Business support system, business support method, and computer program

Abstract

The present invention provides a business support system, a business support method, and a computer program for smoothly carrying out administrative procedures for foreigners. [Solution] The business support system of the present invention comprises a pre-processing unit that creates specific document analysis information by analyzing a specific document and stores the specific document analysis information in a storage device in association with specific document data of the specific document; an input accepting unit that accepts search information input by a first user; a document identification unit that identifies specific document data related to the search information from the specific document data stored in the storage device based on the search information accepted by the input accepting unit; a generation unit that generates guidance information related to the specific document based on the specific document data identified by the document identification unit and the analysis information associated with the specific document data; and an output unit that outputs the guidance information generated by the generation unit.

Description

[Technical Field]

[0001] The present invention relates to a business support system, a business support method, and a computer program. [Background technology]

[0002] With the advancement of internationalization, many foreigners are visiting Japan. These foreigners visit government offices to carry out various administrative procedures, but they sometimes find it difficult to communicate with the officials due to language differences and other reasons.

[0003] In recent years, to address these issues, development of speech translation tools to support oral communication at government offices has been progressing. For example, a conversation assistance service has been proposed that displays the content of a conversation on a partition and also translates it (Patent Documents 1 and 2). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2024-040187 [Patent Document 2] Japanese Patent Application Publication No. 2024-040188 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the administrative documents required for these foreigners to carry out various administrative procedures contain formats and annotations unique to Japanese, and simply providing a translation can still be difficult to understand. There is also the problem that it is a heavy workload for the person in charge to provide supplementary explanations every time they receive a request.

[0006] Therefore, it is an object of the present disclosure to provide technical improvements that solve or mitigate at least some of the above-mentioned problems.

[0007] A more specific object of the present disclosure is to provide a business support system, a business support method, and a computer program for smoothly carrying out administrative procedures for foreigners. [Means for solving the problem]

[0008] The business support system of the present invention is a business support system equipped with one or more computer processors, and is characterized in that it comprises a pre-processing unit that analyzes a specific document to create specific document analysis information including a summary, a translation, and at least one of keywords of the specific document, and stores the specific document analysis information in a storage device in association with specific document data of the specific document; an input accepting unit that accepts input of search information by a first user; a document identification unit that identifies specific document data related to the search information from the specific document data stored in the storage device based on the search information accepted by the input accepting unit; a generation unit that generates guidance information related to the specific document based on the specific document data identified by the document identification unit and the analysis information associated with the specific document data; and an output unit that outputs the guidance information generated by the generation unit.

[0009] The pre-processing unit analyzes documents related to administrative procedures handled at administrative counters as specific documents, and the generation unit generates information as guidance information to assist a second user visiting the administrative counter in carrying out the administrative procedures.

[0010] The pre-processing unit can analyze, as the specific document, a document to be submitted to the government and which requires the second user to fill in the necessary information.

[0011] The generation unit can generate, as guidance information, information for supporting the second user in filling in the necessary information.

[0012] The input receiving unit further receives text input of language information by a first user and / or voice input of language information by a second user, and the one or more computer processors further include a language identification unit that identifies a language to be used in generating the guidance information based on the language information received by the input receiving unit, and the generation unit can generate the guidance information in the language identified by the language identification unit.

[0013] The generation unit can use the generation AI to generate guidance text as guidance information for the first user to assist the second user in completing administrative procedures.

[0014] The input receiving unit can receive text input or voice input of a predetermined keyword as input of search information.

[0015] The pre-processing unit can analyze, as the specific document, the document to be submitted to the government, as well as annotation information and / or description requirements attached to the document.

[0016] If the document identification unit cannot identify one specific document data related to the search information from the specific document data stored in the storage device based on the search information received by the input receiving unit, the generation unit generates question information including additional questions necessary to identify the specific document data, and the output unit can output the question information generated by the generation unit.

[0017] The business support method of the present invention is characterized by having one or more computer processors execute the following steps: a pre-processing step of analyzing a specific document to create specific document analysis information including at least one of a summary, a translation, and keywords of the specific document, and storing the specific document analysis information in a storage device in association with specific document data of the specific document; an input acceptance step of accepting input of search information from a first user; a document identification step of identifying specific document data related to the search information from the specific document data stored in the storage device based on the search information accepted in the input acceptance step; a generation step of generating guidance information related to the specific document based on the specific document data identified in the document identification step and the analysis information associated with the specific document data; and an output step of outputting the guidance information generated in the generation step.

[0018] The computer program of the present invention is characterized by having one or more computer processors realize a pre-processing function that analyzes a specific document to create specific document analysis information including at least one of the summary, translation, and keywords of the specific document, and stores the specific document analysis information in a storage device in association with specific document data of the specific document; an input acceptance function that accepts input of search information by a first user; a document identification function that identifies specific document data related to the search information from the specific document data stored in the storage device based on the search information accepted by the input acceptance function; a generation function that generates guidance information related to the specific document based on the specific document data identified by the document identification function and the analysis information associated with the specific document data; and an output function that outputs the guidance information generated by the generation function. [Effects of the Invention]

[0019] The present invention provides technical improvements that solve or mitigate at least some of the problems discussed above.

