Information processing device, output method, and output program

The information processing device addresses the inefficiency of staff answering repetitive customer inquiries by using voice recognition to identify and output answers to frequently asked questions, enhancing service efficiency and reducing staff workload.

WO2024241564A1PCT designated stage expired Publication Date: 2024-11-28MITSUBISHI ELECTRIC CORP

Patent Information

Application Number
PCT/JP2023/019454
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-25
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

Staff at counters, stations, and tourist spots face a burden from repeatedly answering similar customer inquiries, leading to inefficiencies and increased workload.

Method used

An information processing device equipped with voice recognition capabilities that acquires customer voice data, determines frequently asked questions, and outputs pre-defined answers to a display device, reducing the need for staff intervention.

Benefits of technology

The solution significantly reduces the burden on staff by providing immediate answers to frequently asked questions, thereby improving customer service efficiency and reducing staff workload.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2023019454_28112024_PF_FP_ABST
    Figure JP2023019454_28112024_PF_FP_ABST
Patent Text Reader

Abstract

An information processing device (100) comprises: an acquisition unit (120) that acquires speech data of a customer; a speech recognition execution unit (130) that executes speech recognition using the speech data; a determination unit (140) that determines whether a content of data is a frequently asked question when the content of the data acquired through the speech recognition is a question; and an output unit (150). When the content of the data is a frequently asked question, the acquisition unit (120) acquires an answer to the question which is the content of the data. The output unit (150) outputs the question and the answer to a display device (200).
Need to check novelty before this filing date? Find Prior Art

Description

Information processing device, output method, and output program

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

[0002] A ticket counter is installed at a station or the like. When a customer comes to the ticket counter, an attendant provides guidance, etc. A technology for analyzing the tendency of customer inquiries has been proposed (see Patent Document 1).

[0003] International Publication No. 2009 / 107211

[0004] Various customers come to the counter. Various customers may ask the clerk the same questions. It is a burden for the clerk to answer the same questions every time.

[0005] The purpose of the present disclosure is to reduce the burden on staff.

[0006] An information processing device according to one aspect of the present disclosure is provided. The information processing device is a device capable of outputting information to a display device. The information processing device includes an acquisition unit that acquires customer voice data, a voice recognition execution unit that performs voice recognition using the voice data, a determination unit that, when the content of the data acquired by voice recognition is a question, determines whether the content of the data is a frequently asked question, and an output unit. When the content of the data is a frequently asked question, the acquisition unit acquires an answer corresponding to the question that is the content of the data. The output unit outputs the question and the answer to the display device.

[0007] According to the present disclosure, the burden on staff can be reduced.

[0008] 1 is a diagram illustrating a provision system of a first embodiment. FIG. 1 is a diagram illustrating hardware included in an information processing device of the first embodiment. FIG. 2 is a block diagram illustrating functions of an information processing device of the first embodiment. FIG. 3 is a flowchart illustrating an example of processing executed by an information processing device of the first embodiment. FIG. 4 is a block diagram illustrating functions of an information processing device of the second embodiment. FIG. 5 is a flowchart illustrating an example of processing executed by an information processing device of the second embodiment. FIG. 6 is a diagram illustrating an example of a management table of the second embodiment. FIG. 7 is a block diagram illustrating functions of an information processing device of the third embodiment. FIG. 8 is a flowchart illustrating an example of processing executed by an information processing device of the third embodiment. FIG. 9 is a diagram illustrating an example of a management table of the third embodiment. FIG. 10 is a block diagram illustrating functions of an information processing device of a fourth embodiment. FIG. 11 is a flowchart illustrating an example (part 1) of processing executed by an information processing device of the fourth embodiment. FIG. 12 is a flowchart illustrating an example (part 2) of processing executed by an information processing device of the fourth embodiment. FIG. 13 is a flowchart illustrating an example (part 1) of processing executed by an information processing device of the fourth embodiment. Fig. 10 is a flowchart showing an example of processing executed by an information processing device of embodiment 6. Fig. 11 is a diagram showing an example of a management table of embodiment 6. Fig. 12 is a flowchart showing an example of processing executed by an information processing device of modified example 1 of embodiment 6.

[0009] Hereinafter, embodiments will be described with reference to the drawings. The following embodiments are merely examples, and various modifications are possible within the scope of the present disclosure.

[0010] Embodiment 1. Fig. 1 is a diagram showing a provision system according to embodiment 1. The provision system includes an information processing device 100, a display device 200, and a microphone 300. The information processing device 100, the display device 200, and the microphone 300 are connected via a network. The network may be a wired network or a wireless network.

[0011] The information processing device 100 is a device that executes an output method. The information processing device 100 is a device that can output information to the display device 200. The display device 200 is a device that displays information. For example, the display device 200 is a signage or a projector. The display device 200 is installed in stations, tourist spots, commercial facilities, etc.

[0012] For example, microphone 300 is installed at a counter in a station, a tourist spot, a commercial facility, etc. A customer's voice is input to microphone 300. Alternatively, an attendant's voice may be input to microphone 300. When the attendant's voice is input to microphone 300, information processing device 100 has a function of distinguishing between the attendant's voice data and the customer's voice data. The attendant is an attendant who is present at a station, a tourist spot, a commercial facility, etc.

[0013] Next, the hardware of the information processing device 100 will be described. Fig. 2 is a diagram showing the hardware of the information processing device of embodiment 1. The information processing device 100 is a computer. The information processing device 100 has a processor 101, a volatile storage device 102, and a non-volatile storage device 103.

[0014] The processor 101 controls the entire information processing device 100. For example, the processor 101 is a central processing unit (CPU) or a field programmable gate array (FPGA). The processor 101 may be a multiprocessor. The information processing device 100 may also include a processing circuit.

[0015] The volatile storage device 102 is a main storage device of the information processing device 100. For example, the volatile storage device 102 is a random access memory (RAM). The nonvolatile storage device 103 is an auxiliary storage device of the information processing device 100. For example, the nonvolatile storage device 103 is a hard disk drive (HDD) or a solid state drive (SSD).

[0016] Next, a description will be given of functions of the information processing device 100. Fig. 3 is a block diagram showing functions of the information processing device of embodiment 1. The information processing device 100 has a storage unit 110, an acquisition unit 120, a speech recognition execution unit 130, a determination unit 140, and an output unit 150.

[0017] The storage unit 110 may be realized as a storage area secured in the volatile storage device 102 or the non-volatile storage device 103. Some or all of the acquisition unit 120, the speech recognition execution unit 130, the determination unit 140, and the output unit 150 may be realized by a processing circuit. Furthermore, some or all of the acquisition unit 120, the speech recognition execution unit 130, the determination unit 140, and the output unit 150 may be realized as program modules executed by the processor 101. For example, the program executed by the processor 101 is also referred to as an output program. For example, the output program is recorded on a recording medium.

