Information processing system, information processing method, and program

Abstract

To provide a mechanism to obtain more appropriate responses in continuous dialogue-type question-response processing.SOLUTION: An information processing system includes question acquisition means for acquiring a question, retrieval means for retrieving information using a word specified from the question acquired by the question acquisition means, and output means for outputting a response generated using the information retrieved by the retrieval means, and the acquired question, wherein when a question is further acquired after output of the response by the output means, the retrieval means retrieves information, using a word satisfying a predetermined condition, and a word specified from a newly acquired question, among words specified from the acquired questions.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] In recent years, an increasing number of companies have adopted full-text search systems such as enterprise search to find necessary information from vast amounts of stored digital documents. Furthermore, the introduction of question-answering systems, which allow users to search for and answer questions interactively, has made it easier for them to find the information they need.

[0003] Patent Document 1 discloses a method for determining a set of search terms and a question type from an input question sentence, and then generating an answer using evidence information obtained by searching a set of documents that serve as a knowledge source according to the determined set of search terms and a question type.

[0004] Patent Document 2 discloses a method for managing past answers to questions and acquired basis information, and when a next question is asked, providing an answer while taking into consideration the past answers to questions and the basis information. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2002-132811 [Patent Document 2] Japanese Patent Application Publication No. 2017-037372 DISCLOSURE OF THE INVENTION [Problem to be solved by the invention]

[0006] However, Patent Document 1 has a problem in that it cannot answer questions in a continuous dialogue. For example, if the question "What is the address of the Osaka office?" can be answered and the next question is "Where is the reception desk?", the search term will be only "reception desk", and the information from which the answer is generated cannot be limited to "Osaka office."

[0007] Patent Document 2 is capable of handling continuous dialogue, but it requires continuous management of supporting documents (search results) related to "Osaka office + address" and "reception," and the amount of information to be managed becomes enormous, which poses the problem of inefficiency in storage space and subsequent processing.

[0008] Therefore, it is desirable to realize a question-answering system that allows continuous dialogue and efficient management and processing of memory areas.

[0009] Therefore, an object of the present invention is to provide a mechanism for obtaining more appropriate answers in continuous interactive question-answering processing. [Means for solving the problem]

[0010] The present invention comprises a question acquisition means for acquiring a question, a search means for performing an information search using words identified from the question acquired by the question acquisition means, and an output means for outputting an answer generated using the information searched for by the search means and the acquired question, wherein when a further question is acquired after the output means has output the answer, the search means performs an information search using words that satisfy predetermined conditions from among the words identified from the questions acquired so far and words identified from the newly acquired question. [Effects of the Invention]

[0011] According to the present invention, it is possible to provide a mechanism for obtaining more appropriate answers in a continuous interactive question-answering process. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating an example of a system configuration of a question answering device. [Figure 2] FIG. 1 is a diagram illustrating an example of the hardware configuration of a question answering device and a user terminal. [Figure 3] FIG. 1 is a diagram illustrating an example of a functional configuration of a question answering device. [Figure 4]Flowchart showing an example of question answering processing [Figure 5] A diagram showing an example of the configuration of a domain knowledge storage area. [Figure 6] FIG. 10 is a diagram showing an example of a subject term extraction process. [Figure 7] FIG. 10 is a diagram showing an example of a domain knowledge storage table. [Figure 8] FIG. 10 is a diagram showing an overview of an example of a response sentence generation process. [Figure 9] FIG. 10 is a diagram showing the state of the temporary area in an example of thematic term extraction processing. [Figure 10] Figure showing the tabulation and evaluation results for an example of thematic term extraction processing [Figure 11] A diagram showing an example of a chatbot screen displayed on a user device. [Figure 12] FIG. 10 is a diagram showing an overview of an example of a response sentence generation process according to the second embodiment; [Figure 13] Conceptual diagram of the process of the present invention DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0014] FIG. 1 is a diagram showing an example of a system configuration of a question answering device according to an embodiment of the present invention.

