Electronic apparatus and method for controlling electronic apparatus

Abstract

To provide an electronic apparatus and the like that can deliver a response suited to a question accepted from a user.SOLUTION: An electronic apparatus includes: an acceptance unit that accepts a question from a user; an acquisition unit that acquires first keyword information indicating one or more keywords corresponding to a plurality of respective peripheral apparatuses belonging to a network which is the same as the electronic apparatus; a specification unit that based on question information indicating the accepted question and the first keyword information, specifies a target peripheral apparatus which is a target to which the question information is to be transmitted from the plurality of peripheral apparatuses; a transmission control unit that performs control of transmitting the question information to the specified target peripheral apparatus; and an output unit that outputs a response based on response information for the question information received from the target peripheral apparatus.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an electronic device and a method for controlling an electronic device. [Background technology]

[0002] Patent Document 1 proposes a technology for distributing and executing AI (Artificial Intelligence) processing such as person identification processing, person linking processing, and person classification processing for monitoring in stores and the like. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-177432 Summary of the Invention [Problem to be solved by the invention]

[0004] For example, in recent years, electronic devices such as home appliances that can interact with users have come into use. In response to a question received from a user, the electronic device outputs an answer selected from a plurality of answers stored therein. In a system in which a plurality of electronic devices work together, an electronic device that receives a question from a user may not store an answer appropriate for the question. In this case, the electronic device cannot provide an answer appropriate for the user's question. Patent Document 1 does not solve this problem.

[0005] In one aspect, an object of the present disclosure is to provide an electronic device or the like that can provide an appropriate answer to a question received from a user. [Means for solving the problem]

[0006] An electronic device according to one embodiment of the present invention includes a receiving unit that receives questions from a user, an acquisition unit that acquires first keyword information indicating one or more keywords corresponding to each of a plurality of peripheral devices that belong to the same network as the electronic device, an identification unit that identifies a target peripheral device from the plurality of peripheral devices to which the question information is to be sent based on the question information indicating the received question and the first keyword information, a transmission control unit that controls the transmission of the question information to the identified target peripheral device, and an output unit that outputs an answer based on answer information to the question information received from the target peripheral device. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 illustrates an example of a system according to each embodiment. [Figure 2] FIG. 1 is a diagram illustrating an example of a neck speaker. [Figure 3] FIG. 2 is a diagram illustrating an example of an air conditioning device. [Figure 4] FIG. 1 is a diagram illustrating an example of an electric fan. [Figure 5A] FIG. 10 is a diagram showing an example of first keyword information. [Figure 5B] FIG. 10 is a diagram showing an example of second keyword information. [Figure 6] FIG. 3 is a sequence diagram showing an example of a processing flow according to the first embodiment. [Figure 7] 5 is a flowchart showing an example of a processing flow of the neck speaker in the first embodiment. [Figure 8] 8 is a flowchart continuing from FIG. 7. [Figure 9A] 10 is a flowchart showing a first example of a process for identifying a target peripheral device based on first keyword information. [Figure 9B] 10 is a flowchart showing a first example of a process for identifying a target peripheral device based on second keyword information. [Figure 10A] 10 is a flowchart showing a second example of a process for identifying a target peripheral device based on first keyword information. [Figure 10B]10 is a flowchart showing a second example of a process for identifying a target peripheral device based on second keyword information. [Figure 11] 10 is a flowchart showing an example of a processing flow according to a second embodiment. [Figure 12] FIG. 11 is a sequence diagram showing an example of a processing flow according to a third embodiment. [Figure 13] 13 is a flowchart showing an example of a processing flow according to a fourth embodiment. [Figure 14] 13 is a flowchart showing an example of a processing flow according to a fifth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] First Embodiment The first embodiment will be described below. Fig. 1 is a diagram showing an example of a system 101. The system 101 includes an internal network 102 and an external server 103. The internal network 102 and the external server 103 are connected via, for example, an internet line or the like.

[0009] The internal network 102 is, for example, a network in which multiple devices inside each home are interconnected. The internal network 102 is constructed, for example, by a wireless local area network (LAN). The external server 103 may be a cloud server that manages the internal network 102 of each home.

[0010] The neck speaker 111, the air conditioner 112, the television 113, the electric fan 114, and the refrigerator 115 are devices that belong to the internal network 102. The neck speaker 111, the air conditioner 112, the electric fan 114, the television 113, and the refrigerator 115 correspond to electronic devices or peripheral devices.

[0011] The neck speaker 111 is a wearable device worn around the neck of a user. The air conditioner 112 is, for example, an air conditioner. The television 113 is a display device that receives broadcast waves and displays images. The electric fan 114 has a fan function. The refrigerator 115 has a refrigeration function. The refrigerator 115 may also have a freezing function.

[0012] The external network connection unit 116 is connected to the neck speaker 111, the air conditioner 112, the television 113, the electric fan 114, and the refrigerator 115. The external network connection unit 116 is also connected to the external server 103 via an internet line or the like.

[0013] In the following embodiments, the neck speaker 111 will be described as an electronic device, and the air conditioner 112, the electric fan 114, the television 113, and the refrigerator 115 as peripheral devices. However, any one of the air conditioner 112, the electric fan 114, the television 113, and the refrigerator 115 may be an electronic device. In this case, the neck speaker 111 will be a peripheral device. In the following, the air conditioner 112 and the television 113 will be described as peripheral devices.

[0014] Next, we will explain the neck speaker 111. Fig. 2 is a diagram showing an example of the neck speaker 111. The neck speaker 111 includes a control unit 121, a microphone 122, a speaker 123, a storage unit 124, a communication unit 125, a radio wave intensity detection unit 126, and a position information detection unit 127.

[0015] The control unit 121 executes various processes of the neck speaker 111. The control unit 121 has a processor and a memory. The processor of the control unit 121 executes a plurality of instruction sets (programs) stored in the memory of the control unit 121, thereby realizing various controls of the control unit 121. Any processor such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an FPGA (Field Programmable Gate Array) can be used as the processor.

[0016] The microphone 122 is a receiving unit that receives voice uttered by the user wearing the neck speaker 111. The speaker 123 is an output unit that outputs a predetermined sound based on the control of the control unit 121. The storage unit 124 stores various types of information.

[0017] The communication unit 125 communicates with each peripheral device. The communication unit 125 functions as a receiving unit and a transmitting unit. In each embodiment, the communication unit 125 performs wireless communication. The radio wave intensity detection unit 126 detects the radio wave intensity of the wireless signal output by the communication unit of each peripheral device.

