Information processing apparatus, information processing method, and information processing program

Abstract

To enable a user unsatisfied with an answer to a question to directly inquire of a person familiar with a specialized area relating to contents of the question by presenting, to the user, an inquiry destination for the question or the answer to the question together with the answer corresponding to the question in a chatbot system.SOLUTION: An information processing apparatus 10 for implementing a chatbot system for use in an object organization comprises a document search unit 106 and an inquiry destination search unit 109. The document search unit 106 searches for a document corresponding to an object question from an intra-organization document database. An inquiry destination output unit 111 outputs an intra-organization search inquiry destination group which consists of inquiry destinations to be output together with an answer corresponding to the object question and corresponds to the object question.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] An AI (Artificial Intelligence) chatbot system is a system that answers user questions on behalf of human experts. Here, "AI chatbot system" refers to a system that answers user questions through intelligent processing using a computer, and can also be expressed as a "chatbot system" without the "AI" part. The answers given by an AI chatbot system may not always be appropriate to the user's question. Therefore, in many cases, AI chatbot systems allow users to contact a human operator (contact point) in case their problem is not resolved by the AI ​​chatbot system's response. In this case, the contact point is indicated in some way. In conventional AI chatbot systems, the contact point for inquiries is common across the system. As a specific example, Patent Document 1 discloses an invention that efficiently links an AI chatbot system with a manned chat, but in Patent Document 1, there is only one operator. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7057581 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional AI chatbot systems have a single point of contact for inquiries. Therefore, when a complex AI chatbot system based on knowledge spanning multiple specialized fields is constructed, if a user is not satisfied with the AI ​​chatbot system's response, they cannot always directly contact a person with expertise in each specialized field, and must first contact a person at the primary point of contact common to the system. Therefore, conventional technology requires a secondary response, such as the primary point of contact having to respond to an inquiry in a field outside their expertise, or requesting a response from a secondary point of contact with specialized knowledge related to the inquiry content.

[0005] As a specific example of the conventional technology, let us assume that an AI chatbot system has been built that spans multiple specialized fields (company rules and system usage methods) that are related to each other, such as travel expense settlement rules and how to use a travel expense settlement system. This example will be explained using Figures 1 and 2.

[0006] In Figure 1, the user first inquired about whether the phone charges during a business trip could be reimbursed as travel expenses. This was a question about company rules, and the AI ​​chatbot system appropriately responded that the phone charges could be reimbursed. The "You" column shows the question entered by the user, and the "Chatbot" column shows the answer output based on the question. The user then asked whether travel expenses could be reimbursed for personal phone calls. However, the AI ​​chatbot system was unable to respond appropriately and output the message, "Sorry, we cannot answer that question."

[0007] In Figure 2, after a question and answer session about the reimbursement of telephone charges during a business trip, the user inquired about how to reimburse the telephone charges as travel expenses. The AI ​​chatbot system then responded that the user should select "Other Reimbursements" using the travel expense reimbursement system. However, the AI ​​chatbot system was unable to properly answer which screen (in the travel expense reimbursement system) to select "Other Reimbursements" from, and instead outputted "Sorry, we cannot answer that question."

[0008] In both the examples shown in Figure 1 and Figure 2, the AI ​​chatbot system's response does not solve the user's problem. Therefore, the user wants to solve the problem by contacting a human. In the example shown in Figure 1, the problem the user wants to solve is related to company rules, such as whether personal phone calls are subject to travel expense reimbursement, so it is desirable for the inquiry to be handled by someone who is familiar with company rules.On the other hand, in the example shown in Figure 2, the problem the user wants to solve is related to screen operation in the travel expense reimbursement system, so it is desirable for the inquiry to be handled by someone who is familiar with how to use the travel expense reimbursement system, rather than company rules. However, in conventional AI chatbot systems, it is not possible to change the point of contact depending on the question and answer, so there is no choice but to have a single point of contact for responses (the General Affairs Department in the examples shown in Figures 1 and 2). As a result, depending on the area of ​​expertise related to the content of the inquiry (such as company rules or system operation methods), the person at the point of contact may not be able to provide a satisfactory answer. In this way, when there is only one point of contact for an AI chatbot system that spans multiple specialized fields, it was necessary for the user to look up the contact points themselves (through means other than using the chatbot) and use each contact point separately, or for a person at the single contact point designated by the AI ​​chatbot system to select an expert at a secondary contact point according to the specialized field, and for the user to make an inquiry to the selected expert, or for a secondary response such as introducing the user to that expert was required.

