Processing device, processing method, program and system

Abstract

To provide a processing device, a processing method, a program, and a system that improve convenience for customers more than before.SOLUTION: A contact center server 10 as a processing device includes a first processing unit for sending a first guidance based on a voice-recognized first sound signal to a customer device 30 if the first sound signal received from the customer device 30 is different from information of a push button signal, and a second processing unit for sending a second guidance based on the first sound signal to the customer device 30 if the first sound signal received from the customer device 30 is information of the push button signal.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Conventionally, in inquiries at contact centers, interactive voice response (IVR) has been used to reduce the burden on operators and increase response efficiency (see Patent Document 1). In response to inquiries from customers, an IVR device provides prepared voice guidance or transfers the call to an operator based on the input of a push button (PB) signal or the result of voice recognition of the customer's speech. The push button signal (PB signal) is also called a dual-tone multi-frequency (DTMF) signal. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-076869 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, when an IVR device requests a customer to input information, it is necessary to determine in advance whether the input from the customer terminal is to be voice (the voice of the customer's speech) or button input operation (push button signal) (see, for example, paragraphs 0055 to 0061 (especially "S304" to "S307"), Figs. 3 and 5 of Patent Document 1). For this reason, some customers may find it troublesome.

[0005] The present invention has been made in consideration of the above problems, and provides a processing device, a processing method, a program, and a system that provide improved customer convenience compared to conventional devices. [Means for solving the problem]

[0006] In order to solve the above problems, the processing apparatus according to the present invention comprises: a third processing unit that, upon receiving information indicating the start of a voice inquiry from a customer device, receives a first sound signal from the customer device, transmits the received first sound signal to a first processing unit, and performs a detection process to detect a push button signal from the first sound signal, and, upon detecting a push button signal from the first sound signal in the detection process, transmits the detected push button signal to a second processing unit and stops transmitting the first sound signal to the first processing unit; Voice recognition The above Transmitting a first guidance based on the first sound signal to the customer device. The second processing unit processes the push button signal The second guidance is based on The above Send to customer device 、 It is characterized by:

[0007] The processing method according to the present invention further comprises the steps of: The apparatus includes a first processing unit, a second processing unit, and a third processing unit. A processing method in a processing device, comprising: When the third processing unit acquires information indicating the start of a voice inquiry from the customer device, the third processing unit receives a first sound signal from the customer device, transmits the received first sound signal to the first processing unit, and performs a detection process to detect a push button signal from the first sound signal, and when a push button signal is detected from the first sound signal in the detection process, transmits the detected push button signal to the second processing unit and stops transmitting the first sound signal to the first processing unit, and the first processing unit Voice recognition The above A first guidance based on a first sound signal. The above Send to customer device and a second processing unit that executes a step of The second guidance is based on The above Send to customer device Execute the steps, It is characterized by:

[0008] The program according to the present invention also includes: When information indicating the start of a voice inquiry is obtained from a customer device, the third processing unit receives a first sound signal from the customer device, transmits the received first sound signal to a first processing unit, and performs a detection process to detect a push button signal from the first sound signal, and when a push button signal is detected from the first sound signal in the detection process, transmits the detected push button signal to a second processing unit and stops transmitting the first sound signal to the first processing unit, and the first processing unit functions as a third processing unit. Voice recognition The above Transmitting a first guidance based on the first sound signal to the customer device. The second processing unit processes the push button signal sending a second guidance based on the Characterized by .

[0009] In addition, the system according to the present invention is a system comprising the processing device according to the present invention described above and the customer device, and is characterized in that the processing device and the customer device are connected via a telephone network or an IP (Internet Protocol) network. Effect of the Invention

[0010] According to the present invention, it is possible to improve convenience for customers. [Brief description of the drawings]

[0011] [Figure 1]1 is a schematic configuration diagram of a contact center system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is an example of a functional configuration diagram of a contact center server according to an embodiment of the present invention. [Diagram 3] 1 is an example of a sequence diagram showing an overall operation of a contact center system according to an embodiment of the present invention; [Figure 4] 1 is an example of an IVR processing flow in a contact center system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, the embodiment of the present invention will be described in detail with reference to the drawings as appropriate. Each figure is merely a schematic illustration to the extent that the present invention can be fully understood. Therefore, the present invention is not limited to only the illustrated examples. In addition, in this embodiment, the description of configurations that are not directly related to the present invention or well-known configurations may be omitted. In addition, in each figure, common components or similar components are given the same reference numerals, and their duplicated description will be omitted.