[0018] The position information detection unit 127 detects the position information of the neck speaker 111. The position information detection unit 127 detects the position information of the neck speaker 111 based on a signal received from a GPS (Global Positioning System), for example.

[0019] Next, the control unit 121 will be described. The control unit 121 includes a voice recognition unit 131, a keyword generation unit 132, an acquisition unit 133, an identification unit 134, and a transmission control unit 135. The voice recognition unit 131 recognizes the user's voice received by the microphone 122. In the following description, the user's voice will be described as a question from the user. However, the user's voice may be a voice other than a question.

[0020] The keyword generation unit 132 generates a plurality of question keywords from the recognized voice. For example, suppose the user utters a question such as "It's hot. What's the temperature now?" The microphone 122 receives the voice. The voice recognition unit 131 recognizes the voice received by the microphone 122. The recognized voice of the question is question information.

[0021] The keyword generation unit 132, for example, breaks down the speech data that has been speech-recognized into parts of speech. At this time, the keyword generation unit 132 extracts nouns, verbs, and adjectives from each of the broken down parts of speech and generates them as question keywords. As an example, the keyword generation unit 132 may generate three question keywords, "hot," "now," and "temperature," from the speech data of the above-mentioned question voice, "It's hot. What's the temperature now?"

[0022] The acquisition unit 133 acquires first keyword information corresponding to each of a plurality of peripheral devices (air conditioner 112, television 113, electric fan 114, and refrigerator 115) that belong to the same network as the neck speaker 111. In each embodiment, the first keyword information is assumed to be stored in advance in the storage unit 124. However, the first keyword information may also be stored in any of the plurality of peripheral devices. In this case, the acquisition unit 133 acquires the first keyword information from the peripheral device in which the first keyword information is stored.

[0023] The first keyword information is information indicating one or more keywords corresponding to each of a plurality of peripheral devices (air conditioner 112, television 113, electric fan 114, and refrigerator 115). For example, the first keyword information of air conditioner 112 as a peripheral device is information indicating keywords related to air conditioner 112, such as "temperature" or "degrees." Details of the first keyword information will be described later.

[0024] The identification unit 134 identifies one target peripheral device to which the question information is to be sent, based on the question information and the first keyword information. In each embodiment, the identification unit 134 identifies one target peripheral device to which the question information is to be sent, based on the question keyword generated by the keyword generation unit 132 based on the question information and the first keyword information acquired by the acquisition unit 133.

[0025] For example, suppose the question keywords generated by the keyword generation unit 132 based on the question information are the three question keywords described above: "hot," "now," and "temperature." Also, suppose the keyword "degrees" is included in the first keyword information, and that the keyword is associated with an air conditioner 112. In this case, since the "degrees" in the question keyword matches the "degrees" in the first keyword information, the identification unit 134 identifies the air conditioner 112 corresponding to the keyword "degrees" in the first keyword information as the target peripheral device to which the question information is to be transmitted.

[0026] The transmission control unit 135 controls the transmission of question information to the target peripheral device identified by the identification unit 134. The communication unit 125 transmits the question information to the identified target peripheral device (e.g., the air conditioner 112) based on this control. The transmission control unit 135 may transmit question information such as "It's hot. What's the temperature now?" as is, or may transmit each of the above-mentioned question keywords as question information.

[0027] As will be described later, the target peripheral device that receives the question information transmits answer information to the neck speaker 111. For example, suppose that the air conditioner 112, which is the target peripheral device, receives the question information, "It's hot. What's the temperature now?" Based on the question information, the air conditioner 112, which is the target peripheral device, recognizes that the question is about temperature. As will be described later, the air conditioner 112 detects the temperature. The air conditioner 112 transmits, for example, the detected temperature, "35 degrees," to the neck speaker 111 as answer information to the question information.

[0028] The control unit 121 generates a response based on the response information received from the target peripheral device. For example, the control unit 121 may add the phrases "The current temperature is" and "is" before and after the received response information "35 degrees" to generate a response "The current temperature is 35 degrees." In this case, the speaker 123 outputs the response "The current temperature is 35 degrees." The control unit 121 does not need to add such phrases to the received response information. In this case, the speaker 123 outputs the response "35 degrees."

[0029] The speaker 123 outputs the generated answer. The answer is a response from one of the peripheral devices to the voice of the question uttered by the user. By outputting the answer from the speaker 123, the answer to the question posed by the user to the neck speaker 111 is obtained.

[0030] Next, we will explain the air conditioning equipment 112. Fig. 3 is a diagram showing an example of the air conditioning equipment 112. The air conditioning equipment 112 includes a control unit 221, a microphone 222, a speaker 223, a storage unit 224, a communication unit 225, a radio wave intensity detection unit 226, a position information detection unit 227, an air conditioning equipment driving unit 228, and a temperature detection unit 229.

[0031] The air conditioner driving unit 228 controls various mechanisms, such as a heat exchanger and air direction vanes, that perform air conditioning in the air conditioner 112. The temperature detection unit 229 detects the temperature around the air conditioner 112. The microphone 222, the speaker 223, the memory unit 224, the communication unit 225, the radio wave intensity detection unit 226, and the position information detection unit 227 are the same as the corresponding units in FIG.

[0032] The air conditioner 112 receives the question information transmitted by the neck speaker 111. The control unit 221 analyzes the received question information and generates answer information. For example, as described above, if the question information is "It's hot. What's the temperature now?", the control unit 221 recognizes that the received question information is a question about temperature based on the keyword "temperature" included in the question information.

[0033] In this case, the control unit 221 generates, as answer information, information indicating the temperature (for example, "35 degrees") detected by the temperature detection unit 229. The control unit 221 controls the transmission of the generated answer information to the neck speaker 111 via the communication unit 225.

[0034] The voice recognition unit 231, keyword generation unit 232, acquisition unit 233, identification unit 234, and transmission control unit 235 of the air conditioning equipment 112 perform functions similar to those of the control unit 121 of the neck speaker 111 when the air conditioning equipment 112 functions as an electronic device.

[0035] Next, the television 113 will be described. Fig. 4 is a diagram showing an example of the television 113. The television 113 includes a control unit 321, a microphone 322, a speaker 323, a storage unit 324, a communication unit 325, a radio wave intensity detection unit 326, a location information detection unit 327, and a display 328. The display 328 is a display screen of the television 113. The units in Fig. 4 other than the display 328 are the same as the units of the air conditioner 112 in Fig. 3, and therefore description thereof will be omitted.

[0036] Next, the first keyword information will be described. Fig. 5A is a diagram showing an example of the first keyword information. The first keyword information includes items such as device ID, device, keyword, and location. The first keyword information does not have to be in a table format as shown in Fig. 5A. The same applies to the second keyword information described later.