[0009] The present disclosure aims to provide a chatbot system that presents users with an answer to a question along with a contact point corresponding to the question or the answer to the question, so that if the user is not satisfied with the answer, the user can directly inquire of someone who is knowledgeable in the specialized field related to the content of the question. [Means for solving the problem]

[0010] The information processing device according to the present disclosure includes: An information processing device for realizing a chatbot used in a target organization, a document search unit that searches, as an internal search document group, for one or more documents corresponding to the target question input to the information processing device from an internal document database in which one or more internal documents related to the target organization are registered; an answer processing unit that generates an answer corresponding to the target question as an internal answer based on the internal search document group; an inquiry output unit that outputs a group of in-organization search inquiry destinations corresponding to the target question, the in-organization search inquiry destinations being composed of one or more inquiry destinations that are output together with the in-organization answer; Equipped with. [Effects of the Invention]

[0011] According to the present disclosure, an information processing device for realizing a chatbot includes a contact output unit that outputs one or more contacts corresponding to a target question, the contacts being output together with an internal response. Therefore, according to the present disclosure, in a chatbot system, by presenting to the user an answer corresponding to the question as well as a contact point corresponding to the question or the answer to the question, if the user is not satisfied with the answer, the user can directly inquire of someone who is knowledgeable in the specialized field related to the content of the question. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating a problem associated with the conventional technology. [Figure 2] FIG. 1 is a diagram illustrating a problem associated with the conventional technology. [Figure 3] FIG. 1 is a diagram showing an example of the configuration of a chatbot system 90 according to a first embodiment. [Figure 4] FIG. 3 is a diagram for explaining inquiry related information 3 according to the first embodiment. [Figure 5] 1 is a diagram showing an example of the hardware configuration of an information processing device 10 according to a first embodiment. [Figure 6] 3 is a flowchart showing the operation of the information processing device 10 according to the first embodiment. [Figure 7] 1A to 1C are diagrams illustrating the effects of the first embodiment. [Figure 8] 1A to 1C are diagrams illustrating the effects of the first embodiment. [Figure 9] 1A to 1C are diagrams illustrating the effects of the first embodiment. [Figure 10] FIG. 10 is a diagram showing an example of the hardware configuration of an information processing device 10 according to a modification of the first embodiment. [Figure 11] FIG. 10 is a diagram showing an example of the configuration of a chatbot system 90 according to a second embodiment. [Figure 12] 10A to 10C are diagrams illustrating the effects of the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0013] In the description of the embodiments and the drawings, the same elements and corresponding elements are given the same reference numerals. The description of elements given the same reference numerals will be omitted or simplified as appropriate. Arrows in the drawings mainly indicate the flow of data or the flow of processing. Furthermore, "unit" may be read as "circuit," "step," "procedure," "process," or "circuitry" as appropriate.

[0014] Embodiment 1 Hereinafter, this embodiment will be described in detail with reference to the drawings.

[0015] ***Configuration Description*** 3 shows an example of the configuration of a chatbot system 90 according to this embodiment. The chatbot system 90 includes an information processing device 10, an inquiry application 11, and a document capture tool 12. The chatbot system 90 is also called an AI (Artificial Intelligence) chatbot system. Two or more elements constituting the chatbot system 90 may be configured integrally.

[0016] The inquiry application 11 is an application that receives a question from the user 1 and uses the information processing device 10 to present an answer corresponding to the content of the question received from the user 1 together with the document that is the source of the answer to the user 1. The document that is the source of the answer may be at least a part of the actual document, or may be source information. The inquiry application 11 may accept questions by inputting characters or by inputting voice. The answer may be text information, information including an image, or voice information.

[0017] The document import tool 12 is a tool that imports the document group 2 and the inquiry related information 3 into the information processing device 10. Document group 2 consists of internal organizational documents, which consist of one or more documents that can be the source of an answer. An organization can be, for example, a company, a department, an educational institution, or a government agency, but it can also be the entire entity that includes a service provider and users of a service provided over the Internet. Internal organizational documents are documents maintained within an organization, and for example, internal information such as company rules and information about internal systems. The inquiry contact related information 3 is made up of information related to the inquiry contact corresponding to each document included in the document group 2. The inquiry contact related information 3 is, as a specific example, related information about in-house information. It should be noted that the term "document" is not limited to text information, but may also refer to information representing a web page, an audio file, or a video file.

[0018] The information processing device 10 includes a document registration unit 101, an inquiry registration unit 103, a question processing unit 105, a document search unit 106, an answer processing unit 108, an inquiry search unit 109, and an inquiry output unit 111. The information processing device 10 also stores a document DB 102 and an inquiry related DB 104. DB is an abbreviation for database. The information processing device 10 may use a generation AI such as ChatGPT, or may use other means. The information processing device 10 is a device for realizing a chatbot used in a target organization.

