JP2009175336A - Database system of call center, and its information management method and information management program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide the database system of call center capable of performing multilateral data analysis, and its information management method and information management program. <P>SOLUTION: The call center system 1 includes: a speech recognition device 11 which performs speech recognition on communication speech when an operator communicates with a customer, and which creates a text data by changing a communication content into characters; a feeling recognition device 14 which detects the featured value of speech of a section to be recognized in the communication speech, creates a feeling detection value in which feeling of a speaker is guessed on the basis of the featured value, and correlates the feeling detection value of the section to be recognized with the text data corresponding to the section to be recognized; and a D/B management device 12 in which the text data and the feeling detection value are stored in a state they are correlated with each other. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a call center database system, an information management method thereof, and an information management program.

The call center is a department that specializes in telephone answering operations such as inquiries about products from customers and receiving orders for products. Generally, a call center system includes a private branch exchange (PBX, Private Branch eXchange, automatic call distribution (AC).
D Automatic Call Distribution) device, a terminal used by an operator, and various databases (see, for example, Patent Document 1). Conventionally, in this call center, the operator inputs the contents of the telephone response to the terminal, and the response history information input to the terminal is accumulated in a database. The call center management department analyzed this response history information and used it for product improvement or service improvement.
JP 2007-228273 A

  However, with conventional databases, it has been difficult to analyze, for example, customer satisfaction and operator response from various angles. In addition, even if the operator inputs a keyword or the like of the call content to the terminal in order to analyze the call content, the operator's subjectivity has entered and it has been difficult to objectively evaluate the call content.

  The present invention has been made in view of the above problems, and an object of the present invention is to provide a call center database system, an information management method thereof, and an information management program capable of performing multifaceted data analysis.

  The present invention provides voice recognition means for performing voice recognition on a call voice when a call center operator and a customer make a call, and generating character data obtained by characterizing the call contents; voice of a target section of the call voice; Detecting a feature quantity and associating the emotion detection information of the target section with emotion detection means for generating emotion detection information inferring a speaker's emotion based on the feature quantity and the character data corresponding to the target section Registration means and call information storage means for storing the character data and the emotion detection information in association with each other.

  According to this invention, the character data generated by voice recognition of the call between the operator and the customer is stored in the call information storage means in a state in which the emotion detection information obtained from the feature amount of the call voice is associated with the character data. To do. Accordingly, since the emotion detection information of the speaker and the character data of the target section in which the information is detected can be stored in the database, a multifaceted data analysis can be performed. For this reason, the freedom degree of data analysis can be improved.

In this call center database system, the voice recognition means performs voice recognition on at least the customer's call voice and the operator's call voice, and based on the character data based on the customer's utterance and the operator's utterance. The character data is generated, and the emotion detection means detects the emotion detection information of the target section of the call voice of the customer and the emotion detection information of the target section of the call voice of the operator, and the registration The means associates the emotion detection information of the customer detected in the target section with the character data corresponding to the target section based on the call voice of the customer, and the target based on the call voice of the operator The emotion detection of the operator detected in the target section in the character data corresponding to the section Associate the broadcast.

  According to the present invention, since the emotion detection information of the customer and the operator can be associated with the character data based on the utterances of the customer and the operator, data analysis can be performed from both the customer side and the operator side. For this reason, multilateral data analysis can be performed.

  In this call center database system, the voice recognition means generates the character data obtained by performing voice recognition on both call voices in which the customer call voice and the operator call voice are mixed, and the emotion detection means includes The emotion detection information is generated on the basis of the two call voices, and the registration means associates the emotion detection information of the target section with the character data corresponding to the target section.

  According to the present invention, since the emotion detection information in the entire call by both can be associated with the character data based on the call voice of both, it is possible to perform overall data analysis.

  In this call center database system, the emotion detection means detects a plurality of the emotion detection information from the start to the end of a call, and the registration means uses the emotion detection information as the emotion detection information. Each of the detected character data is associated with the target section.

  According to this invention, a plurality of emotion detection information is associated with each target section of character data. For this reason, since the emotion detection information can be associated in units of words, phrases, or sentences, it is possible to improve the degree of freedom of data analysis, such as extracting words, phrases, or sentences that have strong emotions.

  The call center database system further includes reception history registration means for storing reception history data indicating the contents of reception with a customer in the call information storage means in association with the emotion detection data and the character data.