[0015] As shown in FIG. 1, the question answering apparatus 100 is connected to a user terminal 110 via a network 120 .

[0016] The question answering device 100 presents an answer to a question received from the user terminal 110 and a document that is the basis for the answer.

[0017] The user terminal 110 sends a question entered by a user to the question answering apparatus 100, and displays the answer and evidence information (including information such as the title of the document in which the evidence information is written) returned by the question answering apparatus 100. Specific examples of the user terminal 110 include, but are not limited to, personal computers (such as notebook PCs and desktop PCs), tablet terminals, and smartphones. The configurations of the various terminals or devices connected to the network 120 in FIG. 1 are merely examples, and it goes without saying that there are various configuration examples depending on the application and purpose.

[0018] FIG. 2 is a block diagram showing an example of the hardware configuration of the question answering apparatus 100 and the user terminal 110 according to the embodiment of the present invention.

[0019] As shown in FIG. 2, the information processing device includes a CPU (Central Processing Unit) 201, a RAM (Random Access Memory) 202, a ROM (Read Only Memory) 203, an input controller 205, a video controller 206, a memory controller 207, and a communication I / F controller 208 connected via a system bus 204.

[0020] The CPU 201 comprehensively controls each device and controller connected to the system bus 204 .

[0021] The RAM 202 functions as a main memory, a work area, etc. for the CPU 201. The CPU 201 loads programs and the like required for executing processing from the ROM 203 or the external memory 211 into the RAM 202, and executes the loaded programs to realize various operations.

[0022] ROM 203 or external memory 211 stores the BIOS (Basic Input / Output System) and OS (Operating System), which are control programs executed by CPU 201, computer-readable and executable programs for realizing this information processing method, and various necessary data (including data tables).

[0023] The input controller 205 controls input from an input device such as a keyboard 209 or a pointing device such as a mouse (not shown). If the input device is a touch panel, the user can issue various instructions by pressing (touching with a finger or the like) icons, cursors, or buttons displayed on the touch panel.

[0024] The touch panel may also be a touch panel capable of detecting positions touched by multiple fingers, such as a multi-touch screen.

[0025] The video controller 206 controls the display on an external output device such as a display 210. The display also includes the display of a notebook computer integrated into the main body. Note that the external output device is not limited to a display, and may be, for example, a projector. In addition, for devices capable of receiving the above-mentioned touch operation, an input device is also provided.

[0026] The video controller 206 can control a video memory (VRAM) for display control, and can use part of the RAM 202 as a video memory area, or can provide a separate dedicated video memory.

[0027] The memory controller 207 controls access to the external memory 211. The external memory may be an external storage device (hard disk) that stores a boot program, various applications, font data, user files, edited files, and various data, a flexible disk (FD), or a CompactFlash (registered trademark) memory connected to a PCMCIA card slot via an adapter.

[0028] The communication I / F controller 208 connects and communicates with external devices via a network, and executes communication control processing on the network. For example, communication using TCP / IP, telephone lines such as ISDN, and 3G lines for mobile phones are possible.

[0029] The CPU 201 enables display on the display 210 by, for example, executing a process of expanding (rasterizing) an outline font into a display information area in the RAM 202. The CPU 201 also enables user instructions using a mouse cursor (not shown) or the like on the display 210.

[0030] 3 is a diagram showing an example of the functional configuration of the question answering apparatus 100 and the user terminal 110. The functions of each functional unit will be explained in the description of the flowcharts in FIG.

