JP6863179B2 - Call center system, call center device, dialogue method, and its program with customer complaint detection function - Google Patents

Description

The present invention provides a function in an inbound call center system such as a financial institution to detect a customer's complaint during a customer call and prevent the situation from deteriorating by analyzing the conversation content between the customer and the virtual operator or the operator. Regarding the equipped call center system.

As for the handling of complaints in the conventional call center system, the supervisor is appropriate by automatically determining the degree of emotion of the customer and the situation where the operator is confused about the response, and by requesting from the operator or monitoring by the supervisor who is a senior operator. By performing processing or switching the call to the supervisor, it is possible to prevent the worsening of the complaint state during the call (see, for example, Patent Document 1, Patent Document 2, Patent Document 3, and Patent Document 4).

Japanese Unexamined Patent Publication No. 2004-37989 JP-A-2007-4000 Japanese Unexamined Patent Publication No. 2011-9902 JP-A-2016-119634

However, in the conventional technique, when a virtual operator (hereinafter abbreviated as AI) by AI (Artificial Intelligence) as the call center system side is interacting with the customer (AI dialogue), the customer is clearly from the conversation content. In situations where it cannot be determined that a complaint is being expressed, there is no criterion for switching to advanced operator dialogue, so dialogue cannot be switched at the request of AI, and it is possible to prevent complaints during AI dialogue. There was a problem that it could not be done. Further, as a response to the above situation, it is possible to determine the dialogue switching by monitoring by the senior operator, but it leads to an increase in the burden on the senior operator and loses the significance of unmanned operation by AI.
In addition, even if the initial dialogue is an operator dialogue, in the above situation, it is difficult to determine to switch to an advanced operator dialogue (supervisor dialogue), so the dialogue cannot be switched at the request of the operator, and complaints are made during the operator dialogue. There was a problem that it could not be prevented. Further, as a response in the above situation, it is possible to determine the dialogue switching by monitoring by the supervisor, but this has led to an increase in the burden on the supervisor.

An object of the present invention is to solve such a problem, and an object of the present invention is to prevent complaints during AI dialogue and operator dialogue.

The call center system of the present invention is a call center system including an operator work terminal, a supervisor work terminal, and a call center server to provide a call center service to a customer terminal, and an AI dialogue in which a voice dialogue with a customer is performed on the call center server by AI. A processing unit, a call content analysis unit that analyzes the call content based on the customer's call voice, a complaint detection processing unit that detects a complaint state or a complaint reserve army state based on the analysis result of the call content analysis unit, and the AI Switching from the AI dialogue by the dialogue processing unit to the operator dialogue in which the operator of the operator work terminal has a voice dialogue with the customer, or from the operator dialogue to the supervisor dialogue in which the supervisor of the supervisor work terminal has a voice dialogue with the customer. Controls the dialogue switching unit that performs switching, the AI dialogue processing unit, the call content analysis unit, and the complaint detection processing unit, and further, for the dialogue switching unit, the complaint detection processing unit If the detection result is in the complaint state, the switching is controlled, and if the detection result of the complaint detection processing unit is in the complaint reserve state, the switching is controlled only when the customer's switching request information is acquired from the customer terminal. It is characterized by having a control unit and a control unit.

The call center device of the present invention is a call center device having an operator work terminal and a call center server and having a function of the call center server of a call center system that provides a call center service to a customer terminal, and is an AI that performs voice dialogue with a customer by AI. The dialogue processing unit, the call content analysis unit that analyzes the call content based on the customer's call voice, the complaint detection processing unit that detects the complaint state or the complaint reserve army state based on the analysis result of the call content analysis unit, and the above. A dialogue switching unit that switches from an AI dialogue by the AI dialogue processing unit to an operator dialogue in which the operator of the operator work terminal performs a voice dialogue with a customer, the AI dialogue processing unit, the call content analysis unit, and the above. The complaint detection processing unit is controlled, and if the detection result of the complaint detection processing unit is in a complaint state, the switching is controlled for the dialogue switching unit, and the detection result of the complaint detection processing unit is a complaint. In the reserve army state, it is characterized by having a control unit that controls the switching only when the customer's switching desired information is acquired from the customer terminal.