[0013] <Configuration of contact center system according to embodiment> A contact center system 1 will be described with reference to Fig. 1. Fig. 1 is a schematic configuration diagram of the contact center system 1 according to an embodiment. The contact center system 1 is a system that receives inquiries from customers and responds to the inquiries. In the contact center system 1, responses are made by operators or devices equipped with IVR technology (virtual operators). In this embodiment, the contact center system 1 is assumed to be related to financial operations, but the contact center system 1 can be used in various fields. Therefore, the fields in which the contact center system 1 can be applied are not particularly limited.

[0014] The contact center system 1 mainly comprises a contact center server 10 that provides contact center functions, an operator device 20 operated by an operator who performs response work, and a customer device 30 operated by a customer who makes an inquiry. The contact center server 10 is connected to the operator device 20 via a LAN (Local Area Network) 40. The contact center server 10 is also connected to the customer device 30 via a public telephone network 41 and an IP network 42. The contact center system 1 is an example of a "system", and examples of a "system" are not limited to the contact center system 1. Further, the contact center server 10 is an example of a “processing device”, and an example of the “processing device” is not limited to the contact center server 10.

[0015] The contact center server 10 is a device having, for example, an interface function with telephones (GW (Gateway) function), an ACD (Automatic Call Distribution) function, a voice recognition function, etc. Details will be described later.

[0016] The operator device 20 is a terminal or a group of terminals used by an operator for response work. The operator device 20 is connected to a customer device 30 via the contact center server 10 so as to be able to perform data communication. The operator device 20 in this embodiment is composed of an operator PC 21 and an operator telephone 22.

[0017] The operator's PC 21 is, for example, a computer equipped with an application program for a contact center, and performs call control such as incoming and outgoing calls to external and internal lines through the operation of an operator. The operator telephone 22 is, for example, a telephone that makes calls via a public telephone network 41 or an IP telephone that makes calls via an IP network 42, and is used for voice calls for which the operator PC 21 controls the calls. The operator telephone 22 also exchanges voice response data to be provided to customers with the contact center server 10.

[0018] The customer device 30 is a terminal or a collection of terminals operated by a customer who makes an inquiry to the contact center system 1. The customer device 30 may be, for example, a telephone terminal 31 that makes a call via a public telephone network 41, or a smartphone / PC 32 that makes a call via an IP network 42.

[0019] The connection between the customer's telephone terminal 31 and the contact center server 10 is realized, for example, via the telephone network 41, the GW 43, and the LAN 40. The GW 43 performs processing for connecting the telephone network 41 and the LAN 40, for example, converting between the protocol in the telephone network 41 and the protocol in the LAN 40. This allows signals from the telephone network 41 to the LAN 40 and signals from the LAN 40 to the telephone network 41 to be compatible with the destination network. The connection between the customer's smartphone / PC 32 and the contact center server 10 is realized, for example, via an IP network 42 and a LAN 40.

[0020] The functions of the contact center server 10 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of a functional configuration of the contact center server 10. 2, the contact center server 10 is configured to include a line control unit 11, an IVR service processing unit 12, a voice recognition processing unit 13, an IVR scenario data unit 14, and an ACD processing unit 15. Note that other devices may have some of the functions of the contact center server 10. For example, the voice recognition processing unit 13 and the ACD processing unit 15 may be configured to be included in a server other than the contact center server 10, in which case the contact center server 10 communicates with the other server as necessary. Note that a scenario is a flow (plot) in an automatic voice response.

[0021] The line control unit 11, the IVR service processing unit 12, the voice recognition processing unit 13, the IVR scenario data unit 14, and the ACD processing unit 15 are realized, for example, by a program execution process by a CPU (Central Processing Unit) or a dedicated circuit. The program for the execution process can be provided by storing it in a computer-readable recording medium (e.g., a CD-ROM or an external memory). The program can also be provided via a network such as the Internet. The line control unit 11 is an example of a “third processing unit”, and the example of the “third processing unit” is not limited to the line control unit 11. Moreover, the IVR service processing unit 12 is an example of a “second processing unit”, and an example of the “second processing unit” is not limited to the IVR service processing unit 12. Moreover, the voice recognition processing unit 13 is an example of the “first processing unit”, and the example of the “first processing unit” is not limited to the voice recognition processing unit 13.

[0022] The line control unit 11 serves as a reception desk for the contact center server 10, and connects the customer device 30 and the contact center server 10 so that they can communicate with each other through general call control processing, and also connects the customer device 30 and the operator device 20 so that they can communicate with each other. The line control unit 11 also executes voice switch processing. The voice switch processing is processing for switching the destination to which a sound signal received from the customer device 30 is sent. The voice switch processing will be described in detail later.

