JP2019028604A - Interactive device and program - Google Patents

Abstract

To improve estimation accuracy of a user who is an interaction partner.SOLUTION: An interactive device has: a reception part receiving an input of a first inquiry from a user; an output part outputting a second inquiry inquiring presence of comprehension of a term related to the first inquiry to the user; an estimation part estimating a level of knowledge of the user for a field related to the first inquiry on the basis of a content of an answer to the second inquiry and status of an input operation of a character string indicating the answer; and a generation part generating a content of an answer to the first inquiry according to the level estimated by the estimation part.SELECTED DRAWING: Figure 2

Description

  The present invention relates to an interactive apparatus and a program.

  Many current interactive systems respond uniformly to any user regardless of the user's characteristics. However, if the response is made uniformly regardless of the user's preference or knowledge, the satisfaction or understanding of the response content cannot be increased. Therefore, it is necessary to automatically estimate the user's characteristics and present the response contents according to the estimation result.

  One of the characteristics of the user is the amount of knowledge related to ICT (Information and Communication Technology) such as a PC, a smartphone, and a tablet. Currently, voice and text dialogue systems are often used for inquiries from users regarding ICT devices and services, so the amount of knowledge related to ICT is estimated from the use of the dialogue system, and dialogue according to the amount of knowledge is conducted. It is important to do.

  Conventionally, there has been proposed a technique for converting a term into an expression that can be easily understood by the user in accordance with the level of literacy related to the user's ICT, knowledge of device operation methods, knowledge of terms, and the like (Patent Documents 1 and 2). ). In addition, techniques for estimating a knowledge amount related to a user's ICT have been proposed (Patent Documents 3 and 4).

JP2013-250624A JP 2014-2517 A JP2013-117842A JP 2014-115719 A

  In the technique described in Patent Document 1, an operator manually inputs a user's literacy level based on the user's age or years of Internet use at a call center or the like, and converts ICT terms so that it can be easily understood according to the level. The output is then supported by the operator.

  In the technique described in Patent Document 2, the ICT skill level of the user is calculated in advance based on the result of a preliminary questionnaire, and then the degree of sensation given by each ICT term to the user at that level is estimated. .

  As described above, using the techniques of Patent Documents 1 and 2, it is possible to examine appropriate expressions according to the level of the knowledge amount of the user regarding ICT. However, the calculation method of the amount of knowledge related to the user's ICT is based on the input of the operator or the answer of the questionnaire, and cannot be automatically estimated.

  On the other hand, in the technology described in Patent Document 3, the knowledge amount of the user is divided into two or three stages using the information on the number of questions of the user and the operator and the timing thereof. ”And“ Small amount of knowledge ”. However, from this estimation result, it is impossible to know in detail what terms a user with a large amount of knowledge knows and what terms a user with a small amount of knowledge does not know. For this reason, even if an attempt is made to respond according to the amount of knowledge of the user using the estimation result, it is not possible to know how to explain to a user having a small amount of knowledge, for example.

  Further, in the technique described in Patent Document 4, a vocabulary network of ICT terms is created, and a user corresponding to a node corresponding to the ICT term and a directed link that knows this term if another term is known. Knowledge is estimated from input information on whether or not a certain term is known. With this technique, the user's known and unknown terms can be known. However, if the input information related to the understanding of terms from the user is insufficient, the accuracy will drop.

  The present invention has been made in view of the above points, and an object of the present invention is to improve the accuracy of estimation of the knowledge of the user of the conversation partner.

  Therefore, in order to solve the above-described problem, the dialogue apparatus outputs a second question that asks the user whether or not the terminology related to the first question is understood, and a reception unit that accepts input of the first question from the user. An output unit, and an estimation unit that estimates a level of knowledge of the user regarding a field related to the first question based on a content of an answer to the second question and a state of an input operation of a character string indicating the answer And a generation unit that generates the content of the answer to the first question according to the level estimated by the estimation unit.

  It is possible to improve the estimation accuracy of the knowledge of the conversation partner user.

It is a figure which shows the hardware structural example of the dialogue apparatus 10 in embodiment of this invention. It is a figure which shows the function structural example of the dialogue apparatus 10 in embodiment of this invention. 4 is a flowchart for explaining an example of a processing procedure executed by the dialogue apparatus 10. It is a figure which shows the structural example of the scenario table | surface of the dialogue scenario memory | storage part 161. FIG. 5 is a diagram illustrating a configuration example of a character input speed storage unit 162. FIG. It is a flowchart for demonstrating an example of the process sequence of a question sentence production | generation process. It is a figure for demonstrating the determination example of the presence or absence of term understanding. 6 is a diagram illustrating a configuration example of a term understanding storage unit 163. FIG. 5 is a diagram illustrating a configuration example of a term explanation storage unit 164. FIG. FIG. 6 is a diagram showing a configuration example of a THETERING task table in a dialogue scenario storage unit 161. It is a flowchart for demonstrating an example of the process sequence of an answer sentence production | generation process. It is a figure which shows the 1st example of the calculation method of term understanding. It is a figure which shows the 2nd example of the calculation method of term understanding degree. It is a figure which shows the 1st example of the estimation method of a knowledge amount. It is a figure which shows the 2nd example of the estimation method of a knowledge amount. 6 is a diagram illustrating a configuration example of a response statement table of TEXTERING in a dialogue scenario storage unit 161. FIG.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the present embodiment, an example in which the dialogue apparatus 10 estimates a user's knowledge amount related to ICT (Information and Communication Technology) from input information related to non-linguistic information and terminology understanding and presents an answer according to the knowledge amount. explain.