[0031] First, an overview of the processing of the present invention will be explained using FIG. 13. In this invention, assume a scenario in which an employee searches for information (documents) on a portal site for employees. For example, a user enters the first question, "What is the address of the Osaka office?" into a question input form on the site. Search terms are extracted from the user's question, and for this question, for example, "Osaka," "office," and "address" are extracted. The extracted search terms are used to search domain knowledge (information on the employee site (such as web page information and posted document files) that serves as the basis for generating an answer). The searched domain knowledge and a prompt containing the user's question are provided to the generation AI, which then creates an answer. The AI ​​then obtains the created answer and the basis information referenced in creating the answer, and notifies the user of the obtained information. This allows the user to efficiently collect information on the site. Furthermore, the AI ​​extracts topic words (words central to the conversation, such as "Osaka" and "address" in this example) from the user's question, answer, and domain knowledge, and then completes the processing for the first question. Next, let's assume that the user asks the second question, for example, "Where is the receptionist?" In the second question, in addition to the search term "receptionist" extracted from the question sentence, the domain knowledge is searched including the subject terms "Osaka" and "address" obtained in the first question. The subsequent processing is the same as for the first question. By searching including these subject terms, the answer to the question in the ongoing dialogue is realized. Details of these processes will be described later in Figures 4 to 12.

[0032] (First embodiment) Next, the process executed by the question and answer processing unit 302 in the first embodiment of the present invention will be described with reference to the flowchart in FIG.

[0033] The flowchart in Figure 4 is a process in which the CPU 201 of the question answering device 100 reads and executes a predetermined control program, and is a flowchart showing the process in which the question answering processing unit 302 generates an answer sentence to a question sentence in response to a request from the dialogue management processing unit 301.

[0034] The dialogue management processing unit 301 realizes dialogue (questions and answers) with the user by repeating the processing of the flowchart in FIG.

[0035] The dialogue management processing unit 301 manages the history of dialogues (question sentences and answer sentences) by associating the question sentence with the domain knowledge acquired in step S405 (described later), the answer sentence generated in step S406, and the subject term generated in step S407. The number of dialogues to be managed is not particularly specified, and in this embodiment, it is sufficient to have the immediately preceding dialogue.

[0036] In step S401, the question and answering processor 302 receives the question sentence entered by the user and the list of previous themes from the dialogue management processor 301. In the case of the first question, the list of themes in the dialogue is empty.

[0037] In step S402, the question and answering processor 302 extracts a list of search terms from the question sentence.

[0038] In step S403, if the previous subject word list acquired in step S401 contains a subject word, the question and answering processor 302 proceeds to step S404, otherwise proceeds to step S405.

[0039] In step S404, the question and answering processor 302 adds the subject term to the list of search terms extracted in step S402.

[0040] In step S405, the question and answering processor 302 uses the search processor 303 to acquire domain knowledge related to the search term list from the domain knowledge storage table 501 in the domain knowledge storage area 304. Although the method for acquiring related domain knowledge is not particularly specified, in this embodiment, a full-text search is used. Furthermore, if there are multiple pieces of related domain knowledge, the number of items to be acquired may be limited based on the score of the full-text search or the like.

[0041] In this invention, domain knowledge refers to information that serves as the basis for answers to questions from users. For example, if the present invention is applied as a search system (including a dialogue (chat) style question-answering system) for a company's employee website, the domain knowledge would be the information posted on the employee website (such as information on web pages and posted document files). Domain knowledge is registered and managed by, for example, registering site information obtained by a prefix search of a URL and updating it periodically, or by having an administrator register the data in advance.

[0042] FIG. 7 is a diagram showing the contents of domain knowledge when information on an employee site and a corporate site is used as domain knowledge.

[0043] In step S406, the question answering processor 302 generates an answer sentence using the domain knowledge and the question sentence acquired in step S405, using the answer generation processor 305. There is no particular specification as to how to generate the answer sentence, but in this embodiment, a generation AI is used.

[0044] In step S407, the question and answering processor 302 extracts thematic terms from the question sentence acquired in step S401, the domain knowledge acquired in step S405, and the answer sentence generated in step S406. Thematic term extraction processing will be described later.

[0045] In step S408, the answer to the question generated in step S406 is displayed to the user. The answer may be accompanied by basis information (domain knowledge acquired in step S405).

[0046] Next, the subject word extraction process in step S407 will be described with reference to the flowchart of FIG.