[0023] The IVR service processor 12 performs overall control of the automatic voice response. For example, when the sound signal received from the customer device 30 is push button signal information, the IVR service processor 12 transmits guidance based on the push button signal to the customer device 30.

[0024] The voice recognition processing unit 13 analyzes information on the customer's voice (voice data) acquired by the call and converts the voice information into text data. The voice recognition processing unit 13 also analyzes the contents of the text data, creates guidance to be used in a response, and sends it to the customer device 30. For example, when the sound signal received from the customer device 30 is voice information (i.e., different from the information of the push button signal), the voice recognition processing unit 13 sends guidance based on the voice recognition result to the customer device 30.

[0025] Various information used for automatic voice response is stored in the IVR scenario data unit 14. Guidance for each scene (scenario) used for response is stored in the IVR scenario data unit 14. The IVR scenario data unit 14 passes the stored information (including guidance) to other functions as necessary.

[0026] The ACD processor 15 distributes calls to operators. For example, when a request for transferring a call to an operator is received from a customer, the ACD processor 15 determines the corresponding operator based on a predetermined logic.

[0027] <Operation of the contact center system according to the embodiment> 3 (and also FIG. 1 and FIG. 2 as appropriate), a description will be given of the overall operation of the contact center system 1. FIG. 3 is a sequence diagram showing an example of the overall operation of the contact center system 1.

[0028] First, a call is made from the customer's telephone terminal 31, and the line control unit 11 of the contact center server 10 accepts the call as an incoming call (S01). The line control unit 11 notifies the IVR service processing unit 12 of the accepted incoming call (S02). In response, the IVR service processing unit 12 responds to the line control unit 11 (S03), and the line control unit 11 then responds to the telephone terminal 31 (S04). This connects the call between the telephone terminal 31 and the contact center server 10, and the conversation becomes possible.

[0029] Next, the IVR service processing unit 12 notifies the line control unit 11 of a guidance playback instruction (S05), and the line control unit 11 plays the guidance to the telephone terminal 31 (S06). The customer presses a button on the telephone terminal 31 in accordance with the playback of the guidance, and the telephone terminal 31 sends a push button signal (indicated as a "PB signal" in FIG. 3) (S07). The line control unit 11 notifies the IVR service processing unit 12 of the received PB signal (S08), and the IVR service processing unit 12 determines whether or not to transition to voice recognition processing based on the received PB signal (S09). If the transition is not to voice recognition processing, the process of S10 is continued, whereas if the transition is to voice recognition processing, the process of S20 is continued. A transition to voice recognition processing occurs, for example, when a PB signal with predetermined content is received. The PB signal for transitioning to the voice recognition process is an example of "information indicating the start of a voice inquiry."

[0030] (If not transitioning to speech recognition processing) The process when there is no transition to voice recognition processing will be described. When there is no transition to voice recognition processing in "S09", the IVR service processing unit 12 notifies the line control unit 11 to play the next guidance according to the IVR scenario (S10), and the line control unit 11 plays the guidance to the telephone terminal 31 (S11). The customer presses a button on the telephone terminal 31 in accordance with the played guidance, and the telephone terminal 31 sends a PB signal (S12). The line control unit 11 notifies the IVR service processing unit 12 of the received PB signal (S13).

[0031] Thereafter, the designated guidance is reproduced according to the IVR scenario, and the process of receiving the PB signal is repeated (S14). When the PB signal instructs the call to be transferred to an operator, the call from the customer is transferred to the operator device 20 (see FIG. 1) via the ACD process 15 (see FIG. 2).

[0032] (If transitioning to speech recognition processing) The process of transitioning to voice recognition processing will be described. When transitioning to voice recognition processing is made in "S09", the IVR service processing unit 12 notifies the voice recognition processing unit 13 of a voice recognition processing request (S20) and also instructs the line control unit 11 to operate the voice switch (S21). The telephone terminal 31 sends out the customer's voice (S22), and the line control unit 11 starts detecting the PB signal (represented as "PB detection" in FIG. 3) (S23) and starts sending the voice from the telephone terminal 31 to the voice recognition processing unit 13 (S24).

[0033] The voice recognition processing unit 13 creates a response guidance in accordance with the spoken voice question from the telephone terminal 31 (S25). The voice recognition processing unit 13 plays back the created guidance (S26), and the line control unit 11 plays back the guidance to the telephone terminal 31 (S27). In other words, the guidance played back by the voice recognition processing unit 13 is sent to the telephone terminal 31 via the line control unit 11. The processes from the voice sending in "S22" to the guidance playing in "S27" are repeatedly executed (S28). The guidance played back in response to the spoken voice question in "S27" is an example of the "first guidance."