  FIG. 1 is a diagram illustrating a hardware configuration example of an interactive apparatus 10 according to an embodiment of the present invention. 1 includes a drive device 100, an auxiliary storage device 102, a memory device 103, a CPU 104, an interface device 105, a display device 106, an input device 107, and the like that are mutually connected by a bus B.

  A program for realizing processing in the interactive apparatus 10 is provided by a recording medium 101 such as an SD card or a CD-ROM. When the recording medium 101 storing the program is set in the drive device 100, the program is installed from the recording medium 101 to the auxiliary storage device 102 via the drive device 100. However, the program need not be installed from the recording medium 101 and may be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program and also stores necessary files and data.

  The memory device 103 reads the program from the auxiliary storage device 102 and stores it when there is an instruction to start the program. The CPU 104 realizes functions related to the interactive device 10 according to a program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network. The display device 106 displays a GUI (Graphical User Interface) or the like by a program. The input device 107 includes a keyboard and mouse, a touch panel, or the like, and is used for inputting various operation instructions.

  The dialog device 10 may be a terminal used by the user to make an inquiry, or may be a device different from the terminal, but in the present embodiment, the dialog device 10 is inquired by the user. It is assumed that the terminal is used for In this case, for example, a mobile phone, a smartphone, a tablet terminal, a PC (Personal Computer), or the like can be cited as an example of such a terminal. However, the dialogue apparatus 10 may be realized by one or more computers connected to a terminal operated by a user via a network.

  FIG. 2 is a diagram illustrating a functional configuration example of the interactive apparatus 10 according to the embodiment of the present invention. The dialogue apparatus 10 uses the amount of knowledge regarding the field (in this embodiment, the ICT field) related to the initial question from the user (hereinafter referred to as “user initial question”) during the dialogue between the user and the dialogue apparatus 10. It is an apparatus that presents an explanation according to the amount of knowledge, estimated from non-linguistic information and information input by the user regarding understanding of terms. The dialogue between the user and the dialogue device 10 is basically performed by the user with respect to the question sentence output from the dialogue apparatus 10 in order to estimate the knowledge amount of the user regarding the field related to the user initial question, and the question sentence. This is performed by repeating the input of a character string indicating an answer (hereinafter referred to as “user answer”) one or more times. When a sufficient dialogue is performed to estimate the amount of knowledge of the user, the dialogue apparatus 10 generates an answer to the user opening question (hereinafter referred to as “system answer”) according to the amount of knowledge of the user, Output system answer.

  In FIG. 2, the dialogue apparatus 10 includes a question sentence generation unit 11, a text input unit 12, a dialogue control unit 13, a dialogue sentence output unit 14, an answer sentence generation unit 15, and the like. The question sentence generation unit 11 includes an option determination unit 111 and a term understanding determination unit 112. The answer sentence generation unit 15 includes a knowledge amount estimation unit 151. The knowledge amount estimation unit 151 includes a character input speed calculation unit 1511 and a term understanding level calculation unit 1512. Each of these units is realized by processing that one or more programs installed in the interactive apparatus 10 cause the CPU 104 to execute. The dialogue apparatus 10 also uses a dialogue scenario storage unit 161, a character input speed storage unit 162, a term understanding storage unit 163, a term explanation storage unit 164, and the like. Each of these storage units can be realized using, for example, a storage device that can be connected to the auxiliary storage device 102 or the interactive device 10 via a network.

  Hereinafter, a processing procedure executed by the interactive apparatus 10 will be described. FIG. 3 is a flowchart for explaining an example of a processing procedure executed by the interactive apparatus 10. The flowchart of FIG. 3 shows the overall processing procedure executed by the dialog device 10 when the dialog device 10 estimates the user's knowledge amount and presents a system answer corresponding to the knowledge amount to the user's initial question. Show.

  In step S1, the dialogue apparatus 10 activates the dialogue function in accordance with a predetermined operation by the user. The interactive function is, for example, a function having the functional configuration shown in FIG. 2 realized by processing executed by the CPU 104 by a program such as a text interactive system that operates on the browser of the interactive apparatus 10 or an independent interactive application. It is.

  Subsequently, the dialogue control unit 13 refers to the scenario table stored in the dialogue scenario storage unit 161, acquires the question sentence to be output first (S2), and sends the obtained question sentence to the dialogue sentence output unit 14. Output. The question indicated by the question sentence that is first output by the dialogue apparatus 10 is hereinafter referred to as “system opening question”.