[0020] Specifically, according to the present invention, administrative procedures for foreigners can be carried out more smoothly than ever before. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a system configuration diagram illustrating an example of a system configuration of a business support system according to the present disclosure. [Figure 2] FIG. 2 is a configuration diagram illustrating an example of a hardware configuration of a first information processing device according to the present disclosure. [Figure 3] 1 is a configuration diagram illustrating an example of a functional configuration of a business support system according to the present disclosure. [Figure 4] FIG. 10 is a configuration diagram illustrating another example of the functional configuration of the business support system according to the present disclosure. [Figure 5] FIG. 1 is an image diagram showing an application example of a business support system according to the present disclosure. [Figure 6] 1 is a system configuration diagram illustrating an application example of a business support system according to the present disclosure. [Figure 7] FIG. 1 is a conceptual diagram showing an image of the flow of Process 1 (preparation / learning) in the present disclosure. [Figure 8] FIG. 10 is a conceptual diagram showing an image of a screen displayed in process 2 (entering a search word) in the present disclosure. [Figure 9] FIG. 10 is a conceptual diagram showing an image of the flow of Process 3 (database search) in the present disclosure. [Figure 10] FIG. 10 is a conceptual diagram showing an image of the processing of Process 4 (result shaping / guidance sentence generation) in the present disclosure. [Figure 11] FIG. 10 is a conceptual diagram showing an image of the processing of Process 5 (output of results / presentation of additional questions) in the present disclosure. [Figure 12] FIG. 1 is a flow diagram showing an example of the flow of a business support method according to the present disclosure. [Figure 13] FIG. 1 is a circuit configuration diagram showing an example of a circuit configuration for realizing a computer program according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0022] An embodiment of a business support system disclosed in this specification will be described in detail with reference to the drawings.

[0023] The business support system of the present disclosure may have one or more computer processors, and may be configured with one or more information processing devices that include the one or more computer processors.

[0024] In this embodiment, the business support system disclosed herein will be described as a system that supports operations at administrative offices for foreigners, and the foreigners referred to here will be described as including, in particular, overseas researchers and international students at universities, but the system is not limited to such an embodiment.

[0025] <System configuration> The business support system 1000 of the present disclosure includes a first information processing device 100 (server device) and a storage device 300, as shown as an example in Figure 1, and the first information processing device 100 is configured to be connectable to one or more second information processing devices 200 (counter terminals).

[0026] The storage device 300 may be included in the first information processing device 100, or may be configured as a separate device connectable to the first information processing device 100. The storage device 300 may be provided outside the business support system 1000 of the present disclosure.

[0027] Furthermore, the business support system 1000 of the present disclosure can cooperate with an external service (generative AI service) as needed.

[0028] <Hardware configuration> 2, the hardware configuration of the first information processing device 100 will be described. The first information processing device 100 includes a processor 101, a memory 102, a storage 103, an input / output interface (input / output I / F) 104, and a communication interface (communication I / F) 105. The components are connected to each other via a bus B.

[0029] The first information processing device 100 can realize the functions and methods described in this embodiment through cooperation between the processor 101, memory 102, storage 103, input / output I / F 104, and communication I / F 105.

[0030] The processor 101 executes functions and / or methods implemented by codes or instructions included in a program stored in the storage 103. The processor 101 may include, for example, a central processing unit (CPU), a microprocessing unit (MPU), a graphics processing unit (GPU), a microprocessor, a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc., and may implement each process disclosed in each embodiment using a logic circuit (hardware) or a dedicated circuit formed in an integrated circuit (an integrated circuit (IC) chip, a large-scale integration (LSI)), etc. Furthermore, these circuits may be implemented using one or more integrated circuits, and multiple processes described in each embodiment may be implemented using a single integrated circuit. Furthermore, an LSI may also be referred to as a VLSI, a super LSI, an ultra LSI, etc. depending on the degree of integration.

[0031] The memory 102 temporarily stores programs loaded from the storage 103 and provides a working area for the processor 101. The memory 102 also temporarily stores various data generated while the processor 101 is executing the programs. The memory 102 includes, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), and the like.

[0032] The storage 103 stores programs and includes, for example, a hard disk drive (HDD), a solid state drive (SSD), a flash memory, and the like.

[0033] The communication I / F 105 is implemented as hardware such as a network adapter, communication software, or a combination thereof, and transmits and receives various types of data via a network. The communication may be performed either wired or wirelessly, and any communication protocol may be used as long as mutual communication is possible. The communication I / F 105 communicates with other information processing devices via the network. The communication I / F 105 transmits various types of data to other information processing devices in accordance with instructions from the processor 101. The communication I / F 105 also receives various types of data transmitted from other information processing devices and transmits the data to the processor 101.

[0034] The input / output I / F 104 includes an input device for inputting various operations to the first information processing device 100, and an output device for outputting processing results processed by the first information processing device 100. The input / output I / F 104 may be an integrated input device and output device, or may be separate input device and output device.