According to this invention, since the response history data is stored in association with the emotion detection data and the character data, for example, data analysis can be performed for each product for which an inquiry has been made.
The present invention is the information management method for the database using the control means for managing the database, wherein the control means performs voice recognition on a call voice when a call is made between a call center operator and a customer, Obtaining character data obtained by characterizing, detecting a feature amount of speech in a target section of call speech, obtaining emotion detection information inferring a speaker's emotion based on the feature amount, and the target Storing the emotion detection information of the target section in association with the character data corresponding to the section in the call information storage means.

  According to this method, the character data generated by voice recognition of the call between the operator and the customer is stored in the call information storage means in a state in which the emotion detection information obtained from the feature amount of the call voice is associated. To do. Accordingly, since the emotion detection information of the speaker and the character data of the target section in which the information is detected can be stored in the database, a multifaceted data analysis can be performed. For this reason, the freedom degree of data analysis can be improved.

The present invention is an information management program for the database using a control means for managing a database, wherein the control means performs voice recognition on a call voice when a call center operator and a customer make a call, Character data acquisition means for acquiring character data obtained by characterizing the character, and detection data for detecting the feature amount of the voice of the target section of the call voice and generating emotion detection information inferring the emotion of the speaker based on the feature amount The acquisition means and the character data corresponding to the target section are associated with the emotion detection information of the target section and function as registration means for storing in the call information storage means.

  According to the present invention, in accordance with the information management program, a call is made in a state in which character data generated by voice recognition of a call between an operator and a customer is associated with emotion detection information obtained from the feature amount of the call voice. Store in the information storage means. Accordingly, since the emotion detection information of the speaker and the character data of the target section in which the information is detected can be stored in the database, a multifaceted data analysis can be performed. For this reason, the freedom degree of data analysis can be improved.

Hereinafter, an embodiment embodying the present invention will be described with reference to FIGS. FIG. 1 is a schematic diagram of a call center system 1 as a database system.
The call center system 1 includes a PBX device 5, an operator terminal 6, a center management device 7, and an administrator terminal 8. The PBX device 5, the center management device 7, and the terminals 6 and 8 are connected via a LAN (Local Area Network) 9 so that various data can be transmitted and received.

  The PBX device 5 is connected to a customer's telephone (hereinafter referred to as customer telephone 2) via a public telephone line network N1. The PBX device 5 is connected to each telephone 3 used by the operator. The operation unit of each telephone 3 is provided with a login button B1, a hold button B2, and a preparing button B3. The login button B1 is a button for receiving an incoming call on the telephone 3. The hold button B2 is a button for holding the currently connected telephone, and the preparation button B3 is turned on when preparation for telephone reception is being made.

  The operator terminal 6 includes a CPU, a RAM, a ROM, a communication I / F, and the like, and a plurality of operator terminals 6 are connected to the LAN 9. The operator terminal 6 is connected to an input device I such as a mouse and a keyboard and a display DI. The operator operates the input device I while talking to the customer using a headset (not shown) that receives the voice from the telephone 3 and inputs the call voice of the operator.

  The center management device 7 has a CTI (Computer Telephony Integration) function for connecting the telephone 3 to the call center system 1 and is a server that processes incoming calls to the call center and outgoing calls from the call center. Specifically, the center management device 7 has an ACD function and an IVR (voice automatic response interactive voice response) function, and controls the PBX device 5. The ACD function is a function for automatically allocating a call to a call center to a waiting operator. The IVR function is a voice automatic response function.

  The center management device 7 has a customer information storage unit (not shown). The customer information stored in the customer information storage unit is information related to a customer who has called the call center in the past or information related to a customer registered in advance. The center management device 7 reads the corresponding customer information on the display DI of the operator terminal 6 based on the customer identification data such as the name entered by the operator's operation or the customer identification data inputted via the customer telephone 2. indicate.

The center management device 7 includes a history information storage unit 20 shown in FIG. The history information storage unit 20 stores history data 21 for each incoming call. The history data 21 is data generated by the center management device 7 for each incoming call, and indicates a history of reception. In the present embodiment, the history data 21 includes an incoming call ID 21A, an incoming call date 21B, a call start time 21C, a call end time 21D, an operator ID 21E, a product group 21F, a product model number 21G, a customer ID 21H, and a hold history 21J. Yes. The data configuration of the history data 21 is not limited to this configuration, and other configurations may be used.

