stores this characteristic information (interaction dialogue (bulletin board)) in the storage device 26, associating it with an identifier that identifies information source B14b (for example, the ID of information source B14b).

[0067] Furthermore, if the app provided by information source B14b is a blog that publishes information about home appliances, then, as shown in Figure 3(f), the information generation means 12a generates "Information provision (home appliances)" as one of the characteristic information of information source B14b, and stores this characteristic information (Information provision (home appliances)) in the storage device 26, associating it with an identifier that identifies information source B14b (for example, the ID of information source B14b).

[0068] Furthermore, the information generation means 12a generates characteristic information of the application based on the information collected by the application.

[0069] Here, "information collected by application software" includes, for example, personal information, OS type and version, location information, movement history, IP address, network type, in-app operation history, browsing history and ad click history, purchase history and point usage status, etc.

[0070] For example, if the information generation means 12a obtains browsing history from information collected by an application provided by information source B14b, which is a SaaS, it stores the characteristic information (browsing history) in the storage device 26, as shown in Figures 3(d) to (f), associating it with an identifier that identifies information source B14b (for example, the ID of information source B14b).

[0071] <System terminal / function / startup trigger analysis method> Next, the trigger analysis means 12b will be described.

[0072] The startup trigger analysis means 12b is a means for analyzing a given startup trigger, and in this example, it consists of a program stored in the storage device 26 of the system terminal 12, and the storage device 26, etc.

[0073] As mentioned above, "activation triggers" include, for example, activation triggers provided from outside the AI ​​agent 12 (e.g., a question (prompt) from the user, a signal input from a sensor) and activation triggers provided from within the AI ​​agent 12 (e.g., activation by the internal scheduler, occurrence of an anomaly).

[0074] When a prompt is given by a user of the information processing system 10 (for example, an individual or a specific group of multiple people (team, department, company, etc.)) using an external terminal 16 as a trigger for activation, the activation trigger analysis means 12b acquires the prompt entered by the user, associates the acquired prompt with the user's ID, and stores it in the storage device 26.

[0075] Here, "prompt" refers to information (data) of commands or questions entered by a user of the information processing system 10 using an input means (keyboard, pointing device (mouse, etc.), touch panel, microphone, etc.) of an external terminal 16. The data format of the "prompt" is not particularly limited and may be any of the following: text data, audio data, still image data, video data, file, etc.

[0076] Examples of "prompts" include text data such as commands or questions to the information processing system 10, audio data, files uploaded by users, still image data, or video data.

[0077] Next, the startup trigger analysis means 12b performs a prompt analysis stored in the memory device 26 and generates the analysis result of the prompt.

[0078] Here, the prompt analysis is performed on, for example, the content of the prompt and the user's requests that can be inferred from the content of the prompt.

[0079] For example, if the content of a prompt is to be analyzed, the activation trigger analysis means 12b uses the text data, audio data, image data, etc. contained in the prompt to identify the content of the prompt (e.g., sentences, phrases, words, keywords, feature points, etc.), and stores the identified content in the storage device 26 as the analysis result of the prompt, associating it with the user's ID.

[0080] Furthermore, if, for example, the user's request inferred from the content of the prompt is to be analyzed, the startup trigger analysis means 12b uses the text data, audio data, image data, etc., contained in the prompt to identify the user's request inferred from the content of the prompt (for example, requesting a specific analysis, requesting a translation, requesting program generation, etc.), and stores the identified user's request in the storage device 26 as the result of the prompt analysis, associating it with the user's ID.

[0081] <System terminal / Function / Processing execution means> Next, the processing execution means 12c will be described.

[0082] The processing execution means 12c is a means that performs a specific process for a startup trigger based on the analysis results of the startup trigger, determines whether at least a part of the analysis results of the startup trigger is related to characteristic information, selects an information source 14 based on the characteristic information if the two are related, and performs the specific process using the information obtained from the selected information source 14. In this example, it is composed of a program stored in the storage device 26 of the system terminal 12, or the storage device 26, etc.