[0035] The input device is realized by any one or combination of all types of devices that can receive input from a user and transmit information related to the input to the processor 101. Examples of the input device include hardware keys such as a touch panel, a touch display, and a keyboard, a pointing device such as a mouse, a camera (for inputting operations via images), and a microphone (for inputting operations via voice).

[0036] The operation unit serving as an input device can be one that corresponds to the type of the first information processing device 100. Examples of the operation unit include a touch panel integrated with a display, operation buttons provided on the housing of the user terminal, a keyboard, a mouse, and a controller operated by the user's hands.

[0037] The output device outputs the processing results obtained by the processor 101. The output device includes, for example, a touch panel, a speaker, and the like.

[0038] It should be noted that the functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes a program stored in a memory.

[0039] In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions.

[0040] If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0041] Furthermore, the second information processing device 200 and the storage device 300 in the present disclosure can also be configured to include the same hardware configuration as that in FIG. 2, unless otherwise noted.

[0042] The one or more computer processors included in the business support system 1000 in the present disclosure are characterized by including a pre-processing unit 110, an input receiving unit 120, a document identification unit 130, a generation unit 140, and an output unit 150, as shown as an example in FIG. 3.

[0043] The pre-processing unit 110 analyzes a specific document to create specific document analysis information including at least one of the summary, translation, and keywords of the specific document, and stores the specific document analysis information in the storage device 300 in association with the specific document data of the specific document.

[0044] In this specification, the term "specific document" is a concept that includes, for example, documents related to administrative procedures, and specific examples include documents submitted to the government regarding resident registration, national health insurance, marriage registration, moving-in registration, etc., which require the second user, a foreign national who is carrying out the procedure, to fill in the necessary information.

[0045] In this specification, "analysis" can refer to a process of executing at least one of structuring, gist extraction, vocabulary normalization, annotation extraction, and translation processing of the specific document.

[0046] In this specification, "summary, translation, keywords" may refer to (i) a sentence (summary) that succinctly expresses the key points necessary for submission, (ii) a sentence (translation) converted into a specified language, or (iii) words or phrases (keywords) used for searches, etc., extracted or generated from the contents of the specific document.

[0047] In this specification, the term "storage device" refers to a device capable of holding the specific document data and specific document analysis information, and may include a database server, a storage device, cloud storage, or the like.

[0048] The input receiving unit 120 receives search information input by the first user.

[0049] The first user is, for example, a person in charge at a government office who provides government office services to the second user.

[0050] In this specification, "search information" includes text input or voice input of specified keywords, and may also include attribute information such as language information, procedure type, and expected submission time (information regarding the scheduled submission date or deadline for the procedure) as necessary.

[0051] The document specifying unit 130 specifies, based on the search information received by the input receiving unit 120, specific document data related to the search information from the specific document data stored in the storage device 300.

[0052] In this specification, "based on search information" means using the information as the basis for matching, referencing, weighting, etc., and includes selection based on scoring such as partial matches, synonym expansion, morphological analysis, and embedding vector similarity, as well as exact matches.

[0053] In this specification, "related to the search information" means that the lexical, semantic, and procedural proximity between the search information and specific document data is above a certain threshold, including cases where the procedure name, required documents, and target attributes (e.g., international students, researchers, accompanying family members, etc.) match.

[0054] The generating unit 140 generates guidance information related to the specific document based on the specific document data identified by the document identifying unit 130 and the analysis information associated with the specific document data.

[0055] In this specification, "guidance information" refers to information that supports the execution of the administrative procedure by the second user who visits the administrative counter, and specifically includes at least one of the following information to support the filling in of necessary information (instructions for filling in, examples of filling in, points to note), a list of necessary documents, where to submit them and what to bring, supplementary explanations, and additional questions to fill in missing information. As mentioned above, "second users" include foreign users who carry out the procedure.

[0056] The output unit 150 outputs the guidance information generated by the generation unit 140 .

[0057] The output destination of the guidance information may include, but is not limited to, the display of the second information processing device 200 (counter terminal), a printer, a mobile terminal app, a university portal, and in one embodiment, television broadcasting or data broadcasting.

[0058] The guidance information may be presented directly to the second user, or may be presented only to the first user. Furthermore, it may be presented to both the first user and the second user. When presented only to the second user, the second user conveys the content of the guidance information to the first user verbally or by displaying it on a terminal screen, etc., based on the guidance information. The presentation format may be a display, audio output, distribution of printed materials, or a combination of these.

[0059] The present invention provides technical improvements that solve or mitigate at least some of the problems discussed above.

[0060] Specifically, the above configuration will enable administrative procedures for foreigners to be carried out more smoothly than ever before.

[0061] Furthermore, with the above configuration, the first user can present the key points and filling-out instructions of a specific document to the second user in an appropriate language, reducing the burden of providing supplementary explanations point by point. Furthermore, the second user can accurately fill in the necessary information by referring to the guidance information, reducing the risk of making mistakes or having to resubmit. Furthermore, by sharing the guidance information between the counter staff and the user, communication between them is facilitated, improving the efficiency of the entire counter operation and the quality of service.

