WO2021171381A1 - 情報処理装置、情報処理方法及び記憶媒体 - Google Patents

情報処理装置、情報処理方法及び記憶媒体 Download PDF

Info

Publication number
WO2021171381A1
WO2021171381A1 PCT/JP2020/007527 JP2020007527W WO2021171381A1 WO 2021171381 A1 WO2021171381 A1 WO 2021171381A1 JP 2020007527 W JP2020007527 W JP 2020007527W WO 2021171381 A1 WO2021171381 A1 WO 2021171381A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
response
registration
input
registrant
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2020/007527
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
賢二 永倉
騰箴 邱
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to PCT/JP2020/007527 priority Critical patent/WO2021171381A1/ja
Priority to JP2022502623A priority patent/JP7352847B2/ja
Publication of WO2021171381A1 publication Critical patent/WO2021171381A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/908—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content

Definitions

  • the present invention relates to an information processing device, an information processing method, and a storage medium.
  • Patent Document 1 and Patent Document 2 disclose an information processing device in which a computer automatically answers a question input by a user.
  • Patent Document 1 and Patent Document 2 In an information processing device that automatically answers as described in Patent Document 1 and Patent Document 2, it is necessary to prepare a database that stores a set of expected questions and answers to them. Therefore, it may be a problem that a large amount of man-hours are required to prepare the database.
  • An object of the present invention is to provide an information processing device, an information processing method, and a storage medium that can reduce the man-hours required for preparing a database.
  • the input information, the response information, the first setting information indicating the attribute of the registrant, and the input information or the response information are information unique to the attribute of the registrant.
  • a storage unit that stores a plurality of registration information including a second setting information indicating whether or not the information is present, an acquisition unit that acquires a response request from a user and an attribute of the response request, and a plurality of the registration information.
  • the first registration information in which the attribute of the response request and the attribute indicated by the first setting information match, and the second registration information indicating that the second setting information is not unique information.
  • an information processing apparatus includes a response generation unit that generates a response in response to the response request.
  • the input information, the response information, the first setting information indicating the attribute of the registrant, and the input information or the response information unique to the attribute of the registrant It is an information processing method executed by a computer including a storage unit that stores a plurality of registration information including a second setting information indicating whether or not the information processing is performed, and is a response request from a user and the response request.
  • the step of acquiring the attribute, the first registration information in which the attribute of the response request and the attribute indicated by the first setting information of the plurality of registration information match, and the second setting information are unique.
  • the information processing method is provided, which comprises a second registration information indicating that the information is not the information of the above, and a step of generating a response in response to the response request by referring to the second registration information.
  • the input information, the response information, the first setting information indicating the attribute of the registrant, and the input information or the response information unique to the attribute of the registrant A plurality of steps for acquiring a response request from a user and attributes of the response request in a computer having a storage unit for storing a plurality of registration information including a second setting information indicating whether or not the information is provided.
  • the registration information of the above the first registration information in which the attribute of the response request and the attribute indicated by the first setting information match, and the second setting information are not unique information.
  • a storage medium in which a program for executing an information processing method including a step of generating a response in response to the response request is stored is provided.
  • an information processing device an information processing method, and a storage medium capable of reducing the man-hours required for preparing a database are provided.
  • the information processing system of the present embodiment is a system for automatically responding to a question from a user by referring to a database registered in advance.
  • the information processing system of the present embodiment can be a chatbot that simulates dialogue in natural language.
  • the information processing system in the following explanation shall be a chatbot for answering questions asked by residents or local government officials in the local government. Since many of the questions asked by local governments are standard, replacing manual answers with chatbots has a great effect on improving work efficiency.
