Electronic device and electronic device control method

Abstract

To provide an electronic device or the like capable of providing appropriate responses to questions received from users.SOLUTION: An electronic device includes: a reception unit that receives questions from users; a transmission control unit that controls broadcast transmission of question information indicating the received questions to multiple peripheral devices belonging to the same network as the electronic device; a receiving unit that receives response information corresponding to the question information transmitted by the multiple peripheral devices in response to the broadcast transmission; a response generation unit that determines response information to be output preferentially among the multiple pieces of received response information based on response-related information associated with the response information, and generates the determined response information; and an output unit that outputs the response generated by the response generation unit.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 aspect of the present invention comprises a reception unit that receives questions from a user, a transmission control unit that controls broadcast transmission of question information indicating the received question to multiple peripheral devices that belong to the same network as the electronic device, a reception unit that receives answer information to the question information transmitted by the multiple peripheral devices in response to the broadcast transmission, an answer generation unit that determines which answer information to output preferentially from the multiple received answer information based on answer-related information associated with the answer information, and generates the determined answer information, and an output unit that outputs the answer generated by the answer generation unit. [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 keywords stored in the neck speaker. [Figure 5B] FIG. 4 is a diagram showing an example of keywords held by air conditioning equipment. [Figure 5C] FIG. 10 is a diagram showing an example of keywords held by an electric fan. [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] FIG. 10 is a sequence diagram showing an example of a processing flow according to the second embodiment. [Figure 9] FIG. 11 is a sequence diagram showing an example of a processing flow according to a third embodiment. [Figure 10] FIG. 13 is a sequence diagram showing an example of a processing flow according to a fourth embodiment. [Figure 11] 13 is a flowchart showing an example of a processing flow according to a fifth embodiment. [Figure 12] 13 is a flowchart showing an example of a processing flow according to a sixth embodiment. [Figure 13] 13 is a flowchart showing an example of a processing flow according to the seventh embodiment. [Figure 14] 13 is a flowchart showing an example of a processing flow according to the eighth embodiment. [Figure 15] 13 is a flowchart showing an example of a processing flow according to the ninth 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 electric fan 113, the television 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 113, the television 114, 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 electric fan 113 has a fan function. The television 114 is a display device that receives broadcast waves and displays images. 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 electric fan 113, the television 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 113, the television 114, and the refrigerator 115 as peripheral devices. However, the air conditioner 112, the electric fan 113, the television 114, or the refrigerator 115 may be an electronic device, or the neck speaker 111 may be a peripheral device. In the following, the air conditioner 112 and the electric fan 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, a transmission control unit 133, and an answer generation unit 134. 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 keywords (first keywords) from the recognized voice. For example, suppose the user utters a question such as "It's hot. What temperature is it now?" The microphone 122 receives the voice. The voice recognition unit 131 recognizes the voice received by the microphone 122. The voice of the question that has been voice-recognized 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 keywords. As an example, the keyword generation unit 132 may generate three keywords, "hot," "now," and "how many degrees," from the speech data of the above-mentioned question, "It's hot. What temperature is it now?"

[0022] As will be described later, memory unit 124 pre-stores a plurality of keywords (third keywords) related to neck speaker 111. If the keywords generated by keyword generation unit 132 do not all match the keywords stored in memory unit 124, transmission control unit 133 controls broadcast transmission of voice-recognized question information to each peripheral device. Each peripheral device transmits answer information to the broadcast-transmitted question information to neck speaker 111.

[0023] In this embodiment, the air conditioner 112, which is a peripheral device, receives the broadcasted question information, acquires information indicating the detected temperature as answer information, and transmits the answer information indicating the temperature to the neck speaker 111. The same applies to the electric fan 113, which is also a peripheral device. Temperature detection will be described later.

[0024] Each peripheral device also calculates a score based on the match rate between each keyword included in the broadcasted question information and each keyword stored in the peripheral device. Each peripheral device associates the score with the answer information and transmits it to the neck speaker 111. In the first embodiment, the score corresponds to the answer-related information.

[0025] The answer generation unit 134 determines, as the answer information to be output preferentially, the answer information corresponding to the highest score among the scores received from the peripheral devices. The answer generation unit 134 generates an answer based on the determined answer information.

[0026] For example, if the answer information corresponding to the highest score among the scores received from the peripheral devices is "35 degrees," the answer generation unit 134 may add the sentence "The current temperature is" before the answer information and add the word "desu" after the answer information to generate the answer "The current temperature is 35 degrees." Also, if the answer information received from the peripheral device with the highest score is "The current temperature is 35 degrees," the answer generation unit 134 does not need to add any special information.

[0027] 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 that the user posed to the neck speaker 111 can be obtained.

[0028] 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.

[0029] 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 those in FIG. 2 .

[0030] The air conditioner 112 receives the question information broadcast from the neck speaker 111. The storage unit 224 stores a plurality of keywords (second keywords) related to the air conditioner 112.

