JP2011221627A - Customer service support device, customer service support method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a customer service support device, a customer service support method and a program with which customer service skills and increase in sales can be expected.SOLUTION: A customer service support device comprises: a voice acquisition part 102 which acquires conversation between a salesclerk and a customer; a customer satisfaction calculation part 156 which calculates a degree of customer satisfaction based on the voice of the customer in the acquired conversation; a customer service data recording part 157 which associates the customer, the salesclerk and the degree of customer satisfaction with each other and records them as customer service data in a database DB2; a customer identification part 152 which identifies a visiting customer; an attending salesclerk selection part 163 which selects an attending salesclerk among the multiple salesclerks based on one or more pieces of customer service data associated with the identified customer referring to the database DB2; and a visit notification part 103 which notifies the selected attending salesclerk of the visit of the customer.

Description

  The present invention relates to a customer service support device, a customer service support method, and a program for recognizing emotion based on a person's voice and utilizing the recognition result for sales promotion.

  Conventionally, Patent Document 1 is known as a technique for recognizing emotion based on a person's voice. In Patent Document 1, emotion recognition is performed by associating changes in the intensity, tempo, and inflection of speech with the respective emotional states such as “anger”, “sadness”, and “joy” from the speech signal input by the subject. Is going.

  On the other hand, in stores such as retail stores, attempts are being made to collect customer data and sales data as marketing data for use in sales promotion. For example, Patent Document 2 proposes a marketing data collection / analysis technique that analyzes POS data to quantitatively grasp the tendency of simultaneous sales by consumers and reflects it in sales promotion.

  By the way, in the field of marketing, it is said that increasing customer satisfaction at the expense of productivity and efficiency is better as a result of consumer repeaters. Also, retailers and other stores that emphasize hospitality have a close relationship between sales and customer satisfaction, so customer service skills training and customer impressions are improved to increase customer satisfaction. For training of smiles and greetings. However, since it is very difficult to measure actual customer satisfaction with these efforts, the increase or decrease in sales is indirectly measured, or fixed point observation is performed by a small number of mask investigators. However, in such a method, since it is affected by economic fluctuations and investigators, the real factor for improving customer satisfaction cannot be grasped and effective measures cannot be implemented.

  In addition, it has been found that in stores that manage sales by store clerk, there is a large difference in sales depending on the customer service skills of each store clerk. However, the definition of the customer service skill itself is ambiguous, and there is a current situation that the customer service skill cannot be developed horizontally for the store clerk whose sales are sluggish.

JP 2002-91482 A JP 2007-94592 A

  Therefore, a method of directly measuring customer satisfaction by incorporating the emotion recognition technology of Patent Document 1 into a store such as a retail store can be considered. This should be able to measure customer satisfaction more accurately than at present. However, even if accurate customer satisfaction can be measured, there is no point in using it to improve customer service skills and sales.

  In view of the above problems, an object of the present invention is to provide a customer service support device, a customer service support method, and a program that can be expected to improve customer service skills and sales.

  The customer service support device of the present invention includes a conversation acquisition unit that acquires a conversation between a store clerk and a customer, a customer satisfaction calculation unit that calculates customer satisfaction based on a customer voice included in the acquired conversation, a customer, A customer service data recording unit that associates a store clerk with customer satisfaction and records it in a database as customer service data, a customer identification unit that identifies a customer who visits the store, and a database that is associated with the identified customer Based on the above customer service data, it has a sales clerk selection unit that selects a sales clerk to contact from among a plurality of sales clerk, and a store visit notification unit that notifies the selected sales clerk of the customer's visit to the store It is characterized by.

  In the customer service support method of the present invention, the computer acquires a conversation acquisition step in which the conversation between the store clerk and the customer is acquired, and a customer satisfaction calculation step in which the customer satisfaction is calculated based on the voice of the customer included in the acquired conversation; Associating customers, salesclerks, and customer satisfaction with customer service data recording steps that are recorded in the database as customer service data, customer identification steps that identify customers who visit the store, and referring to the database and associating with the identified customers Based on the received one or more customer service data, a sales clerk selection step for selecting a sales clerk to contact from among a plurality of sales clerk, and a store visit notification step for notifying the selected sales clerk of the customer's store visit. It is characterized by performing.

  According to these configurations, the person in charge of the customer is selected based on the past customer service data recorded in the database, and the customer's visit is notified to the selected person in charge. You can let the store clerk serve you. As a result, the customer satisfaction level of the customer who visited the store can be improved, and as a result, improvement in sales can be expected.

  In the customer service support apparatus described above, the salesclerk selection unit may determine the priority of the salesclerk based on the customer satisfaction included in the one or more customer service data, and select the salesclerk according to the priority. preferable.

  According to this configuration, when a salesclerk with the highest priority cannot receive a customer, a flexible response such as notifying the customer with the next highest priority to the customer's visit can be performed.

  In the customer service support device described above, the customer service data recording unit associates the sales results of the store clerk with the customer and the store clerk, and records them in the database as customer service data. It is preferable to determine the priority of the store clerk based on the sales record included in the customer service data, and select the store clerk according to the priority.

  According to this structure, since the priority of a salesclerk is determined based on the past sales performance, a higher sales effect can be expected.

  In the customer service support apparatus described above, it is preferable that the salesclerk selection unit determines the priority of the salesclerk by setting the weight of the customer satisfaction higher than the sales performance, and selects the salesclerk according to the priority. .

  According to this configuration, the customer satisfaction is weighted more than the sales performance to determine the priority of the store clerk, that is, the customer satisfaction is more important than the immediate sales improvement. Improvement can be expected.

  The customer service support device described above further includes a customer service time measuring unit that measures a customer service time based on the conversation acquired by the conversation acquisition unit, and the customer service data recording unit associates the customer service time with the customer and the store clerk, Data is recorded in the database, and the salesclerk selection unit is in charge of the number of customer service times corresponding to the number of customer service data recorded in the database and the customer service time that is included in one or more customer service data recorded in the database. It is preferable that the priority of the clerk is determined based on at least one of the total time, and the clerk in charge is selected according to the priority.

  According to this configuration, the priority of the store clerk is determined not only according to customer satisfaction but also based on the number of customer service and the total customer service time, so the customer is more likely to receive a service from a familiar store clerk. Can be obtained.

  The customer service support apparatus described above further includes a work status storage unit that stores the work status of the store clerk, and the sales clerk selection unit refers to the work status storage unit and selects a sales clerk from among the sales clerk in the working state It is preferable to do.

  According to this configuration, since the sales clerk is selected from among the clerk in the working state, the customer's visit is not notified to the clerk who is not in the working state.

  The customer service support device described above further includes a customer service status storage unit that stores a customer service status indicating whether or not the store clerk is currently in service, and the salesclerk selection unit in charge refers to the customer service status storage unit and is in a working state It is preferable to select a clerk in charge from among the clerk who are not in service.

  According to this configuration, since the sales clerk is selected from the clerk who is not serving customers, the clerk who is serving other customers is not notified of the customer's visit. As a result, it is possible to avoid a situation inconvenient for both the customer and the store, such as one store clerk serving a plurality of customers.

  The customer service support device described above further includes a customer service status rewriting unit that rewrites the customer service status storage unit, and the customer service status rewriting unit can rewrite the customer service status of any store clerk according to the operation of the operation unit, and notification of store visit It is preferable to rewrite the customer service status of the clerk in charge during customer service by notification of the department.

  According to this configuration, since the customer service situation rewriting unit is provided, the customer clerk can rewrite the customer service situation by his / her own operation. In addition, since the customer service situation of the sales clerk is automatically rewritten during customer service by the notification of the store visit notification unit, the sales clerk can save the trouble of the switching operation.

  In the customer service support apparatus described above, if the salesclerk selection unit refers to the customer service status storage unit and there are no non-customer salesclerks, the salesclerk selection unit is associated with the identified customer from among the salesclerks in the working state It is preferable to select an alternative store clerk based on one or more customer service data, and when the substitute store clerk is selected by the responsible store clerk selecting unit, the store attending notification unit instructs the substitute store clerk to temporarily respond.

  According to this configuration, even when there is no clerk who is not serving customers, an alternative store clerk is selected and a temporary response is instructed, so that it is possible to prevent a trouble that no one responds even though the customer visits the store. . In addition, since the substitute clerk is selected based on past customer service data, there is a high possibility that a clerk with high customer satisfaction or a familiar clerk will respond temporarily, giving the customer a sense of satisfaction and security. Can do.

  The customer service support device described above further includes a customer information storage unit that stores customer information for each customer, and the store visit notification unit notifies the customer in charge of the customer's store visit to the responsible store clerk and refers to the customer information storage unit It is preferable to notify customer information.

  According to this configuration, in addition to notifying the selected sales clerk of the customer's visit, the sales clerk starts a conversation smoothly based on the customer information in order to notify the customer's customer information. Can do. For example, when the customer information includes information on the date of the last visit, a message such as “Long time no see” can be made.

  The program of the present invention causes a computer to execute each step in the customer service support method described above.

  By using this program, it is possible to realize a customer service support method that can be expected to improve customer service skills and sales.