  • the application to which the information processing system can be applied is not particularly limited, and it can also be applied to, for example, a chatbot that answers questions about business procedures in a private company.
  • FIG. 1 is a schematic view showing the overall configuration of the information processing system according to the present embodiment.
  • the information processing system has a server 1 and a plurality of terminals 2.
  • the server 1 and the plurality of terminals 2 are connected to each other so as to be able to communicate with each other via the network NW.
  • the server 1 is an ASP (Application Service Provider) server that provides the chatbot function of the present embodiment to a plurality of terminals 2 via the network NW. In this way, the server 1 functions as an information processing device that realizes the function of the chatbot.
  • ASP Application Service Provider
  • the network NW can be various networks such as LAN (Local Area Network) and WAN (Wide Area Network).
  • the network NW may be, for example, the Internet or LGWAN (Local Government Wide Area Network), which is a closed network for Japanese government agencies.
  • the plurality of terminals 2 are computers used by chatbot users or registrants of data necessary for constructing chatbots.
  • the terminal 2 is, for example, a computer for staff provided at a local government office.
  • FIG. 2 is a block diagram showing a hardware configuration example of the server 1.
  • the server 1 includes a CPU (Central Processing Unit) 101, a RAM (Random Access Memory) 102, a ROM (Read Only Memory) 103, and an HDD (Hard Disk Drive) 104. Further, the server 1 includes a communication I / F (Interface) 105, an input device 106, and an output device 107. Each part of the server 1 is connected to each other via a bus, wiring, a driving device, etc. (not shown).
  • each part constituting the server 1 is shown as an integrated device, but some of these functions may be provided by an external device.
  • the input device 106 and the output device 107 may be external devices different from the parts constituting the functions of the computer including the CPU 101 and the like.
  • the CPU 101 is a processor that performs predetermined calculations according to programs stored in the ROM 103, HDD 104, etc., and also has a function of controlling each part of the server 1.
  • the RAM 102 is composed of a volatile storage medium and provides a temporary memory area necessary for the operation of the CPU 101.
  • the ROM 103 is composed of a non-volatile storage medium and stores necessary information such as a program used for the operation of the server 1.
  • the HDD 104 is a storage device composed of a non-volatile storage medium, which stores a database, a program for operating the server 1, and the like.
  • Communication I / F105 is a communication interface based on standards such as Ethernet (registered trademark) and Wi-Fi (registered trademark).
  • the communication I / F 105 is a module for communicating with other devices such as the terminal 2.
  • the input device 106 is a keyboard, a pointing device, or the like, and is used by the administrator of the server 1 to operate the server 1.
  • pointing devices include mice, trackballs, touch panels, pen tablets and the like.
  • the output device 107 is, for example, a display device.
  • the display device is a liquid crystal display, an OLED (Organic Light Emitting Diode) display, or the like, and is used for displaying information, a GUI (Graphical User Interface) for operation input, or the like.
  • the input device 106 and the output device 107 may be integrally formed as a touch panel.
  • the hardware configuration of the server 1 is an example, and devices other than these may be added, and some devices may not be provided. Further, some devices may be replaced with another device having the same function. Further, some functions of the present embodiment may be provided by other devices via a network, or the functions of the present embodiment may be distributed and realized by a plurality of devices.
  • the HDD 104 may be replaced with an SSD (Solid State Drive) using a semiconductor memory. Further, the HDD 104 may be replaced with cloud storage. In this way, the hardware configuration of the server 1 can be changed as appropriate.
  • the terminal 2 is a computer such as a desktop PC (Personal Computer), a laptop PC, or a tablet PC. Since the hardware configuration of the terminal 2 is the same as that shown in FIG. 2, the description thereof will be omitted.
  • the terminal 2 has at least a display for displaying a registration screen, a chat screen, etc., a keyboard for inputting characters, and a pointing device for operating a GUI such as a combo box.
  • these are not essential.
  • the terminal 2 is a smart speaker that inputs / outputs by voice, these devices are not indispensable.
  • FIG. 3 is a functional block diagram of the server 1 according to this embodiment.
  • the server 1 includes a registration unit 111, an acquisition unit 112, a response generation unit 113, an evaluation reception unit 114, a database output unit 115, and a storage unit 116.
  • the CPU 101 performs a predetermined arithmetic process by loading the program stored in the ROM 103, the HDD 104, etc. into the RAM 102 and executing the program. Further, the CPU 101 controls each part of the server 1 such as the communication I / F 105 based on the program. As a result, the CPU 101 realizes the functions of the registration unit 111, the acquisition unit 112, the response generation unit 113, the evaluation reception unit 114, the database output unit 115, and the storage unit 116. The specific contents of the processing performed by each functional block will be described later.