[0031] The control unit 221 refers to a plurality of keywords stored in the memory unit 224, compares the plurality of keywords included in the broadcasted question information with the plurality of keywords stored in the memory unit 224, and calculates the keyword matching rate as a score.

[0032] For example, as described above, assume that the broadcasted question information is "It's hot. What temperature is it now?" In this case, the keyword generation unit 232 of the air conditioner 112 generates three keywords, "hot," "now," and "what temperature," from the question information. Also assume that the two keywords, "hot" and "what temperature," are stored in the storage unit 224 of the air conditioner 112. In this case, the control unit 221 calculates the match rate as 66%, since two of the three keywords match.

[0033] Furthermore, if the calculated matching rate is not 0% (if the score is not zero), the control unit 221 acquires, as answer information, information indicating the temperature detected by the temperature detection unit 229 (for example, "35 degrees"). The transmission control unit 133 controls the transmission of the score and answer information to the neck speaker 111 via the communication unit 125. As a result, the air conditioner 112 transmits the score and answer information to the neck speaker 111.

[0034] Next, we will explain electric fan 113. Fig. 4 is a diagram showing an example of electric fan 113. Electric fan 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 position information detection unit 327, a fan driving unit 328, and a temperature detection unit 329.

[0035] The fan driving unit 328 drives each mechanism of the fan 113, such as a propeller fan, for example. The units in FIG. 4 other than the fan driving unit 328 are the same as the units in the air conditioner 112 in FIG.

[0036] Next, various keywords will be described. Fig. 5A is a diagram showing an example of keywords held by the neck speaker 111. The keywords held by the neck speaker 111 (neck speaker keywords) are stored in the storage unit 124 of the neck speaker 111, for example.

[0037] As shown in the example of Fig. 5A, the neck speaker keywords are keywords related to the neck speaker 111. The neck speaker 111 is mainly used for playing music, etc. Therefore, the neck speaker keywords include many keywords related to music. The neck speaker keywords may also include keywords other than those related to playing music.

[0038] 5B is a diagram showing an example of keywords held by air conditioners. The keywords held by the air conditioners 112 (air conditioner keywords) are stored in the storage unit 224 of the air conditioners 112, for example.

[0039] As shown in the example of Fig. 5B, the air conditioning equipment keywords are keywords related to the air conditioning equipment 112. Because the air conditioning equipment 112 is equipment that adjusts temperature, the air conditioning equipment keywords include many keywords for performing temperature adjustment operations. The air conditioning equipment keywords may also include keywords other than keywords for performing temperature adjustment operations.

[0040] 5C is a diagram showing an example of keywords held by the electric fan. The keywords held by the electric fan 113 (electric fan keywords) are stored in the storage unit 324 of the electric fan 113, for example.

[0041] As shown in the example of Fig. 5C, the electric fan keywords are keywords related to the electric fan 113. Because the electric fan 113 is a device that blows air, the electric fan keywords include many keywords for performing the blowing operation. The electric fan keywords may include keywords other than the keywords for performing the blowing operation.

[0042] 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 microphone 122 of the neck speaker 111 receives a voice question from the user wearing the neck speaker 111 (step S1001).

[0043] The voice recognition unit 131 recognizes the voice of the question received by the microphone 122 (step S102). For example, as described above, the voice recognition unit 131 recognizes the voice of the question "It's hot. What time is it now?"

[0044] The keyword generation unit 132 generates a plurality of keywords from the voice of the question that has been voice-recognized. For example, the keyword generation unit 132 generates three keywords, "hot," "now," and "what temperature," from the data of the above question.

[0045] The transmission control unit 133 determines whether there is a matching keyword among the multiple keywords generated by the keyword generation unit 132 among the multiple keywords stored in the storage unit 124 of the neck speaker 111. If there is no matching keyword, the neck speaker 111 does not hold an answer to the user's question.

[0046] If the transmission control unit 133 does not hold the keyword (if there is no matching keyword), it controls to broadcast the above-mentioned question information (step S104). Based on this control, the communication unit 125 broadcasts the question information to each peripheral device (air conditioner 112 and electric fan 113 in the example of FIG. 6) connected to the neck speaker 111 so as to be able to communicate with it (step S105).

[0047] Note that the transmission control unit 133 may determine that it does not have an answer to the user's question even if the matching keyword is present. For example, if the neck speaker keywords include the keyword "now," the matching keyword exists. However, it is difficult to interpret the user's question based on the keyword, and it is difficult to generate an appropriate answer.

[0048] For example, each keyword included in the neck speaker keywords, air conditioner keywords, and electric fan keywords may be associated with information indicating whether the keyword is an uninterpretable keyword for the user's question. Even if there is a matching keyword, if the matching keyword indicates an uninterpretable keyword, the transmission control unit 133 may determine in step S104 that the keyword is not held. In the following processes, even if there is a matching keyword, the neck speaker 111 and each peripheral device may determine whether they hold a keyword based on whether the matching keyword is an uninterpretable keyword for the user's question.

[0049] The transmission control unit 133 may, for example, use a command to control broadcast transmission of the question information. The command may include, for example, a source address, a destination address, and parameters. The parameters are also referred to as command parameters.