1 is a system configuration diagram of a customer service support system according to a first embodiment. It is a control block diagram of the terminal for shop assistants. It is a control block diagram of a receipt printer. It is a control block diagram of a management server. It is explanatory drawing of a speech section, a talk section, a conversation section, and a customer service section. It is a functional block diagram of the customer service support system concerning a 1st embodiment. It is explanatory drawing of the database for management servers which concerns on 1st Embodiment. It is a figure which shows the object area of voice recognition and emotion recognition. It is a figure which shows an example of an audio | voice data management table, a salesclerk utterance area management table, and a customer utterance area management table. It is a flowchart which shows the audio | voice data preservation | save process which concerns on 1st Embodiment. It is a flowchart which shows the service area specific process which concerns on 1st Embodiment. It is a flowchart which shows the shop assistant talk area specific process which concerns on 1st Embodiment. It is a flowchart which shows the customer talk area B specific process which concerns on 1st Embodiment. It is a flowchart which shows the customer talk area A specific process which concerns on 1st Embodiment. It is a figure which shows an example of a viewer screen. It is a functional block diagram of the customer service support system which concerns on 2nd Embodiment. It is explanatory drawing of the database for management servers which concerns on 2nd Embodiment. It is a figure which shows an example of a charge clerk discrimination | determination table, and the calculation algorithm of a clerk priority. It is a flowchart which shows the salesclerk selection process which concerns on 2nd Embodiment. It is a functional block diagram of the customer service assistance system which concerns on 3rd Embodiment. It is explanatory drawing of the database for management servers which concerns on 3rd Embodiment. It is a figure which shows an example of a keyword table. It is a figure which shows the collection timing which performs emotion recognition. It is a flowchart which shows the satisfaction calculation process which concerns on 3rd Embodiment. It is a figure which shows the calculation algorithm of various satisfaction.

[First Embodiment]
Hereinafter, a service data recording apparatus, a service data recording method, and a program according to the present invention will be described with reference to the accompanying drawings. In the following embodiments, the case where the customer service data recording apparatus of the present invention is applied to the customer service support system SY is illustrated. The customer service support system SY is built to recognize the emotions of people (customers and visitors) in stores and venues related to retail, restaurants, and services, and to use the results to improve customer satisfaction and sales. It has been done. Thus, in each of the following embodiments, a case where emotion recognition of a customer who is serving a store clerk is performed in a store of an apparel store (clothing store) is illustrated.

  FIG. 1 is a system configuration diagram of a customer service support system SY1 according to the first embodiment. As shown in the figure, the customer service support system SY1 includes a body conduction sound sensor 1, a voice acquisition microphone 2 and a clerk terminal 5 attached to a clerk, and in-store cameras 11 ( In the figure, only one unit is shown), a POS (Point Of Sales) terminal 12 and a receipt printer 13 installed at the checkout counter 14, a management server 15 and a display terminal 16 installed in the backyard of the store. Become.

  The body-conducting sound sensor 1 is mounted on the head and neck of the store clerk, and detects the body-conducted sound that the store clerk's voice reaches the body surface through bones and meat. In the present embodiment, the voice acquired by the voice acquisition microphone 2 is used to identify whether it is that of a store clerk or a customer. The voice acquisition microphone 2 is attached to the clerk's uniform (near the chest) and acquires the clerk's and customer's voices. In place of the body-conducting sound sensor 1 and the voice acquisition microphone 2, microphones having directivity for the store clerk and the customer may be used. In other words, the clerk's voice and the customer's voice may be identified by using two microphones, one for obtaining the clerk's voice and the other for obtaining the customer's voice.

  The store clerk terminal 5 is attached to a store clerk's uniform (belt or the like), and is connected to the body conduction sound sensor 1 and the voice acquisition microphone 2 via a dedicated cable. In addition, it has a wireless communication function with the receipt printer 13, and exchanges information with the management server 15 via the receipt printer 13. The in-store camera 11 is provided on the ceiling and walls of various places in the store, and images customers who have come to the store as well as clerk and customers who are serving customers. As the in-store camera 11, a CCD camera or a PTZ (Pan Tilt Zoom) camera can be used.

  The POS terminal 12 has a general register configuration, and performs accounting processing according to the POS application. Further, a product code is obtained from a bar code scanner or a keyboard (not shown), and receipt data for printing on the accounting receipt R (see FIG. 3) is generated with reference to the product master 18. The product master 18 may be provided in a POS server (not shown) connected to the POS terminal 12.

  The receipt printer 13 is connected to the POS terminal 12 via a dedicated cable, and prints receipt print data acquired from the POS terminal 12 on receipt paper. The receipt printer 13 has a wireless communication function with the clerk terminal 5 and a wired communication function with the management server 15. In this way, by inputting / outputting various information with the receipt printer 13 as the main (the receipt printer 13 filters the acquired various information and outputs necessary information), the POS backbone network (POS terminal 12). Network) is not affected. Further, when applying the present invention to an existing POS system, it is not necessary to change the POS backbone network itself.

  The management server 15 is connected to the receipt printer 13 via a network 19 such as an intranet, and exchanges various information with the clerk terminal 5 via the receipt printer 13. Further, based on various data such as voice data acquired from the clerk terminal 5, voice recognition, emotion recognition, and customer satisfaction are calculated. Further, the management server 15 displays the calculated customer satisfaction and the viewer screen 6 (see FIG. 15) for confirming the recorded voice data on the display screen 16a of the display terminal 16.

  Next, the hardware configuration of the clerk terminal 5, the receipt printer 13, and the management server 15 will be described with reference to FIGS. FIG. 2 is a control block diagram of the clerk terminal 5. The clerk terminal 5 includes a wireless LAN antenna 21, a wireless LAN RF (Radio Frequency) unit 22, a wireless LAN modem unit 23, and a wireless LAN baseband unit 24 for realizing a wireless communication function with the receipt printer 13. . The wireless LAN baseband unit 24 stores a MAC address for identifying the clerk terminal 5. In addition, the store clerk terminal 5 includes an amplifier unit 28 and an A / D converter 29 for acquiring the detection result of the body conduction sound sensor 1, and an amplifier unit 32 and A for acquiring audio data from the audio acquisition microphone 2. / D converter 33.

  The clerk terminal 5 includes a control unit 25 that performs overall control of each unit, a memory 26 that stores various data including the firmware (including voice data from the voice acquisition microphone 2), and a clerk terminal 5. A battery 34 for supplying power. The control unit 25, based on the detection data and the voice data acquired from the A / D converter 29 and the A / D converter 33, a store clerk utterance section specifying function for specifying the clerk's utterance section (continuous voice time zone), A sound level determination function for determining a sound level based on the sound data.

  FIG. 3 is a control block diagram of the receipt printer 13. The receipt printer 13 includes a wireless LAN antenna 41, a wireless LAN RF unit 42, a wireless LAN modem unit 43, and a wireless LAN baseband unit 44 for realizing a wireless communication function with the clerk terminal 5. The wireless LAN baseband unit 44 stores a MAC address for identifying the receipt printer 13. The receipt printer 13 includes an input interface unit 45 for receiving receipt data from the POS terminal 12, a CG-ROM 46 for storing character patterns, a control unit 47 for performing overall control of each unit, a print head, and a head drive mechanism. And a printing mechanism 48 including a receipt paper transport mechanism, and a wired LAN interface unit 49 connected to the management server 15 via a wired LAN.

  The control unit 47 includes a main processing unit 47a that performs analysis of receipt data including a predetermined command, generation of print data to be printed on the accounting receipt R, and a receipt data semantic analysis unit that is a configuration unique to the present embodiment. 47b. The receipt data semantic analysis unit 47b recognizes the terminal number of the POS terminal 12, the receipt number, the product code, the product name, the product unit price, the amount of money, the operator name, and the like from the receipt data, and can be interpreted by the management server 15 serving as the host system. To a predetermined data format (for example, XML format). In addition, what converted the recognition result of the receipt data into a predetermined data format is hereinafter referred to as “converted data”. In addition, the control unit 47 transfers the voice data received from the clerk terminal 5 via the wireless LAN (voice data acquired from the wireless LAN baseband unit 44) to the management server 15 via the wired LAN interface unit 49. To do.

  FIG. 4 is a control block diagram of the management server 15. The management server 15 acquires audio data and conversion data from the receipt printer 13 and also displays a wired LAN interface unit 51 for acquiring video data from the in-store camera 11 and a display for displaying various information on the display terminal 16. The processing unit 52 includes a control unit 53 that acquires input data from an input device 55 such as a mouse or a keyboard and performs overall control of each unit, and a storage unit 54 that stores various types of information. Based on the acquired voice data, the control unit 53 specifies a customer service section (a time zone during which the store clerk is serving customers), a customer satisfaction level per customer service section, and a store-specific section. A satisfaction calculation function for calculating the satisfaction degree for each store and a viewer screen display control function for controlling display of the viewer screen 6 (see FIG. 15) based on information input from the input device 55 are provided. The storage unit 54 is realized by a hard disk, and stores various control programs such as a voice recognition program, an emotion recognition program, and a satisfaction calculation program, and also functions as a management server database DB1 described later.

  Next, the definition of the voice section will be described with reference to FIG. First, a section of speech continuously uttered by the same person (a store clerk or a customer), that is, a section of one phrase that does not contain a breath or the like is referred to as an “utterance section”. In the present embodiment, emotion recognition and voice recognition are performed for each utterance section. Further, as shown in FIG. 5A, a collection of clerk or customer utterance sections that are repeated without interruption for a predetermined time or longer is referred to as a “talking section”. That is, it refers to a set of one or more utterance sections whose interval is less than the predetermined time X (where X is a constant that satisfies X> 0). In the example shown in the figure, a store clerk talk section (hereinafter referred to as “store clerk talk section”) and two customer talk sections (hereinafter referred to as “customer talk section”) around the store clerk talk section. The case where all are composed of two utterance sections is shown.

