JP2020187309A - Handling support device and handling support method - Google Patents

Abstract

To provide a handling support device and a handling support method for supporting operator's handling at a call center.SOLUTION: A handling support device includes: a voice acquisition unit 10 that acquires voice data of a current question response record; a storage unit 20 that stores determination data for use in escalation determination; a determination unit 30 that determines whether or not to perform escalation based on the voice data and the determination data in accordance with a predetermined first criterion and a second criterion different from the first criterion; and a display 40 that displays a determination result obtained by the determination unit.SELECTED DRAWING: Figure 2

Description

The present invention relates to a response support device and a response support method.

Conventionally, support systems for call center operators are known (see, for example, Patent Documents 1 and 2).
Patent Document 1 Japanese Patent Application Laid-Open No. 2010-109895 Patent Document 2 Japanese Patent Application Laid-Open No. 2012-120120

However, in the conventional support system, the operator of the primary reception must actively escalate (for example, Patent Document 1). Further, in the conventional support system, only pre-registered customers can escalate (for example, Patent Document 2).

In the first aspect of the present invention, a voice acquisition unit that acquires voice data of the current question answering record, a storage unit that stores determination data used for escalation determination, and a predetermined first determination criterion. , A determination unit that determines whether or not escalation should be performed based on voice data and determination data according to a second determination criterion different from the first determination criterion, and a display unit that displays the determination result by the determination unit. Provide a response support device to prepare.

The voice acquisition unit may include a text acquisition unit that acquires text data obtained by voice-recognizing the current question-and-answer record from the voice data, and a summary unit that generates a summary sentence that extracts the main points from the text data.

The storage unit may store the registered sentence as the determination data. The determination unit may calculate the similarity between the summary sentence and the registered sentence, and determine that the escalation should be performed when the similarity exceeds a predetermined determination threshold value.

The storage unit may store the registered word as the determination data. The determination unit may determine that the escalation should be performed when the frequency of appearance of the registered word exceeds a predetermined determination threshold value.

The voice acquisition unit may include a voice analysis unit that analyzes voice data and acquires voice information including voice volume and pitch. The determination unit may determine whether or not to escalate using at least one of the amount of change in voice volume and the amount of change in pitch as a determination criterion.

The voice acquisition unit may include a time information acquisition unit that analyzes voice data and acquires time information including conversation elapsed time and silence time. The determination unit may determine whether or not to escalate using at least one of the conversation elapsed time and the silence time as a determination criterion.

In the second aspect of the present invention, a step of acquiring voice data of the current question answering record, a step of storing determination data used for escalation determination, a predetermined first determination criterion, and a first Provided is a response support method including a step of determining whether or not escalation should be performed based on voice data and determination data according to a second determination criterion different from the determination criterion, and a step of displaying the determination result of the determination.

The outline of the above invention does not list all the features of the present invention. Sub-combinations of these feature groups can also be inventions.

The outline of the configuration of the corresponding system 200 is shown. The outline of the configuration of the response support device 100 is shown. An example of the operation flowchart of the correspondence support device 100 is shown. Another example of the operation flowchart of the response support device 100 is shown. An example of the registration sentence stored in the storage unit 20 is shown. An example of the registered word stored in the storage unit 20 is shown. An example of the escalation destination stored in the storage unit 20 is shown. An example of the setting screen 42 for setting the escalation determination threshold value is shown. An example of the text data TD voice-recognized by the text acquisition unit 12 is shown. An example of screen display when displaying a summary sentence is shown. An example of the operation flowchart of the correspondence support device 100 is shown. An example of the operation flowchart of the correspondence support device 100 is shown. An example of the operation flowchart of the correspondence support device 100 is shown. An example of the presentation screen of the escalation destination candidate is shown. An example of the operation flowchart of the correspondence support device 100 is shown. An example of the display area 48 displayed by the escalation system is shown.

Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the inventions claimed in the claims. Also, not all combinations of features described in the embodiments are essential to the means of solving the invention.

FIG. 1 shows an outline of the configuration of the corresponding system 200. The response system 200 is a system for assisting the operator's response when the customer 210 makes an inquiry to the call center. In this example, the case where the corresponding system 200 has the primary reception 230 and the secondary reception 240 will be described, but the reception may have a tertiary reception or more.

