Information processing device, information processing method, and program

Abstract

To assist in asking questions for quickly and accurately grasping problems that a manager has, so that an accurate advice is given to the manager.SOLUTION: A plurality of prepared main question item data and sub-question item data are read out; questions are sequentially executed: and when one main question is executed, a response time taken until an answer is given accordingly is measured; the response time is compared with a predetermined reference time, so that the main question is classified into an immediate-response question for which the response time is less than or equal to the reference time or a non-immediate-response question for which the response time is greater than the reference time; an immediate-response pattern is generated in which the immediate-response pattern is a pattern formed by the immediate-response questions and the non-immediate-response questions for the plurality of main questions based on the order of the questions; one sub-question group is selected from a plurality of sub-question groups corresponding to the immediate-response patterns; and thereby the question is executed.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] In today's world, where social and economic conditions are changing so rapidly that they are difficult to predict, business managers are required to constantly gather information and make quick decisions based on that information. When making such management decisions or formulating new management policies, they often seek the support of various consultants with extensive knowledge and experience, and the presence of excellent consultants with advanced experience and skills is important for business managers.

[0003] On the other hand, even for such capable consultants, catching up with specialized knowledge is a challenge in an advanced technological society where IoT is being incorporated into business, and various attempts have been made to mechanize the consulting work itself. For example, Patent Document 1 proposes a management support system in which a second consultant can share management guidance information created by one consultant with the financial management information of the user receiving the consulting on the system, so that the second consultant can provide a second opinion on the management guidance information created by the first consultant. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6662536 Summary of the Invention [Problem to be solved by the invention]

[0005] However, even the introduction of second opinions as proposed in Patent Document 1 may not provide substantial support to managers who must make important business decisions quickly. In other words, while consulting requires an objective overview of the manager's situation, it is even more important to empathize with the manager's true concerns and uncover deep thoughts that the manager himself may not even be aware of. In this regard, the consultant's ability to elicit information, or in other words, questioning skills, backed by experience and knowledge, is crucial. However, consultants with such questioning skills are not easy to find, posing a pressing problem for managers seeking management advice.

[0006] One of the objects of the present invention is to provide an information processing device, an information processing method, and a program that can assist in asking questions that will enable quick and accurate understanding of problems that a manager is facing in order to provide accurate advice to the manager. [Means for solving the problem]

[0007] In order to achieve the above and other objects, an information processing device according to one aspect of the present invention comprises: a main question memory unit storing data on a plurality of prepared main question items; a sub-question memory unit storing data on a plurality of prepared sub-question items; a question execution unit that reads the main question item data from the main question memory unit and the sub-question item data from the sub-question memory unit and executes questions sequentially; and a response analysis unit that, when the question execution unit executes a main question, measures a response time, which is the time it takes for a response to the main question to be provided, and compares the measured response time with a predetermined reference time to classify the main questions into quick-answer questions, which are main questions whose response times are determined to be equal to or shorter than the reference time, and non-quick-answer questions, which are questions whose response times are determined to be longer than the reference time, and generates quick-answer patterns, which are patterns formed by the quick-answer questions and non-quick-answer questions, for the main questions based on the order in which the questions were asked. The question execution unit selects one sub-question group from a plurality of sub-question groups, each of which includes a plurality of sub-questions, in accordance with the quick-answer pattern and executes the question. [Effects of the Invention]

[0008] According to the present invention, it is possible to assist in asking questions that enable quick and accurate understanding of problems that the manager is facing in order to provide the manager with appropriate advice. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a block diagram illustrating the configuration of hardware and functional blocks of a question support device according to an embodiment of the present invention. [Figure 2] FIG. 10 is a diagram illustrating an example of the configuration of a main question set according to an embodiment of the present invention. [Figure 3] FIG. 10 is a diagram showing an example of a configuration of a quick response pattern in one embodiment of the present invention. [Figure 4] FIG. 2 is a diagram illustrating an example of the configuration of training data according to an embodiment of the present invention. [Figure 5]FIG. 10 is a diagram showing an example of the configuration of a quick-answer pattern / sub-question correspondence table in one embodiment of the present invention. [Figure 6] FIG. 2 is a diagram illustrating an example of the configuration of an advice storage unit in one embodiment of the present invention. [Figure 7] 1 is a flowchart illustrating a question support process flow according to an embodiment of the present invention. [Figure 8] FIG. 2 is a diagram showing an example of a start-up screen of the question support device according to an embodiment of the present invention. [Figure 9] FIG. 2 is a diagram showing an example of an operation screen of the question support device according to an embodiment of the present invention. [Figure 10] FIG. 2 is a diagram showing an example of an operation screen of the question support device according to an embodiment of the present invention. [Figure 11] FIG. 10 is a diagram illustrating an example of a flow of question support in one embodiment of the present invention. [Figure 12] FIG. 10 is a diagram showing an example of a result output screen of a question support device according to another embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An information processing apparatus and an information processing method according to embodiments of the present invention will be described below with reference to the accompanying drawings.