  The incoming call ID 21A is a number assigned by the center management device 7 for each incoming call, and the incoming call date 21B indicates the date and time when the call center received a call from the customer. The call start time 21C and the call end time 21D indicate the time when the operator started and ended the call, respectively. The operator ID 21E is an identification number of the operator who has received the call.

  The product group 21F is a category of a product for which an inquiry has been made. For example, when inquiring about electrical appliances such as printers, projectors, and scanners, the product group 21F includes product categories such as “inkjet printer” and “laser printer”, or “for individuals” or “for business”. A category for each purpose is stored. The product model number 21G indicates the model number of the product for which an inquiry has been made. When accepting an order for a product, the group and model number of the ordered product are stored in the product group 21F and the product model number 21G. When a call is made from a call center to a customer, service and product identifiers corresponding to the contents of the call are stored.

The customer ID 21H is an identifier of the customer who has responded, and corresponds to the customer information. The hold history 21J is data such as the number of hold times, the hold time from the hold start to the hold end.
The administrator terminal 8 is a terminal used by a call center supervisor or the like, and has a CPU, a RAM, a ROM, a communication I / F, etc. (not shown). As shown in FIG. 1, an input device I such as a mouse or a keyboard is connected to the administrator terminal 8, and designated information is transferred to the history information storage unit 20 and other information according to an input operation of the supervisor. Extracted from the database, and the extracted data is displayed on the display DI as a browsing screen.

  Further, as shown in FIG. 1, the call center system 1 includes a voice data registration device 10, a voice recognition device 11 as voice recognition means, a call information storage means, a control means, character data acquisition means, and a database as detection data acquisition means. (D / B) It has the management apparatus 12, the recording device 13, the emotion detection means, and the emotion recognition apparatus 14 as a registration means. Each of these devices 10 to 14 is connected to the LAN 9 so that data for processing to be described later can be transmitted and received not only between the devices 10 to 14 but also with the PBX device 5, the center management device 7, and the like. It is connected. In the present embodiment, the devices 10 to 14 are provided to distribute the processing. However, a plurality of devices among the devices 10 to 14 are integrated into one device, or all the devices 10 to 14 are integrated into one device. It may be a device.

  As shown in FIG. 3, the voice data registration device 10 includes a control unit 30, an overall voice storage unit 32, a customer voice storage unit 33, and an operator voice storage unit 34. The control unit 30 includes a CPU, a RAM, a ROM, a communication I / F, and the like, and acquires an audio signal based only on the customer's utterance from the PBX device 5 or the telephone 3 used by the operator. Further, a voice signal based only on the operator's utterance is acquired from the voice input unit IV (see FIG. 1) such as the telephone 3 or the microphone of the headset. Further, from the PBX device 5, the telephone 3, or the voice input unit IV, the voice signal of both call voices in which the voices of the customer's speech and the voices of the operator are mixed is acquired.

When the control unit 30 acquires a voice signal based only on the customer's utterance, a voice signal based only on the operator's utterance, and a voice signal in which both voices are mixed, the control unit 30 converts the voice signal into digital data such as WAV format. To do. Note that the conversion to audio data may be performed by real time processing or batch processing. Alternatively, the voice of only the customer's utterance, the voice of only the operator's utterance, and the voice of both utterances are recorded in the recording device 13 or the center management device 7 (see FIG. 1), respectively, and the recording device 13 performs A / D. Conversion may be performed to obtain audio data from the recording device 13.

  When the voice data is generated, the control unit 30 assigns the identifier generated for each incoming call to the voice data. The identifier is data serving as a primary key for uniquely identifying a record in the database from other records, and the voice data and the history data 21 can be associated with each other using data elements constituting the history data 21 such as the incoming call ID 21A. To make sure In addition, a speaker code indicating which speaker is the data among the customer, the operator, and both is added to each voice data. And the audio | voice data to which the identifier and the speaker code | symbol were provided are each memorize | stored in each corresponding memory | storage parts 32-34.

  As a result, the entire voice storage unit 32 stores the entire voice data 32A based on the utterances of the customer and the operator, and the customer voice storage unit 33 stores the customer voice data 33A based only on the utterances of the customer. In addition, operator voice data 34 A is stored in the operator voice storage unit 34.