[0019] The document registration unit 101 imports documents input from the document import tool 12 into the document DB 102 .

[0020] The document DB 102, also called an internal document database, contains documents that the AI ​​chatbot refers to when answering questions. The internal document database stores one or more internal documents related to the target organization.

[0021] When the document registration unit 101 registers the documents input from the document import tool 12 in the document DB 102, the inquiry registration unit 103 registers the inquiry contacts for each document registered in the document DB 102 in the inquiry contact related DB 104 based on the inquiry contact related information 3. Note that there may be multiple inquiry contacts for each registered document. The inquiry related DB 104 is also called an internal inquiry database, and the internal inquiry database stores an inquiry address corresponding to each document registered in the internal document database.

[0022] FIG. 4 shows a specific example of the inquiry related information 3. Here, an example is shown in which inquiry destination related information 3 exists independently of the document data registered when each document is registered, and inquiry destination registration unit 103 registers the inquiry destination corresponding to each document in inquiry destination related DB 104. However, there are other methods for associating documents with inquiry destinations. As a specific example, if contact information is described in each document (by attaching a specific tag, for example), when a certain document is used as the source of an answer, the contact information corresponding to that certain document can be obtained from the information described in that certain document (by extracting it from the certain document using the attached tag as a clue, for example). In other words, contact-related information 3 may be included in document group 2. The point of this embodiment is not the method of associating a document with a contact point, but the point of setting a contact point according to the document. Therefore, the method of associating a document with a contact point is not the essence of this embodiment.

[0023] Based on a question input from the inquiry application 11, the question processing unit 105 generates a search query (search formula) corresponding to the question.

[0024] The document search unit 106 searches the document DB 102 for one or more documents corresponding to the target question input to the information processing device 10 as an in-organization search document group. As a specific example, the document search unit 106 is a document search engine that searches the document DB 102 based on the search query received from the question processing unit 105 and obtains search results 107 .

[0025] The search result 107 is data indicating one or more documents that are the source of the answer corresponding to the question.

[0026] The answer processing unit 108 generates an answer corresponding to the target question as an intra-organization answer based on the intra-organization search document group. As a specific example, the answer processing unit 108 processes the search results 107 to generate an answer corresponding to the question. The answer is a summary of each document shown in the search result 107 as an example.

[0027] The inquiry search unit 109 searches the inquiry related DB 104 for one or more inquiry destinations output together with the internal answer based on the target question, as an internal search inquiry destination group. The inquiry search unit 109 may search the internal search inquiry destination group based on the internal search document group. The internal search inquiry destination group corresponds to the target question. The inquiry destination search unit 109 is an inquiry destination search engine that, after the document search unit 106 obtains the search results 107, searches the inquiry destination related DB 104 for the inquiry destination 110 for each document included in the search results 107. Note that the inquiry destination search unit 109 may search for the inquiry destination 110 based on a question. Furthermore, searching for the inquiry destination 110 based on the search results 107 corresponds to searching for the inquiry destination 110 based on a question corresponding to the search results 107.

[0028] The inquiry destination 110 is the inquiry destination searched by the inquiry destination search unit 109, and is output together with the answer corresponding to the question.

[0029] The inquiry output unit 111 outputs the group of in-organization search inquiry destinations. Note that the group of in-organization search inquiry destinations may be made up of inquiry destinations obtained without constructing a physically independent DB (inquiry destination DB 104), for example, by searching from the descriptions in the document itself as described in paragraph

[0022] . As a specific example, the inquiry destination output unit 111 outputs the group of inquiry destinations searched within the organization by the inquiry destination search unit 109, that is, the inquiry destination 110.

[0030] In addition to processing questions and answers as described above, some AI chatbot systems have a mechanism for recording a history of consecutive questions and reflecting the recorded history in the answer to the next question, and some have a mechanism for learning based on questions and answers. These mechanisms can be added to this embodiment, but a description of these mechanisms will be omitted in this embodiment.

[0031] 5 shows an example of the hardware configuration of information processing device 10 according to this embodiment. Information processing device 10 is composed of a computer. Information processing device 10 may be composed of multiple computers. Note that document DB 102 and inquiry related DB 104 do not necessarily need to exist in the same physical computer as the computer that realizes information processing device 10.

[0032] As shown in the figure, the information processing device 10 is a computer including hardware such as a processor 51, a memory 52, an auxiliary storage device 53, an input / output IF (Interface) 54, and a communication device 55. These pieces of hardware are appropriately connected via signal lines 59.

