JP7167797B2 - How to assign masters and extensions - Google Patents

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a main unit that accommodates extension telephones, and more particularly to a technology for allocating extension telephones to users by the main unit.

Patent Literature 1 discloses a free address IP telephone system that allows a user to temporarily use an IP telephone installed on a desk in a free address office as his/her own telephone. In this telephone system, when an IP telephone installed on a desk in a free address office accepts input of a user ID and password from a user, the accepted user ID and password are sent to the setting management server along with the IP address of the own IP telephone. to make a login request. In response to this, the setting management server performs user authentication using the user ID and password. The setting information including this telephone number is transmitted to the IP telephone that requested the login, as well as being registered in association with the IP address of the telephone. As a result, the user's phone number is set in the IP phone, and the user can use this IP phone as his/her own phone.

JP 2007-142621 A

However, in Patent Document 1, when a user wants to make a call using an IP telephone installed on a desk in a free address office, first, the user enters a user ID and password into this IP telephone, After carrying out setting processing for allocating one's own telephone number, it is necessary to carry out a calling operation such as inputting a destination dial number, which involves many procedures and is complicated.

SUMMARY OF THE INVENTION An object of the present invention is to more efficiently assign telephones to users.

In order to solve the above problems, in the present invention, when the extension telephone to be accommodated is off-hooked, the main unit seizes the extension telephone, establishes a communication path with the extension telephone, and Receives audio data representing the content of instructions from. Then, this extension telephone is assigned to the user specified by the voiceprint information of this voice data. In addition, it analyzes the contents of the user's instruction from the voice recognition result of this voice data, executes processing according to the contents of the instruction, and records the execution result in the user's operation history.

For example, the present invention provides
A main device for housing an extension telephone,
voice acquisition means for capturing the off-hook extension phone and receiving voice data representing instruction content from the extension phone;
setting means for assigning a user recognized from the voiceprint information of the voice data acquired by the voice acquisition means to the extension telephone that is the transmission source of the voice data;
analysis means for analyzing the instruction content from a speech recognition result of the speech data acquired by the speech acquisition means;
an instruction processing means for executing a process according to the contents of the instruction analyzed by the analysis means;
a history recording means for recording, in an operation history of the user assigned by the setting means to the extension telephone that is the transmission source of the voice data, a result of execution of processing by the instruction processing means in accordance with the content of the instruction; Prepare.

According to the present invention, when the user off-hooks the extension phone and inputs a voice representing the content of the instruction to the extension phone, the extension phone is assigned to the user and a process corresponding to the content of the instruction is performed. Therefore, the user does not need to perform a special operation for assigning the extension phone to himself/herself, apart from the operation (inputting the voice representing the contents of the instruction) for causing the extension phone to perform the desired processing. Therefore, there are fewer and simpler steps, and phones can be assigned to users more efficiently. In addition, since the result of execution according to the user's instructions is recorded in the user's operation history, the user's operation history can be grasped without depending on the extension telephone used by the user.

FIG. 1 is a schematic configuration diagram of a telephone system according to one embodiment of the present invention. FIG. 2 is a sequence diagram for explaining an operation example of the telephone system according to one embodiment of the present invention. FIG. 3 is a sequence diagram for explaining an operation example of the telephone system according to one embodiment of the present invention, and is a continuation of FIG. FIG. 4 is a schematic functional configuration diagram of the main device 1. As shown in FIG. FIG. 5 is a diagram schematically showing an example of contents registered in the user information storage unit 104. As shown in FIG. FIG. 6 is a diagram schematically showing an example of contents registered in the telephone directory data storage unit 105. As shown in FIG. FIG. 7 is a diagram schematically showing an example of contents registered in the operation history storage unit 106. As shown in FIG. FIG. 8 is a flowchart for explaining the operation of the main device 1. FIG. FIG. 9 is a flow chart for explaining the calling process (S206) shown in FIG. FIG. 10 is a flowchart for explaining the history display process (S207) shown in FIG. FIG. 11 is a flowchart for explaining the telephone directory display process (S208) shown in FIG. FIG. 12 is a schematic functional configuration diagram of the speech recognition server 3. As shown in FIG. FIG. 13 is a diagram schematically showing an example of contents registered in the voiceprint information storage unit 301. As shown in FIG. FIG. 14 is a flowchart for explaining the operation of the speech recognition server 3. As shown in FIG. FIG. 15 is a sequence diagram for explaining an example of user information registration processing in the telephone system according to one embodiment of the present invention.

An embodiment of the present invention will be described below with reference to the drawings.

FIG. 1 is a schematic configuration diagram of a telephone system according to this embodiment.

As shown in the figure, the telephone system according to the present embodiment includes a main unit 1 connected to a WAN (Wide Area Network) 4 and a plurality of extension telephones 2-1 to 2-n ( hereinafter simply referred to as an extension telephone 2) and a speech recognition server 3 having a voiceprint matching function.

The voice recognition server 3 stores the user's voiceprint information in association with the user ID for each user. Information is extracted, and a user ID associated with the extracted voiceprint information is specified. Then, the voice recognition result and the specified user ID are transmitted to the main measure 1 .