[0011] [Concept of question support in this embodiment] In consulting, interviews are typically conducted with a large number of specific questions prepared based on management information about the user, with the aim of gaining a broad and in-depth understanding of the problems the consulting firm is supporting. When conducting such interviews, consultants often spend a significant amount of time gathering information about the user's business environment and formulating questions based on that information. Furthermore, the user must also expend time providing the information, and the interview itself consumes a significant amount of time. On the other hand, while interviews based on a vast amount of information can reveal a general picture of the issues, the actual management decisions the user must make are left entirely up to the user, often resulting in dissatisfaction with the fact that the expected results are not achieved despite the extensive time spent on the consulting.

[0012] The inventors have discovered that, rather than spending a long time preparing a wide range of questions for an interview, they can conduct a one-on-one interview with top management, ask carefully selected questions including those that at first glance do not seem directly related to management issues, and use the answers to those questions, the user's behavior when answering, and other information obtained at short intervals to uncover problems that even the user himself is not aware of. In particular, the inventors have arrived at the present invention based on the discovery that whether or not a user can immediately answer a question posed is correlated with the user's ability to uncover problems.

[0013] [Configuration of the question support device] First, the configuration of a question support device according to one embodiment of the present invention will be described. FIG. 1 is a block diagram showing an example configuration of a question support device 100 according to one embodiment of the present invention. The question support device 100 can be configured as a computer equipped with a communication function. Specifically, it can be suitably configured as, for example, a personal computer, tablet, or smartphone capable of communicating with a communication network such as a mobile communication network or the Internet. The question support device 100 as an information processing device illustrated in FIG. 1 includes a processor 110, a memory 120, an auxiliary storage unit 130, a data interface (IF) unit 150, an input / output unit 140, and a communication unit 160.

[0014] The processor 110 is hardware that implements the overall functions of the question support device 100 by executing the programs stored in the memory 120, and can be configured as a CPU, for example.

[0015] The memory 120 is configured with storage devices such as RAM, ROM, and flash memory, and stores various programs for realizing the functions of the question support device 100.

[0016] The auxiliary storage unit 130 stores question data used by the programs stored in the memory 120, data related to quick answer patterns (described later), etc. The auxiliary storage unit 130 can be configured with a storage device such as a solid-state drive (SSD) or a hard disk drive (HDD). Note that all or part of the programs stored in the memory 120 may be stored in the auxiliary storage unit 130 in advance and read from the auxiliary storage unit 130 to the memory 120 when the processor 110 executes them.

[0017] The input / output unit 140 includes input devices such as a touch panel, keyboard, mouse, and microphone for receiving data input operations to the question support device 100, and output devices such as a display and speaker of an appropriate format.

[0018] The data IF unit 150 is an interface circuit having functions such as data input / output between the processor 110 and the auxiliary storage unit 130, the input / output unit 140, and the communication unit 160. The communication unit 160 is a communication module that controls the communication function of the question support device 100, and has the function of sending data from the data IF unit 150 to a communication network and transferring data received from the communication network to the data IF unit 150. The communication unit 160 is realized as hardware such as a mobile communication module, a network interface card (NIC), or a wireless LAN module.

[0019] Next, we will explain the functions of the question support device 100. The functions of the question support device 100 are realized by the processor 110 executing a question posing unit 121, a response analysis unit 122, and a quick answer pattern learning unit 123, which are programs stored in the memory 120.