  • FIG. 4 is a flowchart showing an outline of the registration process performed in the information processing system according to the present embodiment.
  • the server 1 executes the registration process of FIG.
  • An example of the registration process when newly registering a QA will be described below, but the process when updating an existing QA is almost the same.
  • step S101 the registration unit 111 displays the QA registration screen on the display of the terminal 2 that has requested registration.
  • the QA registration screen is a format for the registrant to input information such as questions and answers.
  • FIG. 5 is an example of a QA registration screen displayed during the registration process according to the present embodiment.
  • the QA registration screen 120 has a text display area 121, text boxes 122, 123, 124, 129 and combo boxes 125, 126, 127, 128.
  • the text display area 121 labeled with "QAID” is an area for displaying a QA identification number (ID: Identifier).
  • the QAID can be, for example, a number that is automatically numbered at the time of registration.
  • the text display area 121 in FIG. 5 is blank because the QAID has not been assigned.
  • the QAID given at the time of new registration is displayed in the text display area 121.
  • the text box 122 labeled "Question Summary” is a column in which the registrant fills in a summary of the question to be registered in a natural sentence.
  • a sentence such as "How many days do I have to submit the move-in notification after moving?" Is entered. Since the description in this column is not used for the search during the answer processing, you may change the expression of the question text so that the registrant can easily check the outline of the question later, and leave the question text as it is. You may fill it out.
  • the text box 123 labeled "Question" is a field in which the registrant fills in the question to be registered in a natural sentence.
  • a sentence assuming an actual question to be entered such as "When should I contact the government office after moving in?" Is entered. Since there can be multiple expressions for the same question, it is possible to enter multiple questions in the text box 123.
  • the text box 124 labeled "answer” is a field in which the registrant enters the answer to the question entered in the text box 122 in a natural sentence.
  • a sentence such as "Please submit the move-in notification within 14 days after moving" is entered.
  • the combo box 125 labeled "Registered Organization” is a field in which the registrant selects and inputs the name of the registrant's affiliated organization from the candidates.
  • the combo box 125 is shaded because the registered organization is set in advance so as to be automatically acquired and no input is required.
  • the registrant may manually select the name of the organization by operating the combo box 125. For example, if the registrant is an employee of a municipality called AAA City, "AAA City" is selected.
  • the registrant selects whether or not the QA to be input is unique to the registered organization from “common” or "unique” and inputs it. It is a column to do. The registrant selects "unique” if the QA to be entered is unique to the registered organization. Further, the registrant selects "common” when the QA to be input is not unique to the registered organization, that is, when it is common to a plurality of registered organizations.
  • the registrant can tell whether the QA to be entered is for the inside of the agency or outside the agency. It is a field to select and enter from "outside the agency”. The registrant selects "inside the agency” if the QA to be entered is for the agency. In addition, the registrant selects "outside the agency” when the QA to be entered is for outside the agency.
  • the combo box 128 labeled with "type” is a field in which the registrant selects the type of QA content to be input from the candidates and inputs it. For example, if the QA relates to the period for submitting a move-in notification, "resident registration" is selected.
  • the text box 129 labeled "Remarks" is a field in which the registrant fills in the QA remarks in natural text. For example, when it is necessary to record the update history of QA, the update date and time can be entered in the text box 129.
  • step S102 the registration unit 111 acquires the information input on the QA registration screen by the registrant.
  • the registration unit 111 refers to the login ID when the registrant logs in to the information processing system.
  • This login ID is associated with registrant information such as the registrant's name and affiliation.
  • the registration unit 111 can automatically acquire the organization to which the registrant belongs as a registered organization by referring to the login ID. In this method, the time required for inputting is reduced as compared with the case where the registrant manually inputs the group name.
  • step S104 the registration unit 111 associates the information input by the registrant with the registration organization, attaches an automatically numbered QAID to these, and stores the information in the database (DB) of the storage unit 116.
  • DB database
  • FIG. 6 is a table showing an example of a database according to this embodiment.
  • FIG. 6 shows an example of a database constructed in the storage unit 116 by repeating the registration process of FIG. 5 a plurality of times.