The main unit 1 stores user information including a user ID and a user name for each user. It accepts voice data to represent, and transmits this voice data to the voice recognition server 3 . Then, this extension telephone 2 is assigned to the user specified by the user information including the user ID received from the voice recognition server 3 . In addition, it analyzes the contents of the user's instruction from the speech recognition result received together with the user ID from the speech recognition server 3, executes processing according to the instruction, and records the execution result in the user's operation history.

2 and 3 are sequence diagrams for explaining an operation example of the telephone system according to the present embodiment.

When the extension telephone 2 is operated off-hook by the user (S100), it transmits an off-hook signal to the main unit 1 (S101). As a result, the main device 1 captures the extension telephone 2 and establishes a communication path with the extension telephone 2 (S102). Next, when the extension telephone 2 receives a voice representing the content of the instruction from the user (S103), the extension telephone 2 transmits this voice data to the main device 1 via the communication path with the main device 1 (S104). .

When the main unit 1 receives the voice data representing the contents of the instruction from the extension telephone 2, it transmits a voice recognition request including this voice data to the voice recognition server 3 via the WAN 4 (S105). In response to this, the voice recognition server 3 extracts voiceprint information from the voice data included in the voice recognition request, compares it with voiceprint information registered in advance, and responds to voiceprint information that matches the extracted voiceprint information. The attached user ID is specified (S106). Also, the voice data included in the voice recognition request is subjected to voice recognition processing (S107). Then, the speech recognition server 3 transmits the speech recognition result to the main device 1 together with the identified user ID (S108).

Next, the main unit 1 searches user information including the user ID received from the voice recognition server 3 from the user information registered in advance, and sends the extension telephone 2 to the user specified by the detected user information. Allocate (S109). Further, the main device 1 analyzes the instruction contents included in the voice recognition result received from the voice recognition server 3 together with the user ID (S110). Specifically, at least one predetermined keyword is registered in advance for each instruction content, and the instruction content is specified by detecting the predetermined keyword included in the speech recognition result. Here, it is assumed that the predetermined keyword included in the speech recognition result represents a transmission instruction accompanied by the unique name of the callee, such as "Call to XX" or "Call to XX".

Next, the main device 1 refers to the pre-registered telephone directory data, and identifies the telephone number of the contact identified by the unique name of the caller "OO" (S111). Then, main unit 1 transmits a connection request to which caller information including user information of the user assigned to extension telephone 2 is added, using the specified telephone number as the destination number (S112). This connection request is sent via the WAN 4 to the external telephone 5 to which the destination number is assigned.

Next, when the outside line telephone 5 receives the connection request, the incoming call rings and, if the outside line telephone 5 has a caller display function, displays the caller information added to the connection request ( S113).

Then, upon receiving the response operation (S114), the external telephone 5 returns a connection response to the main device 1 (S115). Thereby, a communication path is established between the main unit 1 and the outside telephone 5 (S116). The main unit 1 connects the communication path established with the extension telephone 5 and the communication path established with the extension telephone 2, and relays them (S117). As a result, a call can be made between the user assigned to the extension phone 2 and the other party who is the user of the external phone 5, and the main unit 1 starts recording this call (S118).

Next, when the telephone call ends and the user performs an on-hook operation (S119), the extension telephone 2 transmits an on-hook signal to the main unit 1 (S120). As a result, the main unit 1 transmits a disconnection request to the line telephone 5 via the WAN 4 (S121), and the line telephone 5 returns a disconnection response to the main unit 1 (S122). As a result, the communication paths established between the extension telephone 2 and the external telephone 5 are released, and the main unit 1 terminates the relay between these communication paths (S123).

After that, main device 1 finishes recording the call (S124). Then, the date and time of the call, the destination number, the extension number of the extension phone 2, and the execution result of the call processing including the recorded data are recorded in the operation history of the user assigned to this extension phone 2, and the user's operation history is recorded. Update (S125).

Next, the details of the main unit 1 and the voice recognition server 3 that constitute the telephone system according to the present embodiment will be described. Since an existing device can be used for the extension telephone 2, detailed description thereof will be omitted.

First, the details of the main device 1 will be described.

FIG. 4 is a schematic functional configuration diagram of the main device 1. As shown in FIG.

As shown, the main unit 1 includes an extension interface unit 100, a WAN interface unit 101, a call control unit 102, a relay unit 103, a user information storage unit 104, a telephone directory data storage unit 105, and an operation history. A storage unit 106 , a voice acquisition unit 107 , a voice recognition request unit 108 , a user allocation setting unit 109 , an instruction content analysis unit 110 , and an instruction processing unit 111 are provided.

The extension interface unit 100 is an interface for connecting with the extension telephone 2, and the WAN interface unit 101 is an interface for connecting with the WAN4.

The call control unit 102 establishes and releases a call path between the extension telephone 2 and the outside telephone 5 and between the extension telephones 2 in accordance with a predetermined call control protocol such as SIP (Session Initiation Protocol).

Relay unit 103 relays communication paths established between extension telephone 2 and outside telephone 5 and between extension telephones 2 in accordance with a predetermined transmission protocol such as RTP (Realtime Transport Protocol).

User information storage unit 104 stores user information including a user ID and a user name for each user of the telephone system according to the present embodiment.

FIG. 5 is a diagram schematically showing an example of contents registered in the user information storage unit 104. As shown in FIG.