The dialogue method of the present invention is a dialogue method executed by a call center server in a call center system having an operator work terminal and a call center server and providing a call center service to a customer terminal, and is an AI dialogue in which a voice dialogue with a customer is performed by AI. A processing step, a call content analysis step that analyzes the call content based on the customer's call voice, a complaint detection processing step that detects a complaint state or a complaint reserve army state based on the analysis result of the call content analysis step, and the complaint If the detection result of the detection processing step is a complaint state, the step of switching from the AI dialogue by the AI dialogue processing step to the operator dialogue in which the operator of the operator work terminal performs a voice dialogue with the customer, and the detection of the complaint detection processing step. If the result is a complaint reserve state, it is characterized by having a step of switching from the AI dialogue to the operator dialogue only when the customer switching desired information is acquired from the customer terminal.

The program of the present invention is a program for an interaction method executed by the call center server in a call center system having an operator work terminal and a call center server and providing a call center service to a customer terminal, and is a program for a computer of the call center server. AI dialogue processing step in which voice dialogue with the customer is performed by AI, call content analysis step in which the call content is analyzed based on the customer's call voice, and complaint state or complaint reserve army state based on the analysis result of the call content analysis step. If the complaint detection processing step for detecting the above and the detection result of the complaint detection processing step are in a complaint state, the AI dialogue by the AI dialogue processing step is changed to the operator dialogue in which the operator of the operator work terminal has a voice dialogue with the customer. If the detection result of the complaint detection processing step is the complaint reserve army state, the step of switching and the step of switching from the AI dialogue to the operator dialogue are executed only when the customer switching desired information is acquired from the customer terminal. It is characterized by that.

In the case of AI dialogue in this way, the present invention provides a criterion for switching to operator dialogue even in a situation where it cannot be clearly determined from the contents of the call that the customer is complaining, and AI dialogue is provided. It is possible to prevent complaints inside. In addition, it is possible to eliminate the need for the operator to monitor as a response to the above situation, reduce the burden on the operator, and achieve unmanned operation by AI.
Further, even if the initial dialogue is an operator dialogue, it is possible to provide a criterion for switching to the supervisor dialogue in the above situation and prevent complaints during the operator dialogue. Further, it is possible to eliminate the need for the supervisor to monitor as a response in the above situation and reduce the burden on the supervisor.

The block diagram which shows the whole structure of the call center system in 1st Example. The block diagram which shows the functional configuration of the call center server in 1st Example. The flowchart which shows the algorithm of the complaint detection processing in 1st Example. The flowchart which shows the algorithm of the word interval calculation in 1st Example. The explanatory view which shows the result of the voice recognition processing in 1st Example, and the value of the flag with respect to it. The explanatory view which shows the result of the sentiment analysis process in 1st Example, and the value of the flag for it. The explanatory view which shows the result of the word interval calculation in 1st Example, and the value of the flag with respect to it. The explanatory view which shows the customer's response of the process which asks a customer to switch a dialogue in 1st Embodiment, and the value of a flag to it.

Hereinafter, an embodiment of the call center system provided with the customer complaint detection function according to the present invention will be described with reference to the drawings. This embodiment also includes a call center device having a function of a call center server, a switching method, and a program thereof.
In the present invention, a call is defined as a telephone conversation made by a customer to a call center via the Internet or a telephone line, and a dialogue is defined as a response made by the call center side such as a response to a call or an announcement to a customer. The AI dialogue is defined as the dialogue conducted by AI, the operator dialogue is defined as the dialogue conducted by the operator, and the supervisor dialogue is defined as the dialogue conducted by the supervisor. Further, utterance is defined as a series of customer calls between call center dialogues.
The text data, the utterance detection time, the NG word, and the number of NG words are all voice recognition data as a recognition result of voice recognition of the utterance by the conventional voice recognition technology, and the text data is the text of the utterance. Defined as data. The utterance detection time is defined as the time length of the utterance. The NG word is defined as a predetermined word in the utterance indicating that the customer is in a complaint state described later. The number of NG words is defined as the number of NG words in an utterance.
The presence / absence information of angry feelings is defined as sentiment analysis data as an analysis result of sentiment analysis of a utterance by a sentiment analysis technique, and is information indicating whether or not there is an angry feeling in the utterance.
Further, the complaint state is defined as a state in which the content of the call clearly represents the customer's complaint. The complaint reserve state is defined as a state in which the customer cannot clearly conclude from the contents of the call that the customer is complaining, but may be complaining. A state that is neither a complaint state nor a complaint reserve state is defined as a no-complaint state. Complaint detection is defined as detecting a complaint state or a complaint reserve state.