[0062] In one embodiment, the pre-processing unit 110 analyzes, as the specific document, a document related to an administrative procedure handled at an administrative counter, and the generation unit 140 generates, as guidance information, information to assist a second user visiting the administrative counter in carrying out the administrative procedure.

[0063] Here, "administrative service counters" refers to the counter departments for providing resident services at local public organizations such as city halls, ward offices, and town and village offices, and specifically includes the reception staff and staff in the departments that handle administrative procedures such as resident registration, moving-in notifications, marriage notifications, national health insurance, and child allowances. This does not only include the main office building, but also administrative service counters set up in branch offices, service centers, universities, and public facilities.

[0064] "Secondary users" refer to the entities that actually carry out the administrative procedures, and include in particular foreign residents, international students, researchers from overseas, and their families who visit administrative offices to fill out and submit various administrative documents.

[0065] The second type of user often does not have sufficient Japanese language skills and has difficulty understanding the technical terms and annotations contained in administrative documents, and is therefore the target of support provided by the guidance information provided by the system of the present invention.

[0066] With the above configuration, the guidance information is generated in accordance with the formats and operational procedures actually used at government offices, allowing the second user to accurately grasp the entry guidelines and important points that are difficult to understand with a simple translation, significantly reducing errors and omissions. Furthermore, the first user (the person at the office) no longer needs to explain each note point by point, as in the past, which not only improves response efficiency at the office, but also promotes the standardization and uniformity of procedures, reducing differences in explanations between staff and the burden of judgment.

[0067] In one embodiment, the pre-processing unit 110 can analyze, as the specific document, a document to be submitted to an administrative body and which requires the second user to fill in the necessary information.

[0068] Furthermore, the pre-processing unit 110 analyzes, as the specific document, the document to be submitted to the government, as well as annotation information and / or description guidelines attached to the document.

[0069] The above configuration makes it possible to provide guidance information that reflects format-specific points of interest that are difficult to convey through simple translation results. This allows the second user to understand the details of the document, such as the meaning of fields, the order in which they are filled out, and the source of attached documents, reducing the risk of the document being returned or resubmitted after submission. Furthermore, since the first user can avoid having to verbally explain each and every note and requirement, it not only improves the efficiency of customer service at the counter but also enables a standard response that incorporates personal know-how into the system.

[0070] The generating unit 140 can generate, as guidance information, information for supporting the second user in filling in the necessary information.

[0071] With the above configuration, foreign users (secondary users) can accurately fill out the necessary information by referring to examples and important points for filling out administrative documents, preventing errors and omissions. This improves the accuracy of procedural processing and significantly reduces inefficient procedures such as resubmissions and additional confirmations. Furthermore, the burden on counter staff (first users) to provide supplementary explanations is reduced, resulting in more consistent service and shorter processing times. Furthermore, since users can refer to the guidance information and proceed with procedures in a self-contained manner, this also contributes to improving the reliability of counter services overall.

[0072] In one embodiment, the input receiving unit 120 can further receive text input of language information by a first user and / or voice input of language information by a second user.

[0073] In this specification, "language information" refers to information for specifying the language used to generate guidance information. The language information includes either a character string input by a user or a spoken voice, or both.

[0074] Here, "text input" refers to character string data that the first user inputs using a keyboard, touch panel, or other input means of a terminal device. The text input may be a character string in Roman letters, Japanese, English, Chinese, Korean, or other natural languages.

[0075] The term "voice input" refers to voice data uttered by the second user through the microphone of the terminal device or an external input device. The voice input is converted into character string data through speech recognition processing, and the character string data is treated as language information.

[0076] The input receiving unit 120 may receive text input of language information by a first user, voice input of language information by a second user, or a combination of these.

[0077] In this case, as shown in FIG. 4 as an example, one or more computer processors of the present disclosure may further include a language identification unit 160.

[0078] The language identification unit 160 identifies the language to be used in generating the guidance information based on the language information received by the input reception unit 120.

[0079] At this time, the generation unit 140 generates the guidance information in the language identified by the language identification unit 160.

[0080] The above configuration makes it easy to output multiple languages, improving the efficiency of two-way communication at the counter. This allows the second user to receive guidance information in their native language or a language they understand, allowing them to accurately understand the procedure and significantly reducing misunderstandings and anxiety. Meanwhile, the first user can receive appropriate assistance even if they are not proficient in a foreign language, allowing for stable counter service that is not dependent on the language ability of individual staff members. Furthermore, through language selection and automatic identification, a consistent multilingual support system can be established across all government counters in the future, even if diverse language needs exist in each region.

[0081] In one embodiment, the generation unit 140 can use a generation AI to generate guidance text as guidance information for a first user to assist a second user in completing administrative procedures.

[0082] At this time, the generation unit 140 obtains the specific document data identified by the document identification unit 130 and the analysis information associated with the data (summary, translation, keywords, annotation information, description guidelines, etc.) from the storage device 300, and supplies these as inputs (prompts or contexts) for the generation process.