The customer 210 contacts the operator of the primary reception 230 via the public switched telephone network 220 such as PSTN (Public Switched Telephone Network) and the private branch exchange 225 such as PBX (Private Branch eXchange).

The primary reception 230 has a telephone 232 and a reception terminal 234 used by the operator. The secondary reception 240 has a telephone 242 used by the operator and a reception terminal 244. The reception terminal 234 and the reception terminal 244 are connected to the server machine 270 via a LAN (Local Area Network) 260.

The response support device 100, which will be described later, assists the primary reception 230 and the secondary reception 240 in responding to the customer 210. The response support device 100 may be mounted on the server machine 270. The server machine 270 is, for example, a personal computer. The result executed by the server machine 270 is displayed on the reception terminal 234 or the reception terminal 244 via a network such as LAN 260.

The manager 250 manages the operations of the primary reception 230 and the secondary reception 240. In one example, the manager 250 manages the escalation work by the primary reception 230. The administrator 250 may manage the response records of the primary reception 230 and the secondary reception 240 by the management terminal 252. The secondary reception 240 may also serve as the administrator 250.

FIG. 2 shows an outline of the configuration of the response support device 100. The response support device 100 includes a voice acquisition unit 10, a storage unit 20, a determination unit 30, and a display unit 40.

The voice acquisition unit 10 acquires the voice data of the current question answering record. The voice acquisition unit 10 extracts information necessary for determining escalation and inputs it to the determination unit 30. The voice acquisition unit 10 includes a text acquisition unit 12, a summarization unit 14, a voice analysis unit 16, and a time information acquisition unit 18.

The question answering record is a record of conversations such as questions and answers between the customer 210 and the operator. The question answering record may be the question answering record of the primary reception 230 or the question answering record of the secondary reception 240. The current question answering record refers to the real-time question answering record in which the operator responds to the customer.

The text acquisition unit 12 acquires the text data TD from the input voice data. The text acquisition unit 12 of this example acquires the text data TD that voice-recognizes the current question answering record. The text acquisition unit 12 transmits the acquired text data TD of the current question answering record to the summarization unit 14.

The summary unit 14 generates a summary sentence in which the main points are extracted from the text data TD. Specific examples of the abstract will be described later. The summary unit 14 inputs the generated summary sentence to the determination unit 30.

The voice analysis unit 16 analyzes voice data and acquires voice information including voice volume and pitch. Voice information is not limited to voice volume and pitch. In one example, the voice information includes information related to the emotion of the customer or the operator among the voice data. The voice analysis unit 16 inputs the acquired voice information to the determination unit 30.

The time information acquisition unit 18 analyzes the voice data and acquires the time information. For example, time information includes at least one of conversation elapsed time and silence time. The conversation elapsed time is the elapsed time from the start of the conversation between the operator and the customer to the present. The elapsed conversation time may include the time between the customer calling the phone and connecting to the operator. The silence time is the silence time of the customer or operator. The silence time may be reset when the conversation is started, or it may be the total silence time accumulated during the conversation. The time information acquisition unit 18 inputs the acquired time information to the determination unit 30.

The storage unit 20 stores determination data and past question answering records as a master DB. The past question answering record may include the question answering record of both the primary reception 230 and the secondary reception 240. The past question answering record may be used for the escalation determination by the determination unit 30. The storage unit 20 may store advance information such as customer information as a master DB.

The determination data is information used for escalation determination. For example, the determination data includes a registered sentence and a registered word registered as an escalation target. The registration sentence is a sentence registered as an escalation target in the judgment data. The registration sentence may be registered assuming the summary sentence of the summary unit 14. For example, registered words are negative words such as "cannot", "absolutely", "can't help", "responsible person", and "compensation". Further, the registered word may be a word indicating a specific product such as a product name. The determination data may include an escalation destination corresponding to the registered sentence and the registered word.

The past question answering record is a question answering record when the operator responded to the customer in the past. The past question answering record may be the question answering record of the primary reception 230 or the question answering record of the secondary reception 240.