[0037] The device ID is information that identifies the electronic device and each peripheral device (hereinafter, sometimes simply referred to as device). The device ID may be information that uniquely identifies the device, such as a MAC (Media Access Control address) address. The device is information that indicates the name of the device. The keyword is one or more keywords that correspond to the corresponding device. The location is location information of the corresponding device. The first keyword information and the second keyword information may or may not include location information.

[0038] A device ID and a keyword of the first keyword information are initially registered in the neck speaker 111, the air conditioner 112, the electric fan 114, the television 113, and the refrigerator 115. For example, the first keyword information and the second keyword information may be registered in each device before shipping, or each device may periodically obtain the latest first keyword information and second keyword information from a predetermined server or the like.

[0039] The location information of each device can be obtained based on the location information detection unit of each device. It is assumed that the air conditioner 112, the television 113, the electric fan 114, and the refrigerator 115 are located in fixed positions.

[0040] The position information of each of the air conditioner 112, the television 113, the electric fan 114, and the refrigerator 115 may be manually set by the user. For example, the position information of "first floor living room" may be manually set for the air conditioner 112. The position information of "first floor living room" may also be manually set for the television 113. The position information of "second floor bedroom" may also be manually set for the electric fan 114. The position information of "first floor kitchen" may also be manually set for the refrigerator 115. The manual setting of the position information may be performed collectively for any one of the devices.

[0041] The neck speaker 111 is an electronic device worn around the user's neck, and its position information basically changes. Therefore, in the first keyword information, the position information corresponding to the neck speaker 111 may be treated as a variable value. For example, the information "Free" indicating that the position information is treated as a variable value may be registered in the position item corresponding to the neck speaker 111 in the first keyword information.

[0042] When the neck speaker 111, air conditioner 112, electric fan 114, television 113, and refrigerator 115 are first connected, each device broadcasts its own device ID, keyword, and location information to share this information. This allows the neck speaker 111 to obtain first keyword information as shown in Figure 5A. The same applies to each peripheral device.

[0043] Furthermore, when a new device (for example, an air purifier) ​​is connected to the internal network 102, the new device broadcasts a device ID, keyword, and location information for identifying itself to the neck speaker 111, the air conditioner 112, the electric fan 114, the television 113, and the refrigerator 115. As a result, the neck speaker 111, the air conditioner 112, the electric fan 114, the television 113, and the refrigerator 115 each add the device ID, keyword, and location information of the new device to the first keyword information in FIG. 5A.

[0044] As described above, the acquisition unit 133 of the neck speaker 111 acquires the first keyword information stored in the storage unit 124. The identification unit 134 compares the keywords in the acquired first keyword information with the question keywords generated by the keyword generation unit 132 based on the question information. The identification unit 134 identifies devices with keywords in the first keyword information that match the question keywords.

[0045] For example, as described above, assume that three question keywords, "hot," "now," and "temperature," are generated based on the question information "It's hot. What's the temperature now?" The identification unit 134 refers to the keyword item of the first keyword information and searches for a keyword that matches any of "hot," "now," and "temperature."

[0046] In the example of FIG. 5A, the identification unit 134 identifies air conditioner A and air conditioner B that match "temperature" in the first keyword information. The air conditioner A and air conditioner B are candidates for the target peripheral device to which the question information is to be sent. The identification unit 134 may identify the air conditioner of air conditioner A and air conditioner B that is closest to the neck speaker 111 as the target peripheral device to which the question information is to be sent. This identifies one target peripheral device to which the question information is to be sent.

[0047] For example, based on the position information of the neck speaker 111, air conditioner A, and air conditioner B, it is assumed that of the two candidates, air conditioner A is closest to the neck speaker 111. In this case, the identification unit 134 identifies air conditioner A as the target device to which question information is to be transmitted. The transmission control unit 135 transmits the question information to the identified air conditioner A.

[0048] The air conditioner A transmits answer information to the question information to the neck speaker 111. The neck speaker 111 outputs an answer based on the received answer information. Therefore, when there are multiple target peripheral devices from which answer information to the question information can be obtained, the neck speaker 111 can obtain the answer information from the target peripheral device that is closest to the neck speaker 111. Therefore, when there are multiple candidate target peripheral devices, the neck speaker 111 can obtain the answer information from the target peripheral device that is estimated to be able to receive the answer information most quickly.

[0049] Furthermore, as described above, when the specifying unit 134 specifies air conditioner A and air conditioner B as candidates, the specifying unit 134 may specify the device with the strongest radio wave intensity as the target peripheral device to which question information is to be transmitted.

[0050] The radio wave intensity detection unit 126 of the neck speaker 111 detects the radio wave intensity of the wireless signal output by the communication unit of each device. The identification unit 134 may identify one device outputting the strongest radio wave among multiple candidate devices (air conditioner A and air conditioner B) as the target peripheral device to which question information is to be transmitted.

[0051] In this case, the answer information is obtained from the device among the multiple candidates that has the strongest radio wave intensity detected by the neck speaker 111. Therefore, when there are multiple candidates, the neck speaker 111 can obtain the answer information from the device that is estimated to be able to receive the answer information most quickly.

[0052] Next, the second keyword information will be described. FIG. 5B is a diagram showing an example of the second keyword information. The second keyword information includes the following items: device ID, device, keyword, and location. Each item is the same as that of the first keyword information. However, the number of keywords included in the second keyword information is greater than the number of keywords included in the first keyword information. Specifically, for each device included in the second keyword information, the number of corresponding keywords is greater than the number of keywords in the first keyword information.

[0053] The keywords corresponding to each device in the second keyword information are multiple keywords related to each device. For example, the keywords in the second keyword information may be synonyms or similar words of the keywords in the first keyword information, or may be keywords that conceptually extend the keywords in the first keyword information.

[0054] For example, the keywords "hot" and "cold" in the second keyword information that correspond to air conditioner A are keywords related to the keyword "temperature" in the first keyword information that corresponds to air conditioner A. The number of keywords that correspond to the same peripheral device is greater in the second keyword information than in the first keyword information.

[0055] Alternatively, the keyword corresponding to air conditioner A in the first keyword information may be "hot," and the keywords corresponding to air conditioner A in the second keyword information may be "air temperature" and "temperature." In this case, the number of keywords corresponding to the same peripheral device is greater in the second keyword information than in the first keyword information.

[0056] As described above, the identification unit 134 refers to the keyword items in the first keyword information acquired by the acquisition unit 133 and searches for a keyword that matches the question keyword. As a result of the search, there may be a case where the first keyword information does not contain a keyword that matches the question keyword. If the first keyword information does not contain a keyword that matches the question keyword, the identification unit 134 searches for second keyword information. In this case, the acquisition unit 133 acquires the second keyword information from the storage unit 124.