[0050] The source address is, for example, a Media Access Control (MAC) address assigned to the neck speaker 111. The destination address is, for example, a MAC address assigned to each peripheral device. Information about the source address and destination address is stored, for example, in the storage unit 124 of the neck speaker 111. Information about the source address and destination address is also stored in the storage unit of each peripheral device.

[0051] The parameters include the above-mentioned question information as text data. The neck speaker 111 broadcasts information including the above-mentioned sender address and parameters. Each peripheral device receives the above-mentioned question information.

[0052] The control unit 221 of the air conditioner 112 calculates, as a score, the rate of match between each keyword included in the received question information and each keyword stored in the storage unit 224 of the air conditioner 112 (step S106).

[0053] For example, the keywords included in the received question information are "hot," "now," and "what temperature." The control unit 221 of the air conditioning equipment 112 refers to the air conditioning equipment keywords stored in the storage unit 224 and searches for keywords that match the keywords "hot," "now," and "what temperature."

[0054] As shown in Figure 5B, the air conditioner keywords include the keywords "hot" and "what temperature." On the other hand, the air conditioner keywords do not include the keyword "now." The control unit 221 of the air conditioner 112 calculates a score (match rate) of 66% because two of the three keywords match.

[0055] If the score is not zero (if the match rate is not 0%), the control unit 221 of the air conditioner 112 acquires, as answer information, information about the temperature detected by the temperature detection unit 229. 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 score and answer information to the neck speaker 111, which is the electronic device that transmitted the broadcast (step S107).

[0056] The control unit 321 of the electric fan 113 calculates, as a score, the rate of match between each keyword included in the received question information and each keyword stored in the storage unit 324 of the electric fan 113 (step S108).

[0057] As with the air conditioner 112, the control unit 321 of the electric fan 113 refers to the electric fan keywords stored in the storage unit 324 and searches for keywords that match the keywords "hot," "now," and "temperature."

[0058] As shown in Figure 5C, the fan keywords include the keyword "hot." On the other hand, the fan keywords do not include the keywords "now" and "what temperature." Since one of the three keywords matches, the control unit 321 of the fan 113 calculates a score (match rate) of 33%.

[0059] If the score is not zero (if the match rate is not 0%), the control unit 321 of the electric fan 113 acquires, as answer information, information about the temperature detected by the temperature detection unit 329. For example, if the temperature detected by the temperature detection unit 329 is "36 degrees," the control unit 321 of the electric fan 113 acquires the information "36 degrees" as answer information. The electric fan 113 transmits the score and answer information to the neck speaker 111, which is the electronic device that transmitted the broadcast (step S109).

[0060] As described above, the neck speaker 111 receives the score and answer information from each of the air conditioner 112 and the electric fan 113. Although not shown, the neck speaker 111 also receives the score and answer information from the television 114 and the refrigerator 115.

[0061] The answer generation unit 134 of the neck speaker 111 determines which of the answer information "35 degrees" received from the air conditioner 112 and the answer information "36 degrees" received from the electric fan 113 should be output with priority (step S110).

[0062] In this embodiment, the answer generation unit 134 determines that the answer information corresponding to the highest score among the multiple scores is the answer information to be output preferentially. In the above example, the score corresponding to the answer information received from the air conditioner 112 is 66%, and the score corresponding to the answer information received from the electric fan 113 is 33%.

[0063] Therefore, the answer generation unit 134 determines to preferentially output the answer information "35 degrees" corresponding to the score received from the air conditioner 112. As described above, the answer generation unit 134 may add a predetermined sentence to the answer information. For example, the answer generation unit 134 generates an answer such as "The current temperature is 35 degrees."

[0064] The speaker 123 outputs the answer generated by the answer generating unit 134 (step S111). The user wearing the neck speaker 111 can recognize the answer output from the speaker 123.

[0065] 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).

[0066] 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.

[0067] 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 keywords from the voice data of the question that has been voice-recognized (step S203).

[0068] The control unit 121 searches for a keyword that matches the generated keywords from among the neck speaker keywords stored in the storage unit 124 (step S204). The control unit 121 determines whether or not a matching keyword is found as a result of the search (step S205).

[0069] If there is no matching keyword, the neck speaker 111 does not store an answer to the user's question. In this case, the control unit 121 determines No in step S205 and proceeds to step S206. The transmission control unit 133 controls broadcasting of the question information that has been recognized by voice (step S206).

[0070] In response to receiving the broadcasted question information, each peripheral device transmits the score and answer information to the neck speaker 111. The communication unit 125 of the neck speaker 111 receives the score and answer information (step S207).

[0071] The answer generation unit 134 identifies the answer information corresponding to the highest score from the received scores (step S208). The answer generation unit 134 generates an answer to the user as voice data from the identified answer information (step S209).

[0072] If it is determined in step S205 that the above matching keyword is present, the control unit 121 proceeds to step S211. For example, if the neck speaker 111 has a temperature detection function and the neck speaker keyword includes the keyword "degrees," the control unit 211 determines "Yes" in step S205.

