Information processing system, information processing device, information processing method, and program

By designing an information processing system that includes voice information acquisition, analysis and auxiliary control units, the problem of insufficient voice-assisted recognition and understanding capabilities in the prior art is solved, and a more accurate and effective voice-assisted experience is achieved.

JP2025042828APending Publication Date: 2025-03-28HONDA MOTOR CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2023149986
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-09-15
Publication Date
2025-03-28

AI Technical Summary

Technical Problem

The prior art has difficulty providing better voice assistance, especially in identifying user requests and ensuring that the user understands the content of the voice assistant.

Method used

An information processing system is designed, including a voice information acquisition unit, an analysis unit and an auxiliary control unit. The system performs first and second voice assist controls through speech recognition and natural language processing to recognize user requests and ensure that the user understands the description provided by the voice assistant.

Benefits of technology

Improve the accuracy and user experience of voice assistance, ensure that user requests are accurately identified, and that the description of voice assistants can be communicated to the user more effectively.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025042828000001_ABST
    Figure 2025042828000001_ABST
Patent Text Reader

Abstract

To provide an information processing system, an information processing device, an information processing method, and a program that perform better voice assistance in response to a user's request.SOLUTION: In an information processing system 10, an assist control unit 50 of a server device 14 is capable of executing first assist control and / or second assist control. The first assist control is voice assist control for identifying a user's request when it is estimated that there is a discrepancy between the user's request and a content of explanation by voice assist. The second assist control is voice assist control for facilitating transmission of the content of explanation by the voice assist to the user when it is estimated that the content of explanation by the voice assist is not transmitted or hardly transmitted to the user.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

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

[0002] Patent Document 1 discloses an information processing device and an information processing method capable of starting a dialogue that matches the psychological tendency of a user. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-71606 Summary of the Invention [Problem to be solved by the invention]

[0004] Technology that can provide better voice assistance is desirable.

[0005] The present invention aims to solve the above-mentioned problems. [Means for solving the problem]

[0006] The information processing system of the first invention comprises an utterance information acquisition unit that acquires speech information, which is information about a user's utterance; an analysis unit that analyzes the content of the user's utterance based on the utterance information acquired by the utterance information acquisition unit; and an assist control unit that executes assist control, which is control for providing voice assistance in response to the user's request, based on the results of the analysis by the analysis unit, wherein the assist control unit is capable of executing at least one of a first assist control and a second assist control, the first assist control being voice assist control for identifying the user's request when it is estimated that there is a discrepancy between the user's request and the content of the explanation provided by the voice assist, and the second assist control being voice assist control for making it easier to convey the content of the explanation provided by the voice assist to the user when it is estimated that the content of the explanation provided by the voice assist has not been conveyed or is difficult to convey to the user.

[0007] A second invention is an information processing device in the information processing system according to the first invention, comprising the speech information acquisition unit, the analysis unit, and the assist control unit.

[0008] The third invention is an information processing method comprising an utterance information acquisition step of acquiring utterance information, which is information on a user's utterance; an analysis step of analyzing the content of the user's utterance based on the utterance information acquired in the utterance information acquisition step; and an assist control step of executing assist control, which is control for providing voice assistance in response to the user's request, based on the results of the analysis in the analysis step, wherein the assist control step is capable of executing at least one of a first assist control and a second assist control, the first assist control being voice assist control for identifying the user's request when it is estimated that there is a discrepancy between the user's request and the explanation content provided by the voice assist, and the second assist control being voice assist control for making it easier to convey the explanation content provided by the voice assist to the user when it is estimated that the explanation content provided by the voice assist has not been conveyed to the user or is difficult to convey to the user.