The determination unit 30 determines whether or not to escalate based on the voice data and the determination data according to a plurality of determination criteria. For example, the determination unit 30 calculates the similarity between the summary sentence and the registered sentence, and determines that the similarity should be escalated when the similarity exceeds a predetermined determination threshold value. Further, the determination unit 30 may determine that the escalation should be performed when the frequency of appearance of the registered words exceeds a predetermined determination threshold value. In this case, the first criterion is the similarity between the summary sentence and the registered sentence, and the second criterion is the frequency of appearance of the registered word. The determination unit 30 may determine whether or not to escalate using three or more determination criteria.

Further, the determination unit 30 may determine whether or not to escalate using at least one of the amount of change in voice volume and the amount of change in pitch as a determination criterion. The determination unit 30 may determine whether or not to escalate using at least one of the conversation elapsed time and the silence time as a determination criterion. The specific determination method will be described later. The determination unit 30 transmits the determination result to the display unit 40. Further, the determination unit 30 may transmit the text data TD from the text acquisition unit 12 as it is to the display unit 40 in real time.

The display unit 40 displays the determination result determined by the determination unit 30. For example, the display unit 40 highlights the determination result by adding a color or an animation such as blinking. Further, the display unit 40 may gradually emphasize the display of the escalation according to the promotion level of the escalation. In one example, the display unit 40 displays an indicator indicating whether or not the determination threshold value has been exceeded, and visually conveys to the operator that the determination threshold value has been exceeded and the amount that has been exceeded.

Further, the display unit 40 may display the text data TD acquired by the text acquisition unit 12 as it is. That is, the display unit 40 may display the current question answering record between the customer 210 and the operator in real time. The display unit 40 may display both the text data TD of the current question answering record and the determination result. The display unit 40 may have a display for displaying the information, or may display the information on an external terminal such as the reception terminal 234 and the reception terminal 244.

The response support device 100 of this example determines whether or not to escalate based on the contents of the current question answering record. The response support device 100 prompts the operator to escalate when it should be escalated. Therefore, it is possible to reduce the time loss caused by the operator responding too much despite the content beyond his / her own answer range. Then, even an inexperienced operator who cannot actively judge escalation can easily judge escalation. Improving escalation decisions can reduce the risk of a bad customer impression. In this way, the response support device 100 can smoothly escalate and take over by the operator.

Further, since the response support device 100 of this example determines whether or not to escalate based on the real-time conversation information, it is not necessary to register the customer information in advance. Therefore, the response support device 100 can respond to new customers in the same manner as existing customers.

FIG. 3A shows an example of an operation flowchart of the response support device 100. The response support device 100 promotes the escalation of the operator by executing steps S10 to S22.

In step S10, the storage unit 20 stores the determination data and the past question answering record as the master DB. In step S12, the escalation determination threshold is set. The determination threshold may be set by the administrator instead of the user. The past question answering record may be handled by the operator of the primary reception 230 or by the operator of the secondary reception 240.

In step S14, the text acquisition unit 12 acquires voice data and acquires text data TD from the voice data. For example, the text acquisition unit 12 creates text data TD by voice-recognizing the response record between the customer 210 and the operator in real time. The text acquisition unit 12 of this example creates the text data TD of the reception record of the primary reception 230.

In step S16, a summary sentence extracted from the main points of the text data TD is generated. In step S18, the summary sentence and the registration sentence are compared to determine whether or not to escalate. In step S20, the determination result is displayed. As a result, the operator is encouraged to escalate by the result automatically determined by the system. In step S22, escalation is performed according to the displayed determination result. The operator does not have to escalate if it determines that escalation is unnecessary.

FIG. 3B shows another example of the operation flowchart of the response support device 100. Step S14, step S16 and step S20 correspond to each step in FIG. 3A. Steps S180 to S186 are specific examples of step S18 in FIG. 3A. The operation flowchart of this example is an example of the flowchart of escalation determination, and the method of escalation determination is not limited to this example.

In step S180, it is determined whether or not the similarity between the summary sentence and the registered sentence exceeds the determination threshold value. For example, the determination unit 30 calculates the degree of similarity using Doc2Vec. If the similarity exceeds the determination threshold value, the process proceeds to step S20, and if the similarity does not exceed the determination threshold value, the process proceeds to step S182.