[0073] In this case, the answer generation unit 134 generates an answer as voice data using a matching keyword from among the multiple keywords generated by the keyword generation unit 132 (step S211). If the neck speaker 111 holds a keyword that matches one of the multiple generated keywords, it does not need to request an answer from each peripheral device. In this case, the transmission control unit 133 controls so as not to perform broadcast transmission.

[0074] After step S209 or S211 is executed, the speaker 123 outputs the generated voice data of the answer (step S210), thereby providing the user with the answer to the user's question as voice.

[0075] As described above, in this embodiment, when the neck speaker 111 does not store an answer to a question from a user wearing the neck speaker 111 as an electronic device, the neck speaker 111 broadcasts question information to each peripheral device. In response to receiving the broadcasted question information, each peripheral device transmits answer information and a score to the neck speaker 111.

[0076] The neck speaker 111 receives answer information and scores from each peripheral device. The neck speaker 111 determines the answer information corresponding to the highest score among the received scores as the answer information to be output preferentially, and outputs an answer based on the determined answer information. This allows the neck speaker 111 to output an answer appropriate to the question from the user.

[0077] Second Embodiment Next, a second embodiment will be described. Fig. 8 is a sequence diagram showing an example of the processing flow of the second embodiment. The processing from steps S101 to S104 is the same as in the first embodiment. In Fig. 8, steps S101 to S104 are omitted from the illustration.

[0078] In step S105, the neck speaker 111 broadcasts information requesting a score (score request information). In step S106, the control unit 221 of the air conditioner 112 calculates a score in accordance with the broadcast score request information. The air conditioner 112 transmits the calculated score to the neck speaker 111 (step S301). The air conditioner 112 does not transmit answer information to the neck speaker 111 at the time of step S301.

[0079] In step S108, the control unit 321 of the electric fan 113 calculates a score in response to the broadcasted score request information. In this embodiment, the electric fan 113 transmits the calculated score to the neck speaker 111 (step S302). The electric fan 113 does not transmit answer information to the neck speaker 111 at the time of step S302.

[0080] The control unit 121 of the neck speaker 111 determines the peripheral device that transmitted the highest score among the received scores as the peripheral device from which answer information is to be requested (step S303). At this time, the control unit 121 holds information (e.g., MAC address) indicating the peripheral device determined in step S303 for a certain period of time.

[0081] In the example of Fig. 8, it is assumed that the score transmitted by the air conditioner 112 is the highest score. The control unit 121 requests response information from the determined peripheral device (air conditioner 112 in the example of Fig. 8) via the communication unit 125 (step S304).

[0082] Upon receiving the request for response information, the air conditioner 112 transmits the temperature detected by the temperature detection unit 229 (for example, "35 degrees") as response information to the neck speaker 111 (step S305).

[0083] The neck speaker 111 receives answer information from the air conditioner 112. This answer information is the answer information from the peripheral device that transmitted the highest score, and is the answer information to be output preferentially. The answer generation unit 134 generates an answer based on the answer information. In step S111, the speaker 123 outputs the generated answer.

[0084] 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.

[0085] The microphone 122 receives a voice uttered by the user (step S306). 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 S307).

[0086] The control unit 121 transmits the user's voice, which has been recognized as a voice instruction, to the peripheral device (air conditioner 112) determined in step S303 via the communication unit 125 (step S308). The control unit 121 holds the MAC address of the peripheral device (air conditioner 112) determined in step S303. This enables the control unit 121 to identify the destination of the user's voice instruction.

[0087] 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 S309). 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."

[0088] 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 S310). 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.

[0089] 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.

[0090] The processes of steps S306 to S310 may be repeated. For example, after the process of step S309 is performed, the user may issue an instruction to further lower the temperature. For example, in step S306, microphone 122 may again receive a voice command to "lower the room temperature." In this case, the processes of steps S306 to S310 are performed again.

[0091] As described above, the control unit 121 holds the information (e.g., MAC address) indicating the peripheral device determined in step S303 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 that has been recognized by voice recognition, even if the user issues another instruction.

[0092] Third Embodiment Next, a third embodiment will be described. Fig. 9 is a sequence diagram showing an example of the processing flow of the third embodiment. In the third embodiment, each peripheral device (air conditioner 112 and electric fan 113) transmits position information and answer information to the neck speaker 111 in response to question information broadcast. In the third embodiment, answer information to be output with priority among the answer information received from each peripheral device is determined based on the position information. In the third embodiment, the position information corresponds to answer-related information.

[0093] 9, the processes from step S101 to step S104 are the same as those in the first embodiment. In response to receiving the broadcasted question information, the control unit 221 of the air conditioner 112 acquires the location information of the air conditioner 112 from the location information detection unit 227. The control unit 221 of the air conditioner 112 also acquires information indicating the temperature detected by the temperature detection unit 229 as answer information. The air conditioner 112 transmits the location information and answer information to the neck speaker 111 (step S401).