  FIG. 4 is a diagram illustrating a configuration example of a scenario table in the dialogue scenario storage unit 161. The scenario table is a table in which a scenario of a dialogue between the user and the dialogue device 10 is defined, such as “status”, “task”, “option”, “question sentence”, “keyword”, and “jump destination status”. Has columns (items). In FIG. 4, the unit of the line delimited by “status” is hereinafter referred to as “status record”.

  "Status" is a concept that distinguishes the status (state) of a dialog. The “question sentence” is a question sentence to be output to the user in the corresponding status. That is, the status and the question sentence correspond one-to-one. The “keyword” is a keyword for distinguishing the next transition destination status or the like (jump destination status or the like) according to the content of the character string input by the user with respect to the question sentence. The value of “keyword TRUE” in “keyword” indicates a case where the specified keyword is not included in the character string input by the user with respect to the question sentence. Further, the fact that the keyword is not included in the question sentence, that is, that the keyword is not registered indicates that the transition to the next status is made without waiting for the input of the character string from the user after the question sentence is output. For example, in FIG. 4, the “keyword” column for “Status” is “AGAIN ()” and “EXPLAIN ()” is blank. Therefore, when “question text” with “AGAIN ()” and “EXPLAIN ()” is output, the question text corresponding to the next status is not waited for the input of the character string from the user. Is output.

  “Jump destination status” indicates the status of the transition destination according to the keyword included in the character string input by the user. If the “jump destination status” includes a plurality of statuses, it means that each status is selected in order and a question sentence corresponding to each status is output. Further, “next” in “jump destination status” means transition to the status next to the status listed in a plurality of columns in the “jump destination status” of the status that is the transition base of the status including the “next”. To do. That is, the value of “jump destination status” of a status other than the end when the “jump destination status” includes a plurality of statuses is “next”.

  “Task” indicates whether or not the corresponding status is a status of executing a task. Specifically, a status where the value of “task” is “task TRUE” indicates that the task is executed, and a status where “task” is blank indicates that the task is not executed. A task refers to a process finally executed by the dialogue apparatus 10 in response to a dialogue with a user. In this embodiment, an output of an answer sentence indicating a system answer to a user initial question corresponds to a task.

  “Option” indicates whether or not the content of the “question sentence” in the corresponding status is a question sentence that gives a choice of a user answer to term understanding.

  In step S2, the dialogue control unit 13 acquires a question sentence corresponding to the current status as a text from a scenario table as shown in FIG. 4, for example. In the present embodiment, the initial status is “START”. Therefore, the dialogue control section 13, to get the text of the "question" corresponding to the "START" status "Hello! Tell me your business!".

  Subsequently, when the dialog control unit 13 outputs the acquired text of the question sentence to the dialog sentence output unit 14, the dialog sentence output unit 14 outputs the input text of the question sentence to the display device 106 such as a display. And output (S3). For example, the question text is displayed as text on the display device 106. Subsequently, the dialogue control unit 13 determines whether or not a keyword corresponding to the current status is registered in the scenario table (FIG. 4) (S4). If no keyword is registered (No in S4), the process proceeds to step S8. That is, in the scenario table (FIG. 4), when the “keyword” item is blank, the dialogue control unit 13 does not wait for the input of the character string from the user.

  When the keyword is registered in the current status (Yes in S4), the text input unit 12 receives an input of a character string for the question sentence from the user (S5). For example, the user inputs a character string using the input device 107 such as a keyboard. At this time, the text input unit 12 receives a character string input by the user and measures a time required from the start of the input of the character string to the completion of the input by the user. The completion timing of the input of the character string by the user can be detected by, for example, a predetermined operation (for example, pressing of the “Send” button) after the input of the character string. When step S5 is first executed, a question sentence indicating a system opening question is output from the dialogue apparatus 10. The character string input by the user in this state is usually a character string indicating a user opening question. For example, a character string indicating a user opening question such as “What is a tethering method?” Is input. On the other hand, the character string input when step S5 is executed for the second time or later is a character string indicating a user answer to the question sentence output by the dialogue apparatus 10. The user answer is used by the dialogue apparatus 10 to estimate the amount of knowledge of the user regarding the field related to the user initial question.

  Subsequently, the text input unit 12 outputs the input character string and the required time to the dialogue control unit 13 (S6). Subsequently, the dialogue control unit 13 stores the character string and the required time input from the text input unit 12 in the character input speed storage unit 162 (S7).

  FIG. 5 is a diagram illustrating a configuration example of the character input speed storage unit 162. As shown in FIG. 5, the character input speed storage unit 162 stores the character string and the time required to input the character string each time a character string corresponding to the question sentence is input from the user.

  Subsequently, the dialogue control unit 13 updates the status with reference to the scenario table (FIG. 4) (S8). That is, the “jump destination status” specified based on the scenario table (FIG. 4) and the keyword included in the character string input by the user is selected as a new status. For example, if the status before the update is “START” and the character string input to the user is “What is a tethering method?”, “TETHERING” is set as a new status. In addition, when a plurality of statuses are registered in the “jump destination status” and the status is first processed, the first (highest) status among the statuses is newly set. Selected as the status. The second and subsequent statuses among the plurality of statuses are selected based on “next” of “jump destination status” in the new status.