In step S182, it is determined whether or not the appearance frequency of the negative word in the summary sentence exceeds the determination threshold value. For example, the frequency of occurrence of negative words includes the appearance rate and the number of occurrences of negative words. If the frequency of appearance exceeds the determination threshold value, the process proceeds to step S20, and if the frequency does not exceed the determination threshold value, the process proceeds to step S184.

In step S184, it is determined whether or not the amount of change in the voice exceeds the determination threshold value. For example, the amount of change in voice is the amount of change in voice volume, the amount of change in pitch of voice, and the amount of change in emotion. If the amount of change in voice exceeds the determination threshold value, the process proceeds to step S20, and if the change amount does not exceed the determination threshold value, the process proceeds to step S186.

In step S186, it is determined whether or not the conversation elapsed time and the silence time exceed the determination threshold value. If the conversation elapsed time and the silence time exceed the determination threshold value, the process proceeds to step S20. If the conversation elapsed time and the silence time do not exceed the determination threshold value, the process returns to step S14. Step S20 and step S22 correspond to steps S20 and S22 of FIG. 3A.

In the operation flowchart of this example, it is determined whether or not the determination threshold value is exceeded in the order of steps S180 to S186, but the order is not limited to this. That is, after determining the appearance frequency in step S182, the similarity may be determined in step S180. Steps S180 to S186 may be executed in any order, and none of the steps may be executed.

FIG. 4A shows an example of a registered sentence stored in the storage unit 20. A registration number and an escalation destination are registered in each registration statement. In this example, the registration number is No. 1-No. 6 is set. In addition, reception A or reception B are set as escalation destinations, respectively. When a conversation similar to the registered sentence is detected, the registered escalation destination is displayed to the operator.

For example, No. 1-No. 4 assumes a technical inquiry. For technical inquiries such as "inverter circuit", "converter circuit", "frequency change method" and "control method", the escalation destination is set to "reception A".

On the other hand, No. 5-No. 6 assumes a failure inquiry. The escalation destination is set to "Reception B" for failure inquiries such as "inverter stopped" and "wiring burned out".

FIG. 4B shows an example of the registered words stored in the storage unit 20. The registered word in this example is a negative word, but is not limited to this. The assumed speaker of each registered word is also registered, and when the assumed speaker speaks the registered word, it is determined to be a negative word. In this example, No. 1-No. 2 is supposed to be a remark for reception, and No. 4 to No. No. 5 assumes a statement for the customer, and No. 3 assumes remarks for both receptionists and customers. If there is no distinction between receptionist and customer remarks, all negative words may be registered as both receptionist and customer remarks.

For example, "I can't" and "Absolutely" are registered as negative words for reception. If the operator says "I can't" or "Absolutely", it is judged as a negative word.

On the other hand, "responsible person" and "compensation" are registered as negative words for customers. If the customer says "responsible" or "compensation", it is judged as a negative word. "I can't help" is registered as a negative word for reception and customers. If either the operator or the customer says "it can't be helped", it is judged as a negative word.

FIG. 4C shows an example of the escalation destination stored in the storage unit 20. In FIG. 4C, the priority when the operator name, telephone number, and negative word of the escalation destination exceed the determination threshold value is registered. In this example, three escalation destinations, "reception A", "reception B", and "reception C", are set.

The negative word priorities of "reception A", "reception B" and "reception C" are "3", "2" and "1", respectively. Therefore, when the negative word exceeds the determination threshold, escalation is preferentially proposed in the order of "reception C", "reception B", and "reception A". For example, if "reception C" is dealing with customers when the negative word exceeds the determination threshold, "reception B", which has the next highest priority, is proposed as the escalation destination.

FIG. 5 shows an example of the setting screen 42 for setting the escalation determination threshold value. This screen is presented when the administrator 250 accesses the server machine. When the operator of the secondary reception 240 has the administrator authority, the setting screen may be presented by accessing the server machine with the reception terminal 244.

Similarity is set as a determination threshold value in the "registration sentence". When the similarity between the summary sentence and the registered sentence exceeds the judgment threshold, it is judged that escalation should be performed. The similarity determination threshold is set between 0.000 and 1.000. When the similarity exceeds the set judgment threshold, the operator is prompted to escalate. That is, the closer to 1.000 is set as the similarity determination threshold, the less likely it is that escalation will be promoted. The similarity can be set individually for each customer and receptionist.