[0094] In response to receiving the broadcasted question information, the control unit 321 of the electric fan 113 acquires the position information of the electric fan 113 from the position information detection unit 327. The control unit 321 of the electric fan 113 also acquires, as answer information, information indicating the temperature detected by the temperature detection unit 329. The electric fan 113 transmits the position information and answer information to the neck speaker 111 (step S402).

[0095] The control unit 121 of the air conditioner 112 detects the peripheral device closest to the air conditioner 112 based on the location information received from each peripheral device (the air conditioner 112 and the electric fan 113 in the example of FIG. 9) (step S403).

[0096] The control unit 121 acquires position information of the neck speaker 111 from the position information detection unit 127. The control unit 121 calculates the distance between the position indicated by the acquired position information of the neck speaker 111 and the position indicated by the position information of each peripheral device. The control unit 121 detects the peripheral device corresponding to the position information with the shortest distance among the calculated distances as the peripheral device closest to the air conditioner 112.

[0097] The answer generation unit 134 determines that the answer information received from the peripheral device detected as the peripheral device closest to the air conditioner 112 is to be preferentially output (step S404). Then, in step S111, the speaker 123 outputs an answer based on the answer information.

[0098] As described above, an answer to a user's question can be provided to the user based on answer information acquired from a peripheral device that is closest to the neck speaker 111. For example, an answer to a user's question can be provided to the user based on answer information acquired from a peripheral device that is located in the same room as the user wearing the neck speaker 111.

[0099] (Variation of the third embodiment) In the third embodiment, each peripheral device may calculate the score described in the first and second embodiments in response to receiving broadcast-transmitted question information. Then, in steps S401 and S402 of Fig. 9, each peripheral device may transmit the calculated score to the neck speaker 111 in addition to the position information and answer information. In this case, the answer generation unit 134 may determine the answer information to be output with priority based on the score and position information.

[0100] For example, if the match rate between each of the broadcast keywords and each of the keywords held by the peripheral device closest to the neck speaker 111 is 0%, the score will be zero. In this case, the peripheral device closest to the neck speaker 111 does not hold an appropriate answer to the question from the user.

[0101] In step S403, the answer generation unit 134 of the neck speaker 111 detects the peripheral device closest to the neck speaker 111. If the score received from the detected peripheral device closest to the neck speaker 111 indicates zero, in step S404 the answer generation unit 134 excludes the answer information received from the peripheral device closest to the neck speaker 111 from the items to be output.

[0102] In this case, the answer generation unit 134 determines whether the scores received from the peripheral devices closest to the neck speaker 111 are zero, and determines answer information received from a peripheral device with a score that is not zero as the answer information to be output preferentially. This makes it possible to provide the user with an answer to the user's question based on answer information acquired from a peripheral device that holds an answer appropriate to the user's question and is located close to the neck speaker 111.

[0103] Furthermore, the answer generation unit 134 may determine that answer information received from a peripheral device with the highest score among multiple peripheral devices located within a predetermined distance from the neck speaker 111 is the answer information to be output preferentially.

[0104] For example, assume that multiple peripheral devices are located within a predetermined distance from the neck speaker 111 (for example, in the same room). The multiple peripheral devices are peripheral devices located within a predetermined distance from the neck speaker 111.

[0105] Assume that two peripheral devices located within a predetermined distance from the neck speaker 111 have transmitted scores that are not zero to the neck speaker 111. In this case, the answer generation unit 134 may determine that the answer information to be output is preferentially the answer information received from the peripheral device that transmitted the highest score, rather than the peripheral device that is closest to the neck speaker 111.

[0106] For example, suppose that the score (matching rate) transmitted by the peripheral device (peripheral device A) closest to the neck speaker 111 among two peripheral devices located within a predetermined distance from the neck speaker 111 is 33%. On the other hand, suppose that the score (matching rate) transmitted by the peripheral device (peripheral device B) located within the predetermined distance from the neck speaker 111 but farther from the neck speaker 111 than peripheral device A is 66%.

[0107] In the above case, it is preferable that, of peripheral device A and peripheral device B that are located within a predetermined distance from the neck speaker 111, answer information received from peripheral device B that has a higher score is preferentially determined as answer information to be output. In this case, the answer generation unit 134 preferentially determines answer information received from peripheral device B as answer information to be output. This makes it possible to provide an answer that is appropriate for the question from the user.

[0108] It is also assumed that the air conditioner 112 is installed in a fixed location. For example, the storage unit 124 of the neck speaker 111 may store location information of the air conditioner 112 in advance. In this case, the air conditioner 112 does not need to transmit its location information to the neck speaker 111 in step S401.

[0109] <Fourth embodiment> Next, a fourth embodiment will be described. Fig. 10 is a sequence diagram showing an example of the processing flow of the fourth embodiment. In the fourth embodiment, each peripheral device (air conditioner 112 and electric fan 113) transmits answer information to the neck speaker 111 in response to the broadcasted question information. In the fourth embodiment, answer information to be output with priority among the answer information received from each peripheral device is determined based on radio wave intensity information. In the fourth embodiment, radio wave intensity information corresponds to answer-related information.