[0020] The question execution unit 121 has a function of reading and outputting question data stored in the main question storage unit 131 and the sub-question storage unit 132 (described later). In this embodiment, "executing a question" includes the meaning that the question support device 100 outputs the contents of the main question or the sub-question visually or acoustically to the outside via the input / output unit 140. FIG. 2 shows an example of the configuration of a main question set stored in the main question storage unit 131 of the auxiliary storage unit 130. The main question set is a collection of question sets, each containing 10 questions, and includes the questions that are initially given to the respondent when using the question support device 100 of this embodiment. In the example of FIG. 2, n main question sets S1 to Sn are prepared as main question sets, but at least one main question set is sufficient. The inventors have found that main questions are carefully selected questions that are considered suitable for revealing the true feelings hidden deep in the respondent's mind, or psychological states that the respondent himself or herself is not aware of, and that the next question to be given to the respondent is determined depending on the response time to these questions. The sub-question storage unit 132 contains a sub-question set, which is a collection of sub-questions selected depending on the response status to such main questions. Although not shown in the figure, the sub-question storage unit 132 stores the sub-question set in a configuration similar to that of the main question storage unit 131 in Figure 2. The content of the sub-questions included in the sub-question set naturally differs from that of the main question, and can be questions that ask more specific content based on the content of the main question.

[0021] The response analysis unit 122 measures the response time, which is the time required from when the question execution unit 121 poses a question to the respondent until the respondent begins to respond. The response time is measured based on the audio level collected by a microphone, from the time the questioner finishes reading the question aloud or from the time the question screen is displayed to the respondent until the respondent begins to speak, but the method is not limited to this. The response analysis unit 122 also compares the measured response time with a predetermined threshold value, and determines that a response is immediate if the response time is below the threshold value, and not immediate if the response time is above the threshold value. The response analysis unit 122 then generates an immediate response pattern based on whether the response to each main question is immediate or not. Figure 3 shows an example of the configuration of an immediate response pattern. In this embodiment, the immediate response pattern is a pattern obtained by recording whether the respondent was able to immediately answer each of 10 main questions when asked. Whether or not a response is immediate may be determined based on any appropriate criteria. In this embodiment, an immediate response is determined if the respondent begins to respond within three seconds after the question is finished. In the configuration example of Figure 3, a 1 is assigned to an immediate answer to 10 main questions, and a 0 is assigned to an inability to give an immediate answer, and a string of 10 0s and 1s is used as an immediate answer pattern.

[0022] The quick response pattern learning unit 123 has a function of learning the correlation between quick response patterns obtained from the respondent's response time to the main question and the questioning results between the sub-questions posed corresponding to each quick response pattern, using the training data stored in the training data storage unit 133 of the auxiliary storage unit 130. FIG. 4 shows an example of the configuration of the training data in this embodiment. In the example of FIG. 4, the training data is a dataset that records evaluation values ​​for the correspondence between quick response patterns and sub-question sets, which evaluate whether the interview with the respondent was successful for each combination. In other words, the combination of the main question and the sub-question used elicited an expected or unexpected response from the respondent in a short time, and to what extent. In the example of FIG. 4, the evaluation values ​​are expressed on a 10-point scale from 0 (lowest) to 10 (highest), but are not limited to this.

[0023] The quick answer pattern learning unit 123 uses the above-mentioned teacher data to perform learning so that it can output a set of sub-questions that will obtain a higher evaluation value when a quick answer pattern is given as input. A well-known method as a supervised learning algorithm can be used for this learning, and a detailed description thereof will be omitted. In the question support device 100 of this embodiment, the quick answer pattern learning unit 123 performs a learning process based on teacher data prepared offline in advance, generates a quick answer pattern trained model, and stores it in the quick answer pattern storage unit 134. When the question support device 100 is first used, the question support process is executed using the quick answer pattern trained model. The response analysis unit 122 can input a quick answer pattern obtained through a main question into this trained model, thereby selecting a set of sub-questions to use correspondingly.

[0024] Alternatively, a simpler configuration may be used in advance to set a set of sub-questions to be used in association with a quick answer pattern based on the evaluation results of combinations of a quick answer pattern determined from past main question responses and a set of sub-questions used in response to that quick answer pattern. Figure 5 shows an example of a quick answer pattern-sub-question correspondence table. The quick answer pattern-sub-question correspondence table shows the sub-question set to be used next in association with the quick answer pattern obtained as a result of the main question. In the example of Figure 5, if quick answer pattern P1 is obtained as a result of the main question, sub-question set No. 2 is selected to continue the question. Furthermore, if it is determined that there is no quick answer as a result of the main question (quick answer pattern P0), the answerer was unable to respond effectively to the main question, and therefore there is no point in proceeding to sub-questions, and the question is terminated. As an embodiment of the present invention, a simple question support device 100 that does not use a learning process can also be realized.

