JPH08163252A - Pbx/computer interlock system - Google Patents

Abstract

PURPOSE: To execute the system setting of a PBX with a voice according to the guide of a composite voice and to enable call origination regulation for the unit of an individual or the like by adding a voice recognizing/composing device to the PBX/computer interlock system. CONSTITUTION: A voice recognizing device 11 and a voice composing device 12 are connected through a voice input/output interface to a computer 7. The computer 7 controls a system setting operation from an extension terminal 6, the instruction of the setting operation due to the composite voice is applied, and the voice recognizing device 11 recognizes the voice inputted according to that instruction. Then, the computer 7 outputs an instruction to a PBX 1 corresponding to the recognized word (sequence) and performs system setting. Besides, the function of speaker recognition is added to the voice recognizing device 11 so that the uttering individual can be identified or only the specified person enables the system setting operation or a call origination regulation level can be set for each individual.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a PBX-computer linked system which provides various services by connecting a PBX to a computer and controlling the PBX from the computer.

[0002]

2. Description of the Related Art In a conventional private telephone system, as shown in FIG. 11 (a block diagram of a conventional private telephone system), a private branch exchange (PBX) 1 is connected with an extension line 4 and an office line (external line) 2. . The user of the extension 4 makes a call between the extensions 4 through the PBX 1 or connects to the office line 2 from the extension 4 to access the public telephone network 3 to make a call with an external telephone.

[0003]

In the conventional private telephone system, each extension telephone can only provide the function of making or receiving a call as described above.

In addition, in order to set a function such as call forwarding for the PBX, many button operations must be performed from a specific extension terminal. In addition, at that time, it is a very complicated work because it is referred to a manual or the like.

Therefore, an object of the present invention is to provide a convenient PBX-computer interlocking system for connecting a PBX and a computer to provide various services.

[0006]

Various services can be provided by linking a PBX and a computer. As one of them, by incorporating a voice recognition / synthesis device in the computer, a system as described above is provided. It provides a mechanism such as setting by voice and limiting the system setting operation by speaker recognition technology.

Specifically, a computer incorporating a voice recognition / synthesis device controls the system setting operation from the extension terminal, performs the instruction of the setting operation by the synthesized voice, and recognizes the voice input according to the instruction. Is recognized, and the computer gives an instruction to the PBX according to the recognized word (string) to set the system. Also, by adding a speaker recognition function to the voice recognition device, it is possible to identify the uttered individual so that the system setting operation can be performed only by a specific person, and the call restriction level can be set for each individual. And other means are provided.

[0008]

By adding a voice recognition / synthesis device to the PBX-computer interlocking system as described above,
It becomes possible to set the PBX system by voice in accordance with the guide of the synthesized voice, and to control the transmission on an individual basis.

[0009]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below in detail with reference to the drawings.

First, FIG. 1 shows P in one embodiment of the present invention.
It is a block diagram which shows the structure of a BX-computer linked system. In FIG. 1, reference numeral 1 is a private branch exchange (PBX).
A plurality of extension telephones 5 and extension terminals 6 are connected to the PBX 1 by extension lines 4.

The PBX 1 has functions such as control of outgoing and incoming calls and switching of line connection, and is connected to the public telephone network 3 by the office line 2. A computer 7 is connected to the PBX 1 via a PBX-computer connection interface by a transmission line 9 having a serial interface. The computer 7 is adapted to control the functions of the PBX 1. Further, the computer 7 has a P
An external storage device 8 for storing an interface program or the like for controlling the BX 1 is connected.
As computers, there are a computer 7 connected to the PBX 1 and a computer 10 connected to the extension terminal 6 composed of a multifunction telephone with a serial interface. Further, the computer 7 has a voice recognition device 11 and a voice synthesis device 12 via a voice input / output interface.
Is connected.

The audio system setting and other functions of this embodiment are built on the computer 7. However, when the computer 10 is connected, the functions of the present invention can be realized on the computer 10. In the present embodiment, the process of system setting by voice and other processing will be described on the premise of the configuration on the computer 7, but it may be implemented on the computer 10.