FIG. 1 is a block diagram showing an overall configuration of a call center system according to the first embodiment.

In FIG. 1, the call center system 1 is a call center server (call center device) 11 that controls communication between a customer and an operator (including AI), text data by inputting voice, a speech detection time, and a predetermined keyword (in the present invention). A voice recognition system 12 configured by a known technique (for example, Patent Document 4) that outputs (the number of NG words for a predetermined NG word) instead of the keyword itself, inputs voice and identifies the emotion of the voice (in the present invention). An operator work terminal 14 having a monitor for displaying the contents of a data storage unit, which will be described later, and an emotion analysis system 13 composed of known technology (for example, Patent Document 3), which outputs only information on the presence or absence of angry emotions for each speech. It consists of a customer terminal 15 connected via the Internet or a telephone line (including a supervisor work terminal).

FIG. 2 is a block diagram showing a functional configuration of the call center server in the first embodiment.

In FIG. 2, the control unit 111 has a function of controlling each functional block of the call center server 11 by executing a program, and processing data and arithmetic processing of the memory unit 112, which will be described later, by executing the program. This program may be stored and provided in the memory unit 112 described later, or may be stored and provided in the memory built in the control unit 111.
The memory unit 112 has a function for temporarily storing data obtained from each processing unit of the call center server 11 and for using it for data processing and arithmetic processing performed by the control unit 111.
The data storage unit 113 includes voice recognition data (text data, utterance detection time, number of NG words), sentiment analysis data (information on the presence or absence of angry feelings), word intervals and the number of text characters described in FIG. 4 described later, and the number of text characters described later for each utterance. It has a function of accumulating the value of each flag.
The AI dialogue processing unit 114 has a function of receiving a customer's utterance and responding from the AI. The AI dialogue processing unit includes a function of determining a customer's response to an announcement to the customer of AI.
The voice recognition input / output processing unit 115 has a function of passing the customer's uttered voice to the voice recognition system 12 and receiving the voice recognition data from the voice recognition system 12.
The sentiment analysis input / output processing unit 116 has a function of passing the customer's voice to the sentiment analysis system 13 and receiving information on the presence or absence of angry emotions, which is sentiment analysis data, from the sentiment analysis system 13.
The complaint detection processing unit 117 has a function of detecting a complaint state or a complaint reserve state based on the information received from the voice recognition input / output processing unit 115, the emotion analysis input / output processing unit 116, and the word interval processing unit 118 described later. .. The call content analysis unit has the functions of the voice recognition input / output processing unit 115, the emotion analysis input / output processing unit 116, and the word interval processing unit 118.
The word interval processing unit 118 has a function of calculating the word interval issued by the customer based on the information received from the voice recognition input / output processing unit 115 and passing the obtained value to the complaint detection processing unit 117.
The dialogue switching unit 119 has a function of switching from the AI dialogue to the operator dialogue based on the correspondence of the AI dialogue processing unit 114.

FIG. 3 is a flowchart showing an algorithm for customer complaint detection processing in the first embodiment. This will be described with reference to FIGS. 1, 2, 5, 6, 6, 7, and 8 according to the steps represented by S in the flow chart.
The AI dialogue processing unit 114, the call content analysis unit (voice recognition input / output processing unit 115, the sentiment analysis input / output processing unit 116, and the word interval processing unit 118), and the complaint detection processing unit 117 are all controlled by the control unit 111. The procedure is controlled according to this flowchart, and the description of the control operation of the control unit 111 will be omitted in the following description.

S100: The value of the identification number i indicating the number of utterances of the customer held by the memory unit 112 is set to 0. This value of i is added by 1 in S101, which will be described later, each time the customer speaks.