[0033] The processor 51 is an integrated circuit (IC) that performs arithmetic processing and controls the hardware of the computer. Specific examples of the processor 51 include a central processing unit (CPU), a digital signal processor (DSP), or a graphics processing unit (GPU). The information processing device 10 may include a plurality of processors that take the place of the processor 51. The plurality of processors share the role of the processor 51.

[0034] The memory 52 is typically a volatile storage device, specifically a random access memory (RAM). The memory 52 is also called a primary storage device or a main memory. Data stored in the memory 52 is saved in the secondary storage device 53 as needed.

[0035] The auxiliary storage device 53 is typically a non-volatile storage device, and specific examples thereof include a ROM (Read Only Memory), an HDD (Hard Disk Drive), or a flash memory. Data stored in the auxiliary storage device 53 is loaded into the memory 52 as needed. The memory 52 and the auxiliary storage device 53 may be integrated into one unit.

[0036] The input / output IF 54 is a port to which an input device and an output device are connected. A specific example of the input / output IF 54 is a USB (Universal Serial Bus) terminal. Specific examples of the input device are a keyboard and a mouse. A specific example of the output device is a display.

[0037] The communication device 55 is a receiver and a transmitter, and is specifically a communication chip or a network interface card (NIC).

[0038] Each unit of the information processing device 10 may use the input / output IF 54 and the communication device 55 as appropriate when communicating with other devices.

[0039] The auxiliary storage device 53 stores an information processing program. The information processing program is a program that causes a computer to realize the functions of each unit included in the information processing device 10. The information processing program is loaded into the memory 52 and executed by the processor 51. The functions of each unit included in the information processing device 10 are realized by software.

[0040] Data used when executing an information processing program and data obtained by executing the information processing program are stored in a storage device as appropriate. Each part of the information processing device 10 uses a storage device as appropriate. Specific examples of the storage device include at least one of the memory 52, the auxiliary storage device 53, a register in the processor 51, and a cache memory in the processor 51. Note that the terms "data" and "information" may have the same meaning. The storage device may be independent of the computer. The functions of the memory 52 and the auxiliary storage device 53 may be realized by other storage devices.

[0041] The information processing program may be recorded on a computer-readable non-volatile recording medium. Specific examples of the non-volatile recording medium include an optical disk and a flash memory. The information processing program may be provided as a program product.

[0042] ***Explanation of Operation*** The operation procedure of the information processing device 10 corresponds to an information processing method, and the program that realizes the operation of the information processing device 10 corresponds to an information processing program.

[0043] As a preliminary preparation for answering a question, the document registration unit 101 uses the document import tool 12 to import the document group 2 into the document DB 102. At this time, the document registration unit 101 also simultaneously performs preprocessing so that the question processing unit 105 can appropriately search for documents. Note that this preprocessing varies depending on the technology, such as the generation AI, used in the chatbot system 90. However, the preprocessing is not the essence of this embodiment.

[0044] As a preliminary preparation for responding to inquiries, the inquiry registration unit 103 uses the document import tool 12 to store inquiry contacts corresponding to each document imported by the document registration unit 101 in the inquiry related DB 104 based on the inquiry related information 3, in conjunction with the import of the document group 2 by the document registration unit 101.

[0045] 6 is a flowchart showing an example of the operation of the information processing device 10. The operation will be described with reference to FIG. After completing the preparations for answering a question, the user 1 inputs a question into the inquiry application 11, and the process shown in this flowchart is executed. As a result, the user 1 obtains information indicating the answer corresponding to the input question, the document on which the answer is based, and the contact information for the answer.

[0046] (Step S101) The question processor 105 generates a search query based on the question entered by the user 1 .

[0047] (Step S102) The document search unit 106 obtains search results 107 by searching the document DB 102 using the search query generated by the question processing unit 105. Note that the search results 107 may be information indicating a plurality of documents.

[0048] (Step S103) The answer processing unit 108 generates a summary to be used as an answer based on each document indicated by the search results 107 obtained by the document search unit 106. Here, the answer processing unit 108 may generate a summary corresponding to each document indicated by the search results 107, or may generate one summary from multiple documents indicated by the search results 107. Here, the mechanism for generating an answer varies depending on the technology such as the generation AI used in the chatbot system 90. However, this mechanism is not the essence of this embodiment. The generated summary is output to the query application 11.