[0047] In step S601, the question and answering processor 302 initializes a temporary area and a topic list.

[0048] In step S602, the question and answering processor 302 saves the list of search terms acquired in step S404 (or the search terms acquired in S402 if there is no previous subject term) in a temporary area.

[0049] In step S603, the question and answering processor 302 temporarily stores the list of words extracted from the domain knowledge acquired in step S405. It also extracts words from the answer sentence generated in step S406 and stores them in the temporary area.

[0050] In step S604, the question and answering processor 302 counts and evaluates the words in the temporary area based on their frequency of appearance.

[0051] In step S605, the question and answering processor 302 starts the repeated process up to step S608 for each of the words counted and evaluated in step S604.

[0052] In step S606, the question and answering processor 302 determines whether the evaluation value of the word is equal to or greater than a reference value. If it is equal to or greater than the reference value, the process proceeds to step S607. If it is less than the reference value, the process proceeds to step S608.

[0053] In step S607, the question and answering processor 302 adds the words that satisfy the criteria to the topic word list.

[0054] In step S608, if there are still words to be processed, the question and answering processor 302 repeats the process from step S605, otherwise it ends the process.

[0055] Next, as a specific example of the question answering process shown in the flowchart of FIG. 4, a case where the question answering process is performed on the domain knowledge table 501 of FIG. 7 will be described.

[0056] In step S401, the question and answering processor 302 receives the question "What is the address of the Osaka office?" and the list of previous themes input by the user from the dialogue manager 301. Since this is the first question, the list of themes is empty.

[0057] In step S402, the question answering processor 302 extracts a list of search terms from the question. In this embodiment, the search terms are obtained by extracting only independent words from the results of morphological analysis of the question. In response to the question "What is the address of the Osaka office?", a list consisting of the three words "Osaka," "office," and "address" is obtained.

[0058] In step S403, the question and answering processor 302 moves the process to step S405 because the subject word is not included in the subject word list acquired in step S401.

[0059] In step S405, the question and answer processing unit 302 uses the search processing unit 303 to obtain the top three full-text search results, domain knowledge 701 to 703, from the domain knowledge table 501 in the domain knowledge storage area 304 as domain knowledge related to the search term list ("Osaka," "office," and "address").

[0060] In step S406, the question answering processor 302 generates an answer sentence by providing the domain knowledge 701 to 703 acquired in step S405 and the question sentence to the answer generation processor 305. Fig. 8 shows an overview of the answer sentence generation process using the generation AI in this embodiment.

[0061] The answer sentence generation process using the generation AI will be described with reference to FIG.

[0062] The top three full-text search results obtained in step S405, namely, the domain knowledge 701 to 703 texts (C in FIG. 8) and the question entered by the user (Q in FIG. 8), are input into a template to create a prompt as shown in FIG. 8, which is then given to the generation AI. In S406, the generation AI generates an answer sentence 801 from this prompt.

[0063] In step S407, the question and answering processor 302 invokes the subject term extraction process for the question sentence acquired in step S401, the domain knowledge acquired in step S405, and the answer sentence generated in step S406.

[0064] The process of step S407 will be described in detail with reference to the flowchart of FIG.

[0065] In step S601, the question and answering processor 302 initializes the temporary area and the subject list by emptying them. Fig. 9 shows the state of the temporary area in a series of processes.

[0066] In step S602, the question and answering processor 302 saves the list of search terms acquired in step S404 (or the search terms acquired in S402 if there is no previous subject term) in a temporary area (901).

[0067] In step S603, the question and answering processor 302 stores in a temporary area the list of words extracted from the domain knowledge acquired in step S405 (902-904). Furthermore, words are extracted from the answer sentence generated in step S406 and stored in the temporary area (905).

[0068] In step S604, the question and answering processor 302 counts and evaluates the words in the temporary domain based on their frequency of appearance. In this embodiment, the frequency of appearance in the temporary domain itself is used as the evaluation value, but the evaluation method is not particularly specified. tf·idf in the domain knowledge storage table may also be used. Figure 10 shows the results of the counting and evaluation.