  As shown in FIG. 4, the voice recognition device 16 includes a voice recognition processing unit 41, a recognition information storage unit 42, a utterance information storage unit 43, a customer utterance information storage unit 44, and an operator utterance information storage unit 45. .

  The voice recognition processing unit 41 stores a CPU, RAM, ROM, communication I / F, and the like, and performs voice recognition processing according to a voice recognition program stored in a storage unit (not shown). The voice recognition process may be a real-time process that is sequentially performed during a call or the like, or may be a batch process that is collectively performed on a plurality of voice data. The recognition information storage unit 42 stores recognition information 42A used for voice recognition processing. As the recognition information 42A, for example, an acoustic model in which a feature amount of speech and a phoneme are associated, a recognition dictionary in which tens of thousands to hundreds of thousands of words associated with a phoneme string are stored, a probability of being located at the beginning / end of a sentence In addition, there are various data such as a connection probability between consecutive words and a language model modeling a dependency relationship.

  The speech recognition processing unit 41 converts each of the speech data 32A to 34A into character data using the recognition information 42A in accordance with a speech recognition program. A known method can be used for this treatment. For example, the speech recognition processing unit 41 uses the speech data 32 </ b> A to 34 </ b> A to calculate features of speech waveforms, collates this feature amount with an acoustic model, and selects phonemes. Also, each phoneme string and the recognition dictionary are collated to select a recognition candidate word. Further, the speech recognition processing unit 41 calculates a connection relation probability using a language model, and determines consistency. When the recognition result is confirmed, the text is stored in association with the time when the text is spoken.

  Further, as shown in FIG. 5, the speech recognition processing unit 41 assigns the identifier C1 and the speaker code C2 to the text TXT in which the content of the call is converted into text as text data, similarly to the speech data. Data TX is generated. Further, the generated text data TX is stored in each of the storage units 43 to 45.

That is, the character data obtained by voice recognition of the entire voice data 32A based on the utterances of the customer and the operator is stored in the utterance information storage unit 43 as the both text data TX1. Both pieces of text data TX1 are converted into character data in a state where contents uttered by the customer and the operator are mixed. The character data obtained by voice recognition of the customer voice data 33A based only on the customer utterance is stored in the customer utterance information storage unit 44 as customer text data TX2. Character data obtained by voice recognition of the operator voice data 34A is stored in the operator utterance information storage unit 45 as operator text data TX3. In addition, when not distinguishing both text data TX1, customer text data TX2, and operator text data TX3, it demonstrates as text data TX.

  The emotion recognition device 14 includes a CPU, a RAM, a ROM, a communication I / F, and the like, and calculates an emotion detection value obtained from the feature amount of the call voice according to an emotion recognition program stored in a storage unit (not shown). The emotion recognition device 14 performs emotion recognition based on call voice in which customer and operator voices are mixed, emotion recognition based on customer call voice, and emotion recognition based on operator call voice. The emotion recognition process may be a real-time process that is sequentially performed at the end of a call or the like, or a batch process that is collectively performed on a plurality of voice data. In this emotion recognition process, a value indicating the strength of emotion is specified for each type of emotion such as “anger”, “joy”, and “sadness”.

  A known method can be used as the emotion recognition method. For example, the emotion recognition device 14 acquires the sound intensity based on the sound data 32A to 34A (or sound signal) of the customer, the operator, or both.

  In addition, the emotion recognition device 14 acquires a recognition target section for emotion recognition. This recognition target section may be a section of words, phrases or sentences of the text data TX, or may be a section divided every predetermined time such as 5 seconds. Or based on the waveform of audio | voice data 32A-34A, it is good also considering the area containing a predetermined pattern as a recognition object area. Then, the sound intensity for each recognition target section is detected, and the sound inflection is calculated based on the intensity change pattern.

  Furthermore, the phoneme data calculated by the speech recognition processing unit 41 and the like is acquired, and the number of phonemes is acquired as the tempo. In addition, physical feature quantities of speech such as scale, pitch, melody, frequency, etc. may be detected.

  The emotion recognition device 14 stores in advance a voice characteristic pattern in an angry state, a voice characteristic pattern in a joyful state, a voice characteristic pattern in a sadness state, and the like. The emotion recognition device 14 compares the pattern based on each audio signal with a previously stored pattern, and specifies the current emotion strength. For example, the values “−2”, “−1”, “0”, “+1”, and “+2” are set for the emotions of “anger”, “joy”, and “sadness”, respectively. The device 14 identifies any of these values as emotional strength.