[0009] A program according to a fourth aspect of the present invention causes a computer to execute the information processing method according to the third aspect of the present invention. Effect of the Invention

[0010] According to the present invention, better voice assistance can be provided. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a schematic configuration diagram of an information processing system according to the first embodiment. [Diagram 2] FIG. 2 is a sequence diagram of the first voice assistance. [Diagram 3] FIG. 3 is a sequence diagram of the second voice assistance. [Figure 4] FIG. 4 is a flowchart of the second assist control. [Diagram 5] FIG. 5 is a schematic diagram showing an explanatory sentence by voice assistance. [Figure 6] FIG. 6 is a schematic configuration diagram of an information processing system according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] [1 First embodiment] [1-1 Configuration of information processing system 10] FIG. 1 is a schematic configuration diagram of an information processing system 10 according to the first embodiment. The information processing system 10 includes an information device 16 and an information processing device 18. In the first embodiment, the information device 16 is provided in a vehicle 12. The information processing device 18 is provided in a server device 14. The information device 16 and the information processing device 18 can perform two-way communication via a communication line 20 such as the Internet. It is to be noted that the information device 16 does not have to be provided in the vehicle 12. For example, the information device 16 may be a computer such as a personal computer or a mobile terminal.

[0013] [Configuration of information device 16 installed in vehicle 12] The information device 16 provided in the vehicle 12 includes a sound collection device 22, a sound output device 24, a communication device 26, and a control device .

[0014] The sound collection device 22 includes a microphone. The sound collection device 22 collects the speech of a user (a passenger of the vehicle 12) and outputs voice information that has been converted into data from the speech to the control device 28. The voice information that has been converted into data from the speech is also referred to as speech information.

[0015] The audio output device 24 includes a speaker. The audio output device 24 acquires audio information from the control device 28, and outputs audio based on the audio information. The audio output from the audio output device 24 reaches the user.

[0016] The communication device 26 is configured by, for example, a TCU (Telematics Control Unit). The communication device 26 can realize two-way communication between the control device 28 and a device (such as the information processing device 18) outside the vehicle 12. The communication device 26 includes a communication circuit for performing two-way communication with the control device 28, a wireless communication module (integrated circuit module) for performing two-way communication with a device outside the vehicle 12 via the communication line 20, and a microcomputer for performing data processing.

[0017] The control device 28 may be configured by an ECU (Electronic Control Unit). The control device 28 includes a calculation unit 30 and a storage unit 32. The calculation unit 30 may be configured by a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). That is, the calculation unit 30 may be configured by a processing circuit. The calculation unit 30 includes an utterance information acquisition unit 34, a voice output control unit 36, and a communication control unit 38 (utterance transmission unit). The utterance information acquisition unit 34, the voice output control unit 36, and the communication control unit 38 may be realized by the calculation unit 30 executing a program stored in the storage unit 32. At least a part of the calculation unit 30 may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array). At least a part of the calculation unit 30 may be realized by an electronic circuit including a discrete device.

[0018] The speech information acquisition unit acquires the speech information supplied from the sound collection device 22. The audio output control unit outputs the speech information to the audio output device 24. The communication control unit controls communication with the communication device .

[0019] The storage unit 32 is configured with a volatile memory (not shown) and a non-volatile memory (not shown) which are computer-readable storage media. The volatile memory is, for example, a random access memory (RAM). The non-volatile memory is, for example, a read only memory (ROM) or a flash memory. Data and the like are stored, for example, in the volatile memory. Programs, tables, maps, and the like are stored, for example, in the non-volatile memory. At least a part of the storage unit 32 may be provided in the above-mentioned processor, integrated circuit, and the like.

[0020] [Configuration of information processing device 18 provided in server device 14] The server device 14 may be provided by a physical server or a cloud server. An information processing device 18 included in the server device 14 may perform two-way communication with other server devices via a communication line 20.

[0021] The information processing device 18 includes a calculation unit 42 and a storage unit 44. The calculation unit 42 may be configured by a processor such as a CPU or a GPU. That is, the calculation unit 42 may be configured by a processing circuitry. The calculation unit 42 includes an utterance information acquisition unit 46, an analysis unit 48, and an assist control unit 50. The utterance information acquisition unit 46, the analysis unit 48, and the assist control unit 50 may be realized by the calculation unit 42 executing a program stored in the storage unit 44. At least a part of the calculation unit 42 may be realized by an integrated circuit such as an ASIC or an FPGA. At least a part of the calculation unit 42 may be realized by an electronic circuit including a discrete device.

[0022] The speech information acquisition unit 46 acquires speech information supplied from the information device 16 via the communication line 20. The analysis unit 48 analyzes the content of the user's speech based on the speech information acquired by the speech information acquisition unit 46. The analysis unit 48 has, for example, a voice recognition function. The assist control unit 50 executes assist control, which is control for providing voice assistance in response to a user request, based on the result of the analysis by the analysis unit 48. The assist control unit 50 has, for example, a natural language processing function.