[0025] The question support device 100 according to this embodiment can be further configured to provide the answerer with advice extracted based on a quick answer pattern obtained by answering the main question and a group of sub-questions selected according to the quick answer pattern. The advice is stored in advance as advice item data in the advice storage unit 135 provided in the auxiliary storage unit 130 (FIG. 2). An example of the configuration of the advice storage unit 135 is shown in FIG. 6. In the example of FIG. 6, the advice item data includes an advice ID for uniquely identifying each advice item, advice content (text indicating the advice content), a corresponding quick answer pattern, and each item of the corresponding sub-question group. The quick answer pattern corresponds to the quick answer pattern exemplified in FIG. 3. The sub-question group indicates a group of sub-questions selected according to a quick answer pattern obtained based on the response time to the main question. In this embodiment, advice content that has been given to the answerer in accordance with a combination of a quick answer pattern and a corresponding sub-question group is associated with an advice ID and stored in the advice storage unit 135. In other words, the advice storage unit 135 is a data table in which advice items that have been given to respondents in the past are organized using quick answer patterns and sub-questions as keys. In the question support device 100 of this embodiment, the response analysis unit 122 can extract advice item data based on combinations of quick answer patterns and sub-questions, and output the contents as described below (FIG. 12).

[0026] [Question Support Processing by the Question Support Device 100] Next, a description will be given of question support data processing by the question support device 100 of this embodiment. An example of the question support data processing flow is shown in a flowchart in Fig. 7. The question support data processing is executed by the question posing unit 121 and the response analysis unit 122 of the question support device 100.

[0027] Fig. 8 shows an example of the startup screen of the question support device 100. By operating the "Start Question" button on the screen of Fig. 8, the question execution unit 121 reads out the main question set from the main question storage unit 131 in step S701 of Fig. 7, and asks a question in step S702. The following modes of question execution are possible.

[0028] (1) When the interviewer conducts a face-to-face interview with the respondent In this case, the question support device 100 is in the form of a laptop or tablet and can support the questioner by displaying questions on a display, reading out questions aloud, or performing both operations. Fig. 9 shows an example of the operation screen of the question support device 100. In the example of Fig. 9, main question 1 is displayed on the screen, along with an operation button for executing the next question. (2) When the questioner conducts an online interview with the respondent In this case, the procedure is basically the same as when the question is answered face-to-face, but the output screen of the question support device 100 can be shared online with the respondent to display the questions. (3) When the respondent answers the questions alone The question support device 100 can also be used as a self-questioning tool to help the user receiving support become aware of their own unconscious deep psychology. In this case, the answerer actually answers verbally to the question support device 100, and the question support device 100 measures the response time.

[0029] In step S703, the response analysis unit 122 measures the time that has elapsed since the question was read and the answerer began speaking. Specifically, for example, the response analysis unit 122 determines the time from when the questioner finished reading the question to when the answerer next began speaking based on the input voice level of the microphone, and records the time that has elapsed between them.

[0030] In step S704, the response analysis unit 122 determines whether the measured response time is equal to or less than a predetermined threshold. In this embodiment, this threshold is set to 3 seconds. If it is determined that the response time is equal to or less than the threshold (YES in step S704), the response analysis unit 122 determines in step S705 that the response was immediate. If it is determined that the response time is greater than the threshold (NO in step S704), the response analysis unit 122 determines in step S706 that the response was not immediate.

[0031] In step S707, the response analysis unit 122 determines whether there is a next question in the main question set. If it is determined that there is a next question (YES in step S707), the response analysis unit 122 returns to step S701 and reads out the next main question. If there is no next question, that is, if it is determined that all questions in the main question set have been answered (NO in step S707), the response analysis unit 122 generates a quick-answer pattern in step S708.