With the above system configuration, the function of the present invention will be described based on the flowcharts of FIGS. 2 to 7 and FIG. 8 (screen image diagram of the display device of the telephone in one embodiment of the present invention).

(Embodiment 1) Hereinafter, a specific example of the function realizing means according to claim 1 of the present invention will be described with reference to FIG. 2 (flow chart of the PBX-computer interlocking system in one embodiment of the present invention) and FIG. To do.

In step 1-1, the handset of the extension terminal 6 is hooked off and an application program relating to system setting by voice is executed on the computer 7. Then, the extension terminal 6 off-hook
Guidance by synthesized voice from the voice synthesizer 12 (such as "Set up the system. Please say the item to set up") is played on the handset of the device (step 1-
2). In step 1-3, an item (for example, call forwarding) to be set is selected, and the handset is uttered. The uttered voice is input to the voice recognition device 11 through the voice input / output interface, and recognition processing is performed according to an instruction from the computer 7. The uttered voice is stored in the voice recognition device 11 in advance as voice data 13 for synthesis / recognition. If it matches a word in a specific word group for PBX setting (step 1-4), in step 1-5, the computer 7 utters the word (string) recognized for confirmation by synthetic speech and, at the same time, the extension The display shown in FIG. 8 is displayed on the display device of the terminal 6. If there is no mistake, the operator informs the computer 7 of the confirmation by pressing a specific key of the extension terminal 6 (steps 1-6, 7). If no match is found in step 1-4, then in step 1-8, a voice prompting for another voice such as "please speak again" is sent to the handset, and the handset waits for a re-voice (step 1-3). Return to). In step 1-6, when the uttered content and the content recognized by the voice recognition device 11 are inconsistent (in the case of erroneous recognition), the operator presses a predetermined key, and re-voices the step 1-3. Return to. In steps 1-7,
If the recognition is done correctly, until the setting is completed, step 1
-3 to 7 are repeated (step 1-9). When finished, set other items in step 1-10,
Alternatively, the voice synthesizer 12 inquires whether to end the setting operation. The operator gives an instruction to the computer 7 by uttering "end" or pressing a predetermined key of the extension terminal 6 if it is okay to end, and the computer 7 receiving the instruction sends the instruction to the step 1-11.
Then, a series of processing ends. When the setting of another item is selected (by voice or key operation) in step 1-10, the process returns to step 1-2.

(Embodiment 2) A more specific example (setting of absence transfer) will be described with reference to the flowchart of FIG. 3 and FIGS. 9 and 10.

In step 2-1, the handset of the extension terminal 6 is hooked off and an application program relating to system setting by voice is executed on the computer 7. Then, the voice guidance from the voice synthesizer 12 to the handset of the extension terminal 6 that has gone off-hook is used to give a voice prompt to confirm the speaker (“Confirm your qualifications. Please say the confirmation text. Etc.) (step 2-2). Step 2
In -3, the voice uttered by the operator (name, confirmation text, etc.) is captured in the voice recognition device 11, and speaker identification processing is performed.

The speaker identification processing here is shown in FIG. 9 (flowchart of speaker identification processing in one embodiment of the present invention) and FIG. 10 (block diagram of speaker identification processing means in one embodiment of the present invention). It will be explained based on.

The voice input through the telephone line is filtered by the bandpass filter 171 and then sampled and quantized by the A / D converter 172 (step 20).
1) The audio analysis unit 173 cuts out a voice section from the input signal (step 202), and converts the voice signal into a series of parameters (pitch cycle and average amplitude) that more clearly represent the characteristics of the speaker (step 203). Next, in step 204, the pattern conversion unit 174 discretizes and associates the time with the reference pattern to form a pattern vector. In step 205, the determination unit 175 calculates the distance between this pattern vector and the standard pattern of each registrant registered in advance, and which speaker the speaker is registered in the system (speaker identification), Alternatively, it is determined whether or not it matches the speaker of the speaker ID input separately (speaker verification) (step 206).