[0023] The storage unit 44 is configured with a volatile memory (not shown) and a non-volatile memory (not shown) which are computer-readable storage media. The volatile memory is, for example, a RAM. The non-volatile memory is, for example, a ROM, a flash memory. Data and the like are stored, for example, in the volatile memory. Programs, tables, maps, and the like are stored, for example, in the non-volatile memory. At least a part of the storage unit 44 may be provided in the above-mentioned processor, integrated circuit, and the like.

[0024] [1-2 Voice assistance performed by the information processing device 18] In this specification, the information processing device 18 generating voice information in response to a user's spoken request is referred to as voice assist. The information processing device 18 is capable of having a dialogue with the user. When the user makes a request for some explanation to the information processing device 18, the information processing device 18 executes voice assist control for providing an explanation in response to the user's request. As a result, an explanatory voice in response to the user's request is output from the voice output device 24 of the information device 16.

[0025] The information processing device 18 is capable of performing at least one of a first voice assist and a second voice assist, which will be described below.

[0026] (First voice assistant) The information processing device 18 is capable of having a dialogue with the user by executing the voice assist control. However, due to the accuracy of the machine, the way the user speaks, and the like, the information processing device 18 may not be able to accurately recognize the user's request. In such a case, the information processing device 18 may provide an inappropriate explanation for the user's request. If the user feels that there is a discrepancy between the user's request and the explanation provided by the voice assist, the user may have a negative reaction to the explanation provided by the voice assist.

[0027] The first voice assist includes a first assist control for dealing with such a situation. The first assist control is a voice assist control for identifying a user's request, and is performed when it is estimated that there is a discrepancy between the user's request and the content of the explanation by the voice assist.

[0028] Fig. 2 is a sequence diagram of the first voice assist. Fig. 2 shows a process flow in which the information processing device 18 responds to one utterance by the user. When the dialogue between the user and the information processing device 18 continues, the process shown in Fig. 2 is repeatedly executed. Among the processes shown in Fig. 2, the process of step S6 is a voice assist control process for identifying a user request. The process of step S6 is executed after the processes of steps S1 to S5 and steps S7 to S9 have been executed at least once.

[0029] In step S1, the speech information acquisition unit 34 of the information device 16 acquires the speech information collected by the sound collection device 22. When step S1 ends, the process proceeds to step S2.

[0030] In step S2, the communication control unit 38 of the information device 16 controls the transmission of the speech information to the information processing device 18. As a result, the speech information is transmitted to the information processing device 18 via the communication device 26 and the communication line 20. When step S2 ends, the process proceeds to step S3.

[0031] In step S3, the utterance information acquisition unit 46 of the information processing device 18 acquires the utterance information via the communication line 20. When step S3 ends, the process proceeds to step S4.

[0032] In step S4, the analysis unit 48 of the information processing device 18 analyzes the speech information. For example, the analysis unit 48 performs voice recognition based on the speech information and generates text data of the voice. When step S4 ends, the process proceeds to step S5.

[0033] In step S5, the assist control unit 50 of the information processing device 18 performs natural language processing based on the text data generated by the analysis unit 48. Furthermore, the assist control unit 50 determines whether or not the user's utterance includes a negative response. For example, the assist control unit 50 determines whether or not the text data generated by the analysis unit 48 includes a predetermined negative expression. The predetermined negative expression is an expression used by the user when the user denies the content of the explanation by the voice assistance. An example of the predetermined negative expression is an expression such as "that's not true." The predetermined negative expression is stored in the storage unit 32 in advance. If the user's utterance includes a negative response (predetermined negative expression), the assist control unit 50 presumes that there is a discrepancy between the user's request and the content of the explanation by the voice assistance. If the user's utterance includes a negative response (predetermined negative expression) (step S5: YES), the process proceeds to step S6. On the other hand, if the user's utterance does not include a negative response (predetermined negative expression) (step S5: NO), the process proceeds to step S7.