[0069] In step S605, the question and answering processor 302 starts the repeated process up to step S608 for the word 1001 "Osaka."

[0070] In this embodiment, the reference value in step S606 is set to 5, which is the maximum evaluation value of the aggregation and evaluation results. The reference value is not particularly specified. It may be calculated dynamically as in this embodiment, or may be a fixed value.

[0071] In step S606, the question and answering processor 302 advances the process to step S607 because the evaluation value 5 of the word 1001 "Osaka" is equal to or greater than the reference value.

[0072] In step S607, the question and answering processor 302 adds the word 1001 "Osaka" to the topic word list.

[0073] In step S608, the question and answering processor 302 repeats the process from step S605 because there is a word 1002 "office" to be processed.

[0074] In step S606, the question and answering processor 302 advances the process to step S607 because the evaluation value 5 of the word 1002 "office" is equal to or greater than the reference value.

[0075] In step S607, the question and answering processor 302 adds the word 1002 "office" to the subject word list.

[0076] In step S608, the question and answering processor 302 repeats the process from step S605 because there is a word 1003 "address" to be processed.

[0077] In step S606, the question and answering processor 302 advances the process to step S608 because the evaluation value 4 of the word 1003 "address" is less than the reference value.

[0078] In step S608, since there are still words to be processed, the question and answering processor 302 returns to the repeat process from step S605. After performing the same process on all remaining words, the subject word list is filled with the words 1001 "Osaka" and 1002 "office," and the process ends.

[0079] When the processing of the flowchart in FIG. 6 is completed, the processing proceeds to step S408 in FIG.

[0080] In step S408, the answer to the question generated in step S406 is displayed to the user. The acquired domain knowledge may also be displayed as evidence information at the same time.

[0081] FIG. 11 shows an example of a screen that displays an answer sentence and evidence information (domain knowledge acquired in step S405) to the user. The user's question, "What is the address of the Osaka office?", is entered in question form 1101. The domain knowledge generated in S406 and the answer sentence generated from the question sentence are displayed in answer form 1102. The domain knowledge acquired in step S405 is displayed together with the answer sentence as evidence information 1103. The evidence information 1103 is a link, and the contents of the evidence information can be displayed by clicking or other instructions. The link may display the contents of the domain storage table 501, or may be configured to refer to external information. There may also be a function that allows the user to evaluate the answer sentence generated from the question sentence. The follow-up question form 1104 allows the user to enter questions that they would like to continue asking.

[0082] Next, suppose that the question "What about reception?" is subsequently input (question input field 1104 in FIG. 11).

[0083] The dialogue management processing unit 301 invokes the question and answer processing of the question and answer processing unit 302 for the question "Where is the reception?" and the subject word list ("Osaka" and "office").

[0084] In step S401, the question and answering processor 302 receives from the dialogue management processor 301 the question "Where is the reception?" input by the user and the list of previous themes ("Osaka" and "office").

[0085] In step S402, the question and answering processor 302 extracts a list of search terms ("reception") from the question "What about reception?".

[0086] In step S403, the question and answering processor 302 proceeds to step S404 because the subject word is included in the previous subject word list acquired in step S401.

[0087] In step S404, the question and answering processor 302 adds the subject words ("Osaka" and "office") to the list of search words ("reception") extracted in step S402. As a result, the list of search words becomes ("reception", "Osaka", "office").

[0088] In step S405, the question and answer processing unit 302 uses the search processing unit 303 to retrieve the top three full-text search results, domain knowledge 702, 701, and 704, from the domain knowledge table 501 in the domain knowledge storage area 304 as domain knowledge related to the search term list ("reception," "Osaka," and "office").