[0083] Generative AI refers to technology that uses a trained language model, etc. to generate natural language sentences that match given analysis information or specific document data, and is not limited to simple machine translation. In other words, rather than simply outputting the translation results as is, it also includes reconstructing the results into a format that is easy for users to understand, reflecting form-specific notes and submission requirements while referencing the basis information stored in the storage device 300.

[0084] In this specification, "guidance text" refers to a natural language sentence containing information necessary to carry out the administrative procedure. Specifically, it may include at least one of the following: (i) sample entries or instructions, (ii) a list of required documents, (iii) information on the submission destination / counter, (iv) important points or supplementary explanations, and (v) additional questions to confirm missing information. The guidance text is formatted to allow the second user to proceed with the procedure accurately and smoothly, and serves to reduce the workload of the first user, the counter staff.

[0085] With the above configuration, rather than simply presenting fragmented search results, the generation AI can construct consistent natural language sentences based on the administrative document data and analysis information stored in the storage device 300. This allows the second user to be guided through procedures in easy-to-understand sentences that are tailored to the user's attributes and situation, improving the effectiveness of assistance in filling out forms. Furthermore, the first user is freed from conventional standardized explanations, and flexible and consistent guidance can be provided for each case, simultaneously improving the quality and efficiency of counter service.

[0086] The input receiving unit 120 can receive text input or voice input of a predetermined keyword as input of search information.

[0087] Here, "keywords" refers to words or phrases related to administrative procedures, and may include attributes such as the procedure name (e.g., moving-in notification, marriage notification), residence status (e.g., study abroad, research), whether or not family members are accompanying the applicant, expected submission time, residence category, and name of the office where the application is to be submitted.

[0088] With the above configuration, the counter staff can quickly find appropriate candidate documents even with limited verbal information or fragmentary phrases obtained from the second user. By combining this with the presentation of additional questions as described later in this specification as necessary, the risk of misguided guidance or repeat visits can be further reduced.

[0089] The pre-processing unit 110 can analyze, as the specific document, the document to be submitted to the government, as well as annotation information and / or description guidelines attached to the document.

[0090] With the above configuration, the guidance information can reflect not only the main text of the administrative document but also its surrounding information, allowing for supplementary explanations of technical terms and expressions unique to Japanese that are difficult for users to understand. This allows the second user to correctly understand the nuances of the text that cannot be fully grasped through a simple translation, leading to the prevention of input errors. Furthermore, the first user no longer needs to provide standardized supplementary explanations based on annotations and writing guidelines, realizing uniformity and efficiency in counter responses. Furthermore, by consistently systemizing annotation information, differences in explanations between staff members can be reduced, contributing to the standardization of administrative services.

[0091] In one embodiment, if the document identification unit 130 cannot identify one specific document data related to the search information from the specific document data stored in the storage device 300 based on the search information received by the input receiving unit 120, the generation unit 140 generates question information including additional questions necessary to identify the specific document data, and the output unit 150 can output the question information generated by the generation unit 140.

[0092] Here, "question information" refers to information that includes attribute confirmation (e.g., number of accompanying family members, period of stay, residential area, etc.) to eliminate branching of candidate documents, and the content of which changes sequentially depending on the user's additional answers, ultimately leading to the appropriate specific document data.

[0093] With the above configuration, the completion of missing information is automated, reducing the risk of repeat visits or return of applications, and eliminating the need for counter staff to repeatedly ask ambiguous questions. As a result, the consistency and accuracy of responses is improved, and users can quickly access the most appropriate guidance information. Furthermore, unlike conventional FAQ systems or simple keyword searches, this system uses generative AI to dynamically generate questions, allowing for sequential supplementary confirmation of search information that contains insufficient information or ambiguous expressions. This has the effect of flexibly responding to foreign users with different language abilities and new residents with limited administrative knowledge.

[0094] <Application example> In one embodiment, the system of the present invention can be used to support foreign residents and international students. In this embodiment, administrative documents and notification forms are stored in the storage device 300, and a generation AI is used to summarize and translate them, creating a system that appropriately provides necessary information at administrative offices.

[0095] With the increase in foreign residents, administrative staff at the counter face the following challenges: Difficulty in communication due to not understanding or being able to communicate in the language - Difficulty in understanding expressions specific to administrative documents · With normal translation, the amount of text becomes huge, making it difficult to convey the main points.

[0096] To address these issues, the system of the present invention is configured to register administrative documents necessary for administrative services for foreigners in a database in advance and output guidance information as natural language text via generation AI (see Figure 5).

[0097] In this embodiment, the system of the present invention is used as a mechanism to support administrative counter services for foreign residents, particularly researchers and their families, international students, and the like.

[0098] The system of this invention utilizes generative AI to pre-learn administrative documents that are difficult for foreigners to understand, and then presents a summary or translation of how to proceed with the necessary procedures in response to individual requests.