[0049] (Step S104) The inquiry destination search unit 109 obtains an inquiry destination 110 by searching the inquiry destination related DB 104 based on each document indicated by the search result 107 obtained by the document search unit 106 . The inquiry destination output unit 111 outputs the inquiry destination 110 obtained by the inquiry destination search unit 109 to the inquiry application 11 .

[0050] As described above, the user 1 can obtain from the inquiry application 11 an answer to the question that takes into account the search result 107 and the inquiry destination 110.

[0051] ***Explanation of the effect of the first embodiment*** The chatbot system 90 according to this embodiment has a function of changing the contact point depending on the question from the user and the answer output by the AI ​​chatbot. Therefore, according to this embodiment, it is possible to show the contact point directly according to the content of the question and answer. Therefore, when a composite AI chatbot system based on knowledge across multiple specialized fields is constructed using this embodiment, if a user is unable to solve a problem with the answer provided by the AI ​​chatbot system and needs to inquire with a human, the system can provide the user with a contact point that corresponds to a human with expertise in the respective specialized field according to the question and answer. As a result, the user can obtain an appropriate answer from the contact point, eliminating the need to make a secondary inquiry.

[0052] A specific description will be given using the screen examples of FIGS. In Figure 7, the user first inquires whether telephone charges during a business trip can be reimbursed as travel expenses, and receives a response from the chatbot system 90 that the charges can be reimbursed. The user then inquires whether personal phone calls can also be reimbursed as travel expenses, but the chatbot system 90 is unable to provide an appropriate response. At this time, the chatbot system 90 indicates in its previous response that the inquiry should be directed to the General Affairs Department, so the user can inquire at the General Affairs Department about whether or not travel expenses for personal phone calls can be reimbursed.

[0053] In Figure 8, after asking and answering a question about whether telephone charges during a business trip can be reimbursed as travel expenses, the user inquired about how to reimburse telephone charges as travel expenses, and the chatbot system 90 replied that they should select "Other Reimbursements" using the travel expense reimbursement system. However, the chatbot system 90 was unable to provide an appropriate answer as to which screen (of the travel expense reimbursement system) to select "Other Reimbursements." At this time, the chatbot system 90 indicates in its previous response that the contact point for inquiries is the Information Systems Department, so the user can inquire at the Information Systems Department about how to select "Other Settlements."

[0054] 7 and 8, different contact points are shown depending on the user's question and the answer generated by the chatbot system 90, even though the inquiries are directed to the same chatbot system 90. Therefore, according to this embodiment, the user can directly request a response from the appropriate contact point. Even in the case of an AI chatbot system that spans multiple specialized fields, the chatbot system 90 indicates the appropriate contact point, so there is no need for the user to look up the contact points themselves (through means other than using the chatbot system 90) and use each contact point differently, or for a person at a fixed primary contact point to select an expert at a secondary contact point according to the area of ​​expertise.

[0055] In both the examples of Figures 7 and 8, each contact point is for the previous question and its answer (which the chatbot system 90 was able to answer appropriately), not for the last question which the chatbot system 90 was unable to answer appropriately. In an AI chatbot system, the user and the system continue to dialogue to narrow down the content of the question. Therefore, if the answer immediately before a certain answer is the last answer that the AI ​​chatbot system was able to answer appropriately, there is a high possibility that the contact point for that answer will also be the appropriate contact point for the last question that the AI ​​chatbot system was unable to answer. Therefore, the contact point for the answer immediately before that certain answer can be considered the optimal contact point that the AI ​​chatbot system can suggest as the contact point for the last question (that the AI ​​chatbot was unable to answer appropriately).

[0056] If the chatbot system 90 could associate a contact point with a question rather than associating an answer (answer document) with a contact point, then, as mentioned above, it would be possible to select the "contact point for the current question" rather than the "contact point for the previous answer." To select "contact points for current questions," it is necessary to create a list like a FAQ (Frequently Asked Questions) that anticipates the questions users will have. Therefore, it is necessary to anticipate the types of questions that will be asked, or to limit the number of question patterns to the number of patterns that can be created in the FAQ. Here, AI chatbot systems that utilize generative AI technology have the advantage of being backed by a huge amount of learning data and a huge amount of search target data, and can generate answers without having to predetermine user question patterns in the form of an FAQ.With an AI chatbot system that makes use of this advantage, it is not possible to limit all question patterns in advance, and therefore it is not possible to show all contact points in the same way as selecting "contact points for the current question." Here, it is conceivable to separate the part that is dealt with based on FAQs from the other part, and realize the former by associating question patterns with contact points, while using this embodiment for the latter. Note that the solution using this method is merely an application example of this embodiment.