[0034] Here, even during the processing from the voice transmission in "S22" to the reproduction of the guidance in "S27", the customer can operate the telephone terminal 31 to call an operator, etc. Specifically, when the customer wants to call an operator, the customer can press a button on the telephone terminal 31 even while the voice recognition processing unit 13 is reproducing the guidance. When the customer presses a predetermined button on the telephone terminal 31 during the reproduction of the guidance, the telephone terminal 31 transmits a PB signal corresponding to the pressed button (S31). Since the line control unit 11 starts detecting the PB signal in "S23", it detects the PB signal transmitted in "S31" and notifies the IVR service processing unit 12 that the PB signal has been detected (S32). The PB signal is a method of transmitting 16 types of codes, for example, numbers from "0 to 9" and symbols "*, #, A, B, C, D", as signal tones of two frequency bands, low group and high group, and the line control unit 11 detects the signal tones of these frequency bands.

[0035] The IVR service processing unit 12, which has been notified of the detection of the PB signal in "S32", interrupts the voice recognition process (S33), notifies the voice recognition processing unit 13 of the end of the voice recognition process (S34), and instructs the line control unit 11 to release the voice switch (S35). This stops the transmission of voice to the voice recognition processing unit 13. The IVR service processing unit 12 then plays back guidance or transfers the call to an operator according to the IVR scenario (S36). The guidance played in accordance with the IVR scenario in "S36" is an example of the "second guidance."

[0036] Next, the above-mentioned IVR processing flow will be described with reference to Fig. 4 (and Figs. 1 to 3 as appropriate). Fig. 4 shows an example of an IVR processing flow in the contact center system 1.

[0037] When the IVR service processing unit 12 of the contact center server 10 accepts an incoming call (T01), it instructs the line control unit 11 to play back guidance according to an IVR scenario (T02). The customer presses a button on the telephone terminal 31 according to the played back guidance, and the telephone terminal 31 sends out a PB signal.

[0038] When the IVR service processing unit 12 receives a PB signal from a customer (T03), it determines the content of the PB signal (T04). Here, it is assumed that when button "1" of the telephone terminal 31 is pressed, a response is made not to proceed to voice recognition processing, and when button "2" of the telephone terminal 31 is pressed, a response is made to proceed to voice recognition processing. Note that the correspondence between the buttons of the telephone terminal 31 and the voice recognition processing shown here is merely an example, and is not limited to the correspondence shown here.

[0039] When the IVR service processing unit 12 determines that the content of the PB signal is "1" in "T04", it plays back guidance according to the PB signal (T05), for example, and receives the next PB signal from the customer (T06). Then, the IVR service processing unit 12 determines whether the content of the received PB signal is transfer to an operator (T07), and if it is not transfer to an operator ("No" in T07), it plays back the guidance again to prompt the customer to receive the next PB signal. That is, the IVR service processing unit 12 plays back guidance to prompt the customer to press a button on the telephone terminal 31, and determines whether transfer to an operator is necessary every time a new PB signal is received (T05 to T07). The guidance here may have different content for each scenario. When the content of the received PB signal is transfer to an operator ("Yes" in T07), the IVR service processing unit 12 transfers the telephone call (call) from the customer to the operator device 20 (see FIG. 1) via the ACD processing unit 15 (see FIG. 2) (T08).

[0040] When the IVR service processing unit 12 determines in "T04" that the content of the PB signal is "2", it shifts to voice recognition processing (T10). In response to this, the voice recognition processing unit 13 creates a response guidance from the result of voice recognition processing of the uttered voice, and sends the created response guidance to the customer (T11). At this time, if the customer wishes to call an operator, the customer can press a button on the telephone terminal 31 even while the voice recognition processing unit 13 is playing back the guidance. The line control unit 11 detects the reception of a PB signal while playing back the guidance (T12), and if the voice recognition processing unit 13 has not received a PB signal, the process proceeds to T12 to create and send the next response guidance. In other words, the voice recognition processing unit 13 creates and sends out a response guidance for each voice reception until it receives a PB signal (T13).

[0041] If a PB signal is received during the playback of the guidance ("Yes" in T12), the process is transferred to the IVR service processing unit 12 (T14), and the IVR service processing unit 12 plays the guidance and proceeds with the process according to the IVR scenario (T15). In other words, if a PB signal is received from the customer while repeatedly creating and sending the response guidance in "T11", the voice recognition process is interrupted, the guidance is played, and the process returns to the process according to the IVR scenario.