[0099] The guidance information may be presented not only to the administrative staff member who is the first user, but also to the foreign national himself who is the second user.

[0100] This reduces the burden on the counter staff and allows users to refer to the guidance information themselves and proceed with the procedure.

[0101] Furthermore, continued use of the system will improve its learning accuracy, making it possible to present highly accurate search results that are in line with local government needs (see Figure 6).

[0102] When a user searches for a term or phrase they do not understand at the counter in Japanese or English, the system will refer to a trained database and present the most appropriate answer formatted by the generative AI.

[0103] Furthermore, in this embodiment, when registering administrative documents, the experience and know-how of experienced staff can be incorporated as additional information. This allows for the accumulation of unique information in existing databases, and if the generation AI detects missing information, it can present additional questions, ensuring that users can access the information they need.

[0104] This system can expand the range of languages ​​and administrative documents it supports depending on the stage of use. For example, in the initial stage, it can support a combination of Japanese and English, and limit the target documents to health insurance-related documents. Later, the target languages ​​can be expanded to Chinese, Korean, etc., and the target documents can be expanded to other administrative fields, such as marriage registrations and moving-in notifications. Furthermore, it is possible to expand its functions based on collected and analyzed usage data.

[0105] This system can be applied not only to administrative counter services but also to disaster prevention and public service announcements. For example, in the event of a disaster, it can distribute multilingual information to foreigners regarding evacuation shelter registration and the issuance of disaster victim certificates.

[0106] Furthermore, in this application example, the necessary feedback is realized through a series of processes as follows.

[0107] Process 1: Advance preparation (studying administrative documents) Administrative documents are summarized using generation AI, and search terms are extracted. The summaries, translations, and keywords are saved in a training database. For example, by targeting representative documents such as those related to health insurance and registering them, including annotations written in the original documents, it becomes possible to create guidance information that incorporates expressions and nuances unique to Japanese (see Figure 7).

[0108] Step 2: Enter search terms Administrative officials enter the necessary keyword information obtained from foreign users into a dedicated input screen (see Figure 8).

[0109] Process 3: Database search The entered words are compared with a pre-trained administrative document database to obtain the relevant administrative document information. Since there is no need to collect information from the Internet, unstable results can be avoided and stable and highly accurate feedback can be provided (see Figure 9).

[0110] Process 4: Formatting search results The acquired administrative document information is given to a generation AI and converted into natural language guidance text. For example, it is formatted into English and presented in a format that is easy for users to understand (see Figure 10).

[0111] Process 5: Output of results The generated guidance information is output in Japanese and foreign languages ​​(see Figure 11). Furthermore, by registering the knowledge of experienced staff in advance, the system is configured to present additional questions as needed and allow users to enter supplementary information.

[0112] This system can be flexibly adapted to users' attributes such as nationality, gender, religion, age, and Japanese language proficiency, and can also generate guidance information that includes expressions and questions that take cultural and religious backgrounds into consideration. This allows for government support that meets a wide range of user needs.

[0113] (Example 1: Support for moving-in notification) When a foreigner moves in from overseas, the person at the counter enters "Notification of Moving-in, Country Name, Family." The document identification section extracts related documents from the database, and the generation section creates a guide message. The Japanese version displays "Please fill in the purpose of stay, visa, and passport number. Required document: Notification of Moving-in (for those moving from overseas)," while the foreign language version displays "Please fill in the purpose of stay, visa, and passport number. Required document: Notification of Moving-in (for those moving from overseas)." The additional question display section displays "Please confirm the number of family members accompanying you," to prevent omissions.

[0114] (Example 2: Health insurance enrollment support) When an international student wishes to enroll in health insurance, the staff member enters "National Health Insurance International Student." The necessary documents (resident card, student ID) are presented, and a supplementary explanation is displayed, such as "If your period of stay is less than one year, you may not be eligible to enroll."

[0115] (Example 3: Multilingual support) The system will initially support Japanese and English, and can be expanded to other languages ​​such as Chinese and Korean in the future. For example, when searching for marriage registration information, it will be possible to include culturally appropriate notes in the guidance information.

[0116] (Example 4: Cooperation between counters) If the user's search results indicate that additional submission to another department is required, the system will forward that information to the next contact point, thereby reducing the user's need to visit multiple contact points.

[0117] (Example 5: Publicizing administrative procedures through collaboration with broadcasting infrastructure) Utilizing broadcasting infrastructure, multilingual information generated based on government documents will be distributed via data broadcasting, etc. Foreign residents will be able to find out in advance what documents they need and where to go via subtitles on their TV screens or QR codes.

[0118] (Example 6: Emergency procedure guidance in the event of a disaster) By using the emergency broadcast network, in the event of a disaster, information on shelter registration for foreigners and the issuance of disaster damage certificates can be distributed in real time in multiple languages.

[0119] (Example 7: Collaboration with educational institutions and support for researchers) The system can provide guidance to researchers and their families regarding resident registration, health insurance, and school enrollment procedures for their children. Information is provided via the university portal and dedicated online channels, helping researchers to focus on their research activities.