[0034] When the process proceeds from step S5 to step S6, the assist control unit 50 executes the first assist control. In the first assist control, the assist control unit 50 identifies the user's request by inquiring of the user about the request. For example, the assist control unit 50 generates first voice information by voice synthesis or the like. The first voice information is voice information for inquiring of the user whether the content of the speech information recognized by the assist control unit 50 is correct or not. An example of the first voice information is voice information such as "Is this a question about XX?". Note that a fixed phrase for a query may be stored in advance in the storage unit 44, and the assist control unit 50 may generate the first voice information based on the fixed phrase stored in the storage unit 44. The assist control unit 50 controls the transmission of the generated first voice information. As a result, the first voice information is transmitted to the information device 16 via the communication line 20. When step S6 ends, the process proceeds to step S8.

[0035] When the process moves from step S5 to step S7, the assist control unit 50 executes normal assist control. The normal assist control is voice assist control for providing explanations in response to a user's request. For example, the assist control unit 50 generates normal voice information by voice synthesis or the like. The normal voice information is voice information for providing explanations in response to a user's request. Note that a plurality of explanatory sentences may be stored in advance in the storage unit 44, and the assist control unit 50 may generate the normal voice information based on the explanatory sentences stored in the storage unit 44. The assist control unit 50 controls the transmission of the generated normal voice information. As a result, the normal voice information is transmitted to the information device 16 via the communication line 20. When step S7 ends, the process moves to step S8.

[0036] When the process proceeds from step S6 or step S7 to step S8, the communication control unit 38 of the information device 16 acquires voice information (first voice information or normal voice information) via the communication line 20 and the communication device 26. When step S8 ends, the process proceeds to step S9.

[0037] In step S9, the audio output control unit 36 ​​of the information device 16 outputs the audio information (first audio information or normal audio information) to the audio output device 24. As a result, the audio output device 24 outputs audio. The audio output from the audio output device 24 reaches the user.

[0038] According to the first voice assist, when it is estimated that there is a discrepancy between the user's request and the explanation content by the voice assist, voice assist control is performed to identify the user's request. Therefore, the user's request and the explanation content by the voice assist tend to match. Therefore, the accuracy of the voice assist can be improved. That is, the voice assist can be performed more satisfactorily.

[0039] (Second voice assistant) There are cases where the user cannot hear the explanation given by the voice assistant. Also, there are cases where the user cannot understand the explanation given by the voice assistant. In these cases, the user may react by asking for a repeat.

[0040] The second voice assist includes a second assist control for dealing with such a situation. The second assist control is a voice assist control for making it easier to convey the contents of an explanation given once to the user, and is performed when it is estimated that the contents of the explanation given by the voice assist have not been conveyed to the user or are difficult to convey.

[0041] Fig. 3 is a sequence diagram of the second voice assistance. Like Fig. 2, Fig. 3 shows a process flow in which the information processing device 18 responds to one utterance by the user. Steps S11 to S14 and steps S17 to S19 in the process of Fig. 3 are the same as steps S1 to S4 and steps S7 to S9 in the process of Fig. 2. Here, the process of Fig. 3 that is different from the process of Fig. 2 (mainly steps S15 and S16) will be described.

[0042] In step S15, the assist control unit 50 of the information processing device 18 performs natural language processing based on the text data generated by the analysis unit 48. Furthermore, the assist control unit 50 determines whether or not the user's utterance includes a response to asking back. For example, the assist control unit 50 determines whether or not the text data generated by the analysis unit 48 includes a predetermined response expression. The predetermined response expression is an expression used by the user when the user cannot hear the explanation content by the voice assistance or cannot understand the explanation content by the voice assistance. Examples of the predetermined response expression include "Hmm?" and "What?". The predetermined response expression is stored in the storage unit 44 in advance. When the user's utterance includes a response to asking back (predetermined response expression), the assist control unit 50 estimates that the explanation content by the voice assistance is not conveyed to the user or is difficult to convey. When the user's utterance includes a response to asking back (step S15: YES), the process proceeds to step S16. On the other hand, if the user's utterance does not include a response to asking back (a predetermined expression for asking back) (step S15: NO), the process proceeds to step S17.