Upon receipt of the speaker identification processing result as described above, the processing from step 2-4 onward in FIG. 3 is performed. That is, in step 2-4, if a corresponding person is found among the registrants in the identification process, the process proceeds to step 2-5, and if not, the process of step 2-6 is performed. Step 2
At -5, it is determined whether or not the person determined by the speaker identification is a qualified person for the system setting operation. If the qualified person is a qualified person, the processing from step 2-7 is performed. If you are not a qualified person, you will be notified by synthetic voice (such as "You cannot set the system"), and the process will end (step 2-8).

In step 2-6, the operator waits for a judgment as to whether or not to carry out the identification process again or to end it. If the operator selects the identification process again by pressing the key of the extension terminal 6 or uttering a voice, the process returns to step 2-2, and if the end is selected, the ending process is performed in step 2-9.

In step 2-7, the normal system setting process of the first embodiment is performed (omitted here).

(Third Embodiment) A specific example of the function realizing means according to the third aspect of the present invention will be described below with reference to the flowchart of FIG. The explanation is for the extension terminal 6 to which the PBX 1 is connected.
Processing after the state where the off-hook of the handset is detected is performed.

In step 3-1, the PBX 1 notifies the computer 7 of the number of the extension terminal 6 that has gone off-hook.
The computer 7 that received the notification then proceeds to step 3-2,
In order to perform speaker verification, the operator is prompted to enter his or her own speaker ID by key input or voice. Speaker I
When D is received, it is stored in the internal memory of the computer 7 (step 3-3). Next, in step 3-4, a message for prompting the utterance of a predetermined word string (name, simple sentence, etc.) is played using the voice synthesizer 12. The input voice signal is collated in step 3-5 by the processing according to the flow of FIG. Note that step 20 in FIG.
6, the speaker ID stored in step 3-3 in this case.
Matching processing with the standard pattern of the person having Then, in step 3-6 of FIG. 4, the process branches depending on the comparison result. If the verification results match, step 3-
At 7, the computer 7 looks at the registrant confirmed as the number of the extension terminal 6 and determines whether the registrant is permitted to make a call from the extension terminal 6 from reference information registered in advance,
If it is permitted, in step 3-8, send a message such as "Please enter the number of the destination", receive the number entered by the operator using the key or voice, and perform the normal calling operation (step 3-9). If the call is not permitted, in step 3-10, a message notifying that the call is not permitted is played and the process ends (step 3-13).

If the collation does not match in step 3-6,
A message prompting to determine whether to perform collation again or to end is sent (step 3-11). If collation is selected again, the process returns to step 3-5, and if end is selected, step 3-13. Ends with (Step 3-1)
2).

(Embodiment 4) In the following, in the confirmation system using the voice of the call restriction level, the processing after the state where the off-hook of the handset of the extension terminal 6 to which the PBX 1 is connected is detected will be described.

In step 4-1 of FIG. 5, the PBX 1 notifies the computer 7 of the number of the extension terminal 6 that has gone off-hook. The computer 7 that received the notification then proceeds to step 4
At -2, send out a message prompting you to say a password (simple word string) that corresponds to the calling level (city, suburbs, etc.). The computer 7 receives the uttered voice data, performs the recognition process by the voice recognition device 11 (step 4-3), and compares it with the voice data of the password registered in advance (step 4-4). If they match, a message corresponding to each level such as "Allow outgoing calls to the suburbs" is sent (step 4-5), and normal outgoing call processing is performed (step 4-6). If they do not match, a message asking whether to utter again or end is sent (step 4-7). If uttering again, the process returns to step 4-2, and if finished, end processing is performed in step 4-9. (Step 4-8).

Further, the following applications can be considered in the above configuration. (Embodiment 5) A function of inputting a conference contact or the like from the extension terminal 6 by voice, automatically calling the set content at a set time, and notifying by voice is shown in the flowchart of FIG. It will be explained based on.