[0032] In step S709, the response analysis unit 122 inputs the generated quick answer pattern into the trained model and determines whether there is a corresponding sub-question. If it is determined that there is a corresponding sub-question (YES in step S709), the question execution unit 121 executes the question using the selected sub-question set. Thereafter, in step S711, the response analysis unit 122 extracts corresponding advice item data from the advice storage unit 135 based on the combination of the quick answer pattern and the sub-question set, outputs the advice content, and ends the question support process. If it is determined that there is no corresponding sub-question (NO in step S709), the question execution unit 121 proceeds to the process of step S711. Figure 10 shows an example of an operation screen when the main question has been completed and a sub-question set has been selected based on a quick answer pattern. In the example of Figure 10, the quick answer pattern of the main question is P6, and the sub-question set No. 3 has been selected corresponding to it. This operation screen is configured so that the questioner can choose whether to continue the question using the selected sub-question set or to interrupt the question. The flow of the above-mentioned question support process is shown in Fig. 11. In the example of Fig. 11, based on the quick answer pattern P1 obtained as a result of the 10 main questions, further questions are asked using sub-questions included in sub-question set No. 1. In addition, advice AD1 is extracted from the advice storage unit 135 in correspondence with the selected sub-question set No. 1.

[0033] According to the question support process described above, questions that are considered to be more likely to get to the respondent's innermost thoughts and true feelings can be selected and asked based on the quick response pattern that indicates the respondent's degree of quick response to questions that have already been asked, thereby achieving the effect of obtaining information that will help the respondent solve the problems they are facing in a shorter amount of time.

[0034] [Example of output of question execution results] Fig. 12 shows an example of an output screen that is displayed when the question support process according to this embodiment is completed. The example in Fig. 12 is configured to display the quick answer patterns determined for the main question set used in the completed questioning (interview), the response time for each main question and whether or not it was a quick answer, the type of sub-question set selected based on the quick answer patterns, and their question items. By displaying these items, the questioner can use them to review and summarize the content of the question and answer.

[0035] The output screen example shown in FIG. 12 also includes a comment input field, an advice field, and a result evaluation field. The comment input field allows the questioner who asked the question or the answerer who used the question support device 100 as a self-question-and-answer tool to enter text about the question item, their impressions at the time of the response, and their evaluation of the Q&A content. This field is useful for evaluating the results of the Q&A session. The advice field displays the text of advice item data extracted from the advice storage unit 135 based on the combination of the corresponding quick-answer pattern and sub-question group. The result evaluation field allows the questioner or answerer to enter a subjective numerical evaluation of the required time and the quality of the Q&A content. The evaluation value is, for example, a 10-point scale ranging from 0 (lowest) to 10 (highest), although the evaluation method may be changed as appropriate. The entered result evaluation value is incorporated into training data for learning quick-answer patterns by operating the “Send Evaluation Result” button. This improves the accuracy of the correlation between quick-answer patterns and sub-question sets.

[0036] As described above, the question support device according to the embodiment of the present invention can support the asking of questions that enable the problems that the manager is facing to be grasped quickly and accurately in order to provide the manager with appropriate advice.

[0037] It is also possible to provide a teacher data storage unit that stores teacher data that associates, for combinations of the quick answer patterns and the sub-questions selected corresponding to each quick answer pattern, evaluation values ​​related to the results of questions and answers using the sub-questions; a quick answer pattern learning unit that generates, based on the teacher data, a trained model that is configured to output the sub-questions when the quick answer pattern is input; and a quick answer pattern storage unit that stores the trained model generated by the quick answer pattern learning unit. In this way, it becomes possible to learn a suitable combination from the results of evaluation of questions and answers performed using combinations of quick answer patterns and sub-questions, and to present a group of sub-questions to be selected for a quick answer pattern.

[0038] Furthermore, the evaluation values ​​recorded in the training data may include evaluation values ​​for one of the evaluation items, for the combination of the quick answer pattern and the group of sub-questions, the time required for questions and answers conducted using the group of sub-questions, and the level of satisfaction with the results obtained by the questions and answers. In this way, the combination of a quick-answer pattern and a group of sub-questions is evaluated based on the time required for the question and answer session or the degree of satisfaction with the results obtained, so that a group of sub-questions that is likely to receive high marks for these evaluation items can be selected.

[0039] The question support device may also generate and output an output screen including at least any of the items of the quick answer patterns obtained for the answers to the main questions, the response times and the type of quick answer as to whether or not the answers were quick, and the sub-questions used. In this way, the quick answer pattern, the response time to each main question, the type of quick answer or not, and the sub-questions used are displayed, making it easier for the user to review the content of the questions and answers.