[0057] The identification unit 134 refers to the keyword item of the second keyword information and searches for a keyword that matches the question keyword. Through this search, the identification unit 134 identifies devices in the second keyword information that have a keyword that matches the question keyword.

[0058] For example, suppose the user utters a question such as "Is it cold now?" The microphone 122 receives the voice. The voice recognition unit 131 recognizes the voice received by the microphone 122 and generates question information.

[0059] The keyword generation unit 132 generates two question keywords, "now" and "cold", based on the question information. The identification unit 134 refers to the keyword items in the first keyword information acquired by the acquisition unit 133 and searches for keywords that match the two question keywords, "now" and "cold". The first keyword information in FIG. 5A does not contain these two question keywords.

[0060] If the identification unit 134 determines that the first keyword information does not contain a keyword that matches the question keyword, the acquisition unit 133 acquires second keyword information from the storage unit 124. The identification unit 134 refers to the keyword items in the second keyword information acquired by the acquisition unit 133 and searches for a keyword that matches the two question keywords, "now" and "cold."

[0061] 5B includes a keyword "cold." The peripheral devices corresponding to the keyword "cold" are air conditioner A and air conditioner B. The identification unit 134 identifies air conditioner A and air conditioner B as candidates for the target peripheral devices to which question information is to be transmitted.

[0062] As described above, the identification unit 134 identifies one of air conditioner A and air conditioner B as the target peripheral device to which question information is to be transmitted, based on the location information or radio wave intensity. Assume that the identified target peripheral device is air conditioner A. In this case, answer information such as "15 degrees" is obtained from air conditioner A.

[0063] As described above, the identification unit 134 first identifies a target peripheral device to which question information is to be sent based on first keyword information that has a small number of keywords. This shortens the time required to search for first keyword information, and therefore allows the identification of a target peripheral device to which question information is to be sent quickly.

[0064] If the question keyword generated from the question information is not found in the first keyword information, the identification unit 134 searches for second keyword information that has a larger number of keywords than the first keyword information, thereby enabling the identification unit 134 to more broadly search for target peripheral devices to which the question information is to be sent.

[0065] The identification unit 134 first searches the first keyword information for keywords that match the multiple question keywords generated from the question information, and if no corresponding peripheral device is extracted, searches the second keyword information. This allows the target peripheral device to be identified quickly and a wider range of target peripheral devices to be targeted.

[0066] Next, the processing flow of the first embodiment will be described. Fig. 6 is a sequence diagram showing an example of the processing flow of the first embodiment. The sequence diagram of the example in Fig. 6 shows neck speaker 111, air conditioner 112, and television 113, but peripheral devices such as electric fan 114 and refrigerator 115 also perform the same processing as air conditioner 112 and television 113.

[0067] The neck speaker 111, the air conditioner 112, and the television 113 share keywords with each other (step S101). For example, the neck speaker 111, the air conditioner 112, and the television 113 each initially stores first keyword information and second keyword information that indicate keywords related to the neck speaker 111, the air conditioner 112, and the television 113. The neck speaker 111, the air conditioner 112, and the television 113 broadcast the first keyword information and second keyword information. The neck speaker 111, the air conditioner 112, and the television 113 each store the first keyword information and second keyword information of each of the other devices.

[0068] When a new peripheral device is connected to the internal network 102, the new peripheral device broadcasts first keyword information and second keyword information indicating keywords related to the new peripheral device. The neck speaker 111, the air conditioner 112, and the television 113 store the first keyword information and second keyword information of the new peripheral device that have been broadcast.

[0069] Next, it is assumed that the user speaks into the microphone 122 of the neck speaker 111. The microphone 122 of the neck speaker 111 receives the voice of a question from the user wearing the neck speaker 111 (step S102).

[0070] The voice recognition unit 131 recognizes the voice of the question received by the microphone 122 (step S103). For example, as described above, the voice recognition unit 131 recognizes the voice of the question, "It's hot. What's the temperature now?"

[0071] The keyword generation unit 132 generates a plurality of question keywords from the voice of the question that has been voice-recognized. For example, the keyword generation unit 132 generates three question keywords, "hot," "now," and "temperature," from the question information, "It's hot. What's the temperature now?"

[0072] The acquiring unit 133 acquires the first keyword information stored in the storage unit 124 (Step S105). The identifying unit 134 identifies a target peripheral device to which the question information is to be transmitted, based on the acquired first keyword information and the question information (Step S106).

[0073] As described above, if the question keyword generated from the question information is not included in the first keyword information, the acquiring unit 133 acquires the second keyword information stored in the storage unit 124. Then, the identifying unit 134 identifies a target peripheral device to which the question information is to be transmitted, based on the acquired second keyword information and the question information. In the example of Fig. 6, it is assumed that the air conditioner 112 is identified as the target peripheral device.

[0074] The transmission control unit 135 controls the transmission of the question information to the air conditioner 112 identified by the identification unit 134 (step S107). As a result, the question information is transmitted from the communication unit 125 to the identified air conditioner 112.

[0075] The control unit 221 of the air conditioner 112 recognizes that the question information is a question about temperature based on the question information received from the neck speaker 111. The control unit 221 of the air conditioner 112 generates information about the temperature detected by the temperature detection unit 229 as answer information (step S108).

[0076] For example, if the temperature detected by the temperature detection unit 229 is "35 degrees," the control unit 221 of the air conditioner 112 acquires the information "35 degrees" as answer information. The air conditioner 112 transmits the acquired answer information to the neck speaker 111 that transmitted the question information (step S109).

[0077] The neck speaker 111 outputs a response based on the received response information (step S111). If the received response information is "35 degrees," the neck speaker 111 may add the phrases "The current temperature is" and "is" before and after the response information to generate a response such as "The current temperature is 35 degrees." The user wearing the neck speaker 111 can recognize the response "The current temperature is 35 degrees" output from the speaker 123.

[0078] Next, the processing of the neck speaker 111 as an electronic device will be described. Fig. 7 is a flowchart showing an example of the processing flow of the neck speaker in the first embodiment. The control unit 121 determines whether or not voice has been received from the user (step S201).

[0079] For example, control unit 121 may make the determination in step S201 based on whether the frequency of the sound received by microphone 122 is within the frequency band of human speech. Control unit 121 may also make the determination in step S201 based on whether the interval between sounds received by microphone 122 matches the interval between sounds when humans converse. Information about the frequency band of human speech and information about the interval between sounds when humans converse may be stored in storage unit 124 in advance.