[0089] A detailed description of the subsequent processing will be omitted. In this processing, if a domain knowledge search is performed without including the subject term for the second or subsequent questions, the desired information may not be obtained. For example, suppose the first question is, "What is the address of the Osaka office?" and the second question is, "Where is the reception desk?" The second question is searched without including the subject terms "Osaka" and "office." Therefore, the search is performed using only the search term "reception desk," and the reception desk at the "head office" or "Nagoya office" may be generated as the answer. In contrast, by including "Osaka" and "office desk" in the search term list from the subject term list as in the present invention, it is possible to include domain knowledge 702 necessary for an appropriate answer in the top search results. As described above, the searched domain knowledge is provided to the generation AI as a prompt to generate an answer. Therefore, the search for appropriate domain knowledge ensures that the prompt provided to the generation AI is appropriate. As a result, correct question and answering is possible even for questions with omitted subjects (such as the question "Where is the reception desk?" in this embodiment).

[0090] (Second embodiment) Next, a second embodiment of the present invention will be described.

[0091] The second embodiment differs from the first embodiment in the domain knowledge provided to the answer sentence generation process in step S406 and the topic word extraction process in step S407 in the question answering process.

[0092] In step S406 in the second embodiment, the question answering processing unit 302 uses the answer generation processing unit 305 to generate an answer sentence using the domain knowledge acquired in step S405 and the question sentence, and at the same time selects answer basis information (knowledge used to generate the answer sentence from the domain knowledge acquired in step S405).

[0093] Figure 12 shows an example of answer generation involving basis information selection. A prompt is created that includes the domain knowledge text (C1 to C3 in Figure 12) that is the top three full-text search results obtained in step S405 and the question text (Q in Figure 12) entered by the user, and is given to the generation AI. In S406, the generation AI generates an answer text from this prompt. At that time, the generation AI selects the domain knowledge used to generate the answer to the question as answer basis information 1201 and displays it together with the answer text.

[0094] Then, in step S407 in the second embodiment, the topic word extraction process is performed using only the selected answer basis information as domain knowledge. In the first embodiment, in S602, the list of search terms acquired in step S402 and the list of words extracted from the domain knowledge acquired in step S405 were temporarily saved (902-904). Words were extracted and evaluated from each of these domain knowledge and answer sentences to determine topic words. On the other hand, in the second embodiment, only the selected answer basis information is extracted from the domain knowledge acquired in S405, and topic words are determined using only the list of words acquired from it and the search terms.

[0095] In this way, by further limiting the domain knowledge obtained by full-text search etc. to only the domain knowledge required for generating an answer sentence, more accurate question answering becomes possible.

[0096] Although the embodiments have been described above, the present invention can be embodied as, for example, a system, an apparatus, a method, a program, a recording medium, etc. Specifically, the present invention may be applied to a system made up of multiple devices, or may be applied to an apparatus made up of a single device.

[0097] Furthermore, the program of the present invention is a program that enables a computer to execute the processing methods of the flowcharts shown in Figures 4 and 6, and the storage medium of the present invention stores a program that enables a computer to execute the processing methods of Figures 4 and 6. Note that the program of the present invention may be a program for each processing method of each device in Figures 4 and 6.

[0098] As described above, it goes without saying that the object of the present invention can also be achieved by supplying a recording medium on which a program that realizes the functions of the above-mentioned embodiments is recorded to a system or device, and having the computer (or CPU or MPU) of that system or device read and execute the program stored on the recording medium.

[0099] In this case, the program itself read from the recording medium will realize the novel functions of the present invention, and the recording medium on which the program is recorded will constitute the present invention.

[0100] Examples of recording media for supplying the program include flexible disks, hard disks, optical disks, magneto-optical disks, CD-ROMs, CD-Rs, DVD-ROMs, magnetic tapes, non-volatile memory cards, ROMs, EEPROMs, and silicon disks.

[0101] Furthermore, it goes without saying that not only are the functions of the above-mentioned embodiments realized by the computer executing a program it has read, but also cases are included in which an OS (operating system) running on the computer performs some or all of the actual processing based on the instructions of the program, and the functions of the above-mentioned embodiments are realized through that processing.