  • "QAID”, "question summary”, “question”, “answer”, "registered organization”, “common / unique”, “inside the agency /” Information on each item of "outside the agency” and "type” is stored in association with each other.
  • Each item corresponds to the label in the QA registration screen 120 of FIG.
  • a set of information with one QAID is sometimes called registration information.
  • the "question” item may include questions that are not questions from the user to the chatbot. For example, greetings, thanks, etc. from the user to the chatbot (for example, "hello", "thank you") may be included.
  • the information in the "question” item is more commonly referred to as input information.
  • the item of "answer” may include items that are not answers to the question. For example, a response (for example, “hello", “welcome") from the user to a chatbot greeting, thank-you, etc. may be included.
  • the information in the "answer” section is more commonly referred to as response information.
  • the item of "registered organization” may include information other than the name of the municipality to which the registrant belongs. For example, information such as the department name to which the registrant belongs, the job title of the registrant, and the job title of the registrant may be included.
  • the information in the "registered organization” item is more generally referred to as the first setting information indicating the attributes of the registrant.
  • the "common / unique" item indicates whether or not the input information or response information is unique to the registrant's attribute, as described above.
  • the information of the "common / unique” item is more generally referred to as the second setting information.
  • the item "inside / outside the agency” indicates whether or not the input information or response information is for the organization to which the registrant belongs, as described above.
  • the information in the "inside / outside office” item is more generally referred to as the third setting information.
  • the item of "type” indicates the type of input information or response information as described above.
  • the information of the item of "type” is more generally referred to as the fourth setting information.
  • FIG. 7 is a flowchart showing an outline of response processing performed in the information processing system according to the present embodiment.
  • the server 1 executes the response process shown in FIG. 7.
  • step S201 the acquisition unit 112 displays the chat screen on the display of the terminal 2 that has requested the activation of the chatbot.
  • the chat screen is a screen for a user to input a question and a chatbot to answer the question to chat.
  • FIG. 8 is an example of a chat screen displayed during the response processing according to the present embodiment.
  • the chat screen 130 has balloons 131, 132, 133, 134, a text box 135 and buttons 136, 137, 138, 139.
  • all the balloons 131, 132, 133, and 134 are shown, but in the actual chat, they are displayed in order from the top according to the progress of the chat.
  • the balloon 131 is first displayed.
  • the message "Please enter your question” is written in the balloon 131.
  • the user inputs a question text in the text box 135 according to this message.
  • the text entered in the text box 135 is sent to the server 1.
  • the balloon 132 is displayed.
  • the balloon 132 contains the same message as the one entered by the user, "By when do I have to contact the government office after moving in?". By displaying the balloon 132, the user can recognize that the input message has been correctly transmitted.
  • step S202 the acquisition unit 112 acquires the question text input by the user in the text box 135.
  • the question text entered by the user may not be a question such as a greeting or a thank-you question. This question is more commonly referred to as a response request.
  • the acquisition unit 112 refers to the login ID when the user logs in to the information processing system.
  • the acquisition unit 112 automatically acquires the affiliation of the user. For example, if the user is an employee of a municipality called AAA City, "AAA City" is automatically acquired as the user's affiliation.
  • the user may manually enter the affiliation, but by setting the affiliation to be automatically acquired as in this example, the time required for input is reduced as compared with the case of manually inputting.
  • the information acquired here may have attributes other than the name of the municipality to which the user belongs. For example, it may be an attribute related to a response request such as the department name to which the user belongs, the job title of the user, the job title of the user, and the like.
  • the response generation unit 113 includes the first registration information corresponding to the QAID in which the user's affiliation and the registered organization match, and the second registration information corresponding to the QAID in which the "common / unique" item is "common". Is specified as the search range.
  • the search range In the example of FIG. 6, when the affiliation of the user is AAA city, the QA having QAIDs 1, 2 and 3 is included in the search range, and the QA having QAID 4 is not included in the search range.
  • step S205 the response generation unit 113 searches the search range set in step S204 for the answer corresponding to the input question text.