  Subsequently, the dialog control unit 13 determines whether or not the transition to the status which is a task has been completed (jump) and the acquisition of the parameters regarding the task has been completed (S9). The status that is a task refers to a status in which the value of the task is “task TRUE” in the scenario table (FIG. 4).

  If the status has not been changed to a task status, or if acquisition of parameters related to the task has not been completed (No in S9), the question sentence generation unit 11 executes the question sentence generation process in response to a request from the dialog control unit 13 (S10). Note that the question sentence generation process (S10) is always executed when step S9 is executed for the first time. In the question sentence generation process, a question sentence for the dialogue apparatus 10 to make an appropriate system answer is generated mainly for the user initial question input by the user in step S5. Subsequent to the question sentence generation process, step S3 and subsequent steps are executed. That is, step S3 and subsequent steps are executed for the question sentence generated in the question sentence generation process.

  On the other hand, when the status has been changed to the task status and the acquisition of the parameters related to the task has been completed (Yes in S9), the response text generation unit 15 generates the response text in response to a request from the dialogue control unit 13. Processing is executed (S11). In the answer sentence generation process, an answer sentence indicating a system answer to the user initial question input by the user in step S5 is generated. Subsequently, when the dialog control unit 13 outputs the response text generated by the response text generation unit 15 to the dialog text output unit 14, the dialog text output unit 14 outputs the input response text (S12). Note that FIG. 3 shows an example in which the processing ends as it is, but it is also possible to return to step S <b> 2 and have a dialog regarding another inquiry.

  Next, details of step S10 will be described. FIG. 6 is a flowchart for explaining an example of the processing procedure of the question sentence generation process.

  First, the option determination unit 111 of the question sentence generation unit 11 refers to the scenario table (FIG. 4) (S10-1), and the question sentence output last by the dialogue device 10 indicates the option of the user answer to the term understanding. It is determined whether or not the question sentence is given (S10-2). Specifically, it is determined whether or not the value of “option” corresponding to the immediately preceding status (status before update) is “option TRUE”.

  For example, if the procedure of the first to FIG. 6 is executed, the question statement that interactive device 10 is output to the last is a "Hello! Tell me your business!". Such a question sentence is not a question sentence that gives a user answer option for understanding the terminology. That is, the value of “option” in the status of “START” is not “option TRUE”. Therefore, in this case (No in S10-2), the process proceeds to Step S10-8.

  On the other hand, if the dialog between the user and the dialog device 10 progresses, and the status corresponding to the last question sentence output by the dialog device 10, that is, the previous status is “TETHERING”, the dialog device 10 displays “tethering”. By the way, in addition to the question sentence “Do you know tethering itself?”, The option “Yes / No” was presented to the user in text. If the previous status is “TETHERING_OS”, in addition to the question text “Which OS is the terminal being used?”, An option “OS-A / OS-B / I don't know” is presented to the user. It would have been. Note that the options presented here are options that allow the user to determine the understanding of the term depending on which one the user selects.

  When the question sentence output last by the dialogue apparatus 10 is a question sentence that gives a user answer option for term understanding (Yes in S10-2), the term understanding determination unit 112 performs step S5 on the question sentence. The option entered in is input, and based on the option, it is determined whether or not the user understands the term, and the determination result is stored in the term understanding storage unit 163 (S10-3).

  FIG. 7 is a diagram for explaining an example of determining whether or not a term is understood. As a method of determining whether or not there is an understanding of terms, as shown in FIG. 7, for example, “OS-A”, “OS-B”, “I don't know” as answer options for a question message asking for the OS of the terminal currently used ”And the user answer“ OS-A ”or“ OS-B ”, it is interpreted that both terms are understood, and the determination results are (OS-A, 1) and (OS-B). , 1). Here, the notation of the determination result is (term, 0 or 1), 0 means not understood, and 1 means understood.

  In addition, “Yes” and “No” are presented as user answer choices for questions that directly ask whether or not the term itself is known. If the user answer is “Yes”, it is interpreted that the term is understood. If it is “No”, it is interpreted that the term is not understood, and a determination result is generated in the same manner as described above. Note that the method for determining whether or not there is an understanding of terms is not limited to this.

  The term understanding determination unit 112 stores the determination result of the presence / absence of term understanding in the term understanding storage unit 163. FIG. 8 is a diagram illustrating a configuration example of the term understanding storage unit 163. The term understanding storage unit 163 stores in advance terms related to ICT and their difficulty levels. The difficulty level of the term may be set based on, for example, a questionnaire survey in advance. In the present embodiment, the difficulty level is 5 with the highest difficulty level and 1 with the lowest difficulty level. However, the difficulty level is not limited to five levels, and any number of levels may be used.

  In step S <b> 10-3, the determination result of whether or not the term understanding is determined by the term understanding determination unit 112 is stored in the term understanding storage unit 163 as a value indicating whether or not the term is determined.