S101: Each utterance (that is, identification) of the complaint state detection flag complete, the complaint reserve army state detection flag changer, the dialogue switching flag change, the same announcement continuation flag cont1, and the conversation continuation flag cont2, which are five flags of the memory unit 112 The initial value is set to 0 each time the utterance of (number) starts. Also, in this step, the value of the identification number i is set to i + 1.

S102: This step is a step of performing voice recognition processing. That is, voice data is input to the voice recognition system 12 for each utterance, and the voice recognition input / output processing unit 115 stores the text data received from the voice recognition system 12 for each utterance, the utterance detection time, and the number of NG words in the memory unit 112. .. Further, these stored data are stored in the data storage unit 113 for each identification number i. A predetermined NG word is set in the voice recognition system 12 in advance, the voice recognition system 12 detects the NG word based on the input voice data, and the number of NG words is input / output by voice recognition for each input voice data. It shall be passed to the processing unit 115.

S103: The complaint detection processing unit 117 receives the number of NG words stored in the memory unit 112, and determines whether or not it is in a complaint state according to the number of NG words. As an example of the judgment criteria, when the number of NG words is 1 or more, it is judged to be in a complaint state, and when it is 0, it is judged not to be in a complaint state. When it is determined that the state is a complaint, the complaint detection processing unit 117 sets the flag comp to 1, and when it is determined that the state is not a complaint, the flag complete is set to 0. Then, the value of the comp is stored in the data storage unit 113 for each identification number i.

FIG. 5 is an explanatory diagram showing the result of the voice recognition process and the value of the flag for the result. That is, it is an example of the data accumulated in the data storage unit 113 for each identification number i in S102 and S103 (the utterance detection time is not used for the judgment in S103, so is omitted here). The example of FIG. 5 is a case where the word "stupid" is included in the predetermined NG word, and the text data "So you can't hear me, stupid" is changed to "stupid" with the identification number 4. This is an example in which the number of NG words detected as NG words and the identification number 4 is 1, and the flag compact at this time is 1.

S104: When the flag comp is 1, the flag change is set to 1 and the process proceeds from (S112) to S113, and when the flag comp is 0, the process proceeds to S105.

S105: This step is a step of performing sentiment analysis processing. That is, voice data is input to the sentiment analysis system 13 for each utterance, and the presence / absence information of anger feelings received from the sentiment analysis system 13 by the sentiment analysis input / output processing unit 116 for each utterance is stored in the memory unit 112. Further, this stored data is stored in the data storage unit 113 for each identification number i.
The sentiment analysis system 13 detects the presence or absence of anger emotions from the frequency or the like based on the input voice data, and passes the presence or absence information of anger feelings to the sentiment analysis input / output processing unit 116 for each input voice data. To do.

S106: The complaint detection processing unit 117 receives the anger emotion presence / absence information of the memory unit 112 in S105, determines that it is in a complaint state when there is anger emotion information, and determines that it is not in a complaint state when there is no anger emotion information. to decide. When it is determined that the state is a complaint, the complaint detection processing unit 117 sets the flag comp to 1, and when it is determined that the state is not a complaint, the flag complete is set to 0. Then, the value of the comp is stored in the data storage unit 113 for each identification number i.

FIG. 6 is an explanatory diagram showing the result of the sentiment analysis process and the value of the flag for the result. That is, it is an example of the data stored in the data storage unit 113 for each identification number i in S105 and S106. The example of FIG. 6 is a case where the text data "So you can't hear me, stupid" contains the feeling of anger in the identification number 4, and the information on the presence or absence of the feeling of anger in the identification number 4 is ". This is an example in which the flag compt at this time is 1.

S107: When the flag comp is 1, the flag change is set to 1 and the process proceeds from (S112) to S113, and when the flag comp is 0, the process proceeds to S108.

S108: This step is a step of calculating the word interval. The word spacing processing unit 118 calculates the word spacing based on the voice recognition data stored in the memory section 112, and stores the results (word spacing SP (i), the number of text characters (i), and the value of changer described later) in the memory section. It is stored in 112 and is stored in the data storage unit 113 for each identification number i. This step will be described in detail with reference to FIG. 4 described later.