The appearance rate and the number of appearances are set in the "negative word". The "appearance rate" is the ratio of the number of characters in a negative word to the total number of characters in a conversation. The appearance rate is set between 0.0% and 100.0%. The smaller the appearance rate, the easier it is to promote escalation, and the higher the appearance rate, the higher the appearance rate is required until escalation is promoted.

"Number of appearances" indicates the number of appearances of negative words from the start of conversation. You will be prompted to escalate when the number of times set as the judgment threshold is exceeded. The smaller the number of appearances, the easier it is to promote escalation, and the larger the number of appearances, the larger the number of appearances required until escalation is promoted. The appearance rate and the number of appearances can be set individually for each customer and receptionist.

The determination unit 30 may make an escalation determination based on the amount of change in the appearance frequency of the negative word. The determination unit 30 determines that escalation should be performed when the amount of change in the appearance frequency of the negative word exceeds the determination threshold value. For example, the determination unit 30 calculates the amount of change in the appearance rate of the negative word by comparing the appearance rate of the negative word in the predetermined period with the appearance rate of the negative word in the next period. Further, the determination unit 30 calculates the amount of change in the number of appearances of the negative word by comparing the number of appearances of the negative word in the predetermined period with the number of appearances of the negative word in the next period. This makes it easier to promote escalation when the number of negative words increases rapidly. In one example, the determination unit 30 calculates the appearance frequency of the negative word in 1-minute units and acquires the amount of change in the appearance frequency every 1 minute.

The “change amount” indicates the change amount of the voice acquired by the voice acquisition unit 10. For example, the amount of change is the amount of change in voice volume and pitch. The amount of change in voice volume is set in dB. The amount of change in voice pitch is set in Hz. The amount of change in voice may be set by a moving average. The smaller the amount of change, the easier it is for escalation to be promoted, and the larger the amount of change, the larger the amount of change required until escalation is promoted.

In addition, the amount of change can be set individually for each customer and receptionist. The amount of change in the customer determines that it is an abnormal situation and encourages escalation when the voice becomes loud or loud. On the other hand, the amount of change in the reception desk determines that it is an abnormal situation and encourages escalation when the voice becomes quiet or low.

"Time information" includes conversation elapsed time and silence time. Silence time may be measured for each customer and receptionist. The determination threshold value of the time information may be set in seconds. The determination thresholds of this example are set to 600 seconds for the elapsed conversation time, 10 seconds for the silence time (customer), and 10 seconds for the silence time (reception). The determination unit 30 may make an escalation determination based only on the time information without making an escalation determination based on the registered sentence and the registered word.

The escalation determination threshold may be set for each operator. For example, an operator whose escalation judgment is slow is encouraged to escalate earlier by lowering the judgment threshold value than other operators. The determination threshold value for each operator may be set based on the operator's past response record, profile, and the like.

Further, the escalation determination threshold value may be changed for each customer using voice data. For example, the set value of the determination threshold value may be automatically changed according to the gender of the customer. The determination of the customer's gender is based on voice data. Further, the set value of the determination threshold value may be automatically changed according to the customer's pre-registration information.

FIG. 6 shows an example of the text data TD voice-recognized by the text acquisition unit 12. In this example, the display area 44 of the escalation system is displayed.

The display area 44 displays the text data TD. The text data TD of this example is an example of the voice converted into text data by the text acquisition unit 12 in step S14 of FIG. 3A. The figure is an example of a screen presented on the reception terminal 234 for the primary reception 230. All customer and operator responses are voice-recognized and converted into text in chronological order. In this example, the current question answering record of the primary reception 230 is displayed, but the current question answering record of the secondary reception 240 may be displayed.

In this example, in response to inquiries from customers, "The inverter suddenly stopped." And "I think it is out of order.", The primary receptionist 230 said, "Durability due to our repeated tests. The sex has been proven, so it will never break. " The current question answering record may not be displayed to the operator in charge, or may be displayed to the administrator 250.

FIG. 7 shows an example of screen display when displaying a summary sentence. In this example, the display area 44 and the display area 46 of the escalation system are displayed. The display area 44 has the same contents as the display area 44 of FIG. The figure is an example of a screen presented on the reception terminal 234 for the primary reception 230.

The display area 46 displays a summary sentence extracted from the text data TD. The summarization method is not particularly limited. For example, it may be a rule-based method of extracting when a registered keyword appears. In addition, a summary sentence may be extracted by using a model in which a correct example of the summary is trained. The display unit 40 may display only the display area 46 without displaying the display area 44.

FIG. 8 shows an example of an operation flowchart of the response support device 100. In this example, an example of determining whether or not the similarity between the summary sentence and the registered sentence exceeds the determination threshold value is shown. The method of calculating the similarity of sentences is not limited to the method of this example. The operation of this flowchart may be continued until the conversation ends.

In step S200, the registered sentence registered in the master DB is morphologically analyzed. In step S202, the morphologically analyzed word is converted into vector data. In step S204, the vector data for each sentence of all the sentences registered in the master DB is calculated. For example, when N sentences exist in the master DB, N vector data are calculated. In addition, only a part of the sentences registered in the master DB may be converted into vector data. In step S206, the vector data of the summary sentence of the current question answering record is calculated. The vector data of the summary sentence is calculated for each sentence.

In step S208, the degree of similarity between the vector data of the registered sentence and the vector data of the summary sentence is calculated. For example, the similarity is calculated by comparing the vector data of the summary sentence with each vector data of the registered sentence. In step S210, the calculated similarity and the set determination threshold value are compared. If the similarity exceeds the determination threshold value, the process proceeds to step S20. If the similarity does not exceed the determination threshold value, the process returns to step S206. In step S20, the determination result is displayed. In step S22, escalation is performed according to the displayed determination result. Whether or not to escalate may be finally decided by the operator.

FIG. 9 shows an example of an operation flowchart of the response support device 100. In this example, an example of determining whether or not the frequency of appearance of registered words exceeds the determination threshold is shown. The operation of this flowchart may be continued until the conversation ends.

In step S300, the words registered in the master DB are converted into vector data. In step S302, the text data TD of the current question answering record is morphologically analyzed. In step S304, the morphologically analyzed word is converted into vector data. In step S306, words having a high degree of similarity are extracted from the vector data of the registered words and the vector data of the words in the text data TD. If there are exact matching words, only those with a similarity of 1 may be extracted.

In step S308, the appearance frequency (for example, the appearance rate and the number of occurrences) of the registered word is calculated. The registered word for which the frequency of occurrence is calculated is a word extracted as having a high degree of similarity in step S306. In step S310, the appearance rate of the registered word is compared with the set determination threshold value. If the appearance rate of the registered word exceeds the determination threshold value, the process proceeds to step S20. If the appearance rate of the registered word does not exceed the determination threshold value, the process proceeds to step S312.

In step S312, the number of occurrences of the registered word is compared with the set determination threshold value. The number of occurrences of the registered word is compared with the set judgment threshold. If the number of appearances of the registered word exceeds the determination threshold value, the process proceeds to step S20. As described above, in this example, when either the appearance rate or the number of appearances exceeds the determination threshold value, the process proceeds to step S20. If the number of occurrences of the registered word does not exceed the determination threshold value, the process returns to step S304. Step S20 and step S22 correspond to steps S20 and S22 of FIG. 3A.

FIG. 10 shows an example of an operation flowchart of the response support device 100. In this example, an example of determining the necessity of escalation based on the amount of change in voice is shown. The voice includes conversation-based information such as voice volume and pitch. The method for quantifying the amount of change in voice is not limited to the method of this example. The operation of this flowchart may be continued until the conversation ends.

In step S400, the instantaneous value of voice is measured every predetermined measurement period. For example, the voice analysis unit 16 measures the instantaneous value of voice every minute. The instantaneous value of voice includes an instantaneous value such as voice volume and pitch at each time. In step S402, the moving average of the instantaneous value of the voice is calculated when the measurement period has elapsed. By calculating the moving average, it becomes easier to understand the transition of changes in voice. The instantaneous value of the voice for each measurement period is not limited to the moving average method, and may be calculated by another calculation method such as an arithmetic mean.

In step S404, the difference between the previous and current moving average values is calculated. The previous moving average is the moving average of the measurement period immediately before the current measurement period. In step S406, the amount of change in voice is calculated from the difference between the values of the moving averages of the previous time and the current time. In step S408, the amount of change in voice is compared with the set determination threshold value. If the amount of change in voice exceeds the determination threshold value, the process proceeds to step S20. If the amount of change in voice does not exceed the determination threshold value, the process returns to step S402. Step S20 and step S22 correspond to steps S20 and S22 of FIG. 3A.

FIG. 11 shows an example of an escalation destination candidate presentation screen. In this example, a screen example is shown when the operator of the primary reception 230 is urged to escalate.

The summary sentence of this example includes the sentence "The inverter suddenly stopped". The text is No. 1 of the master DB. It is similar to the sentence "Inverter has stopped" registered in 5. When the similarity exceeds the set determination threshold, the registered operator "reception B" is presented. The operator of the primary reception 230 confirms the presented contents and escalate.

On the other hand, even if the sentence "Inverter has stopped" is not registered in the master DB, the registered word "absolutely" exists in the master DB, and the negative word appears once and the judgment threshold is set. If it has been set, escalation will be prompted. The display unit 40 displays on the screen the "reception C", which is the operator having the highest priority in FIG. 4C, as the escalation destination. The display unit 40 may display the telephone number of the escalation destination in the display area 46. This encourages operator escalation.

Further, the display unit 40 may highlight the fact that the escalation should be performed when the operator does not escalate after presenting the escalation destination. For example, the display unit 40 highlights the escalation destination when the conversation between the customer and the operator continues even after a lapse of a predetermined time after the presentation of the escalation. Further, the display unit 40 may highlight that the escalation should be performed when the value equal to or higher than the determination threshold value continues. The highlighting may be an alert such as a color change or blinking. The display unit 40 may display a warning message to the effect that it should be escalated. In addition, the administrator 250 may be notified by e-mail that the escalation should be performed.

FIG. 12 shows an example of an operation flowchart of the response support device 100. The response support device 100 may store the determination data and set the determination threshold value in advance according to steps S10 and S12 of FIG. 3A. In this example, an example of an operation flowchart for determining whether or not to escalate based on a plurality of determination criteria is shown. The criteria for escalation include four types: sentence similarity, frequency of negative word appearance, amount of change in voice, and conversation time. Encourage escalation when multiple criteria are met at the same time. The response support device 100 of this example prompts escalation when two or more determination criteria are satisfied, but may promote escalation when three or more or four or more determination criteria are satisfied.

In step S500, the text data TD that voice-recognizes the current question answering record is acquired. In step S502, a summary sentence extracted from the main points of the text data TD is generated. In step S504, as the determination criterion 1, it is determined whether or not the similarity between the summary sentence and the registered sentence exceeds the determination threshold value. In step S506, as the determination criterion 2, it is determined whether or not the number of occurrences of the negative word in the response content exceeds the determination threshold. In step S508, as the determination criterion 3, it is determined whether or not the amount of change in the voice exceeds the determination threshold. In step S510, as the determination criterion 4, it is determined whether or not the conversation elapsed time and the silence time exceed the determination threshold value.

In step S512, it is determined whether or not two or more of the determination criteria 1 to 4 exceed the determination threshold value. If two or more types exceed the determination threshold value, the process proceeds to step S20. In step S22, escalation is performed according to the displayed determination result. If two or more types do not exceed the determination threshold value, the process returns to step S500. The content and number of judgment criteria are not limited to this example. Further, the order of determining whether or not the determination threshold has been exceeded is not limited to this example. These steps may be modified as appropriate depending on the circumstances in which they are applied.

FIG. 13 shows an example of the display area 48 displayed by the escalation system. The display area 48 shows the reason for escalation. The display area 48 of this example may be displayed at the same time as the display area 44 and the display area 46 shown in FIG.