  Subsequently, the question sentence generation unit 11 determines whether or not the user understands the term to be determined whether or not the term is understood, that is, the value stored in the term understanding storage unit 163 is 1 for the term. (S10-4). If the user understands the term (Yes in S10-4), that is, if 1 is stored, the process proceeds to step S10-8.

  On the other hand, when the user does not understand the term (No in S10-4), that is, when 0 is stored, the question sentence generation unit 11 refers to the dialogue scenario storage unit 161 and corresponds to the current status. To obtain a question sentence (S10-5). That is, a question sentence corresponding to the character string input by the user is acquired.

  For example, in FIG. 4, the question sentence that is output last by the dialogue apparatus 10 is “Tethering method! You know tethering itself? Yes / No”. And the user inputs a character string “No”. In this case, since the dialog control unit 13 selects “EXPLAIN ()” that is the first status among the “jump destination status” corresponding to “No”, the status becomes “EXPLAIN ()”. Note that a term determined to be a term that the user does not understand is passed as an argument to the “EXPLAIN ()” status. Of the terms constituting the question sentence output last by the interactive apparatus 10, the terms registered in the term understanding storage unit 163 are specified as terms that the user does not understand.

  In this case, as shown in FIG. 4, the question sentence ““ #WORD ”” corresponding to the “EXPLAIN ()” status is “#EXP”! Is acquired. Here, “#WORD” and “#EXP” indicate specific character string embedding locations. “#WORD” indicates a term that is passed as an argument to the “EXPLAIN ()” status and determined to be a term that the user does not understand. “#EXP” indicates an explanation (term explanation) corresponding to the term.

  Subsequently, the question sentence generation unit 11 determines whether or not there is an embedded portion in the question sentence acquired in step S10-5 (S10-6). When there is an embedded part such as “#WORD” or “#EXP” (Yes in S10-6), the question sentence generation unit 11 refers to the term explanation storage part 164 and embeds the embedded part of the question sentence ( S10-7).

  FIG. 9 is a diagram illustrating a configuration example of the term explanation storage unit 164. As shown in FIG. 9, the term explanation storage unit 164 stores a difficulty level, a term explanation sentence, and the like for each term.

  For example, “question text” is “#WORD” means “#EXP”! If the term that is determined not to be understood is “tethering”, “Tethering” is a mobile router that turns a smartphone into a mobile router and uses the 3G line of the smartphone or LTE to connect the PC to the Internet. It's a function that can be connected! Is generated. In the present embodiment, an example in which the question sentence generation unit 11 generates a question sentence indicating the explanation of terms by filling in “#WORD”, “#EXP”, and the like in the templated “question sentence”. However, the method of generating the question sentence indicating the explanation of the term is not limited to this. For example, the question sentence generation unit 11 acquires a term explanation corresponding to a term determined not to be understood from the term explanation storage unit 164, and automatically selects a natural sentence including the term and the term explanation sentence. It may be generated.

  Subsequently, the question sentence generation unit 11 outputs the question sentence to the dialogue control unit 13 (S10-9). In this case, the question text is output in step S3 of FIG.

  On the other hand, the question sentence generation unit 11 acquires a question sentence corresponding to the current status in step S10-8 in the same manner as step S10-5, and then in step S10-9, the question sentence generation unit 11 Output question text.

  In FIG. 4, “EXPLAIN ()” is the “jump destination status” when the previous status is “TETHERING” and the character string input by the user to the question sentence is “No”. Next to this, “see THETERING task table” is included. In addition, the corresponding keyword is not registered in the “EXPLAIN ()” status, and the “jump destination status” of the “EXPLAIN ()” status is “next”. Therefore, in this case, "Tethering" is a function that allows you to connect your PC to the Internet using your smartphone's 3G line or LTE by turning your smartphone into a mobile router! Is output in step S3, the process proceeds to step S8 without executing steps S5 to S7. In step S8, based on “next”, the dialog control unit 13 displays “TETERING task table reference”, which is the second status among the “jump destination status” corresponding to “NO” in the “TETHERING” status. select.

  In this case, in step S 10-5, the question sentence generation unit 11 refers to the THETERING task table stored in the dialogue scenario storage unit 161 based on the current status “refer to the THETERING task table”. To do.

  FIG. 10 is a diagram illustrating a configuration example of a THETERING task table in the dialogue scenario storage unit 161. In the task table, a status in which the value of “task” is “task TRUE” is selected, and the “jump destination status” based on the character string input by the user with respect to the question sentence in the status is “see the task table of“ THETERING ”. ", That is, a table referred to when it is determined to execute" TETHERING task table reference ".

  In FIG. 10, the task table stores “task name” for each task, one or more “parameters”, “usage status” for each parameter, “acquired value” for each parameter, “acquisition destination of answer sentence”, and the like. It is configured to be possible. The “task name” corresponds to the “status” value of the scenario record whose “task” value is “task TRUE” in the scenario table in FIG.