  Similarly, as shown in FIG. 5A, a group of talking sections in which the talking sections of the store clerk and the customer are alternately repeated without being interrupted for a predetermined time or longer are referred to as “conversation sections”. That is, it refers to an aggregate of one or more talking sections whose interval is less than the predetermined time Y (where Y is a constant satisfying Y ≧ X). In the present embodiment, a group of customer talk sections before and after the store staff talk section (that is, a collection of at least one and up to three talk sections) is expressed as “one conversation pattern” = “one conversation section”. Define.

  In addition, as shown in FIG. 5B, a collection of conversation sections that are repeated without interruption for a predetermined time or longer is referred to as a “service section”. That is, it refers to an aggregate of one or more conversation sections whose interval is less than the predetermined time Z (where Z is a constant such that Z> Y). The example of the figure shows a service section 1 composed of two conversation sections and a service section 2 composed of three conversation sections. Thus, the number of conversation sections included in the customer service section is arbitrary. Note that it is preferable that the value of Z is obviously large compared to the values of X and Y, such as several minutes to several tens of minutes.

  Next, with reference to FIG. 6 and FIG. 7, the functional configuration of the customer service support system SY1 according to the first embodiment will be described. FIG. 6 is a block diagram of the customer service support system SY1. The in-store camera 11 has a customer service imaging unit 111 as a main functional configuration. The customer service imaging unit 111 captures a customer service situation including a clerk and a customer. In the present embodiment, the customer service imaging unit 111 always performs imaging, and the video data is output to the management server 15 as needed.

  The body sound sensor 1 has an utterance detection unit 101 as a main functional configuration. The utterance detection unit 101 detects that the clerk uttered and the utterance section based on the body conduction sound. The voice acquisition microphone 2 has a voice acquisition unit 102 as a main functional configuration. The voice acquisition unit 102 acquires a voice (voice signal) based on the conversation between the store clerk and the customer. The clerk terminal 5 has an audio data transmission unit 105 as a main functional configuration. The audio data transmission unit 105 determines the presence / absence of audio using a power filter in the audio level determination function, and transmits audio data of a predetermined audio level or higher (for example, 1.5 v or higher after amplifier amplification) to the management server 15. . Further, the store clerk utterance section is specified based on the detection result of the utterance detection unit 101 and the voice acquisition result of the voice acquisition unit 102 (store clerk utterance section specifying function), and the management server 15 is notified of the occurrence of the clerk utterance section. Note that the clerk terminal 5 and the management server 15 communicate via the receipt printer 13.

  The receipt printer 13 has a conversion data transmission unit 113 as a main functional configuration. The conversion data transmission unit 113 transmits the conversion data obtained by converting the receipt data output from the POS terminal 12 into the XML format to the management server 15.

  The management server 15 includes a video recording unit 151, a customer identification unit 152, a conversation recording unit 153, a voice recognition unit 154, a customer emotion recognition unit 155, a customer satisfaction calculation unit 156, a customer service data recording unit 157, as main functional configurations. A conversion data receiving unit 158, a screen display unit 159, and a management server database DB1 are provided.

  The video recording unit 151 acquires video data from the customer service imaging unit 111 and records it in the management server database DB1. The customer identifying unit 152 identifies a customer based on the facial feature amount included in the video data. Specifically, the customer identification information and the customer's facial feature quantity are associated in advance and stored in the management server database DB1 (see the customer information storage unit 81 in FIG. 7), and the imaging result of the in-store camera 11 is analyzed. Then, face detection is performed, and the face feature amount calculated by normalizing the detected image of the face portion is compared with the face feature amounts of a large number of customers stored in the management server database DB1. It is determined that the customer has the highest degree of similarity. Note that when there are a plurality of store clerk in the store, it is necessary to associate the store clerk with the customer, so the store clerk may also be identified from the facial feature amount included in the video data. That is, the clerk identification information and the clerk's facial feature quantity are associated in advance and stored in the management server database DB1 (see the clerk information storage unit 82 in FIG. 7), and the calculated clerk's facial feature quantity and the management The face feature amount of each clerk stored in the server database DB1 is collated, and it is determined that the clerk with the highest similarity is serving customers among them.

  The conversation recording unit 153 records the conversation between the store clerk and the customer, that is, the voice data transmitted from the voice data transmission unit 105 (records it in the management server database DB1). The voice recognition unit 154 recognizes the voices of the clerk and the customer included in the recording data recorded by the conversation recording unit 153 for each utterance section. The speech recognition unit 154 includes an acoustic analysis unit, an acoustic model, a language model, a word dictionary, and a text conversion unit (all not shown). The voice recognition unit uses these to convert voice data into text information and record it in the management server database DB1.

  Further, as shown in FIG. 8A, the voice recognition unit 154 identifies an overlapping section in which the customer utterance section and the clerk utterance section overlap on the time axis, and the utterance section including the overlapping section is “voice recognition”. As the “non-target section”, voice recognition is performed on the utterance section of the clerk and the customer other than the utterance section. In this way, misrecognition (detection of incorrect keywords) is performed by excluding voice recognition non-target sections in which customer voice and store clerk voice are mixed and accurate voice recognition cannot be performed. Can be prevented. A method for identifying the overlapping section will be described later.

  The customer emotion recognition unit 155 recognizes the customer's emotion based on the customer's voice included in the conversation. Specifically, emotion recognition is performed based on the amount of change in voice intensity, voice generation speed (number of mora per unit time, etc.), word-by-word intensity, volume, and voice spectrum. In this case, the customer emotion recognition unit 155 determines whether the voice included in the conversation is the voice of the clerk based on the detection result of the utterance detection unit 101 (information on the clerk utterance section specified by the voice data transmission unit 105). Determine if it is customer voice.

  Further, the customer emotion recognition unit 155 performs emotion recognition for each customer utterance section included in the recording data of the conversation recording unit 153. Thus, highly accurate emotion data can be obtained by performing emotion recognition for each phrase. Further, as shown in FIG. 8 (b), the customer emotion recognition unit 155 identifies an overlapping section in which the customer utterance section and the clerk utterance section overlap on the time axis, and identifies the overlapping section as “emotion recognition non-target section”. "Emotion recognition is performed on the customer talk section excluding the overlap section. In this way, misrecognition is prevented by performing emotion recognition except for emotion recognition non-target sections (overlapping sections) in which customer voice and store clerk voice are mixed and accurate emotion recognition cannot be performed. Can do.

  The customer satisfaction calculation unit 156 calculates customer satisfaction based on the recognition result of the customer emotion recognition unit 155. Further, as the customer emotion recognition unit 155 performs emotion recognition for each utterance section, the customer satisfaction calculation unit 156 also calculates the customer satisfaction for each utterance section. A specific method for calculating customer satisfaction will be described in detail in the third embodiment.

  Each time the customer service section is completed, the customer service data recording unit 157 stores the customer identification information that is the identification result of the customer identification unit 152, the clerk identification information that is the identification result of the clerk, and the satisfaction that is the calculation result of the customer satisfaction calculation unit 156. Customer service data including degree data is recorded in the management server database DB1. Note that the customer identification information and the clerk identification information are specified from the face feature amount as described above. Further, the clerk identification information and the MAC address of the clerk terminal 5 are stored in association with each other (see the clerk information storage unit 82 in FIG. 7), and the video data acquired by the management server 15 is associated with the audio data. Can be done.

  The conversion data reception unit 158 receives the conversion data transmitted from the conversion data transmission unit 113 of the receipt printer 13 and records it in the management server database DB1. The conversion data is used to obtain information related to sales results recorded as a part of the customer service data. In addition, the record of conversion data extracts only information that can specify the presence or absence of sales and the sales amount, such as customer identification information (membership number, etc.), receipt number and total amount from the information included in the conversion data, This may be recorded as a sales record, or all of the conversion data may be recorded in the management server database DB1. The screen display unit 159 displays the viewer screen 6 (see FIG. 15) for confirming the recorded customer service data on the display screen 16a. The viewer screen 6 will be described in detail later.

  FIG. 7 is an explanatory diagram of the management server database DB1 according to the first embodiment. The management server database DB1 includes a customer information storage unit 81, a clerk information storage unit 82, an audio data storage unit 83, a video data storage unit 84, an audio data management table 85, a clerk utterance section management table 86, and a customer utterance section management table 87. And functions as a customer service data storage unit 88. The management server database DB1 may be provided for each store, or may be shared by a plurality of stores.

  The customer information storage unit 81 associates customer identification information (customer ID and the like), customer face feature amounts, and customer data (including personal information such as name, address, telephone number, date of birth, and sex). Remember. The store clerk information storage unit 82 stores store clerk identification information (store clerk ID, etc.), the store clerk's facial feature quantity, and the MAC address of the store clerk terminal 5 in association with each other. In addition, the voice data storage unit 83 stores the voice data recorded by the conversation recording unit 153 at all times. In addition, the video data storage unit 84 stores video data always captured by the customer imaging unit 111.

  The voice data management table 85 is a table in which the acquired voice data is recorded for each continuous voice section (hereinafter referred to as “continuous speech section”) without distinguishing between the store clerk and the customer (FIG. 9). (See (a))). Further, the store clerk utterance section management table 86 is a table in which store section utterance sections are recorded (see FIG. 9B). The customer utterance section management table 87 is a table in which customer utterance sections are recorded (see FIG. 9C).

  In addition, the customer service data storage unit 88 includes customer identification information that is the identification result of the customer identification unit 152, clerk identification information that is the identification result of the clerk, and voice data stored in the voice data storage unit 83. Recording data corresponding to the audio data for minutes, imaging data corresponding to the video data for the customer service section among the video data stored in the video data storage unit 84, and the calculation result of the customer satisfaction calculation unit 156. , Satisfaction data indicating the change (transition) of customer satisfaction in each utterance section in the customer service section, and sales indicating the presence or absence of sales (in the customer service section or within a predetermined time after the customer service section) and the sales amount The actual result, the customer service time that is the length of the customer service segment, and one or more keywords that are the recognition results of the voice recognition unit 154 for each utterance segment in the customer service segment are described. To. Note that the sales record can be associated with the customer identification information included in the conversion data transmitted from the receipt printer 13.