The display area 48 displays the reason why it is determined that the escalation should be performed in time series. The display area 48 may display the reason for escalation in real time. By displaying the reason for the judgment, it can be used as a judgment material for escalation by the operator. “Target” indicates either “reception” or “customer”. “Judgment criteria” indicates the specific contents of the criteria for which the escalation judgment has been made. For example, the "judgment criterion" includes "the appearance rate of negative words" and "the number of occurrences of negative words". The "judgment threshold value" indicates a judgment threshold value when it is determined that escalation should be performed. A "detailed link" is a link to a more specific reason that has been determined to be escalated. The display area 50 can be displayed by pressing the detail link button.

The display area 50 shows the appearance rate for each word. In this example, the appearance rates of the negative words "I can't", "Absolutely", and "I can't help" are displayed as 20%, 10%, and 0%, respectively. In this way, when the operator wants to know the details of the reason for escalation, he / she can know more specific contents by clicking the detail link. The response support device 100 can improve the work of the operator by feeding back the negative word used by the operator to the operator.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various changes or improvements can be made to the above embodiments. It is clear from the description of the claims that such modified or improved forms may also be included in the technical scope of the present invention.

The order of execution of operations, procedures, steps, steps, etc. in the devices, systems, programs, and methods shown in the claims, specification, and drawings is particularly "before" and "prior to". It should be noted that it can be realized in any order unless the output of the previous process is used in the subsequent process. Even if the scope of claims, the specification, and the operation flow in the drawings are explained using "first," "next," etc. for convenience, it means that it is essential to carry out in this order. It's not a thing.

10 ... Voice acquisition unit, 12 ... Text acquisition unit, 14 ... Summary unit, 16 ... Voice analysis unit, 18 ... Time information acquisition unit, 20 ... Storage unit, 30 ... Judgment unit, 40 ... Display unit, 42 ... Setting screen, 44 ... Display area, 46 ... Display area, 48 ... Display area, 50 ... Display area, 100 ... Correspondence support device, 200 ... Correspondence system, 210 ... Customer, 220 ... Public switched telephone network, 225 ... Private branch exchange, ... 230 ... Primary reception, 232 ... Telephone, 234 ... reception terminal, 240 ... secondary reception, 242 ... telephone, 244 ... reception terminal, 250 ... administrator, 252 ... management terminal, 260 ... LAN, 270 ... Server machine

Claims (7)

The voice acquisition unit that acquires the voice data of the current question answering record,
A storage unit that stores judgment data used for escalation judgment,
A determination unit that determines whether or not to escalate based on the voice data and the determination data according to a predetermined first determination criterion and a second determination criterion different from the first determination criterion. ,
A corresponding support device including a display unit that displays a determination result by the determination unit. The voice acquisition unit
A text acquisition unit that acquires text data obtained by voice-recognizing the current question answering record from the voice data,
The response support device according to claim 1, further comprising a summary unit that generates a summary sentence that extracts the main points from the text data. The storage unit stores a registration sentence as the determination data, and stores the registration statement.
The response support according to claim 2, wherein the determination unit calculates the similarity between the summary sentence and the registration sentence, and determines that the similarity should be escalated when the similarity exceeds a predetermined determination threshold value. apparatus. The storage unit stores the registered word as the determination data, and stores the registered word.
The response support device according to any one of claims 1 to 3, wherein the determination unit determines that escalation should be performed when the frequency of appearance of the registered word exceeds a predetermined determination threshold value. The voice acquisition unit includes a voice analysis unit that analyzes the voice data and acquires voice information including voice volume and pitch.
The response support device according to any one of claims 1 to 4, wherein the determination unit determines whether or not escalation should be performed using at least one of the change amount of the voice volume and the change amount of the pitch as a determination criterion. The voice acquisition unit includes a time information acquisition unit that analyzes the voice data and acquires time information including a conversation elapsed time and a silence time.
The response support device according to any one of claims 1 to 5, wherein the determination unit determines whether or not to escalate using at least one of the conversation elapsed time and the silence time as a determination criterion. Steps to get the voice data of the current question answering record,
A step to store the judgment data used for escalation judgment, and
A step of determining whether or not to escalate based on the voice data and the determination data according to a predetermined first determination criterion and a second determination criterion different from the first determination criterion.
A response support method including a step of displaying a judgment result based on the judgment.

Images