  Of the items in the task table, the “acquired value” is initially empty. This is because the “acquired value” is stored in accordance with the dialogue with the user. Specifically, in step S10-5, when the current status is “refer to task table of THETERING”, the question sentence generation unit 11 includes “parameter” of the record whose “task name” is “TETHERING”. The question text corresponding to the “usage status” of the “parameter” in which the “acquired value” is not stored is acquired from the scenario table (FIG. 4). For example, in FIG. 10, “parameters” of “OS” and “CONNECT” are defined for the “TETHERING” task, but since neither “acquired value” is initially stored, The sentence generation unit 11 first obtains a question sentence “Which terminal is used? ...” corresponding to “TETHERING_OS” which is a “usage status” corresponding to “OS” from the scenario table (FIG. 4). Then, the dialogue sentence output unit 14 outputs the question sentence in step S3 of FIG.

  Therefore, when viewed from the user, when the user inputs the character string “No” in response to the question “Do you know tethering? Yes / No”, “ "Is a function that allows smartphones to be connected to the Internet using a smartphone's 3G connection or LTE by turning it into a mobile router! Followed by a question sentence such as “Which terminal is used? That is, two question sentences are output in succession.

  In addition, if the user inputs the character string “Yes” in response to the question sentence “Tethering, is it a tethering method! Do you know tethering itself? Yes / No”, As shown in FIG. 4, “EXPLAIN ()” is not included in the “jump destination status”, and only “see TETERING task table”, and therefore “see TETERING task table” is executed. In this case, the question sentence generation unit 11 searches “usage status” of “parameter” in which “acquired value” is not stored in the task table of FIG. 10 in order from the upper side of the task table, and is detected first. In addition, a question sentence corresponding to “usage status” of “parameter” in which “acquired value” is not stored is acquired from the scenario table (FIG. 4). For example, when the “acquired value” corresponding to the parameter “OS” is not stored, the question sentence generation unit 11 corresponds to “THETERING_OS” that is the “usage status” of the parameter “OS” as described above. The question sentence to be obtained is acquired from the scenario table (FIG. 4), and the question sentence “Which terminal is used?...

  Note that the method for acquiring a question sentence when the current status is “refer to the task table of TETERING” is the same as in step S10-8.

  The character string input in step S5 with respect to the question sentence output based on the task table is stored as an “acquired value” corresponding to the “parameter” that is the source of the question sentence in the task table of the question sentence. Is done.

  Further, in the scenario table (FIG. 4), the “jump destination status” of the “TETHERING_OS” status is “refer to the task table of the THETERING”. Therefore, in this case, the task table of FIG. 10 is referred again. When the task table is referred to for the second time, in step S10-5 or S10-8, the question sentence generation unit 11 obtains a question sentence corresponding to the “usage status” of the parameter “CONNECT” corresponding to “TETHERING_CONNECT”. In step S10-9, the question sentence is output to the dialogue control unit 13. In FIG. 10, for convenience, a scenario record having a “TETHERING_CONNECT” status is omitted.

  In this case, a character string for the question sentence is input by the user in step S5 of FIG. 3, and the character string is stored in the task table (FIG. 10) as an acquired value for “CONNECT” in FIG. As a result, all the parameters corresponding to the “TETHERING” task have been acquired.

  In this state, the determination in step S9 in FIG. In the task table (FIG. 4), since the value of “task” has been changed to the “TETHERING” status with “task TRUE”, acquisition of all parameters corresponding to the task related to the “TETHERING” status has been completed. It is. In this case, steps S11 and S12 are executed.

  Note that there may be a plurality of task tables stored in the dialogue scenario storage unit 161 other than THETHERING, such as those relating to Wi-Fi (registered trademark) and those relating to other ICT terms. In this case, a status corresponding to each task table (for example, “refer to task table of Wi-Fi (registered trademark)” or the like may be set in the “jump destination status” of the scenario table (FIG. 4).

  Next, details of step S11 will be described. FIG. 11 is a flowchart for explaining an example of a processing procedure of an answer sentence generation process.

  In step S11-1, the answer sentence generation unit 15 requests the knowledge amount estimation unit 151 to estimate the knowledge amount of the user.

  Subsequently, the character input speed calculation unit 1511 of the knowledge amount estimation unit 151 calculates the character input speed with reference to the character input speed storage unit 162 (FIG. 5) (S11-2). For example, the number of characters is counted for each character string input by the user, and the speed (number of input characters per second) is calculated for each character string by dividing the number of characters by the required time of the character string. Furthermore, the character input speed calculation unit 1511 calculates the average value of the speeds of all the character strings input so far as the character input speed.

For example, if the stored contents of the character input speed storage unit 162 are as shown in FIG. 5, the character input speed is calculated as follows.
No. 1 speed = 12 characters / 10 seconds = 1.2 characters / second 2 speed = 3 characters / 3 seconds = 1 character / second Speed of 3 = 5 characters / 3 seconds = 1.667 characters / second Character input speed = (1.2 + 1 + 1.667) /3=1.289
Subsequently, the term understanding level calculation unit 1512 of the knowledge amount estimation unit 151 calculates the term understanding level with reference to the term understanding storage unit 163 (FIG. 8) (S11-3).