  Next, the voice data management table 85, the clerk utterance section management table 86, and the customer utterance section management table 87 will be described with reference to FIG. FIG. 9A shows an example of the audio data management table 85. The voice data management table 85 includes “voice data No.” continuously assigned to each continuous utterance section (section including at least one utterance section) which is a continuous voice section that does not distinguish between the clerk and the customer's voice. “Recording start time” corresponding to the start time of the utterance section and “Recording end time” corresponding to the end time of the continuous utterance section and voice data based on the customer's utterance or voice data based on the clerk's utterance, or The “duplicate flag” indicating whether the voice data is based on both utterances and the “voice data storage destination address” for storing the voice data are associated with each other. For example, the voice data of “voice data No .: 201” is a continuous utterance section having a start time of 12:36:03 and an end time of 12:36:16. Indicates that the clerk ’s voice and the clerk ’s voice overlap.

  FIG. 9B is a diagram showing an example of the store clerk utterance section management table 86. The clerk utterance section management table 86 includes a “clerk utterance number” assigned to each clerk utterance section, a “clerk utterance start time” that is the start time of the clerk utterance section, and a “clerk clerk utterance section end time” End of the overlapping section of "Speech end time", "Speaking No." indicating which store clerk talk section belongs to, "Overlapping start time" which is the start time of overlapping section with customer utterance, and customer utterance The “duplication end time”, which is the time, is associated with each other. For example, the utterance sections of “Clerk utterance No .: 100” and “Clerk utterance No .: 101” are regarded as a series of talk sections because the interval is less than a predetermined time X (for example, 3 seconds), and are the same. Talk No. Is added. Further, the utterance section of “clerk utterance number: 100” indicates that the entire section overlaps with the customer's utterance.

  FIG. 9C is a diagram illustrating an example of the customer utterance section management table 87. The customer utterance section management table 87 includes “customer utterance No.” given to each customer utterance section, “customer utterance start time” which is the start time of the customer utterance section, and “customer utterance section end time”. End of the overlapping section of the “speech end time”, “speaking No.” indicating which customer speaking section it belongs to, “duplication start time” which is the start time of the overlapping section with the clerk utterance, and the clerk utterance The “duplication end time”, which is the time, is associated with each other. For example, the utterance sections of “customer utterance No .: 101” and “customer utterance No .: 102” are regarded as different talk sections because the intervals exceed a predetermined time X (for example, 3 seconds). Talk No. Is granted. Further, the utterance section of “customer utterance No .: 100” indicates that 6 seconds out of the section length of 13 seconds overlaps with the clerk's utterance.

  Next, the audio data storing process will be described with reference to the flowchart of FIG. As described above, the clerk terminal 5 and the management server 15 communicate with each other via the receipt printer 13, but the illustration is omitted because the receipt printer 13 simply passes information.

  When the store clerk terminal 5 (control unit 25) acquires an audio signal (audio) from the audio acquisition microphone 2 (S11), the audio level is determined by the power filter of the audio level determination function (S12). Here, if the audio level is equal to or higher than the predetermined level, it is determined that the audio is “present”, and buffering of the audio data is started in the audio data storage area (not shown) in the memory 26 (S13). At this time, the recording start time is recorded in the audio data storage area.

  Subsequently, when no audio signal is received, the recording end time is determined and recorded in the audio data storage area, and the buffering is ended (S14). Thereafter, transmission of audio data is declared to the management server 15 (S15), and the audio data buffered in the audio data storage area is transmitted together with the recording start time and recording end time (S16).

  When the management server 15 (control unit 53) receives the voice data from the store clerk terminal 5 (S17), the voice data No. uniquely determined in the voice data management table 85 (see FIG. 9A) is obtained. Then, the recording start time and recording end time are registered (S18). Also, the audio data is stored in the audio data storage destination (predetermined folder) designated in the audio data management table 85 (S19).

  Next, with reference to the flowcharts of FIGS. 11 to 14, a series of flow of the service area identification process will be described. FIG. 11 is a flowchart showing the main process (service section identification process), and FIGS. 12 to 14 are flowcharts showing the subroutine. As shown in FIG. 11, the management server 15 (control unit 53) first specifies a store clerk talk section (S21), then specifies a customer talk section B that occurs after the store clerk talk section (S22), and also stores the store clerk talk. The customer talk section A that occurred before the section is specified (S23). Thereafter, a conversation section is specified based on the conversation section specified by the steps S21 to S23 (see S24, FIG. 5A). Further, by repeating the steps S21 to S24, the customer service section is specified (S25, see FIG. 5B).

  Next, with reference to the flowchart of FIG. 12, the clerk talk section specifying process corresponding to S21 of FIG. 11 will be described. When the clerk terminal 5 acquires the detection data from the body conduction sound sensor 1 (S31), the clerk terminal section determines the detection level by the power filter of the clerk utterance section specifying function. The time is determined and recorded in the memory 26 (S32). Subsequently, the voice level is determined by the power filter of the voice level determination function, and if it is equal to or higher than the predetermined level, it is determined that the detection data is based on the voice utterance (S33). Although not particularly shown in the flowchart, when the detection level or the audio level is less than a predetermined level, the process is terminated. Further, after confirming that the detection data is based on voice utterance, the clerk utterance end time is determined from a non-speech period following the voice utterance, and recorded in the memory 26. Thereafter, the management server 15 is notified of the occurrence of the clerk utterance section (S34). At this time, the clerk utterance start time and the clerk utterance end time recorded in the memory 26 are also transmitted.

  On the other hand, when the management server 15 (control unit 53) receives the notification of the occurrence of the clerk utterance section from the clerk terminal 5 (S35), it is uniquely determined in the clerk utterance section management table 86 (see FIG. 9B). Sales clerk utterance data No. And the clerk talk number set for each clerk talk section. Then, the clerk utterance start time and the clerk utterance end time are registered (S36). Thereafter, it is determined whether or not a notification of occurrence of the next clerk utterance section is received within a predetermined time (S37). If received (S37: Yes), the clerk utterance data No. And the same clerk Talk No. Then, the clerk utterance start time and the clerk utterance end time are registered (S36). Thereby, the salesclerk utterance section generated before and the salesclerk utterance section generated this time can be defined as a series of talk sections. Note that, when the occurrence notification of the next clerk utterance section is not received within a predetermined time (S37: No), the process is terminated assuming that a series of talk sections by the clerk is over.

  Next, with reference to the flowchart of FIG. 13, the customer talk section B specifying process corresponding to S22 of FIG. 11 will be described. The management server 15 (the control unit 53) refers to the voice data management table 85 after the end of identification of a series of talk sections by the clerk, and the voice data is stored within a predetermined time from the clerk utterance end time of the last clerk utterance section. It is determined whether or not it exists (S41). Here, when there is no voice data (S41: No), it is determined that the customer talk section B does not exist, and the process ends. If the voice data exists (S41: Yes), the recording start time and the recording end time of the voice data are read from the voice data management table 85, and the uniquely defined customer utterance number. And customer talk No. determined for each customer talk section. Then, the customer utterance start time and customer utterance end time are registered in the customer utterance section management table 87 (S42).

  Thereafter, referring to the voice data management table 85, it is determined whether or not voice data exists within a predetermined time from the customer utterance end time of the last customer utterance section (S43), and if present (S43: Yes). Unique customer utterance No. And the same customer talk number as above. The customer utterance start time and customer utterance end time are registered (S42). Thereby, the customer utterance section generated before and the customer utterance section generated this time can be defined as a series of talk sections. If there is no voice data within a predetermined time from the customer utterance end time of the last customer utterance section (S43: No), the process is terminated assuming that there is no subsequent talk section by the customer.

  Next, with reference to the flowchart of FIG. 14, the customer talk section A specifying process corresponding to S23 of FIG. 11 will be described. The management server 15 refers to the customer utterance section management table 87 after the identification of the customer talk section B is completed, and from the clerk utterance start time of the clerk utterance section identified in the processing of FIG. Customer utterance no. It is determined whether or not there is a customer utterance section given (S51). Here, when the customer utterance section exists (S51: Yes), the processing is ended on the assumption that the customer talk section specifying process has already been completed. In addition, the customer utterance No. Is not present (S51: No), the voice data management table 85 is referred to, and unprocessed voice data exists before a predetermined time from the clerk utterance start time of the clerk utterance section. Is determined (S52). Here, when there is no unprocessed voice data (S52: No), it is determined that the customer talk section A does not exist, and the process is terminated. If unprocessed voice data exists (S52: Yes), the recording start time and recording end time of the voice data are read, and the customer utterance No. And customer talk No. determined for each customer talk section. Then, the customer utterance start time and the customer utterance end time are registered in the customer utterance section management table 87 (S53).

  Thereafter, referring to the voice data management table 85, it is determined whether or not there is unprocessed voice data from the customer utterance start time of the registered customer utterance section to a predetermined time before (S54). S54: Yes), the recording start time and recording end time of the voice data are read, and the customer utterance No. uniquely determined is read. And the same customer talk number as above. Then, the customer utterance start time and customer utterance end time are registered (S54). Thereby, the customer utterance section registered previously and the customer utterance section specified this time can be defined as a series of talk sections. If there is no unprocessed voice data between the customer utterance start time and a predetermined time before the registered customer utterance section (S54: No), the processing is ended assuming that there is no previous talk section by the customer. To do.