[0083] As a trigger for activation, when a user of the information processing system 10 provides a question (prompt), the processing execution means 12c searches for an answer to the question, generates an answer, and outputs an answer to the question.

[0084] Furthermore, when the processing execution means 12c searches for an answer to a question, it determines whether at least a part of the analysis results of the trigger is related to characteristic information, and if the two are related, it selects an information source 14 based on the characteristic information and outputs an answer to the question using the information obtained from the selected information source 14.

[0085] For example, consider a case where the prompt is "What cosmetics do you recommend for people in their 20s?", and as a result of analyzing the trigger (prompt), the information "Target age is women in their 20s, target product is cosmetics, popular cosmetics among all cosmetics" is stored in the memory device 26, and the characteristic information of information source A14a is "sale of goods, personal information (age, gender)", and the personal information (age, gender) in the characteristic information includes information about women in their 20s.

[0086] In this case, the processing execution means 12c determines that "the target age is women in their 20s," which is part of the analysis result of the activation trigger (prompt), matches (is related to) "personal information (women in their 20s)," which is characteristic information of information source A14a, and selects information source A14a (in this example, an e-commerce site) based on the characteristic information.

[0087] Then, the system searches for answers to the question using the selected information source A14a (e-commerce site), or generates answers using information obtained from information source A14a (for example, information about cosmetics), and outputs answers to the question (for example, text data such as "The best-selling cosmetic product is X").

[0088] Furthermore, consider a case where, for example, the prompt is given with the question, "What cosmetics do you recommend for people in their 20s?", and as a result of analyzing the trigger (prompt), the information "Target age is women in their 20s, target product is cosmetics, popular cosmetics among all cosmetics" is stored in the memory device 26, and the characteristic information of information source A14a is stored in the memory device 26 with the information "Declarative advertisement (cosmetics), personal information (age, gender)".

[0089] In this case, the processing execution means 12c determines that "the target product is cosmetics," which is part of the analysis result of the activation trigger (prompt), matches "advertising (cosmetics)," which is characteristic information of information source A14a, and selects information source A14a (in this example, a cosmetics promotion site) based on the characteristic information.

[0090] Then, using the selected information source A14a (a cosmetics promotion site), the system searches for an answer to the question, or generates an answer using information obtained from information source A14a (for example, information about the cosmetics being promoted), and outputs an answer to the question (for example, text data such as "How about cosmetic Y?").

[0091] When a user of the information processing system 10 provides a task (prompt), the processing execution means 12c searches for or generates a solution to the task and outputs the solution to the task.

[0092] Furthermore, when the processing execution means 12c searches for a solution to the problem, it determines whether at least a part of the analysis results of the triggering event is related to characteristic information, and if the two are related, it selects an information source 14 based on the characteristic information and outputs a solution to the problem using the information obtained from the selected information source 14.

[0093] For example, consider a case where the prompt is "Create a ranking of the top 100 home appliances that are likely to become popular in Japan," and as a result of analyzing the trigger (prompt), the information "Target region is Japan, survey target is home appliances, ranking is from 1st to 100th place" is stored in the memory device 26, and the characteristic information of information source B14b is "Information provided (home appliances), browsing history" which is also stored in the memory device 26.

[0094] In this case, the processing execution means 12c determines that "the subject of the investigation is home appliances," which is part of the analysis result of the activation trigger (prompt), matches "information provision (home appliances)," which is characteristic information of information source B14b, and selects information source B14b (in this example, a blog that publishes information about home appliances) based on the characteristic information.

[0095] Then, the system searches for answers to the question using the selected information source B14b (a blog that provides information on home appliances), or generates answers using information obtained from information source B14b (for example, articles that evaluate or introduce home appliances, or the viewing history of readers who have viewed those articles), and outputs answers to the question (for example, image data illustrating home appliance rankings).

[0096] Furthermore, consider the case where the prompt is given, "Create a ranking of the top 100 home appliances that are likely to become popular in Japan," and as a result of analyzing the trigger (prompt), the information "Target region is Japan, survey target is home appliances, ranking is from 1st to 100th place" is stored in the memory device 26, and the characteristic information of information source B14b is "Interaction (bulletin board), browsing history," and the interaction (bulletin board) characteristic information includes threads related to home appliances.