[0080] If the control unit 121 determines No in step S201, it returns the process to step S201. If the control unit 121 determines Yes in step S201, it proceeds to step S202. The voice recognition unit 131 recognizes the voice of the question received by the microphone 122 (step S202). The keyword generation unit 132 generates a plurality of question keywords from the voice data of the question that has been voice-recognized (step S203).

[0081] Here, the storage unit 124 of the neck speaker 111 may store a plurality of keywords corresponding to the neck speaker 111 as third keyword information. In this case, the control unit 121 searches for a keyword that matches one of the plurality of question keywords generated by the keyword generation unit 132 among the plurality of keywords stored in the storage unit 124 of the neck speaker 111.

[0082] If the search results in a matching keyword being found in the third keyword information, the neck speaker 111 holds the answer to the user's question. Therefore, the neck speaker 111 does not need to acquire answer information from a peripheral device. In this case, the control unit 121 generates an answer based on the answer information to the question information without performing the processes in step S105 and subsequent steps. The speaker 123 outputs the generated answer. On the other hand, if the third keyword information does not contain a matching keyword, the neck speaker 111 does not hold the answer to the user's question. In this case, the control unit 121 proceeds to step S204.

[0083] The acquiring unit 133 acquires the primary keyword information stored in the storage unit 124 (Step S204). The identifying unit 134 determines whether the generated question keyword is included in the primary keyword information (Step S205).

[0084] If the generated question keyword is not included in the first keyword information, the identifying unit 134 determines No in step S205 and advances the process from "A" to step S210 in FIG.

[0085] If the generated question keyword is included in the first keyword information, the identification unit 134 determines Yes in step S205 and proceeds to step S206. As described above, the identification unit 134 performs a process of identifying the target peripheral device based on the first keyword information (step S206).

[0086] The transmission control unit 135 controls the transmission of the question information to the identified target peripheral device (step S207). Based on this control, the communication unit 125 transmits the question information to the identified target peripheral device. The target peripheral device that receives the question information generates answer information to the question information and transmits the generated answer information to the neck speaker 111 that transmitted the question information.

[0087] The neck speaker 111 receives the answer information (step S208). The control unit 121 generates an answer to the user as voice data from the identified answer information. The speaker 123 outputs the voice of the answer indicated by the voice data (step S209). Then, the control unit 121 ends the processing of this embodiment.

[0088] Next, a case where the identification unit 134 determines No in step S205 will be described. In this case, the identification unit 134 proceeds to the process of step S210 in Fig. 8. Fig. 8 is a flowchart continued from Fig. 7.

[0089] The acquiring unit 133 acquires the second keyword information stored in the storage unit 124 (Step S210). Step S210 is performed when the question keyword generated from the question information is not included in the first keyword information. The identifying unit 134 determines whether the generated question keyword is included in the second keyword information (Step S211).

[0090] If the generated question keyword is not included in the second keyword information, the identifying unit 134 determines No in step S211 and proceeds to step S216.

[0091] If the generated question keyword is included in the second keyword information, the identification unit 134 determines Yes in step S211 and proceeds to step S212. As described above, the identification unit 134 performs a process of identifying the target peripheral device based on the second keyword information (step S212).

[0092] The transmission control unit 135 controls the transmission of the question information to the identified target peripheral device (step S213). Based on this control, the communication unit 125 transmits the question information to the identified target peripheral device. The target peripheral device that receives the question information generates answer information to the question information and transmits the generated answer information to the neck speaker 111 that transmitted the question information.

[0093] The neck speaker 111 receives the answer information (step S214). The control unit 121 generates an answer to the user as voice data from the received answer information. The speaker 123 outputs the voice of the answer indicated by the voice data (step S215). Thereafter, the control unit 121 advances the process to "B" in FIG. 7, and ends the process of this embodiment.

[0094] Next, a case where the specification unit 134 determines No in step S211 will be described. In this case, each of the generated question keywords is not included in either the first keyword information or the second keyword information.

[0095] In the above case, the identification unit 134 proceeds to step S216. The transmission control unit 135 controls the transmission of the question information to the external server 103 via the external network connection unit 116 (step S216). As a result, the question information is transmitted to the external server 103.

[0096] The external server 103 is, for example, a cloud server that manages the internal network 102 of each home, and has answer information to the question information of all devices that belong to the internal network 102. The external server 103 generates answer information to the question information based on the received question information. The external server 103 transmits the generated answer information to the neck speaker 111 via the internal network 102.

[0097] The neck speaker 111 receives the answer information (step S217). The control unit 121 generates an answer to the user as voice data from the received answer information. The speaker 123 outputs the voice of the answer indicated by the voice data (step S218). Thereafter, the control unit 121 advances the process to "B" in FIG. 7, and ends the process of this embodiment.

[0098] Next, a first example of the process of step S206 will be described. Fig. 9A is a flowchart showing a first example of the process of identifying a target peripheral device based on first keyword information. The identification unit 134 determines whether the first keyword information acquired in step S204 includes multiple question keywords generated in step S203 (step S301).

[0099] As described above, assume that the question keywords generated from the question information are "hot," "now," and "temperature," and that the first keyword information includes the keyword "temperature" as in the example of FIG. 5A. In this case, the peripheral devices corresponding to the keyword "temperature" in the first keyword information are air conditioner A and air conditioner B. In this case, since there are two candidates for the target peripheral device, the identification unit 134 determines Yes in step S301 and proceeds to step S302.

[0100] The identification unit 134 identifies one peripheral device that is closest to the neck speaker 111 based on the position information of the neck speaker 111 and the position information of the identified multiple peripheral devices (step S302). The identification unit 134 identifies the one peripheral device that is closest to the neck speaker 111 identified in step 302 as a target peripheral device based on the first keyword information (step S303).

[0101] If the first keyword information acquired in step S204 does not include multiple question keywords generated in step S203, only one target peripheral device is identified based on the first keyword information. In this case, it is not necessary to perform step S302, which identifies one target peripheral device using location information. Therefore, if the determination in step S301 is No, the identification unit 134 skips step S302 and proceeds to step S303.

[0102] Next, a first example of the process of step S212 will be described. Fig. 9B is a flowchart showing a first example of the process of identifying a target peripheral device based on the second keyword information. The identification unit 134 determines whether the second keyword information acquired in step S210 includes multiple question keywords generated in step S203 (step S311).

[0103] As described above, assume that the question keywords generated from the question information are "now" and "cold," and the second keyword information includes the keyword "cold" as in the example of FIG. 5B. In this case, the devices corresponding to the keyword "cold" in the second keyword information are air conditioning equipment A and air conditioning equipment B. In this case, since there are two candidates, the identification unit 134 determines Yes in step S311 and proceeds to step S312.