[0042] As described above, the contact center server 10 according to the embodiment detects a push button signal (PB signal) even during processing up to playing back guidance to the customer, and notifies the IVR service processing unit 12 and the voice recognition processing unit 13 when a push button signal is detected. Then, the voice recognition processing is interrupted, the guidance is played back, and processing is returned to the IVR scenario. Therefore, when requesting the customer to input information, it is not necessary to determine in advance whether the input from the customer device 30 is a voice (voice spoken by the customer) or a button input operation (push button (PB) signal [DTMF signal]), and it is possible to receive a push button signal even during a voice recognition processing dialogue and execute dialogue processing according to the received push button signal.

[0043] Furthermore, in the contact center server 10 according to the embodiment, a scenario for IVR and a scenario for voice recognition processing can be created separately. In other words, there is no need to create a scenario that combines IVR and voice recognition processing. Therefore, when a change or replacement occurs in a scenario for IVR or a scenario for voice recognition processing, the other scenario is not affected (the other scenario does not need to be taken into consideration). As a result, operation is easier than when a scenario that combines IVR and voice recognition processing is created.

[0044] [Variations] Although the embodiment of the present invention has been described above, the present invention is not limited to this, and can be practiced within the scope of the claims. For example, the operation of the embodiment has been described taking the telephone terminal 31 as an example, but the invention can also be applied to a smartphone or a PC as long as it has a mechanism for sending push button signals (PB signals). [Explanation of symbols]

[0045] 1. Contact Center System 10 Contact Center Server 11 Line control section 12 IVR service processing section 13 Voice recognition processing unit 14 IVR Scenario Data Section 15 ACD Processing Unit 20 Operator device 30 Customer equipment 40 LAN 41 Telephone network 42 IP network

Claims

1. When information indicating the start of a voice inquiry is obtained from a customer device, a first sound signal is received from the customer device, the received first sound signal is sent to a first processing unit, and a detection process is performed to detect a push button signal from the first sound signal; a third processing unit that, when a push button signal is detected from the first sound signal in the detection process, transmits the detected push button signal to a second processing unit and instructs the first processing unit to stop transmitting the first sound signal; The first processing unit includes: sending a first guidance based on the voice-recognized first sound signal to the customer device; The second processing unit includes: sending a second guidance based on the push button signal to the customer device; A processing device comprising:

2. The third processing unit, When the information indicating the start of the voice inquiry is received from the customer device, the voice switch process is executed. When the push button signal is detected from the first sound signal, the state of executing the voice switch process is cancelled.

2. The processing device according to claim 1 .

3. the third processing unit detects the push button signal from the first sound signal while the first guidance is being reproduced on the customer device; 3. The processing device according to claim 1 or 2.

4. the pushbutton signal is for requesting a call transfer to an operator; the third processing unit transfers the call to the customer device to an operator device operated by the operator; 4. The processing device according to claim 1, further comprising: a processing unit for processing a sample;

5. A processing method in a processing device having a first processing unit, a second processing unit, and a third processing unit, The third processing unit, when acquiring information indicating the start of a voice inquiry from the customer device, receiving a first sound signal from the customer device, transmitting the received first sound signal to a first processing unit, and performing a detection process of detecting a push button signal from the first sound signal; executing a step of, when a push button signal is detected from the first sound signal in the detection process, transmitting the detected push button signal to a second processing unit and instructing the first processing unit to stop transmitting the first sound signal; The first processing unit, executing a step of transmitting a first guidance based on the first sound signal that has been speech-recognized to the customer device; The second processing unit, executing a step of transmitting a second guidance based on the push button signal to the customer device; A processing method comprising:

6. Computer, when acquiring information indicating the start of a voice inquiry from the customer device, receiving a first sound signal from the customer device, transmitting the received first sound signal to a first processing unit, and performing a detection process of detecting a push button signal from the first sound signal; a third processing unit that, when a push button signal is detected from the first sound signal in the detection process, transmits the detected push button signal to a second processing unit and instructs the first processing unit to stop transmitting the first sound signal; The first processing unit includes: sending a first guidance based on the voice-recognized first sound signal to the customer device; The second processing unit is sending a second guidance based on the push button signal to the customer device; A program characterized by:

7. A processing device according to any one of claims 1 to 4, the customer device, The processing device and the customer device are connected via a telephone network or an IP (Internet Protocol) network. A system characterized by:

Images