[0097] In this case, the processing execution means 12c determines that "the subject of the investigation is home appliances," which is part of the analysis result of the activation trigger (prompt), matches the characteristic information of information source B14b, "a thread about home appliances in a chat (bulletin board)," and selects information source B14b (the bulletin board in this example) based on the characteristic information.

[0098] Then, the system searches for answers to the question using the selected information source B14b (bulletin board), or generates answers using information obtained from information source B14b (for example, reviews and comments about home appliances), and outputs answers to the question (for example, information on the URL of a website listing the top 100 home appliances).

[0099] This example demonstrates that information used by AI agents can be collected efficiently, thereby increasing the execution speed of processing performed by AI agents.

[0100] Furthermore, the system includes information gathering means for collecting evaluation information, including ratings, reviews, and comments, for information source 14, and the processing execution means 12c may select information source 14 considering evaluation information when selecting information source 14 based on characteristic information.

[0101] With this configuration, it is possible to select the appropriate information source from among multiple information sources based on evaluation information, thereby improving the accuracy of processing by the AI ​​agent.

[0102] <Information Processing Systems / Summary> As described above, the information processing system according to this embodiment (for example, the information processing system 10 shown in Figures 1 and 2) is an information processing system comprising an AI agent (for example, the AI ​​agent 12 shown in Figure 1, the system terminal 12 shown in Figure 2) and a plurality of information sources (for example, a plurality of information sources 14 shown in Figure 1), wherein the AI ​​agent generates characteristic information representing the purpose and function of the information source based on the information collected from the information source, and stores the characteristic information in a storage means (for example, the storage device 26 shown in Figures 1 to 3) associated with the information source. a) an information processing system comprising: an activation trigger analysis means (for example, the activation trigger analysis means 12b shown in Figures 1 and 2) for analyzing a given activation trigger; and a processing execution means (for example, the processing execution means 12c shown in Figures 1 to 3) for executing a specific process for the activation trigger based on the analysis results of the activation trigger, wherein the processing execution means, when executing the specific process, determines whether at least a part of the analysis results of the activation trigger is related to the characteristic information, and if the two are related, selects the information source based on the characteristic information and executes the specific process using the information obtained from the selected information source.

[0103] Furthermore, the information processing method according to this embodiment (for example, the method executed by the information processing system 10 shown in Figures 1 and 2) is an information processing method executed using an AI agent (for example, the AI ​​agent 12 shown in Figure 1, the system terminal 12 shown in Figure 2) and a plurality of information sources (for example, a plurality of information sources 14 shown in Figure 1), comprising an information generation step (for example, a process executed by the information generation means 12a shown in Figures 1 to 3) which generates characteristic information representing the purpose and function of the information source based on information collected from the information source, associates the characteristic information with the information source and stores it in a storage means (for example, a storage device 26 shown in Figures 1 to 3), and a given startup contract The information processing method comprises a startup trigger analysis step for analyzing the machine (for example, a process performed by the startup trigger analysis means 12b shown in Figures 1 and 2), and a processing execution step for performing a specific process on the startup trigger based on the analysis results of the startup trigger (for example, a process performed by the processing execution means 12c shown in Figures 1 to 3), wherein the processing execution step, when performing the specific process, determines whether at least a part of the analysis results of the startup trigger is related to the characteristic information, and if the two are related, selects the information source based on the characteristic information, and performs the specific process using the information obtained from the selected information source.