  FIG. 12 is a diagram showing a first example of a term comprehension calculation method. In FIG. 12, the content of the term understanding storage unit 163 (FIG. 8) is stored on the coordinates with the vertical axis representing the determination result of whether or not the term is understood (no understanding = 0, with understanding = 1), and the difficulty is the horizontal axis. Is plotted, and an example in which the maximum difficulty level below the inflection point is used as the term comprehension degree by approximating the logistic curve is shown. In the example of FIG. 12, the term comprehension degree calculation result is 2.

  Note that the term comprehension calculation method is not limited to this. FIG. 13 is a diagram illustrating a second example of a term comprehension calculation method. FIG. 13 shows an example in which the maximum difficulty level in which 0 does not exist is defined as the term comprehension level as a result of plotting the storage contents of the term understanding storage unit 163 (FIG. 8) on the same coordinates as in FIG. In this case as well, the term comprehension calculation result is 2.

  Subsequently, the knowledge amount estimation unit 151 estimates the knowledge amount using the character input speed calculated by the character input speed calculation unit 1511 and the term understanding level calculated by the term understanding level calculation unit 1512 (S11-4). . The amount of knowledge is an index indicating the level of knowledge of the user regarding the field related to the user's initial question (ICT field) or terms in the field.

  FIG. 14 is a diagram illustrating a first example of a knowledge amount estimation method. In FIG. 14, a correspondence table in which a knowledge amount corresponding to the character input speed and term comprehension level is prepared, and the knowledge amount is estimated by applying the calculated character input speed and term comprehension level to the correspondence table. An example of doing (determining) is shown. For example, the correspondence table may be stored in advance in the auxiliary storage device 102 or the like.

  FIG. 15 is a diagram illustrating a second example of the knowledge amount estimation method. FIG. 15 shows an example in which a calculation formula is prepared using the character input speed and the term comprehension as variables, and the knowledge amount is obtained based on the calculation result obtained by applying the calculated character input speed and term comprehension to the calculation formula. It is shown.

  14 and 15, both the character input speed and the term comprehension degree are discrete values, but the character input speed and the term comprehension degree may be continuous values. The knowledge amount is also a discrete value in the present embodiment, but may be a continuous value. In other words, the knowledge amount may be any value as long as the knowledge amount can be estimated based on the character input speed and the term comprehension level.

  Subsequently, the answer sentence generation unit 15 acquires an answer sentence from the acquisition destination of the answer sentence corresponding to the task to be executed (S11-5). The acquisition destination can be specified by referring to the value of “response sentence acquisition destination” in the task table (FIG. 10) corresponding to the task. In the example of FIG. 10, the “answer text acquisition destination” for the “TETHERING” task is “TETHERING_R (OS, CONNECT)”. Here, “TETHERING_R” means an answer sentence table stored in the dialogue scenario storage unit 161 in association with the task of “TETHERING”. “(OS, CONNECT)” is information for specifying one record from a plurality of records stored in the answer statement table, and each value of “OS” and “CONNECT” It is replaced with a specific acquired value corresponding to.

  FIG. 16 is a diagram illustrating a configuration example of a response statement table of THETERING in the dialogue scenario storage unit 161.

  As shown in FIG. 16, “answer text” is stored in the answer text table in association with “condition”. “Condition” is a condition for which the corresponding “answer text” is an acquisition target, and corresponds to the value of “answer text acquisition destination” in the task table. “Answer sentence” is a character string constituting the answer sentence.

  For example, when the “acquired value” for the parameter “OS” of the “TETHERING” task is “OS-B” and the “acquired value” for the parameter “CONNECT” is “Wi-Fi (registered trademark)”, FIG. In 16, the answer sentence stored in the first record is acquired.

  Subsequently, the answer sentence generation unit 15 determines whether or not the knowledge amount estimated in step S11-4 is the highest level at the defined stage (S11-6). For example, in the present embodiment, since the difficulty level is defined in five stages of 1 to 5, 5 is the highest level. If the knowledge amount is the highest level, the process proceeds to step S11-9, and if not, the process proceeds to step S11-7.

  In step S11-7, the answer sentence generation unit 15 refers to the term understanding storage part 163 (FIG. 8), and uses a term (hereinafter referred to as “conversion target term”) having a higher difficulty level than the knowledge amount level from the answer sentence. .) Is extracted. For example, when the answer sentence of the first record in the answer sentence table of FIG. 16 is acquired, the term “Wi-Fi (registered trademark)” having a difficulty level of 2 and “ The term “SSID”, the term “tethering” having a difficulty level of 4, and the like are included. In this case, when the user's knowledge amount is 3, “Wi-Fi (registered trademark)” whose difficulty level is equal to or lower than the user's knowledge amount level is not extracted as a conversion target term, and the level of the knowledge amount “SSID” and “tethering” having a higher difficulty level are extracted as conversion target terms.