  As described above, registration into the voice data management table 85, the clerk utterance section management table 86, and the customer utterance section management table 87 is performed by the processes shown in FIGS. And the customer talk section B can be specified. Here, the detection of the overlap section between the store clerk talk section and the customer talk section will be briefly described. After specifying each talking section, the management server 15 refers to the store clerk utterance section management table 86 and the customer utterance section management table 87, detects an overlapping section, and records it in each table 85, 86, 87. Specifically, first, referring to the clerk utterance section management table 86, the same talk No. The earliest clerk utterance start time and the latest clerk utterance end time are set as the start time and end time of the clerk talk section. Similarly, referring to the customer utterance section management table 87, the same talk No. The earliest customer utterance start time and the latest customer utterance end time are set as the start time and end time of the customer talk section. Then, it is determined whether or not there is an overlapping section between the clerk talk section and the customer talk section. If there is a duplicate section, the clerk utterance section management table 86 and the customer utterance section management table 87 indicate the overlapping sections (duplication start time and duplication end time). Time) and a duplication flag is set in the audio data management table 85 (corresponding to “customer / store” in the duplication flag column of FIG. 9A).

  By the way, in this embodiment, as above-mentioned, a conversation area is specified from the specific result of a store clerk talk section and customer talk sections A and B, and also a customer service section is specified from the specific result of the said conversation section. Then, customer service data is recorded for each customer service section. Therefore, the viewer screen 6 for confirming the customer service data will be described in detail below.

  As shown in FIG. 15, the viewer screen 6 includes an inquiry condition selection area E1 for selecting an inquiry condition, a keyword input area E2 for inputting a keyword when performing keyword search, and an extraction result indicating an extraction result of customer service data. An area E3, a customer information area E4 indicating customer information, a customer service video display area E5 for displaying video during customer service, a satisfaction graph area E6 indicating a satisfaction graph in which the satisfaction data is graphed, and customer service data A playback operation area E7 for performing a playback operation of the recorded data included.

  In the inquiry condition selection area E1, a store can be selected, and one of “customer”, “by satisfaction”, and “date” can be selected from the store. Here, when “customer” is selected, customer service data including the customer identification information is extracted by selecting customer identification information (customer name or customer ID). The customer identification information may be directly input instead of selecting from the displayed options. If “By Satisfaction” is selected, customer satisfaction statistics in the customer service data (average value, intermediate value, maximum value, minimum value, etc.) will show customer identification information within the specified range. The customer identification information is listed (for example, customer identification information with an average customer satisfaction degree of 80 or more is listed), and customer identification information can be selected from the list. Further, when “date” is selected, customer identification information of customers who have been serving customers on that day can be listed, and customer identification information can be selected from the list.

  In the keyword input area E2, a keyword for narrowing down the customer service data is input. Thereby, since the customer service data including the keyword is extracted, the customer service data related to the customer service contents to be confirmed can be easily found. Further, the extraction result area E3 displays a file list of customer service data that corresponds to the designated store, is associated with the selected customer identification information, and includes the keyword input in the keyword input area E2. When any one of these files is selected, various data included in the file are displayed in the customer information area E4, the customer service video display area E5, the satisfaction graph area E6, and the reproduction operation area E7.

  The customer information area E4 displays customer data included in the customer service data. Specifically, customer name, customer rank (based on sales performance, number of visits, etc.), sales amount for the corresponding customer service, sales clerk in charge, last visit date, number of days elapsed from the previous visit date to the customer service date, purchased items, etc. Is displayed. In addition, various information can be input as customer data by the input device 55. The input customer data is stored in the management server database DB1 (customer information storage unit 81).

  The customer service video display area E5 displays imaging data included in the customer service data. Note that the imaging data may be a still image or a moving image. In the case of a moving image, it can be played back simultaneously with the recording data in accordance with the playback operation in the playback operation area E7. In addition, by pressing a maximization switching button 291, it is possible to switch between enlarged display / reduced display of an image.

  The satisfaction graph area E6 displays a satisfaction graph in which satisfaction data (change in customer satisfaction for each utterance section) is graphed. The satisfaction graph is a line graph with the horizontal axis representing the time axis and the vertical axis representing the customer satisfaction. The customer satisfaction is represented by a value from 0 to 100, and the numerical value of the scale and the scale interval are varied so that the maximum value and the minimum value of the customer satisfaction included in the satisfaction data are within the vertical axis. The The satisfaction graph allows the user to grasp at a glance changes in customer emotions within the customer service section. In addition, since the satisfaction graph shows the change of customer satisfaction in the customer service section, there is naturally a section where there is no customer utterance. Since the customer satisfaction cannot be calculated in this section, the customer satisfaction in the previous customer utterance section and the customer satisfaction in the next customer utterance section are linearly connected.

  Further, the time axis (horizontal axis in the drawing) of the satisfaction graph area E6 corresponds to the time axis scale of the progress bar 295 included in the reproduction operation area E7. Thereby, the user can easily confirm the customer satisfaction at that time while listening to the recorded data. The satisfaction graph area E6 is provided with a satisfaction slider 292 (slider for setting a range on the vertical axis in the drawing) for designating an upper limit value and a lower limit value of customer satisfaction. By designating the satisfaction slider 292, the corresponding area of the satisfaction graph is colored. That is, the corresponding utterance section that is the utterance section satisfying the designated customer satisfaction is displayed on the satisfaction graph. As a result, the user can easily grasp the utterance section corresponding to the designated customer satisfaction on the satisfaction graph area E6, for example, only the recorded data corresponding to the designated customer satisfaction range is reproduced. For example, it is possible to check the customer service status for each utterance section.

  Furthermore, when the mouse pointer 293 is set to the corresponding utterance section (colored area), the satisfaction graph area E6 displays a keyword extracted from the utterance section. Further, when this keyword matches the keyword input in the keyword input area E2, it is displayed in reverse video (displayed with white characters on a black background). Thereby, the user can grasp the rough contents of each utterance section, and can efficiently confirm the recorded data.

  The reproduction operation area E7 displays a button group 294 for performing reproduction operation of the recorded data in the customer service section, a progress bar 295 indicating the reproduction position, and a volume adjustment slider 296. The progress bar 295 has a time scale in minutes in the horizontal axis direction. Further, the corresponding utterance section (the utterance section corresponding to the specified customer satisfaction) displayed in the satisfaction graph area E6 and the other sections are displayed in different colors. Thereby, the user can reproduce the recording data of the utterance section corresponding to the designated customer satisfaction more strictly. The scale of the progress bar 295 may be a time unit instead of a minute unit. Further, the unit of the scale and the scale interval may be varied according to the length of the recorded data so that the reproduction status of the entire recorded data in the customer service data can be grasped.

  As described above, according to the customer service support system SY1 according to the first embodiment, the customer satisfaction calculation result based on the customer's voice based on the recording data recording the conversation between the store clerk and the customer and the imaging data capturing the customer service situation. Since it is associated with the satisfaction level data and recorded as customer service data, this can be confirmed on the viewer screen 6. Thereby, for example, it is possible to use as a teaching material for a customer service method such as extracting and reproducing only the recording data and imaging data of an utterance section with high customer satisfaction. In other words, the customer service situation of a store clerk with high customer service skills can be efficiently shown to other store clerk, which is useful for the horizontal development of customer service skills.

  Further, since customer service data is recorded in units of customer service sections, there is an advantage that it is easy to grasp the customer service situation when this is confirmed (when recorded data or the like is reproduced). Further, by performing emotion recognition and voice recognition for each utterance section, recognition accuracy can be improved as compared with the case where they are performed for each talk section or conversation section. In addition, since the emotion recognition is performed on the customer talking section excluding the overlapping section where the customer speaking section and the store clerk speaking section overlap, it is possible to prevent erroneous recognition. Furthermore, since voice recognition performs voice recognition on the clerk and customer utterance sections other than the utterance section including the overlapping section, erroneous keyword detection can be prevented.

  In the above embodiment, a group of customer talk sections before and after the store clerk talk section (that is, a collection of at least one and up to three talk sections) is defined as “one conversation section”. The restriction on the number of talking sections included in “one conversation section” may be eliminated. That is, a group of talking sections in which the talking sections of the store clerk and the customer are alternately repeated without interruption for a predetermined time (interval Y) or more may be set as “one conversation section”.

  In the above embodiment, the customer identifying unit 152 identifies the customer using the face recognition technology, but other methods may be adopted. For example, each customer possesses a membership card with a built-in wireless IC (RFID: Radio Frequency Identification, etc.), and this is read with an IC reader installed at the entrance of the store to identify the customer, thereby identifying the customer You may do it. In this case, the store clerk may be required to possess a store clerk card in which a wireless IC is incorporated, and the store clerk may be identified by reading the store clerk card. By this method, when the read clerk card and the membership card are read at the same time, it is possible to associate the two as if the clerk is serving the customer. Further, the customer may be identified by reading the membership card (magnetic card) on which the magnetic information is recorded with a magnetic card reader attached to the POS terminal 12. In this case, the store clerk in charge of customer service can associate the customer with the store clerk by having his / her store clerk card read at the same time. The magnetic card reader may be directly connected to the management server 15. Furthermore, voice recognition technology may be used instead of face recognition technology. In this case, the customer information storage unit 81 and the store clerk information storage unit 82 need to store a voiceprint instead of the face feature amount.