As shown, the user information storage unit 104 stores a user information record 1040 for each user of the telephone system according to the present embodiment. A user information record 1040 includes a field 1041 in which a user ID is registered, a field 1042 in which a user's user name is registered, and an extension telephone (extension telephone for incoming call) 2 fixedly assigned to the user. and a field 1043 in which a number is registered.

The phone book data storage unit 105 stores phone book data including the contact name and phone number for each contact.

FIG. 6 is a diagram schematically showing an example of contents registered in the telephone directory data storage unit 105. As shown in FIG.

As shown, the phonebook data storage unit 105 stores a phonebook data record 1050 for each contact. A record 1050 of telephone directory data includes a field 1051 in which the name or name (unique name) of the contact is registered, a field 1052 in which the telephone number of the contact is registered, and a field 1053 in which the address of the contact is registered. , have

Operation history storage unit 106 stores a user's operation history for each user of the telephone system according to the present embodiment.

FIG. 7 is a diagram schematically showing an example of contents registered in the operation history storage unit 106. As shown in FIG.

As shown, the operation history storage unit 106 stores an operation history table 1060 associated with the user ID for each user of the telephone system according to the present embodiment. The operation history table 1060 stores an operation history record 1061 for each instruction (operation) received from the user via the extension telephone 2 assigned to the user. The operation history record 1061 includes a field 1062 in which the execution date and time of the process corresponding to the instruction (operation) content is registered, a field 1063 in which the instruction content is registered, and a field in which the extension number of the extension telephone 2 used is registered. 1064, a field 1065 in which the destination number is registered when the instruction content is a call origination instruction, a field 1066 in which call recording data or its storage location is registered when the instruction content is a call origination instruction, have

The voice acquisition unit 107 acquires voice data representing the content of the user's instruction from the extension telephone 2 being captured.

The voice recognition request unit 108 transmits a voice recognition request including the voice data acquired by the voice acquisition unit 107 to the voice recognition server 3, and receives the voice recognition result for this voice data from the voice recognition server 3 as the voiceprint information of this voice data. Acquired together with the user ID of the user specified from.

The user allocation setting unit 109 refers to the user information storage unit 104 and assigns the user specified by the user information record 1040 including the user ID acquired from the voice recognition server 3 by the voice recognition request unit 108 to the voice acquisition unit. 107 assigns to the extension telephone 2 from which the acquired voice data is transmitted.

The instruction content analysis unit 110 analyzes the instruction content included in the voice recognition result acquired from the voice recognition server 3 by the voice recognition request unit 108 . Specifically, at least one predetermined keyword is registered in the instruction content analysis unit 110 for each instruction content, and the instruction content analysis unit 110 detects any one of the predetermined keywords from the speech recognition result. specifies the content of the instruction.

The instruction processing unit 111 cooperates with the WAN interface unit 101, the call control unit 102, and the like to perform processing according to the instruction content analyzed by the instruction content analysis unit 110. FIG. In addition, the instruction processing unit 111 stores the operation history table 1060 stored in the operation history storage unit 106 in association with the user assigned to the extension telephone 2 from which the voice data acquired by the voice acquisition unit 107 is transmitted. , records the execution result of the process according to the contents of the instruction.

FIG. 8 is a flowchart for explaining the operation of the main device 1. FIG.

This flow starts when the call control section 102 receives an off-hook signal from the extension telephone 2 via the extension interface section 100 .

First, the call control unit 102 captures the extension telephone 2 that is the transmission source of the off-hook signal (hereinafter referred to as the assignment target telephone 2), and establishes a call path between this extension telephone 2 and the relay unit 103 ( S200). Then, the voice acquisition unit 107 receives voice data representing the content of the instruction from the allocation target telephone set 2 via this communication path (S201).

Next, the speech recognition request unit 108 transmits a speech recognition request including the speech data received by the speech acquisition unit 107 to the speech recognition server 3 via the WAN interface unit 101 (S202). Then, the speech recognition requesting unit 108 receives the speech recognition result for this speech data from the speech recognition server 3 together with the user ID of the user specified from the voiceprint information of this speech data (S203).

Next, the user allocation setting unit 109 searches the user information storage unit 104 for the user information record 1040 including the user ID that the speech recognition requesting unit 108 has acquired from the speech recognition server 3 . Then, the user specified by the detected user information record 1040 is assigned to the assigned telephone set 2 (S204).

Next, the instruction content analysis unit 110 analyzes the instruction content included in the speech recognition result obtained by the speech recognition requesting unit 108 from the speech recognition server 3 (S205). Specifically, a predetermined keyword registered in advance for each instruction content is searched from the speech recognition result, and the instruction content associated with the detected keyword is determined as the instruction content included in the speech recognition result. do.

Here, if a predetermined keyword such as "call to XX" or "call to XX" is detected from the speech recognition result, the instruction content analysis unit 110 determines that the instruction content included in the speech recognition result is the call destination. and instructs the instruction processing unit 111 to make a call to the destination's proper name "OO" ("Send" in S205). Further, when predetermined keywords such as “history display” and “history output” are detected from the voice recognition result, it is determined that the instruction content included in the voice recognition result is a history display instruction, and the instruction processing unit 111 , the history display is instructed (“HISTORY DISPLAY” in S205). Also, when predetermined keywords such as "display phonebook" and "output phonebook" are detected from the speech recognition result, the instruction content included in the speech recognition result is determined to be a phonebook display instruction, and the instruction is processed. The unit 111 is instructed to display the telephone directory ("Display telephone directory" in S205).