  • the response generation unit 113 compares the text data of the input question text with the text data of the text of the "question” item in the search range in the database. Based on this comparison result, the response generation unit 113 outputs the text of the "answer" item associated with the "question” item that is most similar to the input question text.
  • This sentence comparison can be made, for example, by a natural language analysis algorithm constructed by machine learning. Alternatively, sentences may be compared based on the degree of matching of keywords extracted from sentences by morphological analysis or the like. By using these sentence comparison algorithms, even if the question text does not exactly match the question stored in the database, it is possible to search for something close to the question text.
  • the balloon 133 is displayed on the chat screen 130.
  • the search is completed, the balloon 133 is displayed on the chat screen 130.
  • the answer corresponding to this question "Please submit the move-in notification within 14 days after moving.” Is described in the balloon 133.
  • step S205 When the user re-enters the question text, the process of step S205 is performed again.
  • the evaluation reception unit 114 displays the balloon 134 on the chat screen 130.
  • the balloon 134 contains the message "Did this answer help you? Be sure to choose one.” Also, among the balloons 134, there are also a button 137 labeled "Yes”, a button 138 labeled "No", and a button 139 labeled "I want to see another answer”. Is displayed. These are standard responses for receiving a response from a user after presenting an answer.
  • step S207 the evaluation receiving unit 114 acquires the evaluation result corresponding to the pressed button in association with the searched QAID or the like. This evaluation result can be confirmed by the registrant connecting to the server 1 from the terminal 2 and referring to the data management screen.
  • FIG. 9 is an example of a data management screen according to this embodiment.
  • the data management screen 140 shown in FIG. 9 is associated with information labeled "question ID”, “date and time”, “search wording”, “selection QAID”, “answer”, and “result”. It is displayed in tabular format.
  • the "question ID” is a number automatically assigned to the question text entered by the user.
  • the "date and time” is the time when the question text is input by the user and the button 136 is pressed.
  • the "search wording” is a question sentence input by the user.
  • the "selected QAID” is a QAID searched by the response generation unit 113 and used for the answer.
  • "Answer” is an answer sentence corresponding to the selected QAID.
  • “Result” is the evaluation result input by the user.
  • a “Like” is entered in the “Result” column.
  • button 138 labeled “No” is pressed, "Bad” is written in the “Result” column.
  • “Selection QAID” and “Answer” may be blank. This means that the answer corresponding to the question text entered by the user could not be found. In this case as well, "bad” is described in the “result” column.
  • the registrant can confirm the evaluation from the user for the QA registered by himself / herself by referring to this data management screen 140. If this evaluation is bad, the registrant can improve the quality of the response by modifying the contents of the QA as appropriate.
  • step S205 If the user presses the button 139 labeled "I want to see another answer" in step S206, the process of step S205 is performed again. At this time, the response generation unit 113 searches for an answer different from the answer obtained in the previous search. As a result, another answer is displayed on the chat screen 130. In this case, "bad” may be described in the "result" column of the data management screen 140, or the result of re-searching may be described.
  • step S207 the process proceeds to step S202 and accepts the next question.
  • a balloon containing a message such as "Please enter the next question” may be displayed in order to prompt the input of the next question.
  • the server 1 of the present embodiment can search according to the search range according to the affiliation of the user and display the answer, so that the database can be shared by a plurality of groups.
  • the server 1 of the present embodiment has a function of outputting a database for a specific group.
  • FIG. 10 is a flowchart showing an outline of database output processing performed in the information processing system according to the present embodiment.
  • the server 1 executes the database output process of FIG.
  • step S301 the database output unit 115 acquires the output target group.
  • the output target group is the target of using the database.
  • the output target organization is input, for example, when the administrator requests the output of the database.
  • step S302 the database output unit 115 outputs the first registration information corresponding to the QAID in which the output target group and the registered group match, and the second registration information corresponding to the QAID in which the "common / unique" item is "common”. Specify as an output range.
  • step S303 the database output unit 115 outputs the database from which the QA of the output range is extracted and stores it in the storage unit 116.
  • the database output unit 115 By copying the output database from the server 1 to another device, it can be used to generate a chatbot in a system independent of the information processing system of the present embodiment.
  • FIG. 11 is a table for explaining the output range of the database according to the present embodiment.