[0110] 10, the processes from step S101 to step S104 are the same as those in the first embodiment. In response to receiving the broadcasted question information, the control unit 221 of the air conditioner 112 acquires, as answer information, information indicating the temperature detected by the temperature detection unit 229. The air conditioner 112 transmits the answer information to the neck speaker 111 (step S501).

[0111] In response to receiving the broadcasted question information, the control unit 321 of the electric fan 113 acquires, as answer information, information indicating the temperature detected by the temperature detection unit 329. The electric fan 113 transmits the answer information to the neck speaker 111 (step S502).

[0112] The control unit 121 of the air conditioner 112 detects the peripheral device with the strongest radio wave intensity among the peripheral devices (the air conditioner 112 and the electric fan 113) (step S503). The control unit 121 acquires radio wave intensity information indicating the intensity of the radio waves emitted by each peripheral device from the radio wave intensity detection unit 126. The control unit 121 detects the peripheral device with the strongest radio wave intensity based on the acquired radio wave intensity information.

[0113] The answer generation unit 134 determines the answer information received from the peripheral device with the strongest detected radio wave intensity as the answer information to be output preferentially (step S504). Then, in step S111, the speaker 123 outputs an answer based on the answer information.

[0114] The peripheral device with the strongest radio wave intensity detected by the radio wave intensity detection unit 126 is assumed to be the peripheral device closest to the user wearing the neck speaker 111. Therefore, the fourth embodiment can also achieve the same effects as the third embodiment.

[0115] In the fourth embodiment, the answer generation unit 134 may determine answer information to be output with priority based on the acquired radio wave intensity information and the scores and location information received from each peripheral device. This is the same as the variation of the third embodiment. This allows an answer appropriate to the question from the user to be provided.

[0116] Fifth Embodiment Next, a fifth embodiment will be described. Fig. 11 is a flowchart showing an example of the processing flow of the fifth embodiment. The flowchart in Fig. 11 is a flowchart showing the processing flow executed by neck speaker 111 as an electronic device. In the flowchart in Fig. 11, the processing in steps S201 to S211 is the same as the processing in the flowchart in Fig. 7.

[0117] In step S201, if the control unit 121 determines that a voice from the user has been received, the process proceeds to step S601. The control unit 121 determines whether the volume of the voice received by the microphone 122 is equal to or greater than a predetermined volume (step S601). The predetermined volume can be set to any volume.

[0118] If the volume of the sound received by the microphone 122 is equal to or greater than a predetermined volume, the volume is considered to be high. In this case, the control unit 121 recognizes that the neck speaker 111 is operating as an electronic device. If the control unit 121 determines Yes in step S601, it proceeds to step S202. The processes from step S202 onwards are the same as those in the first embodiment. In this case, the transmission control unit 133 executes broadcast transmission in step S206.

[0119] For example, consider a case where a neck speaker 111, an air conditioner 112, and an electric fan 113 are located in the same room, the user is not wearing the neck speaker 111, and the user speaks into the microphone 222 of the air conditioner 112. In this case, the microphone 122 of the neck speaker 111 may detect the voice that the user speaks into the microphone 222 of the air conditioner 112. However, the volume of the user's voice detected by the microphone 122 of the neck speaker 111 is low.

[0120] Not only the neck speaker 111, but also the air conditioner 112 and the electric fan 113 may operate as electronic devices. In the above case, the user is uttering voice into the microphone 222 of the air conditioner 112. For this reason, it is necessary to operate the air conditioner 112 as an electronic device and the neck speaker 111 as a peripheral device. Therefore, if the volume of the voice received by the microphone 122 is low (if the volume is less than a predetermined value), the control unit 121 of the neck speaker 111 determines No in step S601 and proceeds to step S602.

[0121] In the above case, the control unit 121 of the neck speaker 111 switches itself to operation as a peripheral device (step S602). The neck speaker 111 receives the question information broadcast by the air conditioner 112. The control unit 121 of the neck speaker 111 transmits information corresponding to the broadcast question information (for example, score, answer information, location information, etc.) to the air conditioner 112 operating as an electronic device (step S603). In this case, the neck speaker 111 does not perform broadcast transmission.

[0122] In this embodiment, depending on the volume of the voice uttered by the user, one of the devices belonging to the internal network 102 can be made to operate as an electronic device, and the other multiple devices can be made to operate as peripheral devices.

[0123] Sixth Embodiment Next, a sixth embodiment will be described. Fig. 12 is a flowchart showing an example of the processing flow of the sixth embodiment. In the flowchart of Fig. 12, the processing in steps S201 to S211 is the same as the processing in the flowchart of Fig. 7.

[0124] 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 S701. In this case, the control unit 121 controls the speaker 123 to output a predetermined voice (step S701). This causes the speaker 123 to output the predetermined voice. The predetermined voice may be a voice indicating that a response is being made, such as "enquiry in progress." Alternatively, the predetermined voice may 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.