FIG. 7 is an explanatory diagram showing the result of the word interval calculation and the value of the flag for the result. That is, it is an example of the data stored in the data storage unit 113 for each identification number i in S108 (the utterance detection time is in S102). The example of FIG. 7 is a case where the word interval PH (3) of the text data "I'm sorry, I can't hear well from a while ago" is less than PH (1) with the identification number 3, and the flag changer at this time is This is an example of 1.

S109: If the flag changer set in S108 is 1, it is determined that the customer is in the reserve army state, and the process proceeds to the determination process (S110) as to whether or not the customer wants to switch the dialogue. It is determined that the process proceeds to the process (S116) of continuing the dialogue as it is.

S110: This step is a process of asking the customer to switch the dialogue, that is, a process of acquiring the customer's desired switching information from the customer terminal 15. As a specific example, the AI dialogue processing unit 114 announces to the customer "Do you want to switch to the operator dialogue?" (This is just an example of this announcement), and the AI dialogue processing unit 114 determines and acquires the response. To do. When the switching desired information is acquired, the AI dialogue processing unit sets the flag change to 1 and proceeds to S111. The method of making an announcement may be a method of voice synthesis or a method of playing a recorded fixed phrase (synthetic voice or human voice) (the same applies hereinafter). If the switching desired information is not acquired, the process proceeds to S111 with the flag change set to 0 (initial value). As a method of acquiring the customer's desired switching information, even if the AI dialogue processing unit 114 acquires the customer's response from the AI dialogue processing unit 114 by voice-recognizing the customer's response, the announcement of the AI dialogue processing unit 114 is the customer. The AI dialogue processing unit 114 may receive and acquire the bush button signal by prompting the user to press the push button.

FIG. 8 is an explanatory diagram showing the customer's response to the process of asking the customer to switch the dialogue and the value of the flag for the response, and is an example of determining the customer's response by voice recognition. Patterns 1, 2 and 3 are cases where switching is desired and the change is 1, and patterns 4, 5 and 6 are cases where switching is not desired and the change is 0, respectively.

S111: When the flag change is 1, the process proceeds to the dialogue switching process (S113), and when the flag change is 0, the process proceeds to the next announcement process (S114).

S113: When the flag change is 1, the dialogue switching unit 119 switches from the AI dialogue by the AI dialogue processing unit 114 to the operator dialogue by the operator work terminal 14. The dialogue switching unit 119 transfers the accumulated data (text data during AI dialogue, etc.) of the data storage unit 113 to the operator work terminal 14, and ends the customer complaint detection process.

S114: This step is a process of asking the customer to continue the AI dialogue. That is, it is a process of acquiring the customer's AI dialogue continuation desired information from the customer terminal 15. As a specific example, the AI dialogue processing unit 114 announces to the customer "Do you want to continue the AI dialogue in the future?" (This is just an example of this announcement), and the AI dialogue processing unit 114 responds to the announcement. Judge and get. When the AI dialogue desired information is acquired, the AI dialogue processing unit 114 sets the flag cont1 to 1. If the information requesting the continuation of the AI dialogue is not acquired, cont1 remains 0 (initial value). As a method of acquiring the customer's AI dialogue switching desired information, even if the AI dialogue processing unit 114 acquires from the AI dialogue processing unit 114 by recognizing the customer's response by voice, the AI dialogue processing unit 114 The announcement may prompt the customer to press the push button, and the AI dialogue processing unit 114 may receive and acquire the bush button signal.

S115: If the flag cont1 is 1, the process proceeds to S116, and if the flag cont1 is 0, the customer complaint detection process is terminated.

S116: The AI dialogue processing unit 114 determines whether the customer's call is continuing. If it is determined that the continuation is continued, the AI dialogue processing unit sets the flag cont2 to 1.

S117: If the flag cont2 is 1, the process proceeds to S101, and if the flag cont2 is 0, the customer complaint detection process is terminated. If the call with the customer continues after the complaint detection process is completed, the above-mentioned complaint detection process may be started again.

FIG. 4 is a flowchart showing the algorithm for calculating the word interval in the first embodiment. Described with reference to FIGS. 1 and 2 according to the step represented by S in the flowchart. S201: The word spacing processing unit 118 speaks with the text data SP (i) corresponding to the identification number i stored in the memory unit 112. Receive the detection time T (i).