  In the above embodiment, the imaging result of the in-store camera 11 is directly transmitted to the management server 15 via the wired LAN, but may be transmitted to the management server 15 via the receipt printer 13. Conversely, the clerk terminal 5 is configured to transmit audio data to the management server 15 via the receipt printer 13, but may be directly transmitted from the clerk terminal 5 to the management server 15. Each function of the management server 15 may be realized by a POS system or a WWW server.

[Second Embodiment]
Next, with reference to FIG. 16 to FIG. 19, a customer service support apparatus, a customer service support method, and a program according to the present invention will be described as a second embodiment. The customer service support system SY2 according to the present embodiment is characterized in that, when a customer visits the store, an optimal sales clerk is selected based on the recorded customer service data, and the selected store clerk is notified of the customer visit. And Therefore, only differences from the first embodiment will be described. In the present embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and detailed description thereof is omitted. Moreover, the modification applied about the component similar to 1st Embodiment is applied similarly about this embodiment.

  FIG. 16 is a functional block diagram of the customer service support system SY2 according to the second embodiment. As compared to the customer service support system SY1 of the first embodiment, the customer service support system SY2 includes a voice instruction earphone 3 as a system component. The voice instruction earphone 3 is attached to a store clerk's ear and connected to the store clerk terminal 5 via a dedicated cable. The voice instruction earphone 3 has a store visit notification unit 103 as a main functional configuration. When the customer visits the store, the store visit notification unit 103 notifies that fact and also notifies the customer information of the customer (customer data such as the customer's name and past sales record). Specifically, "Customer XX has visited the store. The total sales amount for this fiscal year is XX yen, and this is the first visit since XX month. Please give me a response." . In addition, as a method of notifying the customer's visit to the store, a simple electronic sound may be emitted. In addition, the store visit notifying unit 103 instructs the alternative store clerk to take a temporary action when there is no store clerk who can serve customers, such as when all the store clerk are in customer service. For example, voice guidance such as “Customer XX has visited the store. Please respond temporarily.”

  In the clerk terminal 5 of this embodiment, a voice command receiving unit 106 is added as a functional configuration. The voice command receiving unit 106 receives a voice command from the management server 15 and outputs it to the store visit notification unit 103. Note that the voice acquisition unit 102 of the voice acquisition microphone 2 functions as a conversation acquisition unit.

  In addition, the management server 15 of the present embodiment includes a customer service time measuring unit 161, a customer service status rewriting unit 162, a salesperson clerk selecting unit 163, and a voice command unit 164. The customer service time measuring unit 161 measures the length of the customer service section specified by the service section specifying process shown in the first embodiment. The service section may be the length from the start time to the end time of the service section, or the length of the service section excluding each interval (interval X, Y, Z) meaning no voice. It may be. The customer service time measured by the customer service time measuring unit 161 is recorded in the management server database DB2 as part of the customer service data.

  The customer service situation rewriting unit 162 rewrites the “customer service situation” in the salesperson clerk discrimination table 92 (see FIG. 18A) stored in the management server database DB2. Specifically, according to the operation of the input device 55 or other dedicated terminal (operation unit), the customer service status of an arbitrary store clerk is rewritten as either during customer service or during customer service. When the store visit notification unit 103 notifies the customer (when the voice command unit 164 issues a store visit notification command), the customer service status of the responsible store clerk is rewritten during customer service.

  The salesperson clerk selection unit 163 refers to the management server database DB2 when the customer visits the store, and includes at least one customer service data (customer related to the customer who has visited the store) including customer identification information of the customer who has visited the store (the customer identified by the customer identification unit 152) Based on the past customer service data), a sales clerk who serves customers is selected from a plurality of clerk. In this case, the salesclerk selection unit 163 determines the priority of the salesclerk and selects the salesclerk according to the priority. The method for selecting the sales clerk will be described in detail later. In addition, when there is no non-serving clerk, the responsible clerk selecting unit 163 selects an alternative clerk based on one or more customer service data associated with the identified customer from among the clerk in the working state.

  The voice command unit 164 issues a store attendance notification or a temporary response command to the responsible store clerk or alternative store clerk based on the selection result of the responsible store clerk selecting unit 163. In this case, a voice command is issued by designating the MAC address of the clerk terminal 5 associated with the corresponding clerk.

  FIG. 17 is an explanatory diagram of the management server database DB2 according to the second embodiment. The management server database DB2 functions as a customer information storage unit 81, a store clerk information storage unit 82, a voice data storage unit 83, a customer service data storage unit 91, and a store clerk discrimination table 92. The customer service data storage unit 91 of the present embodiment includes customer identification information that is the identification result of the customer identification unit 152, clerk identification information that is the identification result of the clerk, and voice data stored in the voice data storage unit 83. Recording data corresponding to the voice data for the customer service section and the calculation result of the customer satisfaction calculation unit 156, which is a customer satisfaction statistic (average value in this embodiment) of each utterance section in the customer service section. The satisfaction data shown, the sales record indicating the presence / absence of sales by the customer and the sales amount, and the customer service time measured by the customer service time measuring unit 161 are stored. The salesclerk discrimination table 92 is a table created for the purpose of selecting a salesclerk (work status storage unit and customer service status storage unit).

  Here, with reference to FIG. 18A, the salesclerk discrimination table 92 will be described. The sales clerk discrimination table 92 is a table created for each customer, and shows information on each clerk who has been in the service in the past. Specifically, the “working status”, “customer service status”, “number of customer service”, “total customer service time”, “customer satisfaction”, and “total sales amount” of each store employee are stored in association with each other. Of these, “working status” is information obtained from a shift table (not shown), and indicates whether the employee is working or taking a vacation on that day. The “customer service status” is information obtained from a customer service management table (not shown), and indicates whether the customer service is being performed or not. As described above, this “customer service situation” is information rewritten by a store clerk's operation or a store visit notification.

  “Number of customer service” refers to the number of customer service data stored in association with a customer. Therefore, when the same customer visits in the morning and afternoon in one day, the number of customer service is counted twice. Further, “total customer service time” indicates the total time of customer service in customer service data stored in association with a customer. “Customer satisfaction” indicates an average value of customer satisfaction in customer service data stored in association with a customer. Further, “total sales amount” indicates the total of sales results (sales amount) in customer service data stored in association with customers.

  It should be noted that the items “Service Status”, “Number of Service”, “Total Service Time”, “Customer Satisfaction”, and “Total Sales Amount” are not recorded when “Work Status” is “Closed”. In addition, regarding the “number of customer service”, “total customer service time”, “customer satisfaction”, and “total sales amount”, a target period such as the past three years may be set during this fiscal year.

  Next, with reference to FIG. 18B, a calculation algorithm for obtaining the priority of the store clerk will be described. As shown in the figure, the priority of the store clerk is calculated using “customer satisfaction level”, “sales performance level”, “service count level”, and “customer service total time level” as parameters. Here, “Customer satisfaction level”, “Sales performance level”, “Customer service level” and “Customer service total time level” are the items “Customer satisfaction”, “Total sales amount”, “Customer service” and This is a value obtained by leveling “total customer service time” in N stages (where N is an integer such that N ≧ 2). The value of N is preferably the same value for all items. For example, if the customer satisfaction is less than 20, “level 1”, 20 to less than 40 “level 2”, 40 to less than 60 “level 3”, 60 to less than 80 “level 4”, 80 When “level 5” is determined in the above case, in the example of FIG. 18A, the “customer satisfaction level” of the clerk A is “level 4”, and the “customer satisfaction level” of the clerk C is “level”. 3 ”, and the“ customer satisfaction level ”of the shop assistants B and D becomes“ level 5 ”. Further, each level is multiplied by coefficients P1 to P4 indicating weighting. In this case, the weighting is preferably “customer satisfaction level”, “sales performance level”, “service count level”, and “customer service total time level” in descending order. In other words, it is preferable to calculate the priority of the store clerk with “customer satisfaction level” as the most important factor.

  Next, the salesclerk selection process will be described with reference to the flowchart of FIG. When the customer comes to the store, the management server 15 (the control unit 53) identifies the customer by face recognition (S61), and selects a salesclerk according to the priority of the salesclerk determined by the calculation algorithm shown in FIG. (S62). Here, can the clerk with the highest priority (that is, the clerk with the highest priority among the clerk recorded in the clerk discrimination table 92 shown in FIG. 18A) be able to serve customers? If the customer is available (S63: Yes), the customer's store visit and customer information are notified to the selected sales clerk (the clerk with the highest priority) (S64).

  On the other hand, when the salesclerk with the highest priority is unable to serve customers (S63: No), it is determined whether there is a salesclerk capable of serving customers (S65). In other words, it is determined whether or not there is a salesclerk in the customer service status “not in service” with reference to the responsible salesclerk determination table 92. Here, when there is a salesclerk who can serve customers (S65: Yes), the customer's store visit and customer information are notified to the salesclerk selected according to the priority (S66). Also, record customer visits in the customer service record table of the highest priority store staff (a table that associates the number of customer service with each customer, total customer service time, customer satisfaction, sales performance, etc. for each store employee, not shown). (S67). As a result, the store clerk can grasp that the customer has visited the store during the holiday, and can take appropriate measures such as giving a thank-you postcard to the store.

  If there is no store clerk who can serve customers (S65: No), an alternative store clerk is selected according to the customer satisfaction (S68). That is, in the case of the example shown in FIG. 18A, when the customer service status of all the store clerk is “serving customer”, the store clerk D is selected as an alternative store clerk. After that, the selected substitute clerk is instructed to respond temporarily (S69), and the store clerk who has the highest priority among the clerk at work is notified of the customer's visit (S70). That is, after the current customer service is completed, voice guidance is given to instruct the customer XX who has visited the store to serve. In addition, although a case where an alternative store clerk and a store clerk with the highest priority are the same person is considered, in that case, a temporary response instruction and a store visit notification are made to the same person. Then, the process of S67 is performed and a process is complete | finished.