[0018] The storage unit 110 stores various information. The functions of the acquisition unit 120, the speech recognition execution unit 130, the determination unit 140, and the output unit 150 will be described in detail later.

[0019] Next, the processing executed by the information processing device 100 will be described using a flowchart. FIG. 4 is a flowchart showing an example of processing executed by the information processing device of embodiment 1. (Step S11) The acquisition unit 120 acquires customer voice data. For example, the acquisition unit 120 acquires voice data from the microphone 300. Alternatively, the acquisition unit 120 may acquire voice data from the microphone 300 via an external device. The external device is a device that exists outside the information processing device 100. For example, the external device is a cloud server. Note that the illustration of the external device is omitted. Also, the voice data may be called a voice signal.

[0020] (Step S12) The speech recognition execution unit 130 executes speech recognition using the speech data, thereby allowing the information processing device 100 to obtain data that is a character string.

[0021] (Step S13) The determination unit 140 determines whether the content of the data obtained by speech recognition is a question. For example, the determination unit 140 determines whether the content of the data is a question using a rule base. For example, a method using a rule base includes a dictionary method, a regular expression method, or the like. Furthermore, for example, the determination unit 140 determines whether the content of the data is a question using a trained model. The trained model can be created by machine learning, such as a deep neural network (DNN). For example, in machine learning, a large number of character strings are prepared as input data. Training data is prepared, in which a correct answer label is assigned when the character string in the input data is a question. Then, the trained model is created by performing machine learning using the input data and the training data so that the determination result, which is the output data of the trained model, matches the correct answer label. If the content of the data is a question, the process proceeds to step S14. If the content of the data is not a question, the process ends.

[0022] (Step S14) The determination unit 140 determines whether the content of the data is a frequently asked question. For example, the determination unit 140 makes the determination as follows. The storage unit 110 stores the number of times the information processing device 100 has acquired a question that is the same as or similar to the data. In other words, the storage unit 110 stores the number of times the information processing device 100 has acquired a similar question. The determination unit 140 increments the number. If the number is equal to or greater than a predetermined threshold, the determination unit 140 determines that the content of the data is a frequently asked question. If the condition is met, the process proceeds to step S15. If the condition is not met, the process ends.

[0023] (Step S15) The acquisition unit 120 acquires an answer corresponding to the content of the data (i.e., the question) from the storage unit 110 or an external device. (Step S16) The output unit 150 outputs the question and the answer to the display device 200. Alternatively, the output unit 150 may output the question and the answer to the display device 200 via an external device. As a result, the display device 200 displays the question and the answer. That is, the display device 200 displays frequently asked questions and the answers to those questions. The customer then visually checks the content displayed on the display device 200. As a result, the number of customers who ask questions to the staff member is reduced.

[0024] Therefore, according to the first embodiment, the information processing device 100 can reduce the burden on the staff.

[0025] Second Embodiment Next, a second embodiment will be described. In the second embodiment, differences from the first embodiment will be mainly described. Furthermore, in the second embodiment, descriptions of the commonalities between the first embodiment and the second embodiment will be omitted.

[0026] 5 is a block diagram showing the functions of the information processing device of embodiment 2. The information processing device 100 further includes an estimation unit 160. Part or all of the estimation unit 160 may be realized by a processing circuit. Alternatively, part or all of the estimation unit 160 may be realized as a program module executed by the processor 101. The functions of the estimation unit 160 will be described in detail later.

[0027] Next, the processing executed by the information processing device 100 will be described using a flowchart. FIG. 6 is a flowchart showing an example of the processing executed by the information processing device of embodiment 2. (Step S21) The acquisition unit 120 acquires voice data of the customer. (Step S22) The voice recognition execution unit 130 executes voice recognition using the voice data. As a result, the information processing device 100 obtains data that is a character string. (Step S23) The determination unit 140 determines whether the content of the data obtained by voice recognition is a question. If the content of the data is a question, the process proceeds to step S24. If the content of the data is not a question, the process ends.

[0028] (Step S24) The estimation unit 160 uses the data obtained by speech recognition to estimate a category corresponding to the content of the data. For example, the estimation unit 160 estimates the category using a rule base. Examples of methods using a rule base include a dictionary method and a regular expression method. Furthermore, for example, the estimation unit 160 estimates the category using a trained model. In detail, when the estimation unit 160 inputs the data into the trained model, the trained model outputs a category. Note that, for example, the category may be transfer transportation or lost property. Note that, for example, the trained model can be created by machine learning such as DNN. For example, in machine learning, a large number of character strings are prepared as input data. Training data is prepared in which categories corresponding to the character strings in the input data are used as correct labels. Then, the trained model is created by performing machine learning using the input data and the training data so that the categories, which are the output data of the trained model, match the correct labels.

[0029] (Step S25) The determination unit 140 determines whether a predetermined time has elapsed since the voice data corresponding to the estimated category was first acquired. For example, the determination unit 140 determines whether the time has elapsed since the voice data corresponding to the category "transfer transportation" was first acquired. If the time has elapsed, the process ends. If the time has not elapsed, the process proceeds to step S26.

[0030] (Step S26) The determination unit 140 determines whether the number of times that speech data corresponding to the estimated category has been acquired is equal to or greater than a predetermined threshold. Specifically, the determination unit 140 makes the determination as follows: The storage unit 110 stores the number of times that speech data has been acquired. The determination unit 140 increments the number of times that speech data has been acquired. The determination unit 140 determines whether the number of times that speech data has been acquired is equal to or greater than the threshold. If the number of times that speech data has been acquired is equal to or greater than the threshold, it means that questions in the estimated category are frequently asked. Note that the number of times that speech data has been acquired may be the rate of increase in the number of times that speech data has been acquired. If the number of times that speech data has been acquired is equal to or greater than the threshold, the process proceeds to step S27. If the number of times that speech data has been acquired is less than the threshold, the process ends.

[0031] (Step S27) The acquiring unit 120 acquires a question corresponding to the estimated category and an answer to the question. Specifically, the acquiring unit 120 acquires the question and the answer from a management table. An example of the management table is shown below.

[0032] FIG. 7 is a diagram showing an example of a management table in embodiment 2. Management table 111 is also referred to as management information. Management table 111 shows the correspondence between questions and answers. Specifically, management table 111 has items for item number, category, question, and answer. If the estimated category is transfer transportation, acquisition unit 120 acquires the question and answer corresponding to the category "transfer transportation." In other words, acquisition unit 120 acquires information for frame 11.

[0033] The management table 111 is stored in the storage unit 110 or an external device. If the management table 111 is stored in an external device, the acquisition unit 120 accesses the external device to acquire the questions and answers.

[0034] In this way, if the number of times that voice data corresponding to the estimated category is acquired within a predetermined time period is equal to or greater than a predetermined threshold, the acquisition unit 120 acquires a question corresponding to the estimated category and an answer to the question.