S202: The word spacing processing unit 118 calculates the number of text characters N (i) of SP (i) from SP (i), and calculates the word spacing PH (i) = T (i) / N (i).

S203: The word interval processing unit 118 calculates PH (1) -PH (i), and determines that if it exceeds 0, it is not a claim reserve force, and if it is 0 or less, it is not a claim reserve force.

S204: If the result of S203 is a claim reserve force, the flag changer is set to 1.

S205: If the result of S203 is not the claim reserve force, the flag changer is set to 0.

According to the first embodiment, in the case of the AI dialogue, even in a situation where it cannot be clearly determined from the contents of the call that the customer is complaining, the judgment criteria for switching to the operator dialogue is provided, and the AI dialogue is provided. It is possible to prevent complaints inside. In addition, it is possible to eliminate the need for the operator to monitor as a response to the above situation, reduce the burden on the operator, and achieve unmanned operation by AI.

The content of the first embodiment can also correspond to a call center system having a customer complaint detection function when switching from an operator dialogue to a supervisor dialogue. In the second embodiment, it is assumed that the operator work terminal 14 of FIG. 1 also includes a supervisor work terminal. Further, it is assumed that the initial dialogue is not the AI dialogue by the AI dialogue processing unit 114, but the operator dialogue by the operator work terminal 14.
Only the differences from Example 1 will be described below.
<About dialogue switching unit 119>
The dialogue switching unit 119 has a function of switching from the operator dialogue to the supervisor dialogue based on the correspondence of the AI dialogue processing unit 114 or the correspondence of the operator.
<About S110, S113 to S117 in the description of FIG. 3>
S110: This step is a process of asking the customer to switch the dialogue, that is, a process of acquiring the customer's desired switching information from the customer terminal 15. As a specific example, the AI dialogue processing unit 114 or the operator announces to the customer "Do you want to switch to the supervisor dialogue?" (This is just an example of this announcement), and the AI dialogue processing unit 114 or the operator responds. Judge and get. When the switching desired information is acquired, the AI dialogue processing unit sets the flag change to 1 and proceeds to S111. The method of the announcement by the AI dialogue processing unit 114 may be a method of voice synthesis or a method of playing a recorded fixed phrase (synthetic voice or human voice) (the same applies hereinafter). If the flag change is 0, the process proceeds to S112. As a method for the AI dialogue processing unit 114 to acquire the customer's desired switching information, even if the AI dialogue processing unit 114 acquires the customer's response by voice recognition, the announcement of the AI dialogue processing unit 114 is the customer. The AI dialogue processing unit 114 may receive and acquire the bush button signal by prompting the user to press the push button.

S113: When the flag change is 1, the dialogue switching unit 119 switches from the operator dialogue by the operator work terminal 14 to the supervisor dialogue by the supervisor work terminal. The dialogue switching unit 119 transfers the accumulated data (text data during the operator dialogue, etc.) of the data storage unit 113 to the supervisor work terminal 14, and ends the customer complaint detection process.

S114 to S117: In Example 2, these processes are not performed, and if change = 0 in S109 and change = 0 in S111, both proceed to S101.

According to the second embodiment, even if the initial dialogue is an operator dialogue, a criterion for switching to the supervisor dialogue is provided in a situation where it cannot be clearly determined from the contents of the call that the customer is complaining. It is possible to prevent complaints during operator dialogue. Further, it is possible to eliminate the need for the supervisor to monitor as a response in the above situation and reduce the burden on the supervisor.

1 Call center system 11 Call center server 12 Voice recognition system 13 Sentiment analysis system 14 Operator work terminal 15 Customer terminal 111 Control unit 112 Memory unit 113 Data storage unit 114 AI dialogue processing unit 115 Voice recognition input / output processing unit 116 Sentiment analysis input / output processing unit 117 Complaint detection processing unit 118 Word interval processing unit 119 Dialogue switching unit

Claims (6)