[0043] When the process proceeds from step S15 to step S16, the assist control unit 50 executes, for example, the second assist control shown in FIG. 4. The second assist control shown in FIG. 4 will be described later. The assist control unit 50 generates second voice information by voice synthesis or the like. The second voice information is voice information for explaining the content that has been explained once so that it is easy to convey to the user. Note that a fixed phrase for explanation may be stored in advance in the storage unit 44, and the assist control unit 50 may generate the second voice information based on the fixed phrase stored in the storage unit 44. The assist control unit 50 controls the transmission of the generated second voice information. As a result, the second voice information is transmitted to the information device 16 via the communication line 20. When step S16 ends, the process proceeds to step S18.

[0044] When the process proceeds from step S16 or step S17 to step S18, the communication control unit 38 of the information device 16 acquires voice information (second voice information or normal voice information) via the communication line 20 and the communication device 26. When step S18 ends, the process proceeds to step S19.

[0045] In step S19, the audio output control unit 36 ​​of the information device 16 outputs the audio information (the second audio information or the normal audio information) to the audio output device 24. As a result, the audio output device 24 outputs audio. The audio output from the audio output device 24 reaches the user.

[0046] Fig. 4 is a flow chart of the second assist control. In step S16 shown in Fig. 3, the second assist control shown in Fig. 4 is performed.

[0047] In step S21, the assist control unit 50 determines whether or not the explanation given by the immediately preceding voice assist includes technical terms. For example, as shown in FIG. 5, the explanation given by the voice assist may be composed of multiple sentences 54. If the user responds by asking back during the voice output of sentence 54b, the assist control unit 50 determines whether or not the sentence 54a outputted by voice immediately before sentence 54b includes technical terms. The technical terms are stored in the storage unit 44 in advance. If the explanation given by the immediately preceding voice assist includes technical terms (step S21: YES), the process proceeds to step S22. On the other hand, if the explanation given by the immediately preceding voice assist does not include technical terms (step S21: NO), the process proceeds to step S23.

[0048] When the process proceeds from step S21 to step S22, the assist control unit 50 generates second voice information for explaining the technical term by voice synthesis or the like. The second voice information generated here is voice information including an explanatory text of the technical term. The explanatory text of the technical term is stored in the storage unit 44 in advance.

[0049] When the process proceeds from step S21 to step S23, the assist control unit 50 generates second voice information for restating the immediately preceding voice-assisted explanation by voice synthesis, etc. As shown in Fig. 5, when the user responds by asking again during voice output of sentence 54b, the assist control unit 50 generates second voice information for restating sentence 54a, which was voice-output immediately before sentence 54b, by voice synthesis, etc.

[0050] In step S23, the assist control unit 50 may change the output form of the second voice information related to the re-explanation. For example, the assist control unit 50 may make the voice speed of the re-explanation by the voice assist slower than the voice speed before the re-explanation. The assist control unit 50 may make the volume of the re-explanation by the voice assist louder than the volume before the re-explanation. The assist control unit 50 may make the intonation of the re-explanation by the voice assist different from the intonation before the re-explanation. For example, various patterns of intonation, such as rising and falling of the ending of words, dialect, etc., may be stored in the storage unit 44. These changes in the output form make it easier to understand the contents of the explanation by the voice assist.

[0051] According to the second voice assist, when it is estimated that the explanation content by the voice assist has not been conveyed to the user or is difficult to convey, voice assist control is performed to make it easier to convey the explanation content by the voice assist to the user. This makes it easier for the user to understand the explanation content by the voice assist. Therefore, the accuracy of the voice assist can be improved. In other words, the voice assist can be performed more satisfactorily.

[0052] [2 Second embodiment] 6 is a schematic configuration diagram of an information processing system 10 according to the second embodiment. In the second embodiment, the same components as those in the first embodiment are denoted by the same reference numerals.

[0053] In the second embodiment, the calculation unit 30 of the information device 16 includes, similarly to the first embodiment, an utterance information acquisition unit 34, a voice output control unit 36, and a communication control unit 38. Furthermore, the calculation unit 30 of the information device 16 includes an analysis unit 48 and an assist control unit 50. In other words, the control device 28 of the information device 16 may function as the information processing device 18.

[0054] According to the second embodiment, the accuracy of the voice assistance can be improved, similarly to the first embodiment. That is, the present embodiment can also provide good voice assistance.