[0120] (Example 8: Analysis of administrative needs using usage data) By anonymizing viewing data and survey results held by broadcasters and public institutions and training the system to learn from them, it is possible to analyze the administrative needs of foreign residents, further improving the accuracy of administrative document guidance.

[0121] Next, an example of a business support method according to the present disclosure will be described.

[0122] The information processing method in the present disclosure is a business support method executed in a business support system 1000 shown in FIG. 1 as an example.

[0123] The business support method of the present disclosure is characterized by having one or more computer processors execute a pre-processing step S110, an input receiving step S120, a document identification step S130, a generation step S140, and an output step S150, as shown as an example in FIG. 10.

[0124] In pre-processing step S110, the specific document is analyzed to create specific document analysis information including at least one of the summary, translation, and keywords of the specific document, and the specific document analysis information is stored in a storage device in association with the specific document data of the specific document.

[0125] This pre-processing step S110 can be performed by the above-mentioned pre-processing unit 110. Details of the pre-processing unit 110 are as described above.

[0126] In input receiving step S120, input of search information by the first user is received.

[0127] The input receiving step S120 can be executed by the above-mentioned input receiving unit 120. Details of the input receiving unit 120 are as described above.

[0128] In document specifying step S130, specific document data related to the search information received in input receiving step S120 is specified from the specific document data stored in the storage device based on the search information received in input receiving step S120.

[0129] Such document identification step S130 can be executed by the above-mentioned document identification unit 130. Details of the document identification unit 130 are as described above.

[0130] In the generating step S140, guidance information related to the specific document is generated based on the specific document data identified in the document identifying step S130 and the analysis information associated with the specific document data.

[0131] This generating step S140 can be performed by the above-mentioned generating unit 140. Details of the generating unit 140 are as described above.

[0132] In the output step S150, the guidance information generated in the generation step S140 is output.

[0133] This output step S150 can be performed by the above-mentioned output unit 150. Details of the output unit 150 are as described above.

[0134] The above configuration can provide a technical improvement that solves or alleviates at least some of the problems of the prior art described above.

[0135] Next, a computer program according to an embodiment of the present disclosure will be described.

[0136] The computer program in the present disclosure is, as an example, a computer program executed in the information processing system 1000 shown in FIG.

[0137] The computer program in the present disclosure is characterized by causing one or more computer processors to implement a pre-processing function, an input receiving function, a document identification function, a generation function, and an output function.

[0138] The pre-processing function analyzes a specific document to create specific document analysis information including at least one of the summary, translation, and keywords of the specific document, and stores the specific document analysis information in a storage device in association with the specific document data of the specific document.

[0139] The input reception function receives search information input by the first user.

[0140] The document specifying function specifies specific document data related to the search information from the specific document data stored in the storage device based on the search information received by the input receiving function.

[0141] The generating function generates guidance information related to the specific document based on the specific document data identified by the document identifying function and the analysis information associated with the specific document data.

[0142] The output function outputs the guidance information generated by the generation function.

[0143] The above functions can be realized by a pre-processing circuit 1110, an input receiving circuit 1120, a document identification circuit 1130, a generation circuit 1140, and an output circuit 1150 shown in Fig. 11. The pre-processing circuit 1110, the input receiving circuit 1120, the document identification circuit 1130, the generation circuit 1140, and the output circuit 1150 are realized by the above-mentioned pre-processing unit 110, the input receiving unit 120, the document identification unit 130, the generation unit 140, and the output unit 150, respectively. Details of each unit are as described above.

[0144] The above configuration can provide a technical improvement that solves or alleviates at least some of the problems of the prior art described above.

[0145] Furthermore, an information processing device such as a computer or a mobile phone can be suitably used to function as the server device or terminal device according to the above-described embodiments. Such an information processing device can be realized by storing a program describing the processing content for realizing each function of the server device or terminal device according to the embodiments in a storage unit of the information processing device, and reading and executing the program by a CPU of the information processing device.

[0146] Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, and are also included in the scope of the invention and its equivalents as defined in the claims.

[0147] Furthermore, the methods described in the embodiments can be stored as a program executable by a computer on a recording medium such as a magnetic disk (e.g., a floppy disk, a hard disk, etc.), an optical disk (e.g., a CD-ROM, a DVD, an MO, etc.), or a semiconductor memory (e.g., a ROM, a RAM, a flash memory, etc.), and can also be distributed by transmitting it via a communication medium. The program stored on the medium also includes a configuration program for configuring software means (including not only execution programs but also tables and data structures) within the computer to be executed by the computer. The computer implementing this device reads the program stored on the recording medium and, in some cases, configures the software means using the configuration program, and executes the above-described processing by controlling the operation of this software means. The term "recording medium" as used herein is not limited to a storage medium for distribution, but also includes storage media such as a magnetic disk or semiconductor memory installed within the computer or in a device connected via a network. The storage unit may function as, for example, a main storage device, an auxiliary storage device, or a cache memory. [Explanation of symbols]