[0057] It should be noted that this embodiment is also effective in cases where the chatbot system 90 presents multiple answers. FIG. 9 shows a specific example in which the chatbot system 90 displays multiple answers to a user's question. When user 1 asks a question such as "Please tell me about travel expense settlement for telephone charges," it is unclear whether the question is about rules such as whether settlement is possible or about how to operate the travel expense settlement system. The document search unit 106 searches both the company rules and the travel expense settlement system manual, and generates multiple answers based on each of the documents found. The chatbot system 90 then outputs each answer, the document on which each answer is based, and the contact information corresponding to each answer. 9, when the chatbot system 90 is unable to answer an additional question from the user, that is, when the previous multiple answers are the final answers from the chatbot system 90, the chatbot system 90 displays contact information according to the content of each answer. Therefore, the user can decide for themselves whether they want to ask about the rules or how to operate the system (even though they know that travel expenses can be reimbursed), and can select the contact information that best suits their judgment and contact them as appropriate. In this way, when a user has one question but there are multiple possible answers to the question, this embodiment can display multiple contact points separately if each answer is related to the answer the user is looking for. Therefore, this embodiment eliminates the need for the user to look up the contact points themselves (by means other than using a chatbot) and use each contact point differently, or to take a secondary approach such as having a person at a fixed primary contact point select an expert at a secondary contact point according to their field of expertise.

[0058] ***Other Configurations*** <Variation 1> FIG. 10 shows an example of the hardware configuration of the information processing device 10 according to this modification. The information processing device 10 includes a processing circuit 58 in place of the processor 51 , the processor 51 and memory 52 , the processor 51 and auxiliary storage device 53 , or the processor 51 , memory 52 and auxiliary storage device 53 . The processing circuitry 58 is hardware that realizes at least a part of the components of the information processing device 10. The processing circuitry 58 may be dedicated hardware, or may be a processor that executes a program stored in the memory 52 .

[0059] When processing circuitry 58 is dedicated hardware, processing circuitry 58 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof. The information processing device 10 may include a plurality of processing circuits that replace the processing circuit 58. The plurality of processing circuits share the role of the processing circuit 58.

[0060] In the information processing device 10, some functions may be realized by dedicated hardware, and the remaining functions may be realized by software or firmware.

[0061] Processing circuitry 58 is illustratively implemented in hardware, software, firmware, or a combination thereof. The processor 51, memory 52, auxiliary storage device 53, and processing circuit 58 are collectively referred to as "processing circuitry." In other words, the functions of the functional components of information processing device 10 are realized by the processing circuitry. The information processing device 10 according to other embodiments may also have the same configuration as this modified example.

[0062] Embodiment 2 The following mainly describes the differences from the above-described embodiment with reference to the drawings.

[0063] ***Configuration Description*** 11 shows an example of the configuration of a chatbot system 90 according to this embodiment. The information processing device 10 according to this embodiment stores a document DB 302 and an inquiry destination related DB 304. Like the document DB 102 and the inquiry destination related DB 104, the document DB 302 and the inquiry destination related DB 304 do not necessarily have to be physically present in the same computer as the computer that implements the information processing device 10. The document DB 302 is also called an external document database, and stores one or more external documents related to the target organization. The inquiry related DB 304 is also called an external inquiry database, and contains the inquiry information corresponding to each document registered in the external document database.

[0064] The document import tool 12 according to this embodiment imports a document group 202 in addition to the document group 2 , and imports inquiry related information 203 in addition to the inquiry related information 3 .

[0065] Document set 202 is made up of external documents and includes one or more documents that can be the source of an answer. An external document is a document other than an internal document and is obtainable outside the target organization. Specific examples of external documents include documents held by other departments or other companies, documents obtainable over the internet, and documents used in a chatbot system 90 used in an organization other than the target organization. Specific examples of documents obtainable over the internet include documents containing information about tourism.

[0066] The inquiry destination related information 203 is information in which a document and an inquiry destination are associated with each other, similar to the inquiry destination related information 3. The inquiry destination related information 203 is, as a specific example, related information relating to external information. As a specific example, even if there is no tabular information for external information such as information on the Internet as shown in Figure 4, the correspondence between the external information and the contact point can be extracted in the same way as the example shown in Figure 4 by regarding the provider of the external information as the contact point.

[0067] The document registration unit 101 according to this embodiment has the function of registering the document group 202 in the document DB 302 in addition to the functions of the document registration unit 101 according to the first embodiment.

[0068] In addition to the functions of inquiry registration unit 103 according to the first embodiment, inquiry registration unit 103 according to the present embodiment has a function of registering inquiry related information 203 in inquiry related DB 304.