Next, the instruction processing unit 111 performs processing according to the instruction content notified from the instruction content analysis unit 110 (S206 to S208). Specifically, if the instruction notified by the instruction content analysis unit 110 is a call origination instruction ("Call" in S205), the call control unit 102 cooperates with the call control unit 102 to perform call origination processing (S206), and instructs history display. If so ("display history" in S205), the history display process described later is executed in cooperation with the operation history storage unit 106 (S207). In cooperation with the telephone directory data storage unit 105, the telephone directory is displayed as will be described later (S208).

Then, the instruction processing unit 111 generates an operation history record 1061 indicating the execution result of the instruction notified from the instruction content analysis unit 110, and associates the operation history record 1061 with the user ID of the user assigned to the assignment target telephone set 2. It is registered in the operation history table 1060 stored in the operation history storage unit 106 (S209). Specifically, when the outgoing call process is executed, the execution date and time are registered in the field 1062, the instruction content "call" is registered in the field 1063, the extension number of the assigned telephone set 2 is registered in the field 1064, and the If the destination number is registered and there is recorded data of the call, an operation history record 1061 is generated in which the recorded data or its storage destination is registered in the field 1066 and registered in the corresponding operation history table 1060 . When the history display process is performed, the date and time of execution are registered in the field 1062, the instruction content "display history" is registered in the field 1063, and the extension number of the assigned telephone set 2 is registered in the field 1064. 1061 is generated and registered in the corresponding operation history table 1060 . Further, when the telephone directory display processing is performed, the execution date and time are registered in the field 1062, the instruction content "display telephone directory" is registered in the field 1063, and the extension number of the assigned telephone set 2 is registered in the field 1064. record 1061 is generated and registered in the corresponding operation history table 1060 .

FIG. 9 is a flow chart for explaining the calling process (S206) shown in FIG.

First, instruction processing unit 111 searches telephone directory data storage unit 105 for telephone directory data record 1050 in which the unique name of the destination notified by instruction content analysis unit 110 is registered in field 1051, and detects the record. The telephone number registered in field 1052 of record 1050 is specified as the destination number (S2060). Then, the instruction processing unit 111 notifies the call control unit 102 of the calling party number together with the user information of the user assigned to the assignment target telephone set 2, and instructs the call control unit 102 to make a call.

Upon receiving this, the call control unit 102 transmits a connection request to the destination number notified from the instruction processing unit 111 to which the user information notified from the instruction processing unit 111 is added as caller information (S2061). ).

Next, when call control section 102 receives a connection response as a reply to the connection request (YES in S2062), call control section 102 connects relay section 103 and the telephone specified by the destination number (extension telephone other than outside line telephone 5 or assignment target telephone 2). 2) and connect this communication path to the communication path established between the relay unit 103 and the assigned telephone set 2, and relay the communication between them to the relay unit 103. (S2064). As a result, a call can be made between the user to whom the assigned telephone set 2 is assigned and the other party of the telephone specified by the destination number.

Next, when relay unit 103 starts relaying between the communication path with allocation target telephone set 2 and the communication path with the telephone specified by the destination number, instruction processing unit 111 performs communication via this relay. Recording of the call data to be received is started (S2065).

After that, when the call control unit 102 receives an on-hook signal from the assigned telephone set 2 or a disconnection request from the telephone specified by the destination number, the call path with the assigned telephone set 2 and the destination number When the communication path with the telephone specified by is released and the relay between the two ends (YES at S2066), the instruction processing unit 111 ends the recording of the call data (S2067), and then proceeds to S209 in FIG. move on.

On the other hand, when call control section 102 receives an on-hook signal from assignment target telephone set 2 (YES at S2063) without receiving a connection response as a reply to the connection request (NO at S2062), relay section 103 and assignment target telephone set 2 and then proceeds to S209 in FIG.

FIG. 10 is a flowchart for explaining the history display process (S207) shown in FIG.

First, the instruction processing unit 111 selects the operation history table 1060 stored in the operation history storage unit 106 in association with the user ID of the user assigned to the telephone set 2 to be assigned, and stores the instruction content "Call" in the field 1063. is extracted (S2070).

Next, the instruction processing unit 111 groups the records 1061 of the extracted operation history (call history) by the destination number registered in the field 1065 (S2071), and assigns the priority of each group to the group. It is determined in descending order of the number of records (the number of calls made to the corresponding destination number) of the record 1061 of the operation history (call history) to which it belongs (S2072).

Then, the instruction processing unit 111 displays the groups of the records 1061 of the operation history (call history) grouped by destination number according to the priority, and allows the user to select a desired group (destination number). A history selection screen is generated, and this history selection screen is transmitted to the assignment target telephone set 2 via the extension line interface unit 100 (S2073). In response to this, the assigned telephone set 2 displays a history selection screen. Then, when the selection of any group in the history selection screen is accepted from the user, the information of the accepted group is transmitted to the main device 1 .