[0148] 100 First information processing device 110 Pre-processing section 120 Input reception section 130 Document Identification Section 140 Generation part 150 Output section 160 Language Specification Section 200 Second information processing device 300 storage device

Claims

1. A business support system for supporting the execution of administrative procedures by a second user who is a foreign national visiting an administrative counter, comprising: The business support system includes one or more computer processors, the one or more computer processors: a pre-processing unit that analyzes a specific document, which is a document related to the administrative procedure handled at an administrative counter and includes a document to be submitted to the government, annotation information attached to the document, and / or description guidelines, to create specific document analysis information including at least one of a summary, translation, and keywords of the specific document, and stores the specific document analysis information in a storage device in association with the specific document data of the specific document; an input receiving unit that receives input of search information by a first user who is a person in charge of the administrative office, and text input of language information understandable to the second user, and / or voice input of language information by the second user; a language identification unit that identifies a language to be used in generating guidance information based on the language information received by the input reception unit; a document specifying unit that specifies specific document data related to the search information from the specific document data stored in the storage device based on the search information received by the input receiving unit; a generation unit that generates, based on the specific document data identified by the document identification unit and the specific document analysis information associated with the specific document data, guidance information related to the specific document, the guidance information being a guidance sentence for supporting the second user in carrying out administrative procedures, in the language identified by the language identification unit; an output unit that outputs the guidance information generated by the generation unit; A business support system equipped with:

2. The business support system according to claim 1, characterized in that the pre-processing unit analyzes, as the specific document, a document to be submitted to the government and which requires a second user to fill in the necessary information.

3. 3. The business support system according to claim 2, wherein the generating unit generates, as the guidance information, information for supporting the second user in filling in the necessary information.

4. The business support system described in claim 1, characterized in that the generation unit uses generation AI to generate, as the guidance information, guidance text for the first user to assist the second user in completing the administrative procedure.

5. If the document specifying unit cannot specify one specific document data related to the search information from the specific document data stored in the storage device based on the search information received by the input receiving unit, the generating unit generates question information including an additional question necessary to identify the specific document data; 2. The business support system according to claim 1, wherein the output unit outputs the question information generated by the generation unit.

6. The business support system described in Claim 1, characterized in that the document identification unit calculates a relevance score based on the similarity of the embedded vector to the search information and the specific document analysis information, and identifies specific document data based on the relevance score.

7. The business support system described in Claim 1, characterized in that the output unit outputs the guidance information in a format that can be presented to either or both of the first user and the second user.

8. The business support system described in Claim 1, characterized in that the storage device stores the specific document analysis information in association with additional information indicating the know-how of experienced staff at administrative offices.

9. The business support system described in Claim 1, characterized in that the specific document analysis information is generated by a multi-stage process including summarization processing, translation processing, keyword extraction processing and sentence formatting processing, and is used as input information for generating guidance information in the generation unit.

10. A business support method for supporting the execution of administrative procedures by a second user who is a foreign national visiting an administrative counter, comprising: one or more computer processors, a pre-processing step of analyzing a specific document, which is a document related to the administrative procedure handled at an administrative counter and includes a document to be submitted to the government, annotation information attached to the document, and / or description guidelines, to create specific document analysis information including at least one of a summary, translation, and keywords of the specific document, and storing the specific document analysis information in a storage device in association with the specific document data of the specific document; an input receiving step of receiving input of search information by a first user who is a person in charge of the administrative office, and text input of language information understandable by the second user, and / or voice input of language information by the second user; a language specifying step of specifying a language to be used in generating the guidance information based on the language information received in the input receiving step; a document specifying step of specifying specific document data related to the search information from the specific document data stored in the storage device based on the search information received in the input receiving step; a generating step of generating, in the language identified in the language identifying step, guidance text related to the specific document, the guidance text being for supporting the second user in carrying out administrative procedures, based on the specific document data identified in the document identifying step and the specific document analysis information associated with the specific document data; an output step of outputting the guidance information generated in the generation step; A business support method for carrying out the above.

11. A computer program for supporting the execution of administrative procedures by a second user who is a foreign national visiting an administrative counter, comprising: the one or more computer processors; a pre-processing function that analyzes specific documents related to the administrative procedures handled at administrative offices, including documents submitted to the government and annotations and / or description guidelines attached to the documents, to create specific document analysis information including at least one of a summary, translation, and keywords of the specific documents, and stores the specific document analysis information in a storage device in association with the specific document data of the specific documents; an input receiving function for receiving input of search information by a first user who is a person in charge of the administrative office, and text input of language information understandable to the second user, and / or voice input of language information by the second user; a language identification function that identifies a language to be used in generating guidance information based on the language information received by the input reception function; a document specifying function for specifying specific document data related to the search information from the specific document data stored in the storage device based on the search information received by the input receiving function; a generation function that generates, based on the specific document data identified by the document identification function and the specific document analysis information associated with the specific document data, guidance information related to the specific document, the guidance text being for supporting the second user in carrying out administrative procedures, in the language identified by the language identification function; an output function that outputs the guidance information generated by the generation function; A computer program that makes this happen.

Images