[0055] [3 Notes] In addition to the above disclosure, the following notes are also disclosed.

[0056] (Appendix 1) The information processing system (10) relating to the first disclosure comprises an utterance information acquisition unit (34, 46) that acquires utterance information, which is information on a user's utterance, an analysis unit (48) that analyzes the content of the user's utterance based on the utterance information acquired by the utterance information acquisition unit, and an assist control unit (50) that executes assist control, which is control for providing voice assistance in response to the user's request, based on the result of the analysis by the analysis unit, wherein the assist control unit is capable of executing at least one of a first assist control and a second assist control, the first assist control being voice assist control for identifying the user's request when it is estimated that there is a discrepancy between the user's request and the explanation content provided by the voice assist, and the second assist control being voice assist control for making it easier to convey the explanation content provided by the voice assist to the user when it is estimated that the explanation content provided by the voice assist has not been conveyed to the user or is difficult to convey to the user.

[0057] According to the above configuration, when it is estimated that there is a discrepancy between the user's request and the explanation content by the voice assistance, voice assistance control is performed to identify the user's request. Therefore, the user's request and the explanation content by the voice assistance are more likely to match. Therefore, the accuracy of the voice assistance can be improved. In other words, the voice assistance can be performed more satisfactorily.

[0058] According to the above configuration, when it is estimated that the explanation content by the voice assist is not being conveyed to the user or is difficult to convey, the voice assist control is performed to make it easier to convey the explanation content by the voice assist to the user. Therefore, the user can easily understand the explanation content by the voice assist. Therefore, the accuracy of the voice assist can be improved. In other words, the voice assist can be performed more satisfactorily.

[0059] (Appendix 2) In the information processing system described in Appendix 1, the assist control unit may execute the first assist control when the user's speech includes a negative reaction, and in the first assist control, the user's request may be identified by inquiring about the user's request.

[0060] (Appendix 3) In the information processing system described in Appendix 1, the assist control unit executes the second assist control when the explanation provided by the voice assist includes technical terms and the user's speech includes a response of asking the user to repeat the explanation provided by the voice assist, and the second assist control may make it easier to convey the explanation provided by the voice assist to the user by explaining the technical terms.

[0061] (Appendix 4) In the information processing system described in Appendix 1, the assist control unit executes the second assist control when the user's speech includes a reaction of asking the voice assistant to repeat the explanation content, and the second assist control may make it easier to convey the explanation content provided by the voice assistant to the user by the voice assistant providing a re-explanation.

[0062] (Appendix 5) In the information processing system described in Supplementary Note 4, in the second assist control, a voice speed of the re-explanation by the voice assist may be made slower than the voice speed before the re-explanation.

[0063] According to the above configuration, the content of the explanation given by the voice assistance becomes easier to understand.

[0064] (Appendix 6) In the information processing system according to Supplementary Note 4 or 5, in the second assist control, a volume of the re-explanation by the voice assist may be made larger than the volume before the re-explanation.

[0065] According to the above configuration, the content of the explanation given by the voice assistance becomes easier to understand.

[0066] (Appendix 7) In the information processing system according to any one of Supplementary Notes 4 to 6, in the second assist control, an intonation of the re-explanation by the voice assist may be made different from the intonation before the re-explanation.

[0067] According to the above configuration, the content of the explanation given by the voice assistance becomes easier to understand.

[0068] (Appendix 8) In the information processing system described in any one of claims 1 to 7, the system may include an information processing device (18) having the speech information acquisition unit, the analysis unit, and the assist control unit, and an information device (16) having an utterance sending unit (38) that sends the utterance information to the information processing device.

[0069] (Appendix 9) A second disclosure is an information processing device in the information processing system according to any one of Supplementary Notes 1 to 7, the information processing device including the speech information acquisition unit, the analysis unit, and the assist control unit.