[0104] Furthermore, the program for the information processing system according to this embodiment (for example, the information processing system 10 shown in Figures 1 and 2) is a program for an information processing system configured to have an AI agent (for example, the AI ​​agent 12 shown in Figure 1, the system terminal 12 shown in Figure 2) and a plurality of information sources (for example, a plurality of information sources 14 shown in Figure 1), wherein the AI ​​agent, which is a computer, generates characteristic information representing the purpose and function of the information source based on information collected from the information source, and stores the characteristic information in a storage means (for example, the storage device 26 shown in Figures 1 to 3) associated with the information source. The information processing program is characterized by comprising: a means 12a) for creating an event trigger; a trigger trigger analysis means (for example, the trigger trigger analysis means 12b shown in Figures 1 and 2) for analyzing a given trigger trigger; and a processing execution means (for example, the processing execution means 12c shown in Figures 1 to 3) for executing a specific process for the trigger trigger based on the analysis results of the trigger trigger, wherein when the processing execution means executes the specific process, it determines whether at least a part of the analysis results of the trigger trigger is related to the characteristic information, and if the two are related, it selects the information source based on the characteristic information and executes the specific process using the information obtained from the selected information source.

[0105] Furthermore, the AI ​​agent according to this embodiment (for example, the AI ​​agent 12 shown in Figure 1, the system terminal 12 shown in Figure 2) is an AI agent that operates as a substitute for a human and has the ability to learn and make decisions on its own. The AI ​​agent, which is a computer, generates characteristic information representing the purpose and function of an information source based on information collected from the information source (for example, a plurality of information sources 14 shown in Figure 1), and stores the characteristic information in a storage means (for example, a storage device 26 shown in Figures 1 to 3) associated with the information source. The AI ​​agent also includes an information generation means (for example, the information generation means 12a shown in Figures 1 to 3) that analyzes a given activation trigger. b) The AI ​​agent is configured to function as a processing execution means (for example, processing execution means 12c shown in Figures 1 to 3) that performs a specific process on the trigger based on the analysis results of the trigger, wherein when the processing execution means performs the specific process, it determines whether at least a part of the analysis results of the trigger is related to the characteristic information, and if they are related, it selects the information source based on the characteristic information, and uses the information obtained from the selected information source to perform the specific process, and the analysis results of the trigger and the characteristic information are repeatedly provided as training data, and the AI ​​agent is configured to acquire the information source suitable for the specific process by machine learning.

[0106] According to the information processing system, information processing method, information processing program, and AI agent of this embodiment, information used by the AI ​​agent can be efficiently collected, and the execution speed of processing by the AI ​​agent can be increased.

[0107] Furthermore, the system may include an information gathering means (or information gathering step) for collecting evaluation information, including ratings, reviews, and comments, and the processing execution means (or information gathering step) may select the information source considering the evaluation information when selecting the information source based on the characteristic information.

[0108] With this configuration, it is possible to select the appropriate information source from among multiple information sources based on evaluation information, thereby improving the accuracy of processing by the AI ​​agent.

[0109] Furthermore, the information source may include a website, and the information generation means (or the information generation step) may generate the characteristic information of the website based on tags (e.g., HTML tags, conversion tags, tool control tags) obtained from the website.

[0110] This configuration improves the accuracy of the characteristic information of the source websites, and by selecting information sources that are highly relevant to the analysis results of the trigger, the accuracy of processing by the AI ​​agent can be improved.

[0111] Furthermore, the information generation means may generate characteristic information of the website based on information collected by the website (for example, personal information, browser and OS type and version, location information, visit history, IP address, network type, browsing history and advertisement click history, purchase history and point usage status, etc.).

[0112] This configuration improves the accuracy of the characteristic information of the source websites, and by selecting information sources that are highly relevant to the analysis results of the trigger, the accuracy of processing by the AI ​​agent can be improved.

[0113] Furthermore, the information source may include application software, and the information generation means (or the information generation step) may generate the characteristic information of the application software based on information collected by the application software (for example, personal information, OS type and version, location information, movement history, IP address, network type, in-app operation history, browsing history of pages and advertisements, purchase history and point usage status, etc.).

[0114] With this configuration, the accuracy of the characteristic information of the application software that serves as the information source can be improved, and by selecting information sources that have a high correlation with the analysis results of the trigger for activation, the accuracy of processing by the AI ​​agent can be improved.