[0125] After executing step S209 or S211, control unit 121 advances the process to step S702. Control unit 121 controls speaker 123 to stop outputting a predetermined sound (step S702). As a result, the predetermined sound is no longer output from speaker 123. Thereafter, in step S210, an answer is output from speaker 123.

[0126] 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.

[0127] Seventh Embodiment Next, a seventh embodiment will be described. Fig. 13 is a flowchart showing an example of the processing flow of the seventh embodiment. In the flowchart of Fig. 13, the processing in steps S201 to S211 is the same as the processing in the flowchart of Fig. 7.

[0128] In step S206, the transmission control unit 133 broadcasts the question information to each peripheral device via the communication unit 125. Some or all of the peripheral devices may not respond even if they receive the broadcast question information.

[0129] The control unit 121 determines whether or not answer information has been received after a certain time has elapsed since broadcast transmission (step S801). If the neck speaker 111 has received answer information from any peripheral device, the control unit 121 determines No in step S801 and proceeds to step S207. Then, the processes from step S207 onwards are performed.

[0130] If the neck speaker 111 has not received answer information from any peripheral device after a certain period of time has elapsed since the broadcast transmission, the control unit 121 determines Yes in step S801 and proceeds to step S802. In this case, the control unit 121 transmits question information to the external server 103 via the communication unit 125 (step S802).

[0131] The external server 103 transmits answer information corresponding to the received question information to the neck speaker 111. The communication unit 125 of the neck speaker 111 receives the answer information transmitted by the external server 103 (step S803). Then, in step S209, the answer generation unit 134 generates an answer based on the answer information.

[0132] In this embodiment, even if there is no response from the peripheral devices after a certain time has elapsed since the neck speaker 111 performed broadcast transmission, response information can be acquired from the external server 103. This allows a response to be sent to the user.

[0133] Eighth Embodiment Next, an eighth embodiment will be described. Fig. 14 is a flowchart showing an example of the processing flow of the eighth embodiment. In the flowchart of Fig. 14, the processing in steps S201 to S206, S208, S210, and S211 is the same as the processing in the flowchart of Fig. 7.

[0134] In step S206, the transmission control unit 133 of the neck speaker 111 executes broadcast transmission. As described in the first embodiment, each peripheral device calculates a score and generates answer information in response to receiving the broadcasted question information. In this embodiment, each peripheral device further recognizes information that identifies itself (device identification information). The device identification information is pre-stored in the memory unit of each peripheral device.

[0135] 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 electric fan 113 may be "electric fan."

[0136] 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.

[0137] Each peripheral device transmits the score, answer information, and device identification information to the neck speaker 111. The communication unit 125 of the neck speaker 111 receives the score, answer information, and device identification information (step S901).

[0138] As described in the first embodiment, in step S208, the answer generation unit 134 identifies the answer information corresponding to the highest score. The answer generation unit 134 generates an answer based on the identified answer information and device identification information (step S902).

[0139] In the first embodiment, for example, the answer generation unit 134 generates an answer such as "The current temperature is 35 degrees" based on the answer information "35 degrees." Here, it is assumed that the above-mentioned device identification information is "air conditioner." In the present embodiment, for example, the answer generation unit 134 generates an answer such as "According to the air conditioner, the current temperature is 35 degrees" based on the device identification information. In step S2120, the speaker 123 outputs the answer.

[0140] As a result, the user can recognize which of the peripheral devices included in the internal network 102 has sent the reply.

[0141] Ninth Embodiment 15 is a flowchart showing an example of the processing flow of the 9th embodiment. In the flowchart of FIG. 15, the processing in steps S201 to S206, S208, S210, and S211 is the same as the processing in the flowchart of FIG.

[0142] In step S206, the transmission control unit 133 of the neck speaker 111 executes broadcast transmission. In response to receiving the broadcasted question information, each peripheral device calculates a score and generates answer information. In this embodiment, each peripheral device recognizes information about devices that operate in conjunction with itself (device cooperation information).

[0143] Peripheral devices included in the internal network 102 may operate in cooperation with other peripheral devices. For example, suppose that an air conditioner 112 and an electric fan 113 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 for the air conditioner 112 may be information indicating that the air conditioner 112 operates in cooperation with the electric fan 113.

[0144] In step S206, in response to receiving the broadcasted question information, the transmission control unit 133 of the neck speaker 111 transmits the score, answer information, and device linkage information to the neck speaker 111. The communication unit 125 of the neck speaker 111 receives the score, answer information, and device linkage information (step S1001).

[0145] As described in the first embodiment, in step S208, the answer generation unit 134 identifies the answer information that most closely corresponds to the score. The answer generation unit 134 generates an answer based on the identified answer information and device linkage information (step S1002).

[0146] For example, based on the answer information "35 degrees," the answer generation unit 134 generates an answer "The current temperature is 35 degrees." In this embodiment, the answer generation unit 134 may add information "Shall we turn on the fan as well?" to the answer based on the received device linkage information (information indicating that the air conditioner 112 is operating in linkage with the electric fan 113). In this case, the answer generation unit 134 generates an answer "The current temperature is 35 degrees. Shall we turn on the electric fan?" In step S210, the speaker 123 outputs the answer.