  As described above, according to the customer service support system SY2 according to the second embodiment, the customer in charge is selected based on past customer service data, and the customer is notified of the customer's visit to the customer. The most appropriate salesclerk can be served. As a result, the customer satisfaction level of the customer who visited the store can be improved, and as a result, improvement in sales can be expected.

  Further, since the priority of the store clerk is determined based on various information (customer satisfaction, past sales performance, etc.) included in the customer service data, a higher sales effect can be expected. Furthermore, by increasing the weight of customer satisfaction over the sales results, that is, by placing importance on customer satisfaction rather than immediate sales improvement, long-term sales improvement can be expected. Further, when there is no clerk who is not serving customers in the store, an alternative store clerk is selected and a temporary response is instructed, so that it is possible to prevent a trouble that no one responds even though the customer visits the store. Furthermore, since the customer information (customer name, etc.) is notified to the sales clerk and the substitute clerk, each clerk can take an appropriate action based on the customer information.

  In the above embodiment, the alternative store clerk is selected based on customer satisfaction, but may be selected in consideration of other factors (total sales amount, number of customer service, total customer service time, etc.). Conversely, the sales clerk may be selected based only on customer satisfaction. Furthermore, the user may be able to set the elements for selecting the responsible store clerk and the substitute store clerk and their weights.

  Further, in the above embodiment, as the parameters for calculating the priority of the store clerk, “Customer satisfaction level”, “Sales performance level”, “Service count level” and “Service total time level” are listed. In addition to this, a “total stay time level” may be added. The “total stay time level” is a parameter on the premise that each visitor data is stored including the stay time. That is, the “total stay time level” can be calculated by calculating the total stay time, which is the sum of the stay times included in each customer service data, and leveling it in N stages. The staying time can be obtained from the imaging result of the in-store camera 11, the reading result of the IC reader, the reading result of the magnetic card reader, and the like. For example, when the in-store camera 11 is installed at the entrance of the store, the difference between the time when the store is entered and the time when the store is closed for customers having the same facial feature amount (similarity equal to or higher than a predetermined level) You can ask for time to stay. Similarly, in the case of the IC reader, it can be obtained from the difference between the detection time at the time of entering the store and the detection time at the time of leaving the store. Further, in the case of a magnetic card reader, it can be obtained from the difference in reading time by reading the membership card at the time of entering the store and at the time of accounting or leaving the store. The weighting of the “total stay time level” is preferably lower than the “customer satisfaction level” and the “sales performance level”.

  In the above embodiment, all the past customer service data or the set predetermined period is reflected in the salesclerk discrimination table 92, but for the past M times (M is an integer satisfying M ≧ 1). May be reflected. The value of M may be set by the user.

  In the above-described embodiment, the satisfaction data (average value of customer satisfaction) is calculated for each customer service section. However, a restriction may be provided for the customer service section that is the target of the satisfaction data calculation. For example, the satisfaction data is calculated only when the customer service time is 5 minutes or more, and the satisfaction data is calculated only when the customer's utterance count is included 5 times or more in the customer service section. According to this configuration, since satisfaction data with low reliability is excluded when the customer service time is extremely short, satisfaction data with high reliability can be obtained as a result.

  In the above-described embodiment, the store attendant is notified using the voice instruction earphone 3, but may be notified by display on the display, LED lighting / flashing, vibration by a vibrator, or the like. Moreover, these means may be mounted on the clerk terminal 5 or may be mounted on a separate device. As an independent device, devices around the cashier counter 14 (for example, the POS terminal 12 and the receipt printer 13), terminals owned by a store clerk (for example, an order terminal in the case of a restaurant), and the like are conceivable.

[Third Embodiment]
Next, with reference to FIGS. 20 to 25, a satisfaction calculation method, a satisfaction calculation device, and a program according to the present invention will be described as a third embodiment. The customer service support system SY3 according to the present embodiment is characterized by calculating a highly reliable satisfaction (customer satisfaction or store satisfaction) based on the emotion recognition result. Therefore, only differences from the above embodiments will be described. In the present embodiment, the same components as those in the above-described embodiments are denoted by the same reference numerals, and detailed description thereof is omitted. Moreover, the modification applied about the component similar to said each embodiment is applied similarly about this embodiment.

  FIG. 20 is a functional block diagram of the customer service support system SY3 according to the third embodiment. Compared with the first embodiment, the management server 15 of this embodiment includes a keyword extraction unit 171, an emotion recognition unit 172, an emotion data calculation unit 173, a satisfaction calculation unit 174, and a calculation result output unit 175. The keyword extraction unit 171 extracts keywords included in the keyword table 96 (see FIG. 22) from the store clerk's talking section. The keyword table 96 stores keywords that are expected to be uttered by the store clerk (hereinafter referred to as “store clerk keyword”), and is stored in the management server database DB3. Details will be described later.

  The emotion recognition unit 172 recognizes the customer emotion identified by the customer identification unit 152 (customer identification step) based on the voice (recorded data included in the customer service data) acquired by the voice acquisition unit 102 (voice acquisition step). . In addition, the emotion recognition unit 172 performs emotion recognition for a customer's talk section that occurs immediately before or immediately after the talk section of the store clerk within the conversation section including the talk section of the store clerk from which the store clerk keyword is extracted. Do.

  The emotion data calculation unit 173 calculates emotion data based on the emotion recognition result of the emotion recognition unit 172. Emotion data is a value indicating emotional states such as “joy”, “laughter”, “anger”, “sadness”, “normal”, “excitement”. In this embodiment, four emotion data of “joy”, “laughter”, “anger”, and “sadness” are calculated.

  The satisfaction level calculation unit 174 calculates various satisfaction levels based on a predetermined calculation algorithm. As the satisfaction level, the utterance interval satisfaction, the utterance interval actual satisfaction, the talk interval satisfaction, the customer satisfaction, and the store satisfaction are calculated (see FIG. 25). A specific calculation algorithm will be described in detail later.

  The calculation result output unit 175 outputs the calculation result of the satisfaction degree calculation unit 174 to the display screen 16 a of the display terminal 16. The viewer screen 6 shown in the first embodiment is also an example of an output form by the calculation result output unit 175. In addition to the display unit, the calculation result may be output using a printing unit or a communication unit.

  FIG. 21 is an explanatory diagram of the management server database DB3 according to the third embodiment. The management server database DB3 includes a customer information storage unit 81, a store clerk information storage unit 82, a voice data storage unit 83, a customer service data storage unit 95, a keyword table 96, a customer satisfaction calculation result storage unit 97, and a store satisfaction calculation. It functions as a result storage unit 98. The customer service data storage unit 95 of the present embodiment includes customer identification information that is the identification result of the customer identification unit 152, clerk identification information that is the identification result of the clerk, and voice data stored in the voice data storage unit 83. Recording data corresponding to the voice data for the customer service section and the sales record indicating the presence / absence of sales by the customer and the sales amount are stored. Further, the keyword table 96 records the clerk keyword as described above. Further, the customer satisfaction calculation result storage unit 97 stores the utterance interval satisfaction, the utterance interval actual satisfaction, and the customer satisfaction, which are the calculation results of the satisfaction calculation unit 174. Note that the satisfaction level data in the first embodiment is a change in the satisfaction level by utterance section or the actual satisfaction level by utterance section stored in the customer satisfaction calculation result storage unit 97 in the customer service section. . In addition, the average value in the customer service section of the satisfaction degree by utterance section or the actual satisfaction degree by utterance section stored in the customer satisfaction calculation result storage unit 97 becomes the satisfaction degree data in the second embodiment. The store satisfaction calculation result storage unit 98 stores the store satisfaction, which is the calculation result of the satisfaction calculation unit 174.

  Next, the keyword table 96 will be described with reference to FIG. Here, a table assuming an apparel store is illustrated. The keyword table 96 includes “conversation contents” for classifying store clerk keywords, “weighting (coefficient Pi)” of store clerk keywords, “store clerk keyword”, and “collection timing” (timing information) of voice data for emotion recognition. ) And. “Conversation content” is roughly divided into two items, “handled product” and “service”. Among these, the item “handled product” is classified into “product quality”, “product price”, and “product lineup” according to the conversation content. The item “service” is classified into “proposal” and “correspondence” depending on the conversation content.

  Further, the “weighting (coefficient Pi)” is determined in the range of 0 ≦ Pi ≦ 1 for each conversation content. This weighting is preferably set such that “commodity quality” and “commodity price” are higher than other conversation contents among the conversation contents shown above. In addition, as the “clerk keyword”, an assumed conversation is illustrated, but only the word (clerk keyword) indicated by the underlined part is actually stored. In addition, “collection timing” indicates whether the target section for emotion recognition is set immediately before or after the store clerk talk section for each conversation content.

  As shown in FIG. 23, for example, when a clerk keyword associated with “collection timing: before clerk keyword” is extracted, the emotion recognition unit 172 displays a customer generated immediately before the clerk talk section from which the clerk keyword is extracted. Emotion recognition is performed for the talking section. In addition, when a clerk keyword associated with “collection timing: after clerk keyword” is extracted, the emotion recognizing unit 172 applies emotion to a customer talk section that occurs immediately after the clerk talk section from which the clerk keyword is extracted. Recognize. However, when the customer talk section generated immediately before or after the store clerk talk section belongs to a conversation section different from the store clerk talk section from which the store clerk keyword is extracted, the customer talk section is not a target section for emotion recognition. Further, even when there are a plurality of customer talk sections that occur within the same conversation section and before the store clerk talk section, only one customer talk section that occurs immediately before the store clerk talk section is set as the target section.