[0102] Furthermore, it goes without saying that this also includes cases where a program read from a recording medium is written into a memory provided on a function expansion board inserted into a computer or a function expansion unit connected to the computer, and then a CPU or the like provided on the function expansion board or function expansion unit performs some or all of the actual processing based on the instructions of the program code, thereby realizing the functions of the above-mentioned embodiments.

[0103] Furthermore, the present invention may be applied to a system consisting of multiple devices, or to a device consisting of a single device. It goes without saying that the present invention can also be applied to a case where the present invention is achieved by supplying a program to a system or device. In this case, the system or device can enjoy the effects of the present invention by reading a recording medium containing a program for achieving the present invention into the system or device.

[0104] Furthermore, by downloading and reading a program for achieving the present invention from a server, database, etc. on a network using a communication program, the system or device can enjoy the effects of the present invention. Note that the present invention also includes configurations that combine the above-mentioned embodiments and their modified examples. [Explanation of symbols]

[0105] 100 Question Answering Device 110 User terminal 120 Network

Claims

1. a question acquisition means for acquiring a question; a search means for performing an information search using a word identified from the question acquired by the question acquisition means; an output means for outputting an answer generated using the information searched by the search means and the acquired question; a determining means for determining words that satisfy a predetermined condition from among words identified from the questions acquired so far and words identified from information retrieved by the retrieval means; Equipped with When a further question is acquired after the output of the answer by the output means, the search means performs an information search using the words that satisfy the predetermined conditions and words identified from the newly acquired question. An information processing device characterized by:

2. The determining means further determines words that satisfy a predetermined condition from among words identified from the questions acquired so far, words identified from the information searched by the searching means, and words identified from the output answers.

2. The information processing device according to claim 1,

3. The output means outputs the information used to generate the answer from the searched information in an identifiable manner.

2. The information processing device according to claim 1,

4. The determining means further determines, from among the information searched by the searching means, a word identified from the information used to generate the answer as a word that satisfies a predetermined condition.

2. The information processing device according to claim 1,

5. The predetermined condition is a condition based on the frequency of occurrence of a word.

2. The information processing device according to claim 1,

6. The words identified from the questions acquired so far include words that satisfy the predetermined condition determined by the determining means.

2. The information processing device according to claim 1,

7. The words identified from the question are independent words.

2. The information processing device according to claim 1,

8. The answer output by the output means is created using a generation AI.

2. The information processing device according to claim 1,

9. The output means outputs an answer created by inputting the question acquired by the question acquisition means and the information searched by the search means into a generation AI.

9. The information processing device according to claim 8,

10. The information to be searched by the search means is information specified by a URL that satisfies a predetermined condition.

2. The information processing device according to claim 1,

11. a question acquisition means for acquiring a question; a search means for performing an information search using a word identified from the question acquired by the question acquisition means; an output means for outputting an answer generated using the information searched by the search means and the acquired question; a determining means for determining words that satisfy a predetermined condition from among words identified from the questions acquired so far and words identified from information retrieved by the retrieval means; Equipped with When a further question is acquired after the output of the answer by the output means, the search means performs an information search using the words that satisfy the predetermined conditions and words identified from the newly acquired question. An information processing system characterized by:

12. A question acquisition step in which question acquisition means of the information processing device acquires a question; a search step in which a search means of the information processing device performs an information search using words identified from the question acquired in the question acquisition step; an output step in which an output means of the information processing device outputs an answer generated using the information searched in the search step and the acquired question; a determination step in which a determination means of the information processing device determines a word that satisfies a predetermined condition from among words identified from the question acquired so far and words identified from the information searched by the search step; Equipped with When a further question is acquired after the answer is output in the output step, the search step performs an information search using the words that satisfy the predetermined condition and words identified from the newly acquired question. A method for controlling an information processing device, comprising:

13. A program for causing a computer to function as each of the means according to any one of claims 1 to 10.

Images