A call center system that includes an operator work terminal, a supervisor work terminal, and a call center server to provide call center services to customer terminals.
The call center server
AI dialogue processing unit that conducts voice dialogue with customers by AI,
A call content analysis unit that analyzes the call content based on the customer's call voice,
A complaint detection processing unit that detects a complaint state or a complaint reserve force state based on the analysis result of the call content analysis unit, and
A supervisor that switches from an AI dialogue by the AI dialogue processing unit to an operator dialogue in which the operator of the operator work terminal has a voice dialogue with a customer, or from the operator dialogue to a supervisor in which the supervisor of the supervisor work terminal has a voice dialogue with a customer. A dialogue switching unit that switches to dialogue,
The AI dialogue processing unit, the call content analysis unit, and the complaint detection processing unit are controlled, and the dialogue switching unit is switched to the dialogue switching unit if the detection result of the complaint detection processing unit is a complaint state. If the detection result of the complaint detection processing unit is in the complaint reserve state, the control unit that controls the switching only when the customer's switching request information is acquired from the customer terminal.
A call center system characterized by having. In the call center system according to claim 1,
In the case where the dialogue switching unit is a dialogue switching unit that switches from the AI dialogue to the operator dialogue.
The control unit performs AI only when the detection result of the complaint detection process is in the complaint reserve state and the switching desired information cannot be obtained, and when the customer's AI dialogue continuation desired information is further acquired from the customer terminal. A call center system characterized in that the dialogue processing unit controls the continuation of AI dialogue. In the call center system according to claim 1 or 2.
In the case where the dialogue switching unit is a dialogue switching unit that switches from the AI dialogue to the operator dialogue.
Whether the switching desired information or the continuation desired information is requested by the AI dialogue processing unit to the customer on the customer terminal, the switching desired information is the switching, and the continuation desired information is the continuation of the AI dialogue. The control unit receives an announcement and the AI dialogue processing unit recognizes the customer's response voice to the announcement, or the AI dialogue processing unit receives a push button signal by the customer's customer terminal operation for the announcement. A call center system characterized by the acquisition of. A call center device having an operator work terminal and a call center server and having a function of the call center server of a call center system that provides a call center service to a customer terminal.
AI dialogue processing unit that conducts voice dialogue with customers by AI,
A call content analysis unit that analyzes the call content based on the customer's call voice,
A complaint detection processing unit that detects a complaint state or a complaint reserve force state based on the analysis result of the call content analysis unit, and
A dialogue switching unit that switches from an AI dialogue by the AI dialogue processing unit to an operator dialogue in which the operator of the operator work terminal performs a voice dialogue with a customer.
The AI dialogue processing unit, the call content analysis unit, and the complaint detection processing unit are controlled, and the dialogue switching unit is switched to the dialogue switching unit if the detection result of the complaint detection processing unit is a complaint state. If the detection result of the complaint detection processing unit is in the complaint reserve state, the control unit that controls the switching only when the customer's switching request information is acquired from the customer terminal.
A call center device characterized by having. A method of interaction executed by a call center server in a call center system that includes an operator work terminal and a call center server and provides call center services to customer terminals.
AI dialogue processing step to perform voice dialogue with customers by AI,
A call content analysis step that analyzes the call content based on the customer's call voice,
A complaint detection processing step that detects a complaint state or a complaint reserve force state based on the analysis result of the call content analysis step, and
If the detection result of the complaint detection processing step is a complaint state, a step of switching from the AI dialogue by the AI dialogue processing step to the operator dialogue in which the operator of the operator work terminal performs a voice dialogue with the customer,
If the detection result of the complaint detection processing step is the complaint reserve army state, the step of switching from the AI dialogue to the operator dialogue only when the customer switching request information is acquired from the customer terminal.
A dialogue method characterized by having. A program for an interactive method executed by the call center server in a call center system that includes an operator work terminal and a call center server and provides a call center service to a customer terminal.
To the computer of the call center server
AI dialogue processing step to perform voice dialogue with customers by AI,
A call content analysis step that analyzes the call content based on the customer's call voice,
A complaint detection processing step that detects a complaint state or a complaint reserve force state based on the analysis result of the call content analysis step, and
If the detection result of the complaint detection processing step is a complaint state, a step of switching from the AI dialogue by the AI dialogue processing step to the operator dialogue in which the operator of the operator work terminal performs a voice dialogue with the customer,
If the detection result of the complaint detection processing step is the complaint reserve army state, the step of switching from the AI dialogue to the operator dialogue only when the customer switching request information is acquired from the customer terminal.
A program characterized by executing.

Images