[0069] The document search unit 106 according to this embodiment has the same functions as the document search unit 106 according to the first embodiment, and also has the function of searching the document DB 302 for one or more documents corresponding to the target question as a group of documents searched outside the organization. As a specific example, the document search unit 106 obtains search results 107 by searching for documents in the document DB 102 and the document DB 302 based on the search query.

[0070] The answer processing unit 108 according to this embodiment has the function of generating an answer corresponding to the target question as an external answer based on an external search document group, in addition to the function of the answer processing unit 108 according to embodiment 1. The answer processing unit 108 may generate an internal answer and an external answer using a generation AI.

[0071] In addition to the functions of the inquiry destination search unit 109 according to Embodiment 1, the inquiry destination search unit 109 according to this embodiment has a function of searching, based on the target question, one or more inquiry destinations output together with the external answer as an external-organization search inquiry destination group from the inquiry destination related DB 304. The inquiry destination search unit 109 may search for the external-organization search inquiry destination group based on the external-organization search document group. As a specific example, inquiry destination search unit 109 obtains inquiry destination 110 by searching inquiry destinations in inquiry destination related DB 104 and inquiry destination related DB 304 based on the document indicated by search result 107 .

[0072] The inquiry destination output unit 111 according to this embodiment outputs a group of search inquiry destinations outside the organization.

[0073] ***Explanation of Operation*** As advance preparation for answering a question, in addition to the advance preparation according to the first embodiment, the document registration unit 101 uses the document import tool 12 to import the document group 202 into the document DB 302. Note that when importing documents from outside the organization, it is not necessary to physically import all documents into the document DB 302 in advance, and a means for accessing documents from outside the organization when the document search unit 106 searches for documents may be registered in the document DB 302. In addition to the preparations according to the first embodiment, the inquiry registration unit 103, in preparation for responding to inquiries, stores an inquiry corresponding to each document imported by the document registration unit 101 in the inquiry related DB 304 using the document import tool 12 based on the inquiry related information 203 in conjunction with the import of the document group 202 by the document registration unit 101. Note that even when the import of external documents is not the import of physical documents but the registration of means for accessing external documents, the inquiry related information can be obtained as described in paragraph

[0022] .

[0074] The following mainly describes the differences from the operation of the information processing device 10 according to the first embodiment.

[0075] (Step S102) This step is the same as step S102 according to the first embodiment. However, the document search unit 106 searches the document DB 302 in addition to the document DB 102 .

[0076] (Step S104) This step is the same as step S104 according to the first embodiment. However, when the search result 107 indicates a document outside the organization, the inquiry search unit 109 searches the inquiry related DB 304 to obtain an inquiry 110 corresponding to the document outside the organization.

[0077] ***Explanation of the effect of the second embodiment*** According to this embodiment, the chatbot system 90 can present answers not only to questions that should be answered based on information within the organization, but also to questions regarding information outside the organization.

[0078] FIG. 12 shows a specific example in which user 1 asks a question about external documents to the chatbot system 90 according to this embodiment. User 1 not only inquires about internal information, such as whether travel expenses can be reimbursed if he or she takes a plane to City O, but also requests tourist information (information about an okonomiyaki restaurant) that cannot be answered based on internal information. The chatbot system 90 can present an answer based on both internal and external documents, even for the question shown in FIG. 12. Note that the chatbot system 90 may present an answer based only on external documents, or may present an answer based on both internal and external documents. Also in this embodiment, more than one contact point can be indicated depending on the content of the reply.

[0079] ***Other embodiments*** The above-described embodiments may be freely combined, or any of the components in each embodiment may be modified, or any of the components in each embodiment may be omitted. Furthermore, the embodiments are not limited to those shown in Embodiments 1 and 2, and various modifications are possible as needed. The procedures explained using flowcharts and the like may be modified as appropriate.

[0080] Various aspects of the present disclosure are summarized below as appendices.

[0081] (Appendix 1) An information processing device for realizing a chatbot used in a target organization, a document search unit that searches, as an internal search document group, for one or more documents corresponding to the target question input to the information processing device from an internal document database in which one or more internal documents related to the target organization are registered; an answer processing unit that generates an answer corresponding to the target question as an internal answer based on the internal search document group; an inquiry output unit that outputs a group of in-organization search inquiry destinations corresponding to the target question, the in-organization search inquiry destinations being composed of one or more inquiry destinations that are output together with the in-organization answer; An information processing device comprising:

[0082] (Appendix 2) The information processing device further comprises: a contact search unit that searches, based on the target question, for one or more contacts as the in-organization search contact group from an in-organization contact database in which contacts corresponding to documents registered in the in-organization document database are registered; 2. The information processing device according to claim 1, comprising:

[0083] (Appendix 3) 3. The information processing device according to claim 2, wherein the inquiry search unit searches the intra-organization search inquiry group based on the intra-organization search document group.