  Next, the satisfaction degree calculation process will be described with reference to the flowchart of FIG. When the management server 15 (control unit 53) acquires the customer service data from the customer service data storage unit 95 (S81), the management server 15 (the control unit 53) performs a voice recognition process on the recorded data included in the customer service data (S82, voice recognition step). As a result, the voice keywords included in the keyword table 96 are extracted from one or more salesclerk talk sections included in the recording data (S83, keyword extraction step). Further, based on the collection timing associated with the acquired voice keyword, a customer talk section that is a target section of emotion recognition is specified, and emotion recognition is performed on the voice data of the specified customer talk section (S84, emotion recognition). Step).

  Also, emotion data is calculated based on the emotion recognition result of S84 (S85, emotion data calculation step), and the actual satisfaction level for each utterance section is calculated (S86, satisfaction level calculation step). The actual satisfaction level for each utterance section is calculated based on emotion data of “joy”, “laughter”, “anger”, and “sadness”. Then, based on the calculation result of the actual satisfaction level for each utterance section, the satisfaction level for each speaking section is calculated (S87, satisfaction level calculation step for each speaking section). The satisfaction level for each talking section refers to a statistic (in this embodiment, an average value) of the actual satisfaction level for each speaking section in the customer speaking section that is the target section for emotion recognition.

  Further, the customer satisfaction is calculated based on the calculation result of the conversation section satisfaction (S88, customer satisfaction calculation step). The customer satisfaction refers to a statistic (in this embodiment, an average value) of satisfaction for each talking section. Further, based on the calculation result of customer satisfaction, store satisfaction is calculated (S89, store satisfaction calculation step). The store satisfaction is a statistic (average value in this embodiment) of customer satisfaction obtained from the customer service data of one store among the customer service data stored in the management server database DB3.

  Next, FIG. 25 will be calculated, and various satisfaction calculation algorithms (calculation formulas) will be described. As shown in FIG. 25A, the satisfaction level for each utterance section (“satisfaction data”) is calculated by the formula ““ satisfaction data ”=“ joy data ”+“ smile data ”× A”. Here, “joy data” means emotion data of “joy”, “laugh data” means emotion data of “laughter”, and A means a constant satisfying 0 ≦ A ≦ 1. The calculation algorithm is derived from the idea that the degree of satisfaction of a person is based on the psychological state of “pleasant” and the multiplication result of the psychological strength.

  Further, as shown in FIG. 25 (b), the actual satisfaction for each utterance section (“actual satisfaction data”) is calculated by the formula ““ actual satisfaction data ”=“ satisfaction data ”−“ unsatisfaction data ”× C ”, that is,“ (“joy data” + “laughing data” × A) − (“anger data” + “sad data” × B) × C ”. Here, “anger data” means “anger” emotion data, “sad data” means “sadness” emotion data, B means a constant satisfying 0 ≦ B ≦ 1, and C means a constant satisfying 0 ≦ C ≦ 1. To do. As described above, by using emotion data of “anger” and “sadness” in addition to “joy” and “laughter”, it is possible to calculate a more reliable satisfaction considering complex emotions. . The calculation algorithm is based on the idea that the person's dissatisfaction level is based on the psychological state of “uncomfortable” and the multiplication result of the psychological strength, and the psychological state where the actual satisfaction level is “pleasant” and “unpleasant”. It is derived from the idea of being based on.

  Further, as shown in FIG. 25 (c), the satisfaction level by speaking section (“satisfaction level by speaking section”) is ““ satisfaction level by speaking section ”=“ actual satisfaction of each utterance section included in the customer speaking section ”. It is obtained from “average value of degree data × Pi”. Here, Pi is a weight for the clerk keyword as described above, and means a constant satisfying 0 ≦ Pi ≦ 1. That is, the satisfaction value in the customer talk section is obtained by multiplying the average value of the “actual satisfaction data” of each utterance section included in the customer talk section specified from the collection timing by the coefficient Pi.

  Further, as shown in FIG. 25 (d), customer satisfaction (“customer satisfaction”) is “average customer satisfaction” = “satisfaction by talking section” included in the customer voice. Is obtained from. In other words, the average value of all customer talk sections targeted for emotion recognition is the customer's overall satisfaction with the customer service.

  Further, as shown in FIG. 25 (e), the satisfaction level for each store (“Satisfaction level for each store”) is expressed as ““ Satisfaction level for each store = “Satisfaction level for each customer” ”of a plurality of customers visiting the store” Is obtained from. In other words, the average value of all customers who visit the store (all customer service data) is the customer's overall satisfaction with the store.

  As described above, according to the customer service support system SY3 according to the third embodiment, since emotion data such as “joy” and “laughter” is used, it is possible to calculate a satisfaction level for each utterance section with high reliability. In addition to “joy” and “laughter”, the emotional data of “angry” and “sadness” is used to calculate the actual satisfaction level for each utterance section, so that the satisfaction level with higher reliability can be calculated. In addition, since emotion recognition is performed for each utterance section, emotion recognition can be performed with higher accuracy than when emotion recognition is performed for each long section, and thus more accurate customer satisfaction can be calculated. Further, since customer satisfaction changes with each utterance, by calculating an average value of one or more “actual satisfaction data”, it is possible to calculate customer satisfaction, which is total satisfaction for each customer. Furthermore, by calculating an average value of customer satisfaction calculated for a plurality of customers who have visited the store, it is possible to calculate store satisfaction, which is the overall satisfaction of the customer for the store.

  In addition, store clerk keywords that are likely to show customer emotions, and perform emotion recognition for the customer talk section that occurred immediately before or immediately after the store clerk talk section from which the store clerk keyword was extracted. Can perform emotion recognition. In addition, since it is considered that the degree of contribution to customer satisfaction and the ease of emotions differ depending on the conversation content, the reliability of the calculated customer satisfaction is further improved by considering the weighting Pi based on these. . In addition, depending on the content of the conversation, the customer's emotion may appear before or after the store clerk's conversation, but by storing the collection timing in consideration of it in the keyword table 96, Accurate emotion recognition and reliable customer satisfaction can be calculated.

  In the above embodiment, the calculated customer satisfaction level is not mentioned in comparison between customers, but when comparing between customers, depending on the type of customer (gender, age, etc.) The values of various constants (values such as “A” and “B”) may be varied.

  Moreover, since it is conceivable that the easiness of emotions (emotion appearance rate) varies from customer to customer, customer satisfaction may be compared in consideration of this. In this case, the emotion appearance rate is calculated by the calculation formula ““ joy data ”/ (“ joy data ”+“ lol data ”)” or ““ anger data ”/ (“ anger data ”+“ sad data ”). (Emotion appearance rate calculation step). In addition, it is preferable to normalize customer satisfaction using the calculated emotion appearance rate and compare customers. According to this configuration, it is possible to reduce an error in calculating customer satisfaction due to a difference in the ease of expressing an emotion, and to perform a more reliable comparison.

  Moreover, you may use the element of a sales performance for calculation of customer satisfaction. For example, when sales occur for the customer service, a predetermined number may be added to the customer satisfaction, or the customer satisfaction may be increased by a predetermined percentage. Further, the predetermined number or the predetermined ratio may be varied according to the sales amount.

  In the above embodiment, two items “handled product” and “service” are illustrated as items to be included in the keyword table 96 (see FIG. 22), but the item “store related” may be added. In addition, for the item “Store-related”, “Location” regarding the distance from the station and how to visit the store, “In-store layout / appearance” regarding the in-store image, store layout, store appearance, etc., “Promotion” to confirm the advertising effect, etc. May be classified as “conversation content”. In addition, it is preferable to set the collection timing to “after the clerk keyword” for all of the conversation contents included in the item “store related”. Further, the “weighting (coefficient Pi)” of each conversation content is preferably set to about 0.5 to 0.6.

  Further, in the above embodiment, various satisfaction levels are calculated for the purpose of improving customer service and sales, but this may be used as part of artificial intelligence or artificial sensitivity. Moreover, it does not ask | require about the use of the calculation result of various satisfaction, such as calculating the other party's satisfaction for the purpose of the improvement of an interpersonal relationship by an individual.

  While the first to third embodiments have been described above, it is possible to provide each process of the flowcharts shown in each of these embodiments as a program. Further, the program can be provided by being stored in various recording media (CD-ROM, flash memory, etc.). That is, a program for causing a computer to function as each component of the customer service support system SY1, SY2, SY3 and a recording medium on which the program is recorded are also included in the scope of rights of the present invention. In addition, the system configuration, processing steps, and the like can be appropriately changed without departing from the gist of the present invention, such as combining the customer service support systems SY1, SY2, and SY3, regardless of the above-described embodiments.

DESCRIPTION OF SYMBOLS 1 ... Body-conduction sensor 2 ... Voice acquisition microphone 3 ... Voice instruction earphone 5 ... Clerical terminal 6 ... Viewer screen 11 ... In-store camera 12 ... POS terminal 13 ... Receipt printer 14 ... Register counter 15 ... Management server 16 ... Display Terminal 16a ... Display screen 18 ... Product master 19 ... Network 85 ... Voice data management table 86 ... Sales clerk utterance section management table 87 ... Customer utterance section management table 92 ... Sales clerk discrimination table 96 ... Keyword table 291 ... Maximize switching button 292 ... Satisfaction slider 293 ... Mouse pointer 294 ... Button group 295 ... Progress bar 296 ... Volume control slider E1 ... Inquiry condition selection area E2 ... Keyword input area E3 ... Extraction result area E4