In step 5-1 of FIG. 6, the handset of the extension terminal 6 is taken off-hook, and an application program relating to the conference contact system by voice is executed on the computer 7. Then, the guidance of the conference contact application from the voice synthesizer 12 ("Start registration of conference contact" or the like) flows to the handset of the extension terminal 6 that has gone off-hook (step 5-2).
Then, in step 5-3, a message prompting input is played according to the contact components (date, place, content, etc.). In step 5-4, the information input by voice or key operation according to the above message is fetched and saved in the external storage device 8. This is repeated as many times as necessary (step 5-5).

After that, the computer 7 waits until the time input in the above processing comes (step 5-6), and the computer 7 similarly searches the extension number of the conference participant from the input data (step 5-7). A call is made to the extension 4 and the contact contents are transmitted by the voice synthesizer 12 (step 5-
8) and ends (step 5-9).

(Embodiment 6) Further, regarding a system for identifying a person making a call by a speaker recognition function and managing billing for each individual based on the information, the extension terminal 6 connected to the PBX 1 Processing after the state where the off-hook of the handset is detected will be described.

In step 6-1 of FIG. 7, the voice of the caller of the extension terminal 6 transmitted by the computer 7 is input to the voice recognition device 11, and at the same time, the counting of the call time is started. Subsequently, in step 6-2, the voice recognition device 11 performs speaker identification processing according to the flow of FIG.
After that, wait until the call ends (step 6-3). When the call ends, the charge is calculated based on the call time and the callee in the billing data of the person who is determined as the result of the speaker identification registered on the computer 7, Write to billing data (step 6)
-4), and ends (step 6-5).

[0033]

According to the present invention, a voice recognition / synthesis device is added to the PBX-computer interlocking system to realize the PBX.
By making system settings for the BX by voice or by identifying the individual by voice, it is possible to regulate outgoing calls on an individual basis and greatly improve the convenience of the telephone.

[Brief description of drawings]

FIG. 1 is a block diagram showing the configuration of a PBX-computer interlocking system according to an embodiment of the present invention.

FIG. 2 is a flowchart of a PBX-computer interlocking system according to an embodiment of the present invention.

FIG. 3 is a flowchart of a PBX-computer interlocking system according to an embodiment of the present invention.

FIG. 4 is a flowchart of a PBX-computer interlocking system according to an embodiment of the present invention.

FIG. 5 is a flowchart of a PBX-computer interlocking system according to an embodiment of the present invention.

FIG. 6 is a flowchart of a PBX-computer interlocking system according to an embodiment of the present invention.

FIG. 7 is a flowchart of a PBX-computer interlocking system according to an embodiment of the present invention.

FIG. 8 is a screen image diagram of a display device of a telephone according to an embodiment of the present invention.

FIG. 9 is a flowchart of speaker identification processing according to an embodiment of the present invention.

FIG. 10 is a block diagram of speaker identification processing means in an embodiment of the present invention.

FIG. 11 is a block diagram of a conventional private telephone system.

[Explanation of symbols]

 1 private branch exchange (PBX) 2 office line 3 public telephone network 4 extension 5 extension telephone 6 extension terminal 7 computer 8 external storage device 9 transmission line by serial interface 10 computer 11 speech recognition device 12 speech synthesizer

Claims (3)

[Claims] 1. An interlocking system of a PBX and a computer connected by a dedicated interface, wherein the computer comprises a voice input / output interface, and a voice recognition device for recognizing a specific word group necessary for setting the PBX. And a voice synthesizer for uttering a group of words for confirming the setting of the system setting operation of the PBX, and performing various settings for the PBX by voice from a handset of an extension telephone in accordance with a synthetic voice instruction. And a PBX-computer interlocking system, characterized in that it is provided with means for uttering the setting contents by synthetic speech. 2. The voice recognition device has a speaker recognition function, and is provided with means for enabling system setting only when a specific speaker speaks. PBX-Computer interlocking system. 3. When calling from the extension terminal connected to the PBX to the outside, a call is made only when a pre-registered specific individual utters a pre-registered character string toward the terminal. 3. The PBX-computer interlocking system according to claim 2, further comprising a speaker recognition function that enables the above.