[0104] The identification unit 134 identifies one peripheral device that is closest to the neck speaker 111 based on the position information of the neck speaker 111 and the position information of the identified multiple peripheral devices (step S312). The identification unit 134 identifies the one peripheral device that is closest to the neck speaker 111 as a target peripheral device based on the second keyword information (step S313).

[0105] If the second keyword information acquired in step S210 does not include multiple question keywords generated in step S203, only one target peripheral device is identified based on the second keyword information. Therefore, if the determination in step S311 is No, the identification unit 134 skips step S312 and proceeds to step S313.

[0106] Next, a second example of the processing of step S206 will be described. Fig. 10A is a flowchart showing a second example of the processing for identifying a target peripheral device based on first keyword information. Step S401 is the same processing as step S301 in Fig. 9A, and step S403 is the same processing as step S303 in Fig. 9A, so their explanations will be omitted.

[0107] The identification unit 134 identifies one peripheral device having the strongest radio wave intensity detected by the radio wave intensity detection unit 126 from among the identified peripheral devices (step S402). As a result, when the first keyword information acquired in step S204 includes multiple question keywords generated in step S203, one target peripheral device is identified as the target peripheral device based on the first keyword information.

[0108] Next, a second example of the process of step S212 will be described. Fig. 10B is a flowchart showing a second example of the process of identifying a target peripheral device based on second keyword information. Step S411 is the same process as step S311 in Fig. 9B, and step S413 is the same process as step S313 in Fig. 9B, so their explanations will be omitted.

[0109] The identification unit 134 identifies one peripheral device having the strongest radio wave intensity detected by the radio wave intensity detection unit 126 from among the identified peripheral devices (step S412). As a result, when the second keyword information acquired in step S210 includes multiple question keywords generated in step S203, one target peripheral device is identified as the target peripheral device based on the second keyword information.

[0110] As described above, the neck speaker 111 identifies, from among the multiple peripheral devices, a target peripheral device to which the question information is to be transmitted, based on a question keyword generated from the question information from the user and first keyword information indicating one or more keywords corresponding to each of the multiple peripheral devices. As a result, the neck speaker 111 can identify a target peripheral device that can provide an appropriate answer to the question received from the user, even if the target peripheral device does not have answer information for the question information, and transmit the question information to the identified target peripheral device. Then, the neck speaker 111 outputs an answer based on the answer information received from the target peripheral device, and can provide an appropriate answer to the question received from the user.

[0111] Second Embodiment Next, a second embodiment will be described. Fig. 11 is a flowchart showing an example of the processing flow of the second embodiment. In the flowchart of Fig. 11, the processing of steps S201 to S209 is the same as the processing of the flowchart of Fig. 7, so description thereof will be omitted.

[0112] When the control unit 121 of the neck speaker 111 determines that it has received a voice from the user, it determines Yes in step S201 and proceeds to step S501. In this case, the control unit 121 controls the speaker 123 to output a predetermined voice (step S501). As a result, the predetermined voice is output from the speaker 123. The predetermined voice may be a voice indicating that a response is being made, such as "enquiry in progress." The predetermined voice may also be a word such as "um," which indicates the interval between receiving a question and outputting an answer. The voice data is stored in advance in the storage unit 124, for example.

[0113] In step S208, control unit 121 receives the answer information. Thereafter, control unit 121 proceeds to step S502. Control unit 121 controls speaker 123 to stop outputting a predetermined sound (step S502). As a result, the predetermined sound is no longer output from speaker 123. Thereafter, in step S209, an answer is output from speaker 123.

[0114] As described above, the speaker 123 outputs a predetermined sound from the time when the voice from the user is received until the answer is output, thereby enabling the user wearing the neck speaker 111 to recognize that processing is being performed to obtain an answer to the question.

[0115] Third Embodiment Next, a third embodiment will be described. Fig. 12 is a sequence diagram showing an example of the processing flow of the third embodiment. In the sequence diagram of Fig. 12, the processes of steps S101 to S110 are the same as those in the sequence diagram of Fig. 6, and therefore description thereof will be omitted. In step S111, the speaker 123 outputs the generated answer.

[0116] As a result, a response such as "The current temperature is 35 degrees" is provided to the user. After the response is output, the user may issue a further instruction to the microphone 122. For example, upon hearing the response, the user may issue a voice instruction to the microphone 122 to lower the temperature.

[0117] The microphone 122 receives a voice uttered by the user (step S601). For example, if the user utters, "Please lower the room temperature," the microphone 122 receives the voice. The voice recognition unit 131 recognizes the voice received by the microphone 122 (step S602).

[0118] The control unit 121 transmits the user's voice, which has been recognized as a voice instruction, to the identified target peripheral device (the air conditioner 112 in the example of FIG. 12) via the communication unit 125 (step S603). The control unit 121 holds information about the identified target peripheral device. This enables the control unit 121 to identify the destination of the user's voice instruction.

[0119] The control unit 221 of the air conditioner 112 controls the air conditioner driving unit 228 to control the temperature based on the received instruction (step S604). For example, the keyword generation unit 232 of the air conditioner 112 generates multiple keywords from the received instruction "Lower the room temperature." The generated multiple keywords include the keyword "Lower." The control unit 221 of the air conditioner 112 controls the air conditioner driving unit 228 to lower the temperature based on the keyword "Lower."

[0120] The control unit 221 of the air conditioner 112 performs machine learning on the temperature transmitted to the neck speaker 111 as answer information and the temperature-related instruction from the user (step S605). For example, the control unit 221 of the air conditioner 112 performs machine learning on a learning model that indicates the relationship between the temperature and the instruction, using the temperature transmitted to the neck speaker 111 as answer information and the temperature-related instruction from the user as correct answer data.

[0121] For example, the control unit 221 of the air conditioner 112 inputs the temperature detected by the temperature detection unit 229 into a trained model that has been machine-learned. The trained model is a trained model that has learned the relationship between the ambient temperature of the air conditioner 112 and user instructions. When the temperature detected by the temperature detection unit 229 is input into the trained model, the trained model outputs a temperature according to the user instruction. The control unit 221 of the air conditioner 112 controls the temperature of the air conditioner driving unit 228 so that the temperature is set to the output temperature. This automatically sets the temperature to a value suitable for the user.

[0122] The processes of steps S601 to S605 may be repeated. For example, after the process of step S604 is performed, the user may issue an instruction to further lower the temperature. For example, in step S601, microphone 122 may again receive a voice command to "lower the room temperature." In this case, the processes of steps S601 to S605 are performed again.