[0035] (Step S28) Output unit 150 outputs the question and answer to display device 200. As a result, display device 200 displays the question and answer. The customer then visually confirms the content displayed on display device 200. This reduces the number of customers who ask questions to the staff member.

[0036] Therefore, according to the second embodiment, the information processing device 100 can reduce the burden on the staff.

[0037] Embodiment 3 Next, embodiment 3 will be described. In embodiment 3, differences from embodiment 1 will be mainly described. Furthermore, in embodiment 3, descriptions of matters common to embodiment 1 will be omitted.

[0038] 8 is a block diagram showing the functions of the information processing device of embodiment 3. The information processing device 100 further includes a search unit 170. Part or all of the search unit 170 may be realized by a processing circuit. Alternatively, part or all of the search unit 170 may be realized as a program module executed by the processor 101. The functions of the search unit 170 will be described in detail later.

[0039] Next, the processing executed by the information processing device 100 will be described using a flowchart. FIG. 9 is a flowchart showing an example of processing executed by the information processing device of embodiment 3. (Step S31) The acquisition unit 120 acquires voice data of the customer. (Step S32) The voice recognition execution unit 130 executes voice recognition using the voice data. As a result, the information processing device 100 obtains data that is a character string. (Step S33) The determination unit 140 determines whether the content of the data obtained by voice recognition is a question. If the content of the data is a question, the process proceeds to step S34. If the content of the data is not a question, the process ends. (Step S34) The acquisition unit 120 acquires the management table 111 from the storage unit 110 or an external device.

[0040] (Step S35) The search unit 170 uses the management table 111 to search for questions that are identical or similar to the content of the data obtained by speech recognition (i.e., the question). For example, the search unit 170 uses the data as a query to search the management table 111. Also, for example, the search unit 170 extracts keywords from the data and uses the keywords as a query to search the management table 111. Also, for example, the search unit 170 vectorizes the data and a question registered in the management table 111, and compares the two vectorized data to search for identical or similar questions. As a result, for example, the search unit 170 identifies the question with item number "1."

[0041] (Step S36) The determination unit 140 determines whether a predetermined time has elapsed since the first acquisition of voice data identical or similar to the searched question. If the predetermined time has elapsed, the process ends. If the predetermined time has not elapsed, the process proceeds to step S37.

[0042] (Step S37) The determination unit 140 determines whether the number of times that voice data identical or similar to the searched question has been acquired is equal to or greater than a predetermined threshold. Specifically, the determination unit 140 makes the determination as follows: The storage unit 110 stores the number of acquisitions. The determination unit 140 increments the number of acquisitions. The determination unit 140 determines whether the number of acquisitions is equal to or greater than the threshold. If the number of acquisitions is equal to or greater than the threshold, it means that the searched question is frequently asked. If the number of acquisitions is equal to or greater than the threshold, the process proceeds to step S38. If the number of acquisitions is less than the threshold, the process ends.

[0043] (Step S38) The acquisition unit 120 acquires the searched question and the answer to that question from the management table 111. For example, the acquisition unit 120 acquires the question and answer of item number "1". (Step S39) The output unit 150 outputs the question and answer to the display device 200. As a result, the display device 200 displays the question and answer. The customer then visually checks the content displayed on the display device 200. As a result, the number of customers who ask questions to the staff member is reduced.

[0044] An example of the management table 111 is shown below. FIG. 10 is a diagram showing an example of the management table according to the third embodiment. In the second embodiment, questions and answers corresponding to a category are output. For example, the information in box 11 is output. On the other hand, in the third embodiment, the searched question and the answer to that question are output. For example, the information in box 12 is output. In this way, narrowed-down information is output. Therefore, according to the third embodiment, the information processing device 100 can output questions and answers that are more suited to the situation.

[0045] Embodiment 4 Next, embodiment 4 will be described. In embodiment 4, differences from embodiment 1 will be mainly described. Furthermore, in embodiment 4, description of matters common to embodiment 1 will be omitted.

[0046] A speaker may give a meaningfully connected speech in multiple parts. Therefore, if a determination is made based on the audio data of one speech, the information processing device 100 may not be able to perform appropriate processing. Therefore, the information processing device 100 has the following functions.

[0047] 11 is a block diagram showing the functions of the information processing device of embodiment 4. The information processing device 100 further includes a combining unit 180. Part or all of the combining unit 180 may be realized by a processing circuit. Alternatively, part or all of the combining unit 180 may be realized as a program module executed by the processor 101. The functions of the combining unit 180 will be described later.

[0048] Next, the processing executed by the information processing device 100 will be described using a flowchart. Fig. 12 is a flowchart showing an example (part 1) of the processing executed by the information processing device of embodiment 4. Fig. 13 is a flowchart showing an example (part 2) of the processing executed by the information processing device of embodiment 4. The processing in Figs. 12 and 13 differs from the processing in Fig. 4 in that steps S11a, 13a to 13d, 14a, and 15a are executed. Therefore, steps S11a, 13a to 13d, 14a, and 15a will be described in Figs. 12 and 13. Further, description of the processing other than steps S11a, 13a to 13d, 14a, and 15a will be omitted.

[0049] (Step S11a) The acquisition unit 120 acquires voice data for one episode. (Step S13a) The determination unit 140 determines whether the voice data acquired in step S11a is the first voice data of the same person. If the acquired voice data is the first voice data, the determination unit 140 stores data obtained by voice recognition in the storage unit 110. Then, the process proceeds to step S11a. If the acquired voice data is voice data of the same person, the process proceeds to step S13b. Note that the determination unit 140 can determine whether the acquired voice data is voice data of the same person by analysis.

[0050] (Step S13b) The determination unit 140 determines whether there is a semantic connection between the data obtained by speech recognition and the data stored in the storage unit 110. For example, the determination unit 140 determines whether there is a semantic connection using a rule base. For example, a method using a rule base is a method using a dictionary or a method using regular expressions. Furthermore, for example, the determination unit 140 vectorizes the data obtained by speech recognition and the data stored in the storage unit 110 and compares the two vectorized data to determine whether there is a semantic connection. If there is a semantic connection, the process proceeds to step S13c. If there is no semantic connection, the process proceeds to step S13d.

[0051] (Step S13c) The combining unit 180 combines the data obtained by the voice recognition with the data stored in the storage unit 110. The combining unit 180 stores the combined data in the storage unit 110. Then, the process proceeds to step S11a. (Step S13d) The acquiring unit 120 acquires the combined data from the storage unit 110. The combined data is data in which multiple pieces of voice data of the customer are combined, and is data in which content that is meaningfully connected is combined. If the combined data is not stored in the storage unit 110, the determining unit 140 performs the following process using voice data for one episode.

[0052] (Step S14a) The determination unit 140 determines whether the content of the combined data is a frequently asked question. For example, the determination unit 140 makes the determination as follows. The storage unit 110 stores the number of times the information processing device 100 has acquired a question that is the same as or similar to the combined data. In other words, the storage unit 110 stores the number of times the information processing device 100 has acquired a similar question. The determination unit 140 increments the number of times. If the number of times is equal to or greater than a predetermined threshold, the determination unit 140 determines that the content of the combined data is a frequently asked question. If the condition is met, the process proceeds to step S15. If the condition is not met, the process ends.

[0053] (Step S15a) The acquiring unit 120 acquires an answer corresponding to the content of the combined data (i.e., the question) from the storage unit 110 or an external device.

[0054] According to the fourth embodiment, the information processing device 100 determines whether a question is frequently asked based on multiple utterances that have a similar meaning, thereby enabling the information processing device 100 to make a more appropriate determination.

[0055] Furthermore, there are cases where a speaker inverts a sentence and utters multiple utterances that are connected in meaning. Even when a speaker speaks in this manner, the fourth embodiment is effective.

[0056] Here, the external device may execute steps S11a, S12, S13, and S13a to S13c. If the external device executes the processes, in step S13d, the acquiring section 120 acquires the combined data from the external device.

[0057] Modification 1 of Embodiment 4: Embodiment 4 can be combined with Embodiment 2. The process when Embodiment 2 and Embodiment 4 are combined will be described using a flowchart.

[0058] Fig. 14 is a flowchart showing an example (part 1) of processing executed by the information processing device of Modification 1 of Embodiment 4. Fig. 15 is a flowchart showing an example (part 2) of processing executed by the information processing device of Modification 1 of Embodiment 4. The processing in Figs. 14 and 15 differs from the processing in Fig. 6 in that steps S21a, 23a to 23d, 24a, 25a, and 26a are executed. Therefore, steps S21a, 23a to 23d, 24a, 25a, and 26a will be described in Figs. 14 and 15. Description of processing other than steps S21a, 23a to 23d, 24a, 25a, and 26a will be omitted.

[0059] (Step S21a) The acquisition unit 120 acquires voice data for one episode. (Step S23a) The determination unit 140 determines whether the voice data acquired in step S21a is the first voice data of the same person. If the acquired voice data is the first voice data, the determination unit 140 stores the data obtained by voice recognition in the storage unit 110. Then, the process proceeds to step S21a. If the acquired voice data is voice data of the same person, the process proceeds to step S23b.

[0060] (Step S23b) The determination unit 140 determines whether there is a semantic connection between the data obtained by speech recognition and the data stored in the storage unit 110. If there is a semantic connection, the process proceeds to step S23c. If there is no semantic connection, the process proceeds to step S23d.

[0061] (Step S23c) The combining unit 180 combines the data obtained by speech recognition with the data stored in the storage unit 110. The combining unit 180 stores the combined data in the storage unit 110. Then, the process proceeds to step S21a. (Step S23d) The acquiring unit 120 acquires the combined data from the storage unit 110. (Step S24a) The estimating unit 160 uses the combined data to estimate a category corresponding to the content of the combined data. For example, the estimating unit 160 estimates a category using a rule base. Examples of methods using a rule base include a method using a dictionary and a method using regular expressions. Furthermore, for example, the estimating unit 160 estimates a category using a trained model. Note that the trained model can be created by machine learning, such as DNN. For example, in machine learning, a large amount of combined data is prepared as input data. Training data is prepared in which categories corresponding to the combined data of the input data are used as correct labels. Then, using the input data and training data, a trained model is created by machine learning so that the categories that are the output data of the trained model match the correct labels.

[0062] (Step S25a) The determination unit 140 determines whether a predetermined time has elapsed since the combined data corresponding to the estimated category was first acquired. If the predetermined time has elapsed, the process ends. If the predetermined time has not elapsed, the process proceeds to step S26a.

[0063] (Step S26a) The determination unit 140 determines whether the number of times the combined data corresponding to the estimated category has been acquired is equal to or greater than a predetermined threshold. Specifically, the determination unit 140 makes the determination as follows: The storage unit 110 stores the number of times of acquisition. The determination unit 140 increments the number of times of acquisition. The determination unit 140 determines whether the number of times of acquisition is equal to or greater than the threshold. If the number of times of acquisition is equal to or greater than the threshold, the process proceeds to step S27. If the number of times of acquisition is less than the threshold, the determination unit 140 increments the number of times of acquisition. For example, the number of times of acquisition is managed by the storage unit 110. Then, the process ends.

[0064] According to the first modification of the fourth embodiment, the information processing device 100 determines whether a question is frequently asked based on multiple utterances that have a similar meaning, thereby enabling the information processing device 100 to make a more appropriate determination.

[0065] Here, the external device may execute steps S21a, S22, S23, and S23a to S23c. If the external device executes the processes, in step S23d, the acquiring section 120 acquires the combined data from the external device.

[0066] Modification 2 of Embodiment 4: Embodiment 4 can be combined with Embodiment 3. The process when Embodiments 3 and 4 are combined will be described using a flowchart.

[0067] Fig. 16 is a flowchart showing an example (part 1) of processing executed by the information processing device according to Modification 2 of Embodiment 4. Fig. 17 is a flowchart showing an example (part 2) of processing executed by the information processing device according to Modification 2 of Embodiment 4. The processing in Figs. 16 and 17 differs from the processing in Fig. 9 in that steps S31a, 33a to 33d, 35a, 36a, and 37a are executed. Therefore, steps S31a, 33a to 33d, 35a, 36a, and 37a will be described in Figs. 16 and 17. Descriptions of processing other than steps S31a, 33a to 33d, 35a, 36a, and 37a will be omitted.

[0068] (Step S31a) The acquisition unit 120 acquires voice data for one episode. (Step S33a) The determination unit 140 determines whether the voice data acquired in step S31a is the first voice data of the same person. If the acquired voice data is the first voice data, the determination unit 140 stores the data obtained by voice recognition in the storage unit 110. Then, the process proceeds to step S31a. If the acquired voice data is voice data of the same person, the process proceeds to step S33b.

[0069] (Step S33b) The determination unit 140 determines whether there is a semantic connection between the data obtained by speech recognition and the data stored in the storage unit 110. If there is a semantic connection, the process proceeds to step S33c. If there is no semantic connection, the process proceeds to step S33d.

[0070] (Step S33c) The combining unit 180 combines the data obtained by the speech recognition with the data stored in the storage unit 110. The combining unit 180 stores the combined data in the storage unit 110. Then, the process proceeds to step S31a. (Step S33d) The acquiring unit 120 acquires the combined data from the storage unit 110.

[0071] (Step S35a) The search unit 170 searches for questions that are identical or similar to the content of the combined data (i.e., the question) using the management table 111. For example, the search unit 170 uses the combined data as a query to search the management table 111. Also, for example, the search unit 170 extracts keywords from the combined data and uses the keywords as a query to search the management table 111. Also, for example, the search unit 170 vectorizes the combined data and the questions registered in the management table 111, and compares the two vectorized data to search for questions that are identical or similar.

[0072] (Step S36a) The determination unit 140 determines whether a predetermined time has elapsed since the first acquisition of combined data that is identical or similar to the searched question. If the predetermined time has elapsed, the process ends. If the predetermined time has not elapsed, the process proceeds to step S37a.

[0073] (Step S37a) The determination unit 140 determines whether the number of times combined data identical to or similar to the searched question has been acquired is equal to or greater than a predetermined threshold. Specifically, the determination unit 140 makes the determination as follows: The storage unit 110 stores the number of times acquired. The determination unit 140 increments the number of times acquired. The determination unit 140 determines whether the number of times acquired is equal to or greater than the threshold. If the number of times acquired is equal to or greater than the threshold, the process proceeds to step S38. If the number of times acquired is less than the threshold, the process ends.

[0074] According to the second modification of the fourth embodiment, the information processing device 100 determines whether a question is frequently asked based on multiple utterances that have a similar meaning, thereby enabling the information processing device 100 to make a more appropriate determination.

[0075] Here, the external device may execute steps S31a, S32, S33, and S33a to S33c. If the external device executes the processes, in step S33d, the acquiring section 120 acquires the combined data from the external device.

[0076] Fifth Embodiment Next, a fifth embodiment will be described. In the fifth embodiment and a modified version of the fifth embodiment, differences from the second to fourth embodiments will be mainly described. In the fifth embodiment and a modified version of the fifth embodiment, descriptions of commonalities with the second to fourth embodiments will be omitted.

[0077] 18 is a diagram showing a provision system according to the fifth embodiment. The provision system further includes a server 400. The information processing device 100 and the server 400 communicate with each other via a network. The network may be a wired network or a wireless network.

[0078] The server 400 stores supplemental information used when estimating a category corresponding to a question or when searching for a question. The supplemental information is useful information. For example, the supplemental information may include a character string indicating the content of the useful information. For example, the server 400 stores information on a social networking service (SNS). The server 400 performs filtering to extract useful information from the SNS information. This allows the server 400 to store useful supplemental information. The server 400 periodically updates the supplemental information. The server 400 may also periodically transmit the supplemental information to the information processing device 100. When the acquisition unit 120 of the information processing device 100 acquires supplemental information, the acquisition unit 120 stores the supplemental information in the storage unit 110.

[0079] Next, the processing executed by the information processing device 100 will be described using a flowchart. Fig. 19 is a flowchart showing an example of the processing executed by the information processing device of embodiment 5. The processing in Fig. 19 differs from the processing in Fig. 6 in that steps S23e and 24b are executed. Therefore, steps S23e and 24b will be described in Fig. 19. Further, a description of the processing other than steps S23e and 24b will be omitted.

[0080] (Step S23e) The acquisition unit 120 acquires supplemental information related to the data obtained by speech recognition from the storage unit 110 or the server 400. This sentence may be expressed as follows: The acquisition unit 120 acquires supplemental information related to words included in the data obtained by speech recognition from the storage unit 110 or the server 400. For example, if the data includes a route name, the acquisition unit 120 acquires supplemental information related to the route name.

[0081] (Step S24b) The estimation unit 160 estimates a category corresponding to the content of the data using the data and supplemental information obtained by speech recognition. For example, the estimation unit 160 estimates the category using a rule base. Examples of methods using a rule base include a dictionary method and a regular expression method. Furthermore, for example, the estimation unit 160 estimates the category using a trained model. In detail, when the estimation unit 160 inputs the data and supplemental information into the trained model, the trained model outputs a category. Note that the trained model can be created by machine learning, such as DNN. For example, in machine learning, a large number of character strings and supplemental information are prepared as input data. Training data is prepared in which categories corresponding to the character strings in the input data are correct labels. Then, the trained model is created by machine learning using the input data and training data so that the categories, which are the output data of the trained model, match the correct labels.

[0082] Here, for example, the content of the utterance may lack some information due to a speech recognition error in the voice announcement, an incorrect utterance, or the like. Furthermore, for example, the content of the utterance may lack a prerequisite due to an omission of the utterance, or the like. In such cases, the accuracy of the category estimated based only on the content of the utterance may be low. Therefore, the information processing device 100 uses supplemental information to supplement the missing information in the content of the utterance. This allows a more accurate category to be estimated.

[0083] According to the fifth embodiment, the information processing device 100 can estimate a more accurate category.

[0084] Variation 1 of Embodiment 5. Fig. 20 is a flowchart showing an example of processing executed by an information processing device according to Variation 1 of Embodiment 5. The processing in Fig. 20 differs from the processing in Fig. 9 in that steps S34a and S35b are executed. Therefore, steps S34a and S35b will be described in Fig. 20. Description of processing other than steps S34a and S35b will be omitted.

[0085] (Step S34a) The acquisition unit 120 acquires supplemental information related to the data obtained by speech recognition from the storage unit 110 or the server 400. (Step S35b) The search unit 170 uses the management table 111 to search for questions that are identical or similar to questions based on the data obtained by speech recognition and the supplemental information. For example, the search unit 170 uses the data and the supplemental information as queries to search the management table 111. Also, for example, the search unit 170 extracts keywords from the data and searches the management table 111 using the keywords and the supplemental information as queries. Also, for example, the search unit 170 vectorizes a question based on the data and the supplemental information and a question registered in the management table 111, and compares the two vectorized data to search for identical or similar questions.

[0086] According to the first modification of the fifth embodiment, the information processing device 100 can search for a more accurate question.

[0087] Modification 2 of Embodiment 5 In Modification 2 of Embodiment 5, a case where supplemental information is used will be described, which is applied to Modification 1 of Embodiment 4.

[0088] The process of step S24a is modified as follows: The acquisition unit 120 acquires supplemental information related to the combined data from the storage unit 110 or the server 400. The estimation unit 160 uses the combined data and the supplemental information to estimate a category corresponding to the content of the combined data. For example, the estimation unit 160 estimates a category using a rule base. Examples of methods using a rule base include a dictionary method and a regular expression method. Furthermore, for example, the estimation unit 160 estimates a category using a trained model. In detail, when the estimation unit 160 inputs the combined data and the supplemental information into the trained model, the trained model outputs a category. The process from step S25a onwards is the same as the process of FIG. 15. Note that the trained model can be created by machine learning, such as DNN. For example, in machine learning, a large amount of combined data and supplemental information is prepared as input data. Training data is prepared in which categories corresponding to the combined data of the input data are used as correct labels. Then, using the input data and training data, a trained model is created by machine learning so that the categories that are the output data of the trained model match the correct labels.

[0089] According to the second modification of the fifth embodiment, the information processing device 100 can achieve the effects of the first modification of the fourth embodiment and the effects of the fifth embodiment.

[0090] Modification 3 of Embodiment 5 In Modification 3 of Embodiment 5, a case where supplemental information is used will be described, which is applied to Modification 2 of Embodiment 4.

[0091] The processing of step S35a is modified as follows. The acquisition unit 120 acquires supplemental information related to the data obtained by speech recognition from the storage unit 110 or the server 400. The search unit 170 uses the management table 111 to search for questions that are identical or similar to a question based on the combined data and the supplemental information. For example, the search unit 170 uses the combined data and the supplemental information as a query to search the management table 111. Alternatively, for example, the search unit 170 extracts keywords from the combined data and searches the management table 111 using the combined keywords and the supplemental information as a query. Alternatively, for example, the search unit 170 vectorizes a question based on the combined data and the supplemental information and a question registered in the management table 111, and compares the two vectorized data to search for identical or similar questions. The processing from step S35a onwards is the same as the processing of FIG. 17 .

[0092] According to the third modification of the fifth embodiment, the information processing device 100 can achieve the effects of the second modification of the fourth embodiment and the effects of the first modification of the fifth embodiment.

[0093] Sixth Embodiment Next, a sixth embodiment will be described. In the sixth embodiment and a modified version of the sixth embodiment, differences from the second to fourth embodiments will be mainly described. In the sixth embodiment and a modified version of the sixth embodiment, descriptions of commonalities with the second to fourth embodiments will be omitted.

[0094] 21 is a block diagram showing the functions of the information processing device of embodiment 6. The information processing device 100 further includes an analysis unit 190 and a change unit 191. Part or all of the analysis unit 190 and the change unit 191 may be realized by a processing circuit. Also, part or all of the analysis unit 190 and the change unit 191 may be realized as a program module executed by the processor 101. The functions of the analysis unit 190 and the change unit 191 will be described later.

[0095] Next, the processing executed by the information processing device 100 will be described using a flowchart. Fig. 22 is a flowchart showing an example of processing executed by the information processing device of embodiment 6. The processing in Fig. 22 differs from the processing in Fig. 6 in that steps S23f and 27a are executed. Therefore, steps S23f and 27a will be described in Fig. 22. Further, a description of the processing other than steps S23f and 27a will be omitted.

[0096] (Step S23f) The analysis unit 190 uses the data obtained by speech recognition to analyze whether the content of the data is of high urgency. For example, the analysis unit 190 performs the analysis using a rule base. Examples of methods using a rule base include a dictionary method and a regular expression method. Furthermore, for example, the analysis unit 190 performs the analysis using a trained model. The information processing device 100 obtains information indicating whether the urgency is high through the analysis. For example, high-urgency content is content indicating the occurrence of an accident, fire, disaster, etc. For example, if the content of the data indicates the occurrence of an accident, fire, disaster, etc., the analysis unit 190 outputs information indicating the high urgency. The trained model can be created by machine learning, such as DNN. For example, in machine learning, a large number of keywords are prepared as input data. Training data is prepared in which the level of urgency corresponding to the keywords in the input data is used as a correct answer label. Then, the trained model is created by performing machine learning using the input data and the training data so that the level of urgency, which is the output data of the trained model, matches the correct answer label.

[0097] Furthermore, the analysis unit 190 may use data obtained by speech recognition to analyze the level of urgency corresponding to the content of the data. For example, if the content of the data includes "earthquake" or "disaster," the level of urgency is "highest." For example, if the content of the data includes "accident" or "failure," the level of urgency is "high." For example, if the content of the data includes "congestion" or "delay," the level of urgency is "medium." The level of urgency may also be expressed as a numerical value rather than as a degree such as "high."

[0098] (Step S27a) The acquisition unit 120 acquires questions corresponding to the estimated category and answers to the questions based on the information indicating whether the urgency is high or low and the management table. Two management tables are prepared. The two management tables are shown below.

[0099] FIG. 23 is a diagram showing an example of a management table according to the sixth embodiment. Management table 111a contains information used when the level of urgency is high. Management table 111b contains information used when the level of urgency is low. Management tables 111a and 111b show the correspondence between questions and answers. Note that management tables 111a and 111b are stored in the storage unit 110 or an external device. Management table 111a is also referred to as first management information, and management table 111b is also referred to as second management information.

[0100] When the information indicating whether the urgency is high indicates that the urgency is high, the acquiring unit 120 acquires a question corresponding to the estimated category and an answer to the question using the management table 111a.When the information indicating whether the urgency is high indicates that the urgency is low, the acquiring unit 120 acquires a question corresponding to the estimated category and an answer to the question using the management table 111b.

[0101] Furthermore, when the urgency level is analyzed, a management table corresponding to the urgency level is prepared. The management table is stored in the storage unit 110 or an external device. The management table is also referred to as third management information. The management table indicates the correspondence between questions and answers. The acquisition unit 120 may use the management table to acquire questions corresponding to the estimated category and answers to the questions.

[0102] The modification unit 191 may modify the answer to the question. Furthermore, the modification unit 191 may omit part of the sentence in the answer to the question. For example, the omitted sentence is a sentence that is unlikely to need to be conveyed to the customer. By omitting a sentence that is unlikely to need to be conveyed to the customer from the answer, the customer can easily recognize the answer. As a result, the time that the attendant spends responding to the customer is reduced, thereby reducing the burden on the attendant. The output unit 150 outputs the modified answer or the omitted answer to the display device 200.

[0103] If the management tables 111a and 111b are stored in an external device, the acquisition unit 120 accesses the external device to acquire the questions and answers.

[0104] According to the sixth embodiment, the information processing device 100 outputs a question and an answer according to the degree of urgency, so that the information processing device 100 can output a question and an answer that are more suited to the situation.

[0105] Variation 1 of Embodiment 6. Fig. 24 is a flowchart showing an example of processing executed by an information processing device according to Variation 1 of Embodiment 6. The processing of Fig. 24 differs from the processing of Fig. 9 in that steps S33e, 34b, 35c, and 38a are executed. Therefore, steps S33e, 34b, 35c, and 38a will be described in Fig. 24. Description of processing other than steps S33e, 34b, 35c, and 38a will be omitted.

[0106] (Step S33e) The analysis unit 190 uses the data obtained by voice recognition to analyze whether the content of the data is of high urgency. The information processing device 100 obtains information indicating whether the urgency is high through the analysis. The analysis unit 190 may also analyze the urgency corresponding to the content of the data using the data obtained by voice recognition. (Step S34b) The acquisition unit 120 acquires the management table 111a or the management table 111b based on the information indicating whether the urgency is high. The acquisition unit 120 may acquire a management table according to the urgency.

[0107] (Step S35c) When management table 111a is acquired, search unit 170 uses management table 111a to search for questions that are the same as or similar to the content of the data obtained by voice recognition. When management table 111b is acquired, search unit 170 uses management table 111b to search for questions that are the same as or similar to the content of the data obtained by voice recognition. When a management table based on urgency is acquired, search unit 170 uses the management table to search for questions that are the same as or similar to the content of the data obtained by voice recognition.

[0108] (Step S38a) When management table 111a is acquired, acquisition unit 120 acquires the searched question and the answer to the question based on management table 111a. When management table 111b is acquired, acquisition unit 120 acquires the searched question and the answer to the question based on management table 111b. Furthermore, when a management table according to the urgency level is acquired, acquisition unit 120 may acquire the searched question and the answer to the question using the management table according to the urgency level.

[0109] The modification unit 191 may modify the answer to the question. Furthermore, the modification unit 191 may omit part of the sentence in the answer to the question. For example, the sentence to be omitted is a sentence that is unlikely to need to be conveyed to the customer. By omitting a sentence that is unlikely to need to be conveyed to the customer from the answer, the customer can easily recognize the answer. As a result, the time that the attendant spends responding to the customer is reduced, thereby reducing the burden on the attendant.

[0110] According to the first modification of the sixth embodiment, the information processing device 100 outputs a question and an answer according to the degree of urgency, so that the information processing device 100 can output a question and an answer that is more suited to the situation.

[0111] Modification 2 of Embodiment 6 In Modification 2 of Embodiment 6, a case will be described in which information indicating whether the urgency is high or not is used, and Modification 1 of Embodiment 4 is applied.

[0112] The process of step S27 is modified as follows. The analysis unit 190 uses the combined data to analyze whether the content of the combined data has a high level of urgency. If the information indicating whether the urgency is high, obtained by the analysis, indicates a high level of urgency, the acquisition unit 120 uses the management table 111a to acquire a question corresponding to the estimated category and an answer to the question. If the information indicates a low level of urgency, the acquisition unit 120 uses the management table 111b to acquire a question corresponding to the estimated category and an answer to the question. The process other than the modified step S27 is the same as in the first modification of the fourth embodiment. Furthermore, the analysis unit 190 may use the combined data to analyze the urgency corresponding to the content of the combined data. The acquisition unit 120 may use a management table according to the urgency to acquire a question corresponding to the estimated category and an answer to the question.

[0113] The modification unit 191 may modify the answer to the question. Furthermore, the modification unit 191 may omit part of the sentence in the answer to the question. For example, the sentence to be omitted is a sentence that is unlikely to need to be conveyed to the customer. By omitting a sentence that is unlikely to need to be conveyed to the customer from the answer, the customer can easily recognize the answer. As a result, the time that the attendant spends responding to the customer is reduced, thereby reducing the burden on the attendant.

[0114] According to the second modification of the sixth embodiment, the information processing device 100 outputs a question and an answer according to the degree of urgency, so that the information processing device 100 can output a question and an answer that are more suited to the situation.

[0115] Modification 3 of Embodiment 6 In Modification 3 of Embodiment 6, a case will be described in which information indicating whether the urgency is high or not is used, and Modification 2 of Embodiment 4 is applied.

[0116] The processing of step S34 is changed as follows. The analysis unit 190 uses the combined data to analyze whether the content of the combined data is of high urgency. The acquisition unit 120 selects a management table based on information indicating whether the urgency is high, obtained by the analysis. For example, if the information indicates a high urgency, the acquisition unit 120 acquires management table 111a. If the information indicates a low urgency, the acquisition unit 120 acquires management table 111b. The analysis unit 190 may also use the combined data to analyze the urgency corresponding to the content of the combined data. The acquisition unit 120 acquires a management table according to the urgency.

[0117] The processing of step S35a is changed as follows: When management table 111a is acquired, search unit 170 uses management table 111a to search for questions that are the same as or similar to the content of the combined data. When management table 111b is acquired, search unit 170 uses management table 111b to search for questions that are the same as or similar to the content of the combined data. When a management table based on the urgency level is acquired, search unit 170 uses the management table to search for questions that are the same as or similar to the content of the combined data.

[0118] The processing of step S38 is changed as follows. When management table 111a is acquired, acquisition unit 120 acquires the searched question and the answer to the question based on management table 111a. When management table 111b is acquired, acquisition unit 120 acquires the searched question and the answer to the question based on management table 111b. When a management table based on urgency is acquired, acquisition unit 120 acquires the searched question and the answer to the question based on the management table.

[0119] The modification unit 191 may modify the answer to the question. Furthermore, the modification unit 191 may omit part of the sentence in the answer to the question. For example, the sentence to be omitted is a sentence that is unlikely to need to be conveyed to the customer. By omitting a sentence that is unlikely to need to be conveyed to the customer from the answer, the customer can easily recognize the answer. As a result, the time that the attendant spends responding to the customer is reduced, thereby reducing the burden on the attendant.

[0120] The processes other than steps S34, S35a, and S38 that are changed are the same as those in the second modification of the fourth embodiment.

[0121] According to the third modification of the sixth embodiment, the information processing device 100 outputs a question and an answer according to the degree of urgency, so that the information processing device 100 can output a question and an answer that are more suited to the situation.

[0122] The features of the above-described embodiments can be combined with each other as appropriate.

[0123] The above embodiments describe the generation of questions and answers related to station operations by the information processing device of the present disclosure, but these are merely examples. For example, the information processing device of the present disclosure may generate questions and answers related to guidance operations at tourist spots or commercial facilities.

[0124] 11 Frame, 12 Frame, 100 Information processing device, 101 Processor, 102 Volatile storage device, 103 Non-volatile storage device, 110 Storage unit, 111 Management table, 111a, 111b Management tables, 120 Acquisition unit, 130 Speech recognition execution unit, 140 Determination unit, 150 Output unit, 160 Estimation unit, 170 Search unit, 180 Combination unit, 190 Analysis unit, 191 Change unit, 200 Display device, 300 Microphone, 400 Server.

Claims

1. An information processing device capable of outputting information to a display device, comprising: an acquisition unit that acquires customer voice data; a voice recognition execution unit that performs voice recognition using the voice data; a determination unit that, when the content of the data acquired by the voice recognition is a question, determines whether the content of the data is a frequently asked question; and an output unit; wherein, when the content of the data is a frequently asked question, the acquisition unit acquires an answer corresponding to the question that is the content of the data, and the output unit outputs the question and the answer to the display device.

2. The information processing device according to claim 1, wherein the acquisition unit acquires combined data which is data obtained by combining multiple voice data of the customer and which is data obtained by combining content that is semantically connected, and if the content of the combined data is a frequently asked question, acquires an answer corresponding to the question which is the content of the combined data.

3. The information processing device of claim 1, further comprising an estimation unit that uses the data to estimate a category corresponding to the content of the data, and wherein the acquisition unit acquires a question corresponding to the estimated category and an answer to the question when the number of times voice data corresponding to the estimated category is acquired within a predetermined time period is equal to or greater than a predetermined threshold.

4. The information processing device of claim 3, wherein the acquisition unit acquires supplementary information regarding the data obtained by speech recognition, and the estimation unit estimates a category corresponding to the content of the data using the data obtained by speech recognition and the supplementary information.

5. An information processing device as described in claim 3, further comprising an analysis unit that uses the data obtained by voice recognition to analyze whether the content of the data is of high urgency or not, or the urgency corresponding to the content of the data, wherein when the information obtained by analysis indicating whether the urgency is high indicates a high urgency, the acquisition unit acquires a question corresponding to the estimated category and the answer to the question using first management information which is information used when the urgency is high and which indicates a correspondence between questions and answers, when the information indicates a low urgency, the acquisition unit acquires a question corresponding to the estimated category and the answer to the question using second management information which is information used when the urgency is low and which indicates a correspondence between questions and answers, and when the urgency has been analyzed, the acquisition unit acquires a question corresponding to the estimated category and the answer to the question using third management information which is information according to the urgency and which indicates a correspondence between questions and answers.

6. An information processing device as described in claim 1, further comprising an estimation unit, wherein the acquisition unit acquires combined data, which is data obtained by combining multiple voice data of the customer and which is data obtained by combining content that is semantically connected, the estimation unit uses the combined data to estimate a category corresponding to the content of the combined data, and when the number of times the combined data corresponding to the estimated category is acquired within a predetermined time period is equal to or greater than a predetermined threshold, the acquisition unit acquires a question corresponding to the estimated category and an answer to the question.

7. The information processing device according to claim 6, wherein the acquisition unit acquires supplementary information related to the combined data, and the estimation unit estimates a category corresponding to the content of the combined data using the combined data and the supplementary information.

8. The information processing device of claim 6, further comprising an analysis unit that uses the combined data to analyze whether or not the content of the combined data is of high urgency, or the urgency corresponding to the content of the combined data, wherein the acquisition unit, when the information obtained by the analysis indicating whether or not the urgency is high indicates a high urgency, acquires a question corresponding to the estimated category and the answer to the question using first management information which is information used when the urgency is high and which indicates a correspondence between questions and answers, and when the information indicates a low urgency, acquires a question corresponding to the estimated category and the answer to the question using second management information which is information used when the urgency is low and which indicates a correspondence between questions and answers, and when the urgency has been analyzed, acquires a question corresponding to the estimated category and the answer to the question using third management information which is information according to the urgency and which indicates a correspondence between questions and answers.

9. An information processing device as described in claim 1, further comprising a search unit, wherein the acquisition unit acquires management information indicating a correspondence between questions and answers, the search unit uses the management information to search for questions identical or similar to the content of the data, and when the number of times that voice data identical or similar to the searched question is acquired within a predetermined time period is equal to or exceeds a predetermined threshold, the acquisition unit acquires the searched question and the answer to the question from the management information.

10. The information processing device of claim 9, wherein the acquisition unit acquires supplementary information regarding the data obtained by voice recognition, and the search unit uses the management information to search for questions that are identical or similar to questions based on the data obtained by voice recognition and the supplementary information.

11. The device further comprises an analysis unit which uses the data obtained by voice recognition to analyze whether the content of the data is of high urgency or not, or the urgency corresponding to the content of the data, wherein the search unit, when the information indicating whether the urgency is high or not obtained by the analysis indicates a high urgency, searches for questions that are identical or similar to the content of the data using first management information which is information used when the urgency is high and which indicates a correspondence between questions and answers, and when the information indicates a low urgency, searches for questions that are identical or similar to the content of the data using second management information which is information used when the urgency is low and which indicates a correspondence between questions and answers, and when the urgency has been analyzed, searches for questions that are identical or similar to the content of the data using third management information which is information according to the urgency and which indicates a correspondence between questions and answers; 10. The information processing device of claim 9, wherein the acquisition unit acquires the searched question and the answer to the question based on the first management information when the information indicates a high level of urgency, acquires the searched question and the answer to the question based on the second management information when the information indicates a low level of urgency, and acquires the searched question and the answer to the question based on the third management information when the level of urgency has been analyzed.

12. The information processing device of claim 9, wherein the acquisition unit acquires combined data, which is data obtained by combining multiple voice data of the customer and which is data obtained by combining content that is semantically connected; the search unit uses the management information to search for questions that are identical or similar to the content of the combined data; and if the number of times that combined data that is identical or similar to the searched question is acquired within the time period is equal to or greater than the threshold value, the acquisition unit acquires the searched question and an answer to the question from the management information.

13. The information processing device according to claim 12, wherein the acquisition unit acquires supplementary information related to the combined data, and the search unit uses the management information to search for questions that are identical or similar to questions based on the combined data and the supplementary information.

14. The system further comprises an analysis unit that uses the combined data to analyze whether or not the content of the combined data is of high urgency, or an urgency corresponding to the content of the combined data, wherein the acquisition unit, when the information indicating whether or not the urgency is high obtained by the analysis indicates a high urgency, acquires first management information which is information used when the urgency is high and indicates a correspondence between questions and answers, and when the information indicates a low urgency, acquires second management information which is information used when the urgency is low and indicates a correspondence between questions and answers, and when the urgency is analyzed, acquires third management information which is information according to the urgency and indicates a correspondence between questions and answers; wherein, when the first management information is acquired, the search unit uses the first management information to search for questions that are identical or similar to the content of the combined data, when the second management information is acquired, the search unit uses the second management information to search for questions that are identical or similar to the content of the combined data, and when the third management information is acquired, the search unit uses the third management information to search for questions that are identical or similar to the content of the combined data, 13. The information processing device of claim 12, wherein the acquisition unit acquires the searched question and an answer to the question based on the first management information when the number of times the combined data identical or similar to the searched question is acquired within the time period is equal to or greater than the threshold and the first management information is acquired, acquires the searched question and an answer to the question based on the second management information when the number of times the combined data identical or similar to the searched question is acquired within the time period is equal to or greater than the threshold and the second management information is acquired, and acquires the searched question and an answer to the question based on the third management information when the number of times the combined data identical or similar to the searched question is acquired within the time period is equal to or greater than the threshold and the third management information is acquired.

15. An information processing device as described in any one of claims 1 to 14, further comprising a modification unit that modifies an answer to a question or omits part of the text of the answer to a question, and the output unit outputs the modified answer or the omitted answer to the display device.

16. An output method in which an information processing device capable of outputting information to a display device acquires voice data of a customer, performs voice recognition using the voice data, and if the content of the data acquired by the voice recognition is a question, determines whether the content of the data is a frequently asked question, and if the content of the data is a frequently asked question, acquires an answer corresponding to the question that is the content of the data, and outputs the question and the answer to the display device.

17. An output program that causes a computer capable of outputting information on a display device to execute the following processes: acquire customer voice data; perform voice recognition using the voice data; if the content of the data acquired by the voice recognition is a question, determine whether the content of the data is a frequently asked question; if the content of the data is a frequently asked question, acquire an answer corresponding to the question that is the content of the data; and output the question and the answer to the display device.

Citation Information

Patent Citations

  • Helpdesk system

    JP2002157445A

  • Call center conversational content display system, method, and program

    WO2019003395A1

Cited By

  • Information processing device and information processing method

    WO2026176677A1