[0084] (Appendix 4) the document search unit searches for one or more documents corresponding to the target question as a group of externally searched documents from an external document database in which one or more external documents related to the target organization are registered; the answer processing unit generates an answer corresponding to the target question as an external answer based on the external search document group; the inquiry search unit searches, based on the target question, for one or more inquiry destinations output together with the external answer from an external inquiry destination database in which inquiry destinations corresponding to each document registered in the external document database are registered, as an external search inquiry destination group; 4. The information processing device according to claim 2, wherein the inquiry output unit outputs the group of external search inquiry destinations.

[0085] (Appendix 5) The information processing device according to claim 4, wherein the inquiry destination search unit searches the group of external search inquiry destinations based on the group of external search documents.

[0086] (Appendix 6) The information processing device according to claim 4 or 5, wherein the response processing unit generates the intra-organization response and the external-organization response by utilizing a generation AI (Artificial Intelligence). [Explanation of symbols]

[0087] 1 User, 2,202 Document group, 3,203 Inquiry related information, 10 Information processing device, 101 Document registration unit, 102,302 Document DB, 103 Inquiry registration unit, 104,304 Inquiry related DB, 105 Question processing unit, 106 Document search unit, 107 Search results, 108 Answer processing unit, 109 Inquiry search unit, 110 Inquiry, 111 Inquiry output unit, 11 Inquiry application, 12 Document import tool, 51 Processor, 52 Memory, 53 Auxiliary storage device, 54 Input / output IF, 55 Communication device, 58 Processing circuit, 59 Signal line, 90 Chatbot system.

Claims

1. An information processing device for realizing a chatbot used in a target organization, a document search unit that searches, as an internal search document group, for one or more documents corresponding to the target question input to the information processing device from an internal document database in which one or more internal documents related to the target organization are registered; an answer processing unit that generates an answer corresponding to the target question as an internal answer based on the internal search document group; an inquiry output unit that outputs a group of in-organization search inquiry destinations corresponding to the target question, the in-organization search inquiry destinations being output together with the in-organization answer; An information processing device comprising:

2. The information processing device further comprises: a contact search unit that searches, based on the target question, for one or more contacts as the in-organization search contact group from an in-organization contact database in which contacts corresponding to documents registered in the in-organization document database are registered; The information processing device according to claim 1 , comprising:

3. The information processing apparatus according to claim 2 , wherein the inquiry destination search unit searches the group of internal search inquiry destinations based on the group of internal search documents.

4. the document search unit searches for one or more documents corresponding to the target question from an external document database in which one or more external documents related to the target organization are registered as an external document group; the answer processing unit generates an answer corresponding to the target question as an external answer based on the external search document group; the inquiry search unit searches, based on the target question, for one or more inquiry destinations output together with the external answer from an external inquiry destination database in which inquiry destinations corresponding to each document registered in the external document database are registered, as an external search inquiry destination group; The information processing apparatus according to claim 2 or 3, wherein the inquiry destination output unit outputs the group of external search inquiry destinations.

5. The information processing apparatus according to claim 4 , wherein the inquiry destination search unit searches the group of external search inquiry destinations based on the group of external search documents.

6. The information processing device according to claim 4 , wherein the response processing unit generates the internal response and the external response by utilizing a generation AI (Artificial Intelligence).

7. An information processing executed by an information processing device that is a computer for realizing a chatbot used in a target organization, the information processing device searches for one or more documents corresponding to the target question input to the information processing device as an internal search document group from an internal document database in which one or more internal documents related to the target organization are registered; the information processing device generates an answer corresponding to the target question as an internal answer based on the internal search document group; The information processing method includes outputting a group of in-organization search inquiry destinations corresponding to the target question, the in-organization search inquiry destinations being one or more inquiry destinations output together with the in-organization answer.

8. An information processing program executed by an information processing device, which is a computer for realizing a chatbot used in a target organization, a document retrieval process for retrieving one or more documents corresponding to the target question input to the information processing device from an internal document database in which one or more internal documents related to the target organization are registered as an internal document group; an answering process for generating an answer corresponding to the target question as an internal answer based on the internal search document group; an inquiry output process for outputting a group of in-organization search inquiry destinations corresponding to the target question, the group including one or more inquiry destinations output together with the in-organization answer; An information processing program that causes the information processing device to execute the above.

Images