  • the table on the left side of FIG. 11 shows the database information stored in the storage unit 116 of the server 1.
  • the table on the right side of FIG. 11 shows the database information extracted by the database output unit 115. It is assumed that the output target group at the time of extraction is "EEE City".
  • the "common / unique" item of the QA having QAIDs 11, 12 and 13 is “common” and is therefore included in the output range. Further, since the item of "registered group” of QA having a QAID of 15 is "EEE city” that matches the output target group, it is included in the output range. In addition, the item of "registered group” of QA whose QAIDs are 14 and 16 does not match the output target group, so it is not included in the output range.
  • the QA is associated with the information of the registered organization and the information indicating whether or not it is unique to the registered organization.
  • the QA is associated with the information of the registered organization and the information indicating whether or not it is unique to the registered organization.
  • information common to registered organizations can be shared by a plurality of registered organizations, so that the man-hours required for database preparation are reduced as compared with the case where a database is prepared for each of a plurality of registered organizations. Therefore, according to the present embodiment, there is provided an information processing apparatus capable of reducing the man-hours required for preparing the database.
  • the search can be performed by excluding QAs that are not related to the user, so the answer is irrelevant to the user. Can be reduced.
  • a chatbot of a method in which a registrant prepares a QA database in advance is adopted.
  • this method compared to a chatbot that learns from the user's response, it is possible to perform a chat of a certain level of quality from the initial stage of startup. Therefore, the chatbot of this embodiment is required to have a highly accurate answer. Suitable for local governments.
  • the device or system described in the above-described embodiment can also be configured as in the following second embodiment.
  • FIG. 12 is a functional block diagram of the information processing device 3 according to the second embodiment.
  • the information processing device 3 includes a storage unit 301, an acquisition unit 302, and a response generation unit 303.
  • the storage unit 301 indicates the input information, the response information, the first setting information indicating the attribute of the registrant, and the second setting information indicating whether or not the input information or the response information is information unique to the attribute of the registrant.
  • the acquisition unit 302 acquires the response request from the user and the attribute of the response request.
  • the response generation unit 303 determines that the first registration information in which the attribute of the response request and the attribute indicated by the first setting information match among the plurality of registration information and the second setting information are not unique information. By referring to the second registration information shown, a response corresponding to the response request is generated.
  • the information processing device 3 capable of appropriately managing the collation accuracy is provided.
  • step S204 in the response processing of FIG. 7 "inside the agency” or “inside the agency” in the “inside / outside the agency” item, depending on whether the user is a person inside the agency or a person outside the agency. Only one of “outside the agency” may be specified as the search range. In addition, a part of the "type” item may be specified as the search range according to the type of information requested by the user. As a result, the search range can be further narrowed down and the search accuracy can be improved. Information on whether the user is a person inside the agency or outside the agency, or information on the type of information requested by the user may be entered by the user. It may be automatically acquired from the login ID.
  • step S302 in the response processing of FIG. 10 one of "inside the agency” and “outside the agency” in the "inside / outside the agency” item, depending on the attribute of the chatbot user whose database is used. Only may be specified as the output range. Further, depending on the use of the chatbot in which the database is used, a part of the "type” items may be specified as the output range. With these, the amount of QA contained in the database can be further narrowed down.
  • the chatbot user attributes and usage information are input by the administrator who requests the database output.
  • chatbots for answering questions asked to a local government
  • the present invention can be applied to other uses.
  • it is also applicable to corporate chatbots for answering questions asked by corporate employees or business partners.
  • the first embodiment Municipal chatbots can be replaced with corporate chatbots.
  • a processing method in which a program for operating the configuration of the embodiment is recorded in a storage medium so as to realize the functions of the above-described embodiment, the program recorded in the storage medium is read out as a code, and the program is executed in a computer is also described in each embodiment. Included in the category. That is, a computer-readable storage medium is also included in the scope of each embodiment. Moreover, not only the storage medium in which the above-mentioned program is recorded but also the program itself is included in each embodiment. Further, one or more components included in the above-described embodiment are circuits such as an ASIC (Application Specific Integrated Circuit) and an FPGA (Field Programmable Gate Array) configured to realize the functions of the components. There may be.