[0040] Furthermore, the output screen can be configured to allow input of an evaluation value relating to the results of questions and answers using the sub-questions for each combination of the quick answer pattern and the sub-questions selected corresponding to each quick answer pattern, and the combination of the quick answer pattern, the sub-questions, and the input evaluation value can be stored as training data in a training data storage unit. In this way, teacher data can be generated by entering evaluation values ​​for questions asked on the output screen, and the teacher data can be updated each time a question is asked using the question support process.

[0041] Furthermore, an advice storage unit may be provided in which a plurality of advice item data, each containing advice to be given to the respondent of a question, is stored in advance in association with the quick answer patterns and the group of sub-questions, and the response analysis unit may extract and output the associated advice item data from the advice storage unit based on the quick answer patterns and the group of sub-questions obtained in response to the main question. In this way, based on the combination of the quick answer pattern and the sub-question group, it is possible to select and output advice that is preliminarily associated with the answerer and that is considered to be useful to the answerer.

[0042] The above-described series of processes can be executed by hardware or software. In other words, the functional configuration of FIG. 1 is merely illustrative and is not particularly limited. That is, it is sufficient for the question support device 100 to have the functionality to execute the above-described series of processes as a whole, and the functional blocks used to realize these functions are not particularly limited to the example of FIG. 1. Furthermore, a single functional block may be configured as a single piece of hardware, a single piece of software, or a combination thereof. The functional configuration of this embodiment is realized by a processor that executes arithmetic processing. Processors that can be used in this embodiment include those configured as single processing units such as single processors, multiprocessors, and multicore processors, as well as those that combine these processing units with processing circuits such as ASICs (Application Specific Integrated Circuits) and FPGAs (Field-Programmable Gate Arrays).

[0043] When a series of processes is executed by software, the programs that make up the software are installed into a computer or the like from a network or a recording medium. The computer may be a computer built into dedicated hardware. Alternatively, the computer may be a computer that can execute various functions by installing various programs, such as a general-purpose personal computer.

[0044] The recording medium containing such a program may be a removable medium such as a USB memory that is distributed separately from the device main body in order to provide the program to the user, or may be a recording medium that is provided to the user in a state where it is pre-installed in the device main body. Removable media may be, for example, a magnetic disk (including a floppy disk), an optical disk, or a magneto-optical disk. Optical disks may be, for example, CD-ROMs (Compact Disk-Read Only Memory), DVDs (Digital Versatile Disks), Blu-ray (registered trademark) Discs, etc. Magneto-optical disks may be, for example, MDs (Mini-Disks), etc. Furthermore, recording media that are provided to the user in a state where they are pre-installed in the device main body may be, for example, a ROM on which the program is recorded, or a hard disk included in the storage unit 20.

[0045] In this specification, the steps of describing a program to be recorded on a recording medium include not only processes that are performed chronologically in accordance with the order, but also processes that are not necessarily performed chronologically but are performed in parallel or individually.

[0046] Although several embodiments of the present invention have been described above, these embodiments are merely illustrative and do not limit the technical scope of the present invention. The present invention can take various other embodiments, and it is also possible to combine the configurations of the above embodiments and modifications. Furthermore, various modifications such as omissions and substitutions can be made without departing from the spirit of the present invention. These embodiments and modifications thereof are included within the scope and spirit of the invention described in this specification, etc., and are included in the invention described in the claims and their equivalents. [Explanation of symbols]

[0047] 100 question support device 110 processors 120 memory 121 Question Execution Department 122 Response Analysis Unit 123 Quick Answer Pattern Learning Section 130 Auxiliary storage 131 Main question storage section 132 Subquestion storage section 133 Teacher data storage unit 134 Quick response pattern memory section 135 Advice Memory Unit 140 Input / output section 150 Data interface section 160 Communications Department