Next, when instruction processing section 111 receives information on the selected group from assigned telephone set 2 via extension interface section 100 (YES in S2074), instruction processing section 111 stores the information in record 1061 of the operation history (outgoing call history) belonging to this group. A common destination number is specified (S2076). Then, the instruction processing unit 111 notifies the call control unit 102 of the calling party number together with the user information of the user assigned to the assignment target telephone set 2, and instructs the call control unit 102 to make a call. After that, the process proceeds to S2061 in FIG.

On the other hand, if instruction processing unit 111 does not receive group information from assignment target telephone set 2 (NO in S2074) and call control unit 102 receives an on-hook signal from assignment target telephone set 2 (YES in S2075), the call control unit 102 releases the communication path between relay unit 103 and telephone set 2 to be assigned, and then proceeds to S209 in FIG.

FIG. 11 is a flowchart for explaining the telephone directory display process (S208) shown in FIG.

First, the instruction processing unit 111 generates a phonebook selection screen that includes records 1050 of all phonebook data stored in the phonebook data storage unit 105 and allows the user to select desired phonebook data, This telephone directory selection screen is transmitted to the assignment target telephone set 2 via the extension line interface unit 100 (S2081). In response to this, the assigned telephone set 2 displays a telephone directory selection screen. Then, when the selection of any phonebook data in the phonebook selection screen is accepted from the user, the information of the record 1050 of the accepted phonebook data is transmitted to the main device 1 .

Next, when the instruction processing unit 111 receives the information of the record 1050 of the telephone directory data selected from the telephone set 2 to be assigned via the extension interface unit 100 (YES in S2082), the instruction processing unit 111 receives the telephone number registered in the record 1050. The number is specified as the destination number (S2084). Then, the instruction processing unit 111 notifies the call control unit 102 of the calling party number together with the user information of the user assigned to the assignment target telephone set 2, and instructs the call control unit 102 to make a call. After that, the process proceeds to S2061 in FIG.

On the other hand, if instruction processing unit 111 does not receive the information of record 1050 of telephone directory data from assignment target telephone set 2 (NO in S2082) and call control unit 102 receives an on-hook signal from assignment target telephone set 2 (YES in S2083) ), the call control section 102 releases the communication path between the relay section 103 and the telephone set 2 to be assigned, and then proceeds to S209 in FIG.

Next, the details of the speech recognition server 3 will be described.

FIG. 12 is a schematic functional configuration diagram of the speech recognition server 3. As shown in FIG.

As illustrated, the voice recognition server 3 includes a WAN interface unit 300, a voiceprint information storage unit 301, a voiceprint matching processing unit 302, a voice recognition processing unit 303, and a voice recognition request reception unit 304. .

A WAN interface unit 300 is an interface for connecting to WAN4.

Voiceprint information storage unit 301 stores voiceprint information associated with a user ID for each user of the telephone system according to the present embodiment.

FIG. 13 is a diagram schematically showing an example of contents registered in the voiceprint information storage unit 301. As shown in FIG.

As shown, the voiceprint information storage unit 301 stores a voiceprint information record 3010 for each user of the telephone system according to the present embodiment. A voiceprint information record 3010 has a field 3011 in which a user ID is registered and a field 3012 in which user's voiceprint information or its storage location is registered.

The voiceprint matching processing unit 302 extracts voiceprint information from the voice data received from the voice recognition request receiving unit 304 and compares the extracted voiceprint information with the voiceprint information stored in the voiceprint information storage unit 301 . Then, the user ID associated with the voiceprint information that matches the extracted voiceprint information is passed to the voice recognition request reception unit 304 .

The speech recognition processing unit 303 performs speech recognition processing on the speech data received from the speech recognition request reception unit 304 and passes the speech recognition result to the speech recognition request reception unit 304 .

Voice recognition request receiving unit 304 passes voice data included in the voice recognition request received from main device 1 via WAN interface unit 300 to voiceprint matching processing unit 302 and voice recognition processing unit 303 . Then, the user ID and the voice recognition result received from the voiceprint matching processing unit 302 and the voice recognition processing unit 303 are transmitted to the main device 1 .

FIG. 14 is a flowchart for explaining the operation of the speech recognition server 3. As shown in FIG.

When voice recognition request receiving unit 304 receives a voice recognition request from main device 1 via WAN interface unit 300 (YES in S300), voice data included in the voice recognition request is passed to voiceprint matching processing unit 302 and voice recognition processing unit 304. It is passed to the processing unit 303 .

In response to this, the voiceprint matching processing unit 302 extracts voiceprint information from the voice data received from the voice recognition request receiving unit 304, and compares the extracted voiceprint information with the voiceprint information stored in the voiceprint information storage unit 301. do. Then, the user ID associated with the voiceprint information that matches the extracted voiceprint information is passed to the voice recognition request reception unit 304 (S301).

Also, the speech recognition processing unit 303 performs speech recognition processing on the speech data received from the speech recognition request reception unit 304 . Then, the speech recognition result is passed to the speech recognition request reception unit 304 (S302).

In response to this, the voice recognition request receiving unit 304 transmits the user ID and the voice recognition result received from the voiceprint matching processing unit 302 and the voice recognition processing unit 303 to the main device 1 which is the transmission source of the voice recognition request ( S303).

An embodiment of the present invention has been described above.