[0123] As described above, the control unit 121 holds information (e.g., MAC address) indicating the identified target peripheral device for a certain period of time. This allows the control unit 121 to transmit a second instruction to the destination of the user's voice instruction, which has been recognized by voice recognition, even if the user issues another instruction.

[0124] <Fourth embodiment> Next, a fourth embodiment will be described. Fig. 13 is a flowchart showing an example of the processing flow of the fourth embodiment. In the flowchart of Fig. 13, the processing in steps S201 to S207 is the same as the processing in the flowchart of Fig. 7.

[0125] In step S207, the transmission control unit 135 of the neck speaker 111 transmits the question information to the identified target peripheral device via the communication unit 125. In this embodiment, the peripheral device that receives the question information further recognizes information that identifies itself (device identification information). The device identification information is pre-stored in the memory unit of each peripheral device.

[0126] The device identification information is, for example, text information that indicates a peripheral device. The device identification information for the air conditioner 112 may be "air conditioner." The device identification information for the television 113 may be "television."

[0127] The device identification information does not have to be information that directly identifies a peripheral device. For example, the device identification information may be a MAC address. The storage unit 124 of the neck speaker 111 stores a MAC address corresponding to each peripheral device. The neck speaker 111 can identify a peripheral device based on the MAC address.

[0128] Each peripheral device transmits answer information and device identification information to the neck speaker 111. The communication unit 125 of the neck speaker 111 receives the answer information and device identification information (step S701). The control unit 121 generates an answer based on the received answer information and device identification information. The speaker 123 outputs the generated answer (step S702).

[0129] For example, assume that the above-mentioned device identification information is “air conditioner.” In this embodiment, for example, the control unit 121 generates a response such as “According to the air conditioner, the current temperature is 35 degrees” based on the device identification information.

[0130] In step S702, the speaker 123 outputs the response, thereby enabling the user to recognize which of the peripheral devices included in the internal network 102 has sent the response.

[0131] Fifth Embodiment Fig. 14 is a flowchart showing an example of the processing flow of the fifth embodiment. In the flowchart of Fig. 14, the processing in steps S201 to S207 is the same as the processing in the flowchart of Fig. 7, and therefore description thereof will be omitted.

[0132] In this embodiment, each peripheral device recognizes information (device linkage information) about devices that operate in cooperation with itself. Peripheral devices included in the internal network 102 may operate in cooperation with other peripheral devices.

[0133] For example, suppose that an air conditioner 112 and an electric fan 114 located in the same room operate in cooperation with each other via the internal network 102 or a separate communication means. In this case, the device cooperation information about the air conditioner 112 may be information indicating that the air conditioner 112 operates in cooperation with the electric fan 114.

[0134] For example, suppose that the air conditioner 112 is identified as the target peripheral device. In response to receiving the question information, the air conditioner 112 transmits answer information and device linkage information (information indicating that the air conditioner 112 operates in linkage with the electric fan 114) to the neck speaker 111. The communication unit 125 of the neck speaker 111 receives the answer information and device linkage information (step S801).

[0135] The neck speaker 111 generates a response based on the received response information and device linkage information (step S802).

[0136] For example, the control unit 121 generates a response such as "The current temperature is 35 degrees" based on the response information "35 degrees." In this embodiment, the control unit 121 may add information such as "Do you want to turn on the fan as well?" to the response based on the received device linkage information (information indicating that the air conditioner 112 is operating in linkage with the electric fan 114). In this case, the control unit 121 generates a response such as "The current temperature is 35 degrees. Do you want to turn on the electric fan?" In step S210, the speaker 123 outputs the response.

[0137] This makes it possible to present not only a suitable answer to a question from a user but also additional information to the user when a plurality of peripheral devices are linked together, not just one peripheral device.

[0138] Here, it is assumed that after the speaker 123 outputs the above-mentioned response, the microphone 122 receives the voice "yes" from the user. The control unit 121 transmits a positive instruction for the device cooperation information to the air conditioner 112, which is the peripheral device that transmitted the device cooperation information.

[0139] The control unit 221 of the air conditioner 112 operates the electric fan 114 in cooperation with the air conditioner 112 based on the affirmative instruction received from the neck speaker 111. As a result, both the air conditioner 112 and the electric fan 114 start operating.

[0140] 12 in the third embodiment described above, the control unit 221 of the air conditioner 112 performs machine learning on the relationship between the temperature returned as answer information and temperature-related instructions. This allows the control unit 221 of the air conditioner 112 to automatically set the temperature according to the user's preferences.

[0141] Here, assume that the temperature setting suitable for the user that the control unit 221 of the air conditioner 112 has learned through machine learning is "34 degrees." In this case, the response information sent by the air conditioner 112 is "35 degrees," which is a small difference from the above-mentioned temperature setting of "34 degrees."

[0142] In this case, since the difference is small, the air conditioner 112 may transmit device linkage information such as, "Do you want to turn on the electric fan at a low setting?". As a result, the speaker 123 outputs a response such as, "The current temperature is 35 degrees. Do you want to turn on the electric fan at a low setting?"

[0143] Also, assume that the temperature setting suitable for the user that the control unit 221 of the air conditioner 112 has learned through machine learning is "30 degrees." In this case, the response information sent by the air conditioner 112 is "35 degrees," which is significantly different from the above-mentioned temperature setting of "30 degrees."

[0144] In this case, since the difference is large, the air conditioner 112 may transmit device linkage information such as "Do you want to turn on the electric fan at high setting?". As a result, the speaker 123 outputs a response such as "The current temperature is 35 degrees. Do you want to turn on the electric fan at high setting?"

[0145] As a result, when a peripheral device is operating in conjunction with other peripheral devices, it is possible to present the user with not only appropriate answers to questions from the user, but also additional information according to the user's preferred settings.

[0146] <Modification> In each of the above-described embodiments, if the control unit 121 of the neck speaker 111 determines that the user's voice received by the microphone 122 is not a question, the control unit 121 may perform control so as not to execute the processes from step S203 onwards in FIG. 7.

[0147] For example, suppose that a dictionary of words indicating questions is stored in the memory unit 124 of the neck speaker 111. If any of the multiple keywords generated by the keyword generation unit 132 matches a word registered in the dictionary, the control unit 121 may determine that the received user voice is a question voice.

[0148] On the other hand, if none of the multiple keywords generated by the keyword generation unit 132 matches a word registered in the above dictionary, the control unit 121 may determine that the received user voice is not a question voice and may control the processing from step S203 onwards not to be executed.