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • the storage medium for example, a floppy (registered trademark) disk, a hard disk, an optical disk, an optical magnetic disk, a CD (Compact Disk) -ROM, a magnetic tape, a non-volatile memory card, or a ROM can be used.
  • the program recorded on the storage medium is not limited to the one that executes the processing by itself, but the one that operates on the OS (Operating System) and executes the processing in cooperation with the functions of other software and the expansion board. Is also included in the category of each embodiment.
  • SaaS Software as a Service
  • (Appendix 1) Input information, response information, first setting information indicating the attribute of the registrant, and second setting information indicating whether or not the input information or the response information is information unique to the attribute of the registrant.
  • a storage unit that stores a plurality of registration information including An acquisition unit that acquires the response request from the user and the attributes of the response request, It is shown that the first registration information in which the attribute of the response request and the attribute indicated by the first setting information match among the plurality of registration information and the second setting information are not unique information.
  • a response generation unit that generates a response in response to the response request by referring to the second registration information that is provided.
  • Information processing device is provided.
  • Appendix 2 Further provided with a registration unit that accepts the input of the registration information by the registrant.
  • the registration unit accepts the input of the second setting information by causing the registrant to input whether or not the response information is information unique to the attribute of the registrant.
  • the information processing device according to Appendix 1.
  • the registration unit acquires the first setting information by referring to the login ID (Identifier) of the registrant.
  • the information processing device according to Appendix 2.
  • the acquisition unit acquires the attribute of the response request by referring to the login ID of the user.
  • the information processing device according to any one of Supplementary note 1 to 3.
  • An evaluation reception unit that accepts an input for evaluation of the response generated by the response generation unit is further provided.
  • the information processing device according to any one of Supplementary note 1 to 4.
  • the response generation unit generates a response by selecting the response information corresponding to the input information based on the comparison result between the text input by the user and the text of the input information.
  • the information processing device according to any one of Supplementary note 1 to 6.
  • the registration information further includes a third setting information indicating whether or not the input information or the response information is for the organization to which the registrant belongs.
  • the information processing device according to any one of Supplementary note 1 to 7.
  • the registration information further includes a fourth setting information indicating the type of the input information or the response information.
  • the information processing device according to any one of Appendix 1 to 8.
  • (Appendix 11) Input information, response information, first setting information indicating the attributes of the registrant, and second setting information indicating whether or not the input information or the response information is information unique to the attributes of the registrant.
  • the step of generating a response in response to the response request and Information processing method.
  • (Appendix 12) Input information, response information, first setting information indicating the attributes of the registrant, and second setting information indicating whether or not the input information or the response information is information unique to the attributes of the registrant.
  • a computer equipped with a storage unit that stores a plurality of registration information including Steps to acquire the response request from the user and the attributes of the response request, It is shown that the first registration information in which the attribute of the response request and the attribute indicated by the first setting information match among the plurality of registration information and the second setting information are not unique information.
  • the step of generating a response in response to the response request and A storage medium in which a program for executing an information processing method is stored.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Library & Information Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
PCT/JP2020/007527 2020-02-25 2020-02-25 情報処理装置、情報処理方法及び記憶媒体 Ceased WO2021171381A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2020/007527 WO2021171381A1 (ja) 2020-02-25 2020-02-25 情報処理装置、情報処理方法及び記憶媒体
JP2022502623A JP7352847B2 (ja) 2020-02-25 2020-02-25 情報処理装置、情報処理方法及び記憶媒体