In this embodiment, when the extension telephone 2 is off-hooked, the main unit 1 captures the extension telephone 2 and receives voice data representing the contents of instructions from the extension telephone 2 . Then, this extension telephone 2 is assigned to the user specified by the voiceprint information of this voice data. In addition, it analyzes the contents of the user's instruction from the voice recognition result of this voice data, executes processing according to the contents of the instruction, and records the execution result in the user's operation history.

For example, if the user's instruction analyzed from the speech recognition result of the voice data is a call instruction with the designation of the proper name of the callee, the phonebook data including the callee's proper name is retrieved from the phonebook data storage unit 105. Performs call processing to the phone number included in the searched and detected phone book data. Alternatively, if the user's instruction content analyzed from the voice recognition result of the voice data is an instruction to display a call history, the execution result of the call process is extracted from the user's operation history stored in the operation history storage unit 106. Then, a list of the execution results of the extracted outgoing call process is displayed on the extension telephone 2 assigned to this user. Then, when the selection of the execution result of the calling process is received from the extension telephone 2, the calling process to the destination designated by the selected execution result of the calling process is carried out.

As described above, according to the present embodiment, when the user off-hooks the extension telephone 2 and inputs the voice representing the content of the instruction to the extension telephone 2, the extension telephone 2 is assigned to the user and the instruction is given. Since the process is executed according to the content, the user, apart from the operation for causing the extension phone 2 to execute the desired process (inputting the voice representing the content of the instruction), can perform the operation for allocating this extension phone 2 to himself/herself. No special action is required. Therefore, there are fewer and simpler steps, and phones can be assigned to users more efficiently. In addition, since the result of execution according to the user's instructions is recorded in the user's operation history, the user's operation history can be grasped without depending on the extension telephone 2 used by the user.

In the present embodiment, when executing the call origination process, the main unit 1 transmits the user information of the user assigned to the extension telephone 2, which is the sender of the voice data representing the call origination instruction, to the connection request as caller information. are added. This makes it possible to notify the caller of the caller to the callee without depending on the extension telephone 2 used by the user.

Further, in the present embodiment, main unit 1 records a call with a user to whom extension telephone 2, which is the source of voice data representing a destination and an instruction to make a call, is assigned when carrying out call processing, and records the call. The execution result of call processing including data and call destination is recorded in this user's operation history. As a result, the content of the user's call can be grasped without depending on the extension telephone 2 used by the user.

Further, in the present embodiment, main unit 1, when displaying the outgoing call history, performs outgoing call processing extracted from the operation history of the user assigned to extension telephone 2, which is the source of the voice data representing the instruction to display the outgoing call history. are summarized for each telephone number and displayed on the extension telephone 2 in descending order of the number of outgoing calls. Therefore, it is possible to display the phone numbers that are highly likely to be selected as the destination of the call at the top, thereby improving usability for the user.

It should be noted that the present invention is not limited to the above-described embodiments, and many modifications are possible within the scope of the gist of the present invention.

For example, in the above-described embodiment, the main apparatus 1 requests the voice recognition server 3 to perform voice recognition processing for voice data indicating instruction content and identification processing of a user ID by voiceprint collation. Not limited. The main device 1 is provided with the same functions as the voice recognition server 3 (voiceprint information storage unit 301, voiceprint matching processing unit 302, voice recognition processing unit 303, voice recognition request reception unit 304) so that the main device 1 itself recognizes the instruction content. It is also possible to carry out voice recognition processing on voice data indicating and identification processing of a user ID by voiceprint collation.

Further, in the above embodiment, the user information storage unit 104 and/or the operation history storage unit 106 may be omitted from the main device 1 and managed by an external file server. The main device 1 may be provided with an interface with this file server to access the user information storage section 104 and/or the operation history storage section 106 managed by the file server.

In the above-described embodiment, the main unit 1 is made to store telephone directory data for each user of the telephone system separately from the telephone directory data storage unit 105. When voice data representing "display" is received, the telephone directory data of the user may be displayed on the extension telephone 2. FIG. In this case, the main unit 1 is provided with a telephone directory data update processing unit for updating the telephone directory data of each user of the telephone system based on the user's outgoing call history stored in the operation history storage unit 106. . For each user of the telephone system, the telephone directory data update processing unit determines whether the destination number included in the execution result of the calling process associated with the corresponding user and stored in the operation history storage unit 106 is the corresponding number. It is determined whether or not it is registered in the user's phone book data, and if it is not registered, the phone book data record 1050 having this destination number is searched from the phone book data storage unit 105, and the detected phone book The data record 1050 is registered in the corresponding user's telephone directory data.

Further, in the above embodiment, if the user ID associated with the voiceprint information of the voice data representing the instruction content is not stored in the voiceprint information storage unit 301 of the voice recognition server 3, a new user ID is issued. The user information may be registered in the user information storage unit 104 of the main apparatus 1 .

FIG. 15 is a sequence diagram for explaining an example of user information registration processing in the telephone system according to this embodiment.

First, S100 to S105 in FIG. 2 are performed, and a voice recognition request including voice data representing the instruction content is transmitted from the main device 1 to the voice recognition server 3 (S130).