[0149] In addition, the control unit 121 may input the user's voice data that has been recognized by voice recognition into a trained model that has been machine-learned using the question sentence as correct answer data, and determine whether the received user's voice is a question voice.

[0150] Furthermore, the user's question may be a question other than a question about temperature. For example, the user's question may be a question about the weather. In this case, the multiple keywords generated by the keyword generation unit 132 include a keyword related to the weather, such as "weather."

[0151] For example, the broadcast waves received by the television 113 may contain information about the weather. The weather information is stored in the storage unit 324 of the television 113. If the question information transmitted by the neck speaker 111 contains a keyword related to the weather, the television 113 transmits the weather-related information stored in the storage unit 324 to the neck speaker 111 in response to receiving the question information. This allows an answer about the weather to be presented to the user even if the neck speaker 111 does not hold an answer about the weather.

[0152] Furthermore, the user's question may be a question about cooking, television programs, etc. If the user's question is a question about cooking, refrigerator 115, which holds a keyword related to cooking, transmits answer information to neck speaker 111. If the user's question is a question about television programs, television 113, which holds a keyword related to television programs, transmits answer information to neck speaker 111.

[0153] Furthermore, for example, the neck speaker 111 may learn the user's favorite music through machine learning. For example, suppose the user issues a voice command to the microphone 122 saying, "Play jazz." The voice recognition unit 131 recognizes the voice command. The keyword generation unit 132 generates the keyword "jazz" from the voice-recognized command.

[0154] The control unit 121 trains the learning model using the keyword "jazz" as correct answer data. As a result, the trained model can output the user's preferred music tendencies.

[0155] For example, suppose the user issues a voice command to "play music" into the microphone 122. The voice recognition unit 131 recognizes the voice command. The keyword generation unit 132 generates a keyword "music" from the voice-recognized command. The control unit 121 inputs the keyword "music" into the trained model described above, thereby obtaining the keyword "jazz."

[0156] In the above case, the control unit 121 may acquire music data corresponding to "jazz" from the external server 103 and output the acquired music data from the speaker 123. This allows music that the user likes to be output.

[0157] Furthermore, as described above, the storage unit 124 of the neck speaker 111 serving as an electronic device stores a plurality of keywords related to the neck speaker 111 as third keyword information. The control unit 121 acquires the third keyword information before acquiring the first keyword information.

[0158] For example, if any of the multiple question keywords generated in step S203 of FIG. 7 is included in the third keyword information related to the neck speaker 111, the neck speaker 111 as an electronic device does not need to perform the processes from step S204 onwards.

[0159] In this case, the control unit 121 of the neck speaker 111 may obtain answer information by inputting a question keyword generated from the question information into the trained model described above. For example, the control unit 121 inputs the question keyword "music" generated from the question information "What kind of music do you recommend?" into the trained model described above. In this case, the keyword "jazz" is output from the trained model. The control unit 121 of the neck speaker 111 generates answer information such as "Playing jazz." This allows the neck speaker 111 to output the answer information from the speaker 123 without communicating with each peripheral device.

[0160] <Other> The present disclosure is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. Furthermore, new technical features can be formed by combining the technical means disclosed in each embodiment. Furthermore, the order of the processes in the flowcharts described in the above-described embodiments can be changed as much as possible.

[0161] The program that realizes the functions of this embodiment is stored in a non-transitory recording medium such as a semiconductor medium, an optical recording medium, or a magneto-optical recording medium. For example, a non-volatile memory card can be used as the semiconductor medium. For example, a CD (Compact Disc) or a DVD (Digital Versatile Disc) can be used as the optical recording medium or magneto-optical recording medium. The program may also be supplied to a computer via any transmission medium that can transmit the program. [Explanation of symbols]

[0162] 101 system, 102 internal network, 103 external server, 111 neck speaker, 112 air conditioner, 113 television, 114 electric fan, 115 refrigerator, 121 control unit, 122 microphone, 123 speaker, 124 memory unit, 125 communication unit, 126 radio wave intensity detection unit, 127 location information detection unit, 131 voice recognition unit, 132 keyword generation unit, 133 acquisition unit, 134 identification unit, 135 transmission control unit

Claims

1. An electronic device, a reception unit that receives questions from users; an acquisition unit that acquires first keyword information indicating one or more keywords corresponding to each of a plurality of peripheral devices that belong to the same network as the electronic device; an identification unit that identifies a target peripheral device to which the question information is to be transmitted from the plurality of peripheral devices based on the received question information indicating the question and the first keyword information; a transmission control unit that controls transmission of the question information to the identified target peripheral device; an output unit that outputs a response based on response information to the question information received from the target peripheral device; An electronic device comprising:

2. The Communications Department and A memory unit; Furthermore, when a new peripheral device is connected to the network, the communication unit receives new first keyword information from the new peripheral device, the first keyword information indicating one or more keywords corresponding to the new peripheral device; The electronic device according to claim 1 , wherein the received new first keyword information is stored in the storage unit.

3. 2. The electronic device according to claim 1, wherein when the identification unit identifies multiple target peripheral devices based on the question information and the first keyword information, the identification unit identifies one of the multiple target peripheral devices based on location information of the electronic device and location information of each of the multiple peripheral devices.

4. 2. The electronic device according to claim 1, wherein when the identification unit identifies multiple target peripheral devices based on the question information and the first keyword information, the identification unit identifies one of the multiple target peripheral devices based on radio wave intensity from the multiple peripheral devices.

5. a keyword generating unit that generates a plurality of question keywords from the question information; 2. The electronic device of claim 1, wherein, when it is determined that the first keyword information does not contain any keywords that match the generated plurality of question keywords, the identification unit identifies the target peripheral device based on second keyword information, which contains a plurality of keywords corresponding to each of the plurality of peripheral devices and which has a greater number of keywords than the first keyword information, and the plurality of question keywords.

6. The electronic device according to claim 5 , wherein the second keyword information includes a plurality of keywords related to one keyword of the first keyword information.

7. The electronic device according to claim 1 , wherein the output unit outputs a predetermined sound during the period from when the question is received until when the answer is output.

8. The response information includes information specifying the peripheral device, The electronic device according to claim 1 , wherein the output unit outputs the response together with information that identifies the peripheral device.

9. A method for controlling an electronic device having a reception unit that receives a question from a user, comprising: acquiring first keyword information indicating one or more keywords corresponding to each of a plurality of peripheral devices that belong to the same network as the electronic device; identifying a target peripheral device to which the question information is to be transmitted from the plurality of peripheral devices based on the received question information indicating the question and the first keyword information; Controlling transmission of the question information to the identified target peripheral device; outputting a response based on response information to the question information received from the target peripheral device; How to control electronic devices.

Images