Claims

1. a main question storage unit storing a plurality of main question item data items prepared in advance; a sub-question storage unit storing a plurality of sub-question item data items prepared in advance; a question execution unit that reads the main question item data from the main question storage unit and the sub-question item data from the sub-question storage unit and executes questions in sequence; a response analysis unit that, when the question execution unit executes one main question, measures a response time, which is the time it takes for a response to the main question to be given, compares the measured response time with a predetermined reference time, and classifies the main questions into quick-answer questions, which are main questions whose response times are determined to be equal to or shorter than the reference time, and non-quick-answer questions, which are questions whose response times are determined to be longer than the reference time, and generates quick-answer patterns, which are patterns formed by the quick-answer questions and non-quick-answer questions, for a plurality of the main questions based on the order in which the questions were asked; a training data storage unit that stores training data in which, for each combination of the quick answer pattern and a group of sub-questions selected from a plurality of sub-question groups each including a plurality of sub-questions corresponding to the quick answer pattern, the training data is associated with an evaluation value related to a result of conducting a question and answer session using the group of sub-questions; a quick answer pattern learning unit that generates a trained model configured to output the group of sub-questions when the quick answer pattern is input based on the training data; and a quick response pattern storage unit that stores the trained model generated by the quick response pattern learning unit; the response analysis unit selects one sub-question group from the plurality of sub-question groups by inputting the quick answer pattern into the trained model, and the question execution unit executes a question using the selected sub-question group. Information processing device.

2. 2. The information processing device according to claim 1, wherein the evaluation values ​​recorded in the training data include evaluation values ​​for one of evaluation items, for a combination of the quick answer pattern and the sub-question group, the time required for questions and answers conducted using the sub-question group, and satisfaction with the results obtained by the questions and answers.

3. 3. The information processing device according to claim 1, wherein the information processing device generates and outputs an output screen including at least any of the items of the quick answer patterns obtained for the answers to the main questions, the response times and the type of quick answer for each of the main questions, and the sub-questions used.

4. 4. The information processing device according to claim 3, wherein the output screen is configured to allow input of an evaluation value relating to a result of questioning using a group of sub-questions for a combination of the quick answer pattern and the group of sub-questions selected corresponding to each quick answer pattern, and the combination of the quick answer pattern, the group of sub-questions, and the input evaluation value is stored as training data in a training data storage unit.

5. 3. The information processing device according to claim 1, further comprising an advice storage unit in which a plurality of advice item data, each containing advice to be given to a person answering a question, is stored in advance in association with the quick answer patterns and the group of sub-questions, and the response analysis unit extracts and outputs the associated advice item data from the advice storage unit based on the quick answer patterns and the group of sub-questions obtained in response to the main question.

6. The information processing device Store the data of multiple main questions prepared in advance, Store multiple sub-question item data prepared in advance, read out the stored main question item data and sub-question item data and execute questions in sequence; When one main question is asked, a response time is measured, which is the time it takes for a response to the main question to be given, and the measured response time is compared with a predetermined reference time to classify the main questions into quick-answer questions, which are main questions whose response times are determined to be equal to or shorter than the reference time, and non-quick-answer questions, which are questions whose response times are determined to be longer than the reference time, and a quick-answer pattern is generated for a plurality of the main questions, which is a pattern formed by the quick-answer questions and non-quick-answer questions based on the order in which the questions were asked; storing training data in which, for each combination of the quick answer pattern and a sub-question group selected from a plurality of sub-question groups each including a plurality of sub-questions, the training data associates the combination with an evaluation value related to a result of conducting a question and answer session using the sub-question group; generating a trained model configured to output the set of sub-questions when the quick-answer pattern is input based on the training data; and Storing the generated trained model; The quick answer pattern is input to the trained model to select one sub-question group from the plurality of sub-question groups, and a question is executed using the selected sub-question group. Information processing methods.

7. In the information processing device, Store the data of multiple main questions prepared in advance, Store the sub-questionnaire data that you have prepared in advance, read out the stored main question item data and sub-question item data and execute questions in sequence; When one main question is asked, a response time is measured, which is the time it takes for a response to the main question to be given, and the measured response time is compared with a predetermined reference time to classify the main questions into quick-answer questions, which are main questions whose response times are determined to be equal to or shorter than the reference time, and non-quick-answer questions, which are questions whose response times are determined to be longer than the reference time, and a quick-answer pattern is generated for a plurality of the main questions, which is a pattern formed by the quick-answer questions and non-quick-answer questions based on the order in which the questions were asked; storing training data in which, for each combination of the quick answer pattern and a sub-question group selected from a plurality of sub-question groups each including a plurality of sub-questions, the training data associates the combination with an evaluation value related to a result of conducting a question and answer session using the sub-question group; generating a trained model configured to output the set of sub-questions when the quick-answer pattern is input based on the training data; and Storing the generated trained model; a process of selecting one sub-question group from the plurality of sub-question groups by inputting the quick answer pattern into the trained model, and executing a question using the selected sub-question group; The program to be executed.

Images