In response to this, the voice recognition server 3 extracts voiceprint information from the voice data included in the voice recognition request and compares it with pre-registered voiceprint information. shall not exist. In this case, the voice recognition server 3 newly issues a user ID and registers this user ID in association with the extracted voiceprint information (S131). Also, the voice data included in the voice recognition request is subjected to voice recognition processing (S132). Then, the voice recognition server 3 transmits the voice recognition result to the main device 1 together with the newly issued user ID (S133).

Next, the main apparatus 1 searches for user information including the user ID received from the voice recognition server 3 from the user information registered in advance. However, since the user ID received from the voice recognition server 3 is a newly issued user ID, user information including this user ID is not registered. In this case, the main unit 1 sends voice prompting the user information to the extension telephone 2 through the communication path established with the extension telephone 2, which is the source of the voice data indicating the instruction content. Guidance is transmitted (S134).

In response to this, the extension telephone 2 outputs the voice guidance received from the main unit 1. FIG. Then, when the voice representing the user information is input from the user (S135), this voice data is transmitted to the main device 1 via the communication path with the main device 1 (S136).

When main unit 1 receives voice data representing user information from extension telephone 2, main unit 1 transmits a voice recognition request including this voice data to voice recognition server 3 via WAN 4 (S137). In response to this, the voice recognition server 3 extracts voiceprint information from the voice data included in the voice recognition request, compares it with voiceprint information registered in advance, and responds to voiceprint information that matches the extracted voiceprint information. The attached user ID is specified (S138). Here, the user ID newly issued in S131 is specified. Also, the voice data included in the voice recognition request is subjected to voice recognition processing (S139). Then, the speech recognition server 3 transmits the speech recognition result to the main device 1 together with the identified user ID (S140).

Next, the main device 1 extracts user information from the speech recognition result received from the speech recognition server 3, and registers the extracted user information together with the speech recognition result and the user ID received from the speech recognition server 3 (S141). Then, S109 to S125 in FIG. 2 are performed on the user ID and the voice recognition result received from the voice recognition server 3 in S133 (S142).

Further, in the above-described embodiment, when a connection request with the designation of the extension number of the destination is received, the main unit 1 calls the extension telephone 2 assigned with the extension number and receives a response to the call. If a time-out occurs after a predetermined period of time has elapsed, the incoming call may be transferred to the extension telephone 2 last used by the user to whom this extension number is permanently assigned.

That is, when the call control section 102 of the main apparatus 1 receives a connection request with designation of the destination extension number from the extension telephone 5 via the WAN 4 or from the extension telephone 2 via the extension interface section 100, this Call the extension telephone 2 to which the extension number is assigned. Then, when the called extension telephone 2 does not respond to the call and times out after a predetermined period of time has passed, the call control unit 102 searches the user information record 1040 having this extension number from the user information storage unit 104, A user ID included in the detected user information record 1040 is specified. Then, call control unit 102 selects from operation history table 1060 registered in operation history storage unit 106 associated with this user ID that the instruction content registered in field 1063 is "call" The record 1061 of the operation history other than the extension number of the extension telephone 2 called by the extension number registered in the field 1064 is searched, and among the detected records 1061, the record 1061 with the latest implementation date and time registered in the field 1062 is selected. Search for more. Then, the incoming call is transferred to the extension number registered in the field 1064 of the detected record 1061 .

In the above embodiment, the functional configuration of the main device 1 shown in FIG. 4 and the functional configuration of the speech recognition server 3 shown in FIG. It is implemented in hardware by an integrated logic IC or in software by a computer such as a DSP (Digital Signal Processor). Alternatively, in a general-purpose computer such as a PC (Personal Computer) having a CPU, a memory, an auxiliary storage device such as a hard disk or flash memory, and a communication interface such as a NIC (Network Interface Card), the CPU executes a predetermined program. is loaded from the auxiliary storage device into the memory and executed.

1: main device 2, 2-1 to 2-n: extension telephone 3: speech recognition server 4: WAN 5: outside telephone 100: extension line interface unit 101, 300: WAN interface unit 102: call control unit 103: relay unit 104 : user information storage unit 105: telephone directory data storage unit 106: operation history storage unit 107: voice acquisition unit 108: voice recognition request unit 109: user allocation setting unit 110: instruction content analysis unit 111: instruction processing unit 301: voiceprint information Storage unit 302: Voiceprint matching processing unit 303: Voice recognition processing unit 304: Voice recognition request reception unit

Claims (11)