[0147] 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.

[0148] 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.

[0149] The control unit 221 of the air conditioner 112 operates the electric fan 113 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 113 start operating.

[0150] For example, in step S310 of the second embodiment described above, the control unit 221 of the air conditioner 112 performs machine learning on the relationship between the temperature returned as the answer information and the temperature-related instruction. This allows the control unit 221 of the air conditioner 112 to automatically set the temperature according to the user's preferences.

[0151] Here, assume that the temperature setting suitable for the user that the control unit 121 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."

[0152] 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?"

[0153] Also, assume that the temperature setting suitable for the user that the control unit 121 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."

[0154] 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?"

[0155] 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.

[0156] <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 S205 onwards in FIG. 7.

[0157] For example, suppose that a dictionary of words indicating questions is stored in the memory unit 124 of the neck speaker 111. In this case, 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.

[0158] 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 process not to execute step S205 and subsequent steps.

[0159] 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.

[0160] 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."

[0161] For example, the broadcast waves received by the television 114 may contain information about the weather. The weather information is stored in a memory unit of the television 114. If the question information broadcast from the neck speaker 111 contains a keyword related to the weather, the television 114 transmits the weather information stored in its memory unit to the neck speaker 111 in response to receiving the broadcast question information. This allows the neck speaker 111 to present an answer about the weather to the user even if it does not hold an answer.

[0162] Furthermore, the user's question may be a question about cooking, television programs, etc. If the user's question is about cooking, refrigerator 115, which holds a keyword related to cooking, transmits answer information to neck speaker 111. If the user's question is about television programs, television 114, which holds a keyword related to television programs, transmits answer information to neck speaker 111.

[0163] 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.

[0164] 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.

[0165] 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."

[0166] 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 111. This allows music that the user likes to be output.

[0167] <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.

[0168] 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]

[0169] 101 system, 102 internal network, 103 external server, 111 neck speaker, 112 air conditioner, 113 electric fan, 114 television, 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 transmission control unit, 134 answer generation unit

Claims

1. An electronic device, a reception unit that receives questions from users; a transmission control unit that controls broadcasting of question information indicating the received question to a plurality of peripheral devices that belong to the same network as the electronic device; a receiving unit that receives answer information to the question information transmitted by the plurality of peripheral devices in response to the broadcast transmission; an answer generation unit that determines answer information to be preferentially output from among the plurality of pieces of received answer information based on answer-related information associated with the answer information, and generates an answer based on the determined answer information; an output unit that outputs the answer generated by the answer generation unit; An electronic device comprising:

2. a keyword generating unit that generates a plurality of first keywords from the question information, 2. The electronic device according to claim 1, wherein the answer-related information is information transmitted by the peripheral devices to the electronic device in response to broadcasting the first keywords to the peripheral devices, and is information indicating a match rate between the second keywords held by the peripheral devices and the first keywords.

3. The electronic device according to claim 2 , wherein the answer generating unit determines, as the answer information to be preferentially output, answer information corresponding to answer-related information having the highest matching rate among the plurality of pieces of answer-related information.

4. the answer-related information is location information of each of the plurality of peripheral devices; The electronic device according to claim 2 , wherein the answer generation unit determines, as the answer information to be output preferentially, answer information received from a peripheral device corresponding to position information of a position closest to the position information of the electronic device among the plurality of position information.

5. the answer-related information is radio wave intensity information indicating the intensity of radio waves output from each of the plurality of peripheral devices; The electronic device according to claim 2 , wherein the response generation unit determines, as the response information to be output with priority, the response information received from the peripheral device corresponding to the strongest signal strength information among the plurality of pieces of signal strength information.

6. The electronic device according to claim 1 , wherein the transmission control unit controls whether to execute the broadcast transmission depending on whether a volume of the question received by the receiving unit is equal to or greater than a predetermined volume.

7. a keyword generation unit that generates a plurality of primary keywords from the question information; a storage unit that stores a plurality of third keywords related to the electronic device, 2. The electronic device according to claim 1, wherein the transmission control unit controls broadcasting of the question information to the peripheral devices when it is determined that the plurality of first keywords do not match any of the plurality of third keywords.

8. 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.

9. the transmission control unit controls the transmission of the question information to a server that does not belong to the network when the answer information has not been received after a certain time has elapsed since the question information was transmitted, The electronic device according to claim 1 , wherein the output unit outputs an answer based on answer information to the question information received from the server.

10. 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.

11. A method for controlling an electronic device having a reception unit that receives a question from a user, comprising: control the broadcast transmission of question information indicating the received question to a plurality of peripheral devices that belong to the same network as the electronic device; receiving answer information to the question information transmitted by the plurality of peripheral devices in response to the broadcast transmission; determining, based on answer-related information associated with the answer information, answer information to be output with priority from among the plurality of pieces of received answer information, and generating an answer based on the determined answer information; outputting the answer generated by the answer generation unit; How to control electronic devices.

Images