[0115] It should be noted that the information processing system, information processing method, information processing program, and AI agent according to the present invention are not limited to the embodiments described above, and various modifications can be made without departing from the spirit of the present invention.

[0116] Therefore, for example, in the above embodiment, the "characteristic information" according to the present invention may be any information that represents the purpose or function of the information source, and is not limited to the information exemplified. Furthermore, the "activation trigger" according to the present invention is not limited to a prompt, but may be an activation trigger provided from an external source (e.g., a signal input from a sensor) or an activation trigger provided from an internal source (e.g., activation by an internal scheduler, occurrence of an anomaly).

[0117] Furthermore, the "information source" according to the present invention is not limited to websites or applications, but may also be a database, data warehouse, storage service, search engine, etc. [Industrial applicability]

[0118] The information processing system, information processing method, information processing program, and AI agent according to the present invention can be widely applied in manufacturing, service, retail, and other industries. [Explanation of symbols]

[0119] 10. Information Processing Systems 12 System Terminals 12a Information generation means 12b Activation trigger analysis means 12c Processing execution means 14 Sources of information 16 External terminals 21 CPU 22 ROM 23 RAM 24 Recording media 25 External storage drives 26 Storage device 27 Input devices 28 Display device 29 Communications Department

Claims

1. An information processing system comprising an AI agent and multiple information sources, The aforementioned AI agent, Information generation means that generates characteristic information representing the purpose or function of the information source based on information collected from the information source, and stores the characteristic information in a storage means in association with the information source; A trigger analysis means for analyzing a given trigger, A processing execution means that executes a specific process for the trigger based on the analysis results of the trigger, The system includes an information gathering means for collecting evaluation information, including evaluations, reviews, and comments, for the aforementioned information source. The processing execution means, when executing the specific processing, determines whether at least a part of the analysis result of the trigger is related to the characteristic information, and if they are related, selects the information source based on the characteristic information, and executes the specific processing using the information obtained from the selected information source. When the processing execution means selects the information source based on the characteristic information, it selects the information source taking into consideration the evaluation information. An information processing system characterized by the following:

2. In the information processing system described in claim 1, The aforementioned information sources include websites, The information generation means generates the characteristic information of the website based on the tags obtained from the website. An information processing system characterized by the following:

3. In the information processing system according to claim 1 or 2, The aforementioned information sources include application software, The information generation means generates the characteristic information of the application software based on the information collected by the application software. An information processing system characterized by the following:

4. An information processing method that uses an AI agent and multiple information sources, The aforementioned AI agent, An information generation step of generating characteristic information that represents the purpose or function of the information source based on information collected from the information source, and storing the characteristic information in a storage means in association with the information source, A trigger analysis step that analyzes the given trigger, A processing execution step in which a specific process is performed for the trigger based on the analysis results of the trigger, The information gathering step involves collecting evaluation information, including ratings, reviews, and comments, for the aforementioned information source. The processing execution step, when executing the specific processing, determines whether at least a part of the analysis results of the triggering event is related to the characteristic information, and if both are related, selects the information source based on the characteristic information, and executes the specific processing using the information obtained from the selected information source. The processing execution step, when selecting the information source based on the characteristic information, selects the information source taking into consideration the evaluation information. An information processing method characterized by the following:

5. A program for an information processing system comprising an AI agent and multiple information sources, The aforementioned AI agent, which is a computer, Information generation means that generates characteristic information representing the purpose or function of the information source based on information collected from the information source, and stores the characteristic information in a storage means in association with the information source; A trigger analysis means for analyzing a given trigger, A processing execution means that executes a specific process for the trigger based on the analysis results of the trigger, It functions as an information gathering means for collecting evaluation information, including evaluations, reviews, and comments, regarding the aforementioned information source. The processing execution means, when executing the specific processing, determines whether at least a part of the analysis result of the trigger is related to the characteristic information, and if they are related, selects the information source based on the characteristic information, and executes the specific processing using the information obtained from the selected information source. When the processing execution means selects the information source based on the characteristic information, it selects the information source taking into consideration the evaluation information. An information processing program characterized by the following features.

Images