  As a result, the emotion detection value V1 for the customer utterance, the emotion detection value V2 for the operator utterance, and the emotion detection value V3 for the entire utterance mixed with the customer and operator utterances are obtained. When the emotion detection values V1 and V2 and the emotion detection values V3 are described without being distinguished from each other, they are simply described as the emotion detection value V.

  When the emotion detection value V is generated, the emotion recognition device 14 generates emotion detection data D schematically shown in FIG. 5 using the emotion detection value V and the recognition target section on which emotion recognition has been performed. The emotion detection data D is given an identifier C1 like the text data TX. The emotion detection data D is given a speaker code C2 indicating which speaker is the emotion. Further, an emotion type C3 indicating which type of data among the types such as “anger”, “sadness”, “joy” is given to the emotion detection data D. The emotion detection value V included in the emotion detection data D is associated with the recognition target section S where the value is detected.

Therefore, as shown in FIG. 5, the emotion detection data D and the text data TX can be associated with each other by the identifier C1 and the speaker code C2. Further, since the characters included in the text TXT of the text data TX correspond to the recognition target section S of each emotion detection value V1, the emotion detection value V for “anger”, “joy”, “sadness”, and the like, It can be associated with character data such as words, phrases or sentences. For example, if the customer's anger is “+2” for the character data that the customer uttered “an error has occurred”, the customer feels a strong anger for the error. Can be estimated. On the other hand, when a different customer speaks that “an error has occurred” and the feeling of “anger” is “0”, the customer does not feel too angry that the error has occurred. Can be estimated. Further, it is possible to determine how the emotion of the customer has changed by determining the time-series transition of the emotion detection value V from the start to the end of the call.

  In addition, the emotion recognition device 14 specifies an emotion detection value for the entire call by setting the period from when the call is started to when it is ended as an emotion recognition target section. At this time, the emotion recognizing device 14 specifies the detected emotion value as described above based on the feature amount for the voice of the entire call. As a result, for each type of emotion such as “anger”, “joy”, “sadness”, etc., the total emotion detection value VT for the entire customer utterance and the total emotion detection value VT for the entire operator utterance, Is generated as a whole emotion detection value VT for the entire utterance. When the total emotion detection value VT is generated, the emotion recognition device 14 assigns the identifier C1, the speaker code C2, and the emotion type C3 to the total emotion detection value VT as shown in FIG. Detection data T, operator total emotion detection data T, and both total emotion detection data T are generated.

  The D / B management device 12 includes a CPU, a RAM, a ROM, a communication I / F, and the like, and at a predetermined timing from the center management device 7 and the emotion recognition device 14 according to an information management program stored in a storage unit (not shown). Obtain various information and create a database. The D / B management device 12 acquires the history data 21 from the center management device 7. Also, emotion detection data D and overall emotion detection data T are acquired from the emotion recognition device 14. Then, these data are integrated and added as a new record to the database.

  FIG. 6 is a schematic diagram of a database structure. The database 100 stores text data TX, history data 21, emotion detection data D, and overall emotion detection data T in association with each other by an identifier C1. Further, the voice data 32A to 34A of the voice data registration device 10 are associated by the identifier C1. The audio data 32A to 34A may be distributed and stored in the audio data registration device 10, or may be stored in the D / B management device 12.

  Further, as described above, since the emotion detection value V is associated with each character data of the text TXT of the text data TX, it is possible to estimate the speaker's emotion when speaking a word, phrase, sentence or the like.

  The call center supervisor operates the administrator terminal 8 to perform data analysis using the database 100. At this time, the emotion detection value V, the entire emotion detection value VT, and character data are added as parameters of the database, and morphological analysis and emotion recognition are performed based on the customer's voice, the operator's voice, and both voices. Multifaceted analysis can be performed.

For example, using history data 21, emotion detection data D, and text data TX, data having an emotion detection value V whose emotion strength is a predetermined value or more is extracted for each product, every predetermined period, etc. Alternatively, the emotion detection value V can be compared for each product or for each predetermined period. Furthermore, the character data associated with the extracted emotion detection data D can be extracted from the text data TX. For example, by extracting character data in which “anger” or “joy” is “+2”, it is possible to objectively evaluate what the customer felt strong “anger” or “joy”. By generating the text data TX by voice recognition in this way, it is possible to suppress the occurrence of keyword variations compared to the case where the operator inputs a keyword summarizing the contents of the call.