  Subsequently, the answer sentence generation unit 15 refers to the term explanation storage unit 164 (FIG. 9), acquires the term explanation sentence of the conversion target term, and includes the term explanation sentence in the answer sentence, thereby responding to the user initial question. An answer sentence indicating the system answer is generated (S11-8). For example, in the “... 3. Press“ Tethering ”...” section, “... 3.“ Tethering (by turning the smartphone into a mobile router, you can use your smartphone's 3G line or LTE to connect your PC etc. A term explanation may be included immediately after the term to be converted, such as “a function capable of connecting to the Internet)”. Note that the answer sentence generation unit 15 may generate a natural sentence including a term explanation sentence immediately after the conversion target term without using the answer sentence table.

  In step S <b> 11-9, the answer sentence generation unit 15 outputs an answer sentence to the dialog control unit 13. The dialogue control unit 13 outputs the answer sentence to the dialogue sentence output unit 14. As a result, the dialogue sentence output unit 14 outputs the answer sentence in step S12 of FIG.

  In the above, instead of the character input speed, the number of typographical errors (for example, the number of character deletions) or the character input time (absolute time, not speed) is the information (index) ).

  In the above description, an example in which the user's opening question and the question sentence are input by the user by a character string and the output of the question sentence and the answer sentence are displayed on the display device 106 by the character string has been described. It may be input or output. For example, the user opening question may be input by the user's utterance. In this case, the text input unit 12 receives the text obtained as a result of recognizing the user's utterance by a voice recognition unit (not shown) instead of the character string input by the user, and is completed after the user starts the utterance. Measure the time required to complete. As for the start and completion time point of the utterance by the user, for example, the time point when the immediately previous output processing by the system is completed is set as the start timing of the utterance by the user, and a predetermined operation on the input device 107 (for example, pressing the “send” button) If time is the completion timing of the utterance, it can be detected. In this way, instead of the character string input by the user, text obtained as a result of recognizing the user's utterance by a voice recognition unit (not shown) may be used as the character string. Moreover, the output of the question sentence and the answer sentence by the dialogue apparatus 10 may be outputted in a form in which the agent of the dialogue apparatus 10 speaks as a voice.

  As described above, according to the present embodiment, with respect to the user of the conversation partner, the input information indicating whether or not the term is understood and the non-linguistic information of the user (the state of the input operation of the user response such as the character input speed) Based on the above, it is possible to estimate the level of knowledge (knowledge amount) of the user in the field related to the question from the user (user initial question). Therefore, it is possible to improve the estimation accuracy of the knowledge of the user of the conversation partner, and to enable a more appropriate conversation (generation of an answer sentence). For example, it can be estimated up to what the user's known and unknown terms are.

  Note that this embodiment may be applied to estimation of knowledge in a field other than ICT.

  In the present embodiment, the text input unit 12 is an example of a reception unit. The dialogue sentence output unit 14 is an example of an output unit. The knowledge amount estimation unit 151 is an example of an estimation unit. The answer sentence generation unit 15 is an example of a generation unit.

  Although the embodiments of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications can be made within the scope of the gist of the present invention described in the claims. Deformation / change is possible.

DESCRIPTION OF SYMBOLS 10 Dialogue apparatus 11 Question sentence generation part 12 Text input part 13 Dialogue control part 14 Dialogue sentence output part 15 Answer sentence generation part 100 Drive device 101 Recording medium 102 Auxiliary storage device 103 Memory device 104 CPU
105 interface device 106 display device 107 input device 111 option determination unit 112 term understanding determination unit 151 knowledge amount estimation unit 161 dialogue scenario storage unit 162 character input speed storage unit 163 term understanding storage unit 164 term explanation storage unit 1511 character input speed calculation unit 1512 Term Comprehension Calculation Unit B Bus

Claims (4)

A reception unit that receives input of a first question from a user;
An output unit that outputs a second question that asks the user whether or not he / she understands terms related to the first question;
An estimation unit that estimates a level of knowledge of the user related to a field related to the first question, based on a content of an answer to the second question and a state of an input operation of a character string indicating the answer;
According to the level estimated by the estimation unit, a generation unit that generates the content of an answer to the first question;
An interactive apparatus characterized by comprising: The generation unit is understood by the user among the terms included in the answer to the first question based on the difficulty level stored in the storage unit for each term and the level estimated by the estimation unit. A term that is presumed not to be identified, and an explanation stored in the storage unit for the identified term is included in the answer to the first question,
The interactive apparatus according to claim 1. The estimation unit estimates the level based on a difficulty level stored in a storage unit for a term understood by the user, which is specified based on a content of an answer to the second question. ,
The interactive apparatus according to claim 1 or 2, wherein An acceptance procedure for accepting an input of a first question from a user;
An output procedure for outputting a second question asking the user whether or not he / she understands terms related to the first question;
An estimation procedure for estimating a level of knowledge of the user regarding a field related to the first question, based on a content of an answer to the second question and a state of an input operation of a character string indicating the answer;
A generation procedure for generating a content of an answer to the first question according to the level estimated in the estimation procedure;
A program that causes a computer to execute.

Images