A main device for housing an extension telephone,
voice acquisition means for capturing the off-hook extension phone and receiving voice data representing instruction content from the extension phone;
setting means for assigning a user recognized from the voiceprint information of the voice data acquired by the voice acquisition means to the extension telephone that is the transmission source of the voice data;
analysis means for analyzing the instruction content from a speech recognition result of the speech data acquired by the speech acquisition means;
an instruction processing means for executing a process according to the contents of the instruction analyzed by the analysis means;
a history recording means for recording, in an operation history of the user assigned by the setting means to the extension telephone that is the transmission source of the voice data, a result of execution of processing by the instruction processing means in accordance with the content of the instruction; A main device comprising: A main device according to claim 1,
further comprising phone book storage means for storing phone book data including names and phone numbers for each contact;
The instruction processing means is
when the instruction content analyzed by the analysis means is a call instruction with designation of a call destination, the phone book storage means is searched for phone book data containing the call destination as a name, and the detected phone book data is stored in A master device characterized by performing processing for outgoing calls to the included telephone number. A main device according to claim 2,
The instruction processing means is
A main apparatus characterized in that, when executing the outgoing call process, the information of the user assigned by the setting means to the extension telephone, which is the sender of the voice data, is included as caller information. The main device according to claim 2 or 3,
The instruction processing means is
recording a call between a destination and the extension telephone that is the source of the voice data when the processing according to the instruction content is a call processing;
The history recording means is
The main unit is characterized in that the execution result of call processing including the call recording data and the call destination is recorded in the operation history of the user assigned to the extension phone by the setting means. The main device according to any one of claims 2 to 4,
The instruction processing means is
When the instruction content analyzed by the analysis means is an instruction to display a call history, the instruction recorded in the history recording means and assigned by the setting means to the extension telephone that is the transmission source of the voice data Extracting the execution result of the outgoing call process from the operation history of the user, displaying a list of the extracted execution result of the outgoing call process on the extension phone, and accepting selection of the execution result of the outgoing call process from the extension phone, A main device characterized by carrying out call processing to a call destination designated by the execution result of the selected call processing. A main device according to claim 5,
The instruction processing means is
when the instruction content analyzed by the analysis means is an instruction to display a call history, a result of execution of call processing extracted from the operation history of the user assigned to the extension telephone that is the transmission source of the voice data; , a main unit that displays a list on the extension telephone in descending order of the number of outgoing calls, in order of the number of outgoing calls. The main device according to any one of claims 2 to 6,
Phonebook data for registering, for each user, in the phonebook data of the user, the destination designated by the execution result of the call processing included in the operation history of the user recorded in the history storage means. further equipped with updating means,
The instruction processing means is
When the instruction content analyzed by the analyzing means is an instruction to display telephone directory data, the telephone directory data of the user assigned by the setting means to the extension telephone that is the transmission source of the voice data is displayed. A main unit characterized in that it is displayed on an extension telephone, and when a selection of a contact is received from the extension telephone, a transmission process to the selected contact is performed. The main device according to any one of claims 2 to 7,
number information storage means for storing, for each user, the extension number of the extension telephone fixedly assigned to the user;
calling means for calling the extension telephone specified by the extension number when a call with the specified extension number is received;
The history storage means is
When the processing according to the instruction content by the instruction processing means is a call origination process, the result of execution of the call origination process including the destination and the extension number of the extension telephone that is the transmission source of the voice data is set by the setting means. recorded in the user's operation history assigned to the extension phone by
The calling means is
When there is no response to the call of the extension telephone within a predetermined time, executing the last outgoing call processing from the operation history of the user associated with the extension number of the extension telephone in the number information storage means. A main unit that extracts a result and transfers the incoming call to the extension telephone specified by the extension number included in the execution result. The main device according to any one of claims 1 to 8,
user information storage means for storing user information in association with a user ID for each user;
The voice data acquired by the voice acquisition means is transmitted to a voice recognition server with a voiceprint authentication function that stores voiceprint information for each user in association with a user ID, and the voice data is transmitted from the voice recognition server. voice recognition result acquisition means for acquiring a user ID associated with the voiceprint information and a voice recognition result for the voice data;
The setting means
The user specified by the user information stored in the user information storage means in association with the user ID acquired from the voice recognition server by the voice recognition result acquisition means is the source of the voice data. Assign to an extension phone,
The analysis means is
The main device analyzes the instruction content from the voice recognition result acquired from the voice recognition server by the voice recognition result acquisition means. A main device according to claim 9,
The speech recognition server is
when there is no user ID associated with the voiceprint information of the voice data obtained by the voice obtaining means, issuing a new user ID and storing the voiceprint information in correspondence with the user ID; transmitting the user ID to the main device;
The voice acquisition means is
When the user ID obtained from the speech recognition server by the speech recognition result obtaining means is not stored in the user information storage means, voice prompting the extension telephone, which is the sender of the voice data, to input user information by voice. Sending guidance to acquire voice data representing user information from the extension phone,
The speech recognition result acquisition means is
transmitting the voice data representing the user information acquired by the voice acquisition means to the voice recognition server, and acquiring a voice recognition result of the voice data representing the user ID and the user information from the voice recognition server;
The analysis means is
extracting user information from the speech recognition result of the speech data representing the user information acquired from the speech recognition server by the speech recognition result acquisition means;
The setting means
When the user ID obtained from the speech recognition server by the speech recognition result obtaining means is not stored in the user information storage means, the analysis means obtains the voice obtained together with the user ID by the speech recognition result obtaining means. The main device stores user information extracted from the recognition result in the user information storage means in association with the user ID. A method for allocating extension telephones by a main unit accommodating extension telephones, comprising:
The main device is
captures the off-hook extension telephone, receives voice data representing instruction content from the extension telephone,
assigning a user recognized from the voiceprint information of the received voice data to the extension telephone that is the source of the voice data;
analyzing the instruction content from a speech recognition result of the received speech data;
Carrying out a process according to the analyzed instruction content,
A method for assigning extension telephones, characterized in that a result of execution of processing according to the content of the instruction is recorded in an operation history of the user assigned to the extension telephone that is the transmission source of the voice data.

Images