  Further, for example, even when a plurality of text data TX including the word “paper jam” is accumulated for different products, the customer satisfaction with the product is objectively determined by the magnitude of the emotion detection value V1 for “paper jam”. The customer satisfaction can be fed back to product development. For this reason, it is possible to save the operator from inputting items related to the customer's emotions, and to remove the subjectivity of the judge who determines the customer's emotions.

  In addition, it is determined whether or not there is data whose emotion detection value V is equal to or greater than a predetermined value in the emotion detection data D in which the speaker code C2 is the identifier of the operator. By determining the character data associated with, it is possible to objectively determine at which timing the stress on the operator has increased. Further, based on the transition of the emotion detection value V for the entire call, the change in the emotions of the customer and the operator is measured, the emotion detection value V for “anger” is reduced, and the emotion detection value V for “joy” is increased. Accumulate know-how and reflect that know-how in telephone service. Further, the emotion detection data D or the whole emotion detection data T associated with the history data 21 having the same operator ID 21E is extracted and applied to a predetermined calculation formula every day, every month, or other periods, Each operator can be evaluated.

According to the above embodiment, the following effects can be obtained.
(1) In the above-described embodiment, the call center system 1 includes the voice recognition device 11 that performs voice recognition on the voice of the call between the call center operator and the customer and generates text data TX in which the call content is converted into text. Also, the emotion detection value V and the total emotion detection value VT obtained from the feature amount of the call voice are detected, and the emotion recognition that associates the emotion detection value V with the recognition target section S in which the emotion detection value V is detected in the text data TX. A device 14 is provided. Furthermore, the D / B management apparatus 12 which memorize | stores the text data TX, the emotion detection value V, and the whole emotion detection value VT in the linked state is provided. Therefore, by storing the emotion detection value V that can estimate the speaker's emotion and the character data of the recognition target section S from which the information is detected in the database, customer satisfaction, operator stress determination, operator evaluation For example, multi-dimensional data analysis can be performed.

  (2) In the above embodiment, the voice recognition device 11 performs voice recognition on the customer call voice and the operator call voice to obtain the customer text data TX2 based on the customer utterance and the operator text data TX3 based on the operator utterance. Generate. The emotion recognition device 14 detects the emotion detection value V1 and the total emotion detection value VT of the customer's call voice and the emotion detection value V2 and the total emotion detection value VT of the operator's call voice based on each call voice. In addition, the emotion recognition device 14 associates the detected emotion values V1 and V2 of the customer and the operator with the section corresponding to the recognition target section S in which the detected emotion value V is detected in the text data TX. Further, the entire emotion detection value VT is associated with the text data TX. For this reason, since data analysis can be performed from both the customer side and the operator side, the degree of freedom in data analysis can be improved.

(3) In the said embodiment, both text data TX1 which produced | generated the voice recognition with respect to both call voice in which the customer's call voice and the operator's call voice were mixed is produced | generated. Further, the emotion recognition device 14 detects the emotion detection value V and the entire emotion detection value VT based on both call voices, and the emotion detection value is detected in the recognition target section S in which the emotion detection value V is detected in the text data TX1. Associate V. In addition, the entire emotion detection value VT is associated with the text data TX1.
For this reason, when performing the overall evaluation, by using the data, the amount of data to be handled can be reduced, and the amount of processing such as search processing can be reduced.

  (4) In the above embodiment, the D / B management device 12 stores the history data 21 in association with the text data TX and the emotion detection data D. For this reason, for example, a search can be performed based on the product group 21F, the product model number 21G, the operator ID 21E, the hold history 21J, and the like, and data analysis can be performed from the product group or product, operator, and hold history. For this reason, multilateral data analysis can be performed.

  (5) In the above embodiment, the emotion recognition device 14 detects the emotion detection value V for a plurality of recognition target sections S set between the start of the call and the end of the call, and uses these emotion detection values V. , The emotion detection value V is associated with the detected recognition target section S. That is, since the emotion detection value V can be associated in units of words, phrases, or sentences, the degree of freedom of data analysis such as extracting words, phrases, or sentences in which the emotion detection value V is greater than or equal to a predetermined value is provided. Can be improved.