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/007527 WO2021171381A1 (ja) 2020-02-25 2020-02-25 情報処理装置、情報処理方法及び記憶媒体

Publications (1)

Publication Number Publication Date
WO2021171381A1 true WO2021171381A1 (ja) 2021-09-02

Family

ID=77489993

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/007527 Ceased WO2021171381A1 (ja) 2020-02-25 2020-02-25 情報処理装置、情報処理方法及び記憶媒体

Country Status (2)

Country Link
JP (1) JP7352847B2 (https=)
WO (1) WO2021171381A1 (https=)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7714019B2 (ja) * 2023-12-08 2025-07-28 ソフトバンク株式会社 情報処理システム、情報処理装置の制御方法、及び情報処理装置の制御プログラム

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004086549A (ja) * 2002-08-27 2004-03-18 Just Syst Corp Ｆａｑ検索システム、方法及びプログラム
JP2013250931A (ja) * 2012-06-04 2013-12-12 Canon Inc 情報取得システム、プログラム、サーバ、情報取得方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005348290A (ja) 2004-06-07 2005-12-15 Matsushita Electric Ind Co Ltd セキュリティ機能付情報処理装置
JP2016085638A (ja) 2014-10-27 2016-05-19 キヤノン株式会社 サーバー装置、端末装置、システム、情報処理方法及びプログラム

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004086549A (ja) * 2002-08-27 2004-03-18 Just Syst Corp Ｆａｑ検索システム、方法及びプログラム
JP2013250931A (ja) * 2012-06-04 2013-12-12 Canon Inc 情報取得システム、プログラム、サーバ、情報取得方法

Also Published As

Publication number Publication date
JP7352847B2 (ja) 2023-09-29
JPWO2021171381A1 (https=) 2021-09-02

Similar Documents

Publication Publication Date Title
CN112925898B (zh) 基于人工智能的问答方法、装置、服务器及存储介质
EP3654211A1 (en) Automated response server device, terminal device, response system, response method, and program
JP6438443B2 (ja) 対話基盤の検索サポートシステムおよびその方法
US9262399B2 (en) Electronic device, character conversion method, and storage medium
JP7579555B1 (ja) プログラム、方法、情報処理装置、システム
JP2025068567A (ja) プログラム、方法、情報処理装置、システム
JP2012248161A (ja) 対話型検索システム及びプログラム、並びに、対話シナリオ生成システム及びプログラム
JP2025060386A (ja) プログラム、方法、情報処理装置、システム
JP2021108033A (ja) 質問回答表示サーバ、質問回答表示方法及び質問回答表示プログラム
JP7525127B1 (ja) プログラム、方法、情報処理装置、システム
CN116701583B (zh) 一种问答方法、装置、计算机设备及存储介质
JP7352847B2 (ja) 情報処理装置、情報処理方法及び記憶媒体
JP7688440B2 (ja) プログラム、方法、情報処理装置、システム
US12524401B2 (en) Reverse engineered retokenization for translation of machine interpretable languages
JP7730219B1 (ja) 生成ａｉによる回答の精度を高める処理を行う方法、プログラムおよび情報処理装置
JP6973132B2 (ja) 情報処理装置、情報処理方法および情報処理プログラム
JP6739361B2 (ja) 情報提供装置、情報提供方法、およびプログラム
JP7733368B1 (ja) 情報処理装置、情報処理方法及びプログラム
JP7749618B2 (ja) プログラム、情報処理装置、製造方法、情報処理方法
JP7698926B1 (ja) プログラム、方法、情報処理装置、システム
JP7504513B1 (ja) プログラム及び情報処理装置
JP2025168844A (ja) 情報処理システム、情報処理方法、及びプログラム
JP2012174224A (ja) データ入力支援装置、及びデータ入力支援方法
Resurreccion et al. Lab 2–International Assistant Product Specification
KR20250096055A (ko) 생성형 인공지능 기반 다국어 매뉴얼 동기화 장치, 이를 포함하는 동기화 시스템 및 동기화 방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20921412

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022502623

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20921412

Country of ref document: EP

Kind code of ref document: A1