[0070] (Appendix 10) The third disclosure is an information processing method including an utterance information acquisition step (S3, S13) of acquiring utterance information, which is information on a user's utterance, an analysis step (S4, S14) of analyzing the content of the user's utterance based on the utterance information acquired in the utterance information acquisition step, and an assist control step (S6, S16) of executing assist control, which is control for providing voice assistance in response to the user's request, based on the result of the analysis in the analysis step, wherein the assist control step is capable of executing at least one of a first assist control and a second assist control, the first assist control being voice assist control for identifying the user's request when it is estimated that there is a discrepancy between the user's request and the explanation content provided by the voice assist, and the second assist control being voice assist control for making it easier to convey the explanation content provided by the voice assist to the user when it is estimated that the explanation content provided by the voice assist has not been conveyed to the user or is difficult to convey to the user.

[0071] (Appendix 11) The program according to the fourth disclosure causes a computer to execute the information processing method described in Supplementary Note 10.

[0072] The present invention is not limited to the above disclosure, and various configurations can be adopted without departing from the gist of the present invention. [Explanation of symbols]

[0073] 10...Information processing system 16...Information equipment 18... Information processing device 34, 46... Speech information acquisition unit 38...Communication control unit (speech transmission unit) 48...Analysis unit 50...Assist control unit

Claims

1. an utterance information acquisition unit that acquires utterance information that is information on a user's utterance; an analysis unit that analyzes the content of the user's utterance based on the utterance information acquired by the utterance information acquisition unit; an assist control unit that executes an assist control for providing voice assistance in response to a request from the user based on a result of the analysis by the analysis unit; Equipped with the assist control unit is capable of executing at least one of a first assist control and a second assist control, The first assist control is a voice assist control for identifying a request of the user when it is estimated that there is a discrepancy between the request of the user and the content of the explanation by the voice assist, The second assist control is a voice assist control for making it easier to convey the explanation content by the voice assist to the user when it is estimated that the explanation content by the voice assist has not been conveyed to the user or is difficult to convey to the user. Information processing system.

2. 2. The information processing system according to claim 1, The assist control unit executes the first assist control when a negative reaction is included in the utterance of the user, In the first assist control, the information processing system identifies the user's request by inquiring about the user's request.

3. 2. The information processing system according to claim 1, The assist control unit executes the second assist control when the explanation by the voice assist includes technical terms and the user's speech includes a response of asking the user to repeat the explanation content by the voice assist, In the second assist control, the information processing system makes it easier to convey the explanation content provided by the voice assistance to the user by providing an explanation of the technical terms.

4. 2. The information processing system according to claim 1, The assist control unit executes the second assist control when the user's utterance includes a response of asking the user to repeat the explanation content provided by the voice assist, In the second assist control, the information processing system makes it easier to convey the explanation content provided by the voice assist to the user by providing a re-explanation via the voice assist.

5. 5. The information processing system according to claim 4, In the second assist control, the speech speed of the re-explanation by the voice assist is made slower than the speech speed before the re-explanation.

6. 5. The information processing system according to claim 4, In the second assist control, the volume of the re-explanation by the voice assist is made larger than the volume before the re-explanation.

7. 5. The information processing system according to claim 4, In the second assist control, the intonation of the re-explanation by the voice assistance is made different from the intonation before the re-explanation, in this information processing system.

8. 2. The information processing system according to claim 1, an information processing device including the speech information acquisition unit, the analysis unit, and the assist control unit; an information device including an utterance transmitting unit that transmits the utterance information to the information processing device; An information processing system comprising:

9. An information processing device in the information processing system according to claim 1, An information processing device comprising the speech information acquisition unit, the analysis unit, and the assist control unit.

10. an utterance information acquisition step of acquiring utterance information which is information on a user's utterance; an analysis step of analyzing the content of the user's utterance based on the utterance information acquired in the utterance information acquisition step; an assist control step of executing an assist control for providing voice assistance in response to a request from the user based on a result of the analysis in the analysis step; An information processing method comprising: In the assist control step, at least one of a first assist control and a second assist control can be executed, The first assist control is a voice assist control for identifying a request of the user when it is estimated that there is a discrepancy between the request of the user and the content of the explanation by the voice assist, The second assist control is a voice assist control for making it easier to convey the explanation content by the voice assist to the user when it is estimated that the explanation content by the voice assist has not been conveyed to the user or is difficult to convey to the user. Information processing methods.

11. A program for causing a computer to execute the information processing method according to claim 10.

Citation Information

Patent Citations

  • Information processing device and information processing method

    JP2021071606A