In addition, you may change this embodiment as follows.
In the above embodiment, the emotion recognition device 14 associates the emotion detection value V with the character data, but the D / B management device 12 may associate the emotion detection value V with the character data. In this case, the emotion recognition device 14 detects the emotion detection value V for each predetermined section, and the D / B management device 12 collates the predetermined section with the recognition target section S to obtain the emotion detection value V and the character data. Associate.

The history data 21 may include response content data input to the operator terminal 6 by the operator summarizing the content of the call.
In the above-described embodiment, the emotion detection value V is associated with the text TXT, but audio feature amounts such as frequency, tempo, and intensity may be associated. Even in this case, since the state of the customer's emotion can be estimated from the feature amount, data analysis using text and emotion as parameters can be performed.

1 is a schematic diagram of a call center system of the present embodiment. The schematic diagram of a log | history information storage part. The block diagram of an audio | voice data registration apparatus. The block diagram of a speech recognition apparatus. The schematic diagram of text data and emotion detection data. A schematic diagram of a database.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Call center system as a database system, 7 ... Center management apparatus as reception history registration means, 11 ... Voice recognition apparatus as voice recognition means, 12 ... Call information storage means, control means, character data acquisition means, detection data acquisition D / B management device as means, 15 ... emotion detection means, emotion recognition device as registration means, 20 ... history information storage unit, 21 ... history data as response history data, 100 ... database, D ... emotion detection data, S: Recognition target section, TX: Text data as character data, V: Emotion detection value as emotion detection information, VT: Whole emotion detection value as emotion detection information.

Claims (7)

Voice recognition means for performing voice recognition on a call voice when a call center operator and a customer make a call, and generating character data in which the content of the call is converted;
An emotion detecting means for detecting a feature amount of a voice in a target section of the call voice and generating emotion detection information inferring a speaker's emotion based on the feature amount;
Registration means for associating the emotion detection information of the target section with the character data corresponding to the target section;
A call center database system comprising: call information storage means for storing the character data and the emotion detection information in association with each other. The call center database system according to claim 1,
The voice recognition means
Performing voice recognition on at least the customer's call voice and the operator's call voice to generate character data based on the customer's utterance and the character data based on the utterance of the operator;
The emotion detection means includes
Detecting the emotion detection information of the target section of the call voice of the customer and the emotion detection information of the target section of the call voice of the operator;
The registration means includes
Based on the call voice of the customer, the character data corresponding to the target section is associated with the emotion detection information of the customer detected in the target section, and corresponds to the target section based on the call voice of the operator. A call center database system, wherein the character data is associated with the emotion detection information of the operator detected in the target section. In the call center database system according to claim 1 or 2,
The voice recognition means
Generating the character data by performing voice recognition on both call voices in which the customer call voice and the operator call voice are mixed,
The emotion detection means includes
Generating the emotion detection information based on the voice of both calls;
The registration means includes
A call center database system, wherein the emotion detection information of the target section is associated with the character data corresponding to the target section. In the call center database system according to any one of claims 1 to 3,
The emotion detection means detects a plurality of the emotion detection information from the start to the end of a call,
The call center database system, wherein the registration means associates each emotion detection information with the target section of the character data from which the emotion detection information is detected. In the call center database system according to any one of claims 1 to 4,
A call center database system further comprising: a response history registration unit that stores response history data indicating a response content with a customer in the call information storage unit in association with the feature amount detection data and the character data. An information management method for the database using a control means for managing the database,
The control means is
Performing voice recognition on a call voice when a call center operator and a customer make a call, and obtaining character data obtained by characterizing the call contents;
Detecting a feature amount of speech in a target section of the call speech and obtaining emotion detection information inferring a speaker's emotion based on the feature amount;
And storing the emotion detection information of the target section in association with the character data corresponding to the target section in a call information storage unit. An information management program for the database using a control means for managing the database,
The control means;
Character data acquisition means for performing voice recognition on a call voice when a call is made between a call center operator and a customer, and acquiring character data obtained by characterizing the call contents;
Detection data acquisition means for detecting a feature amount of speech in a target section of the call speech and generating emotion detection information inferring a speaker's emotion based on the feature amount;
An information management program for causing the character data corresponding to the target section to function as registration means for associating the emotion detection information of the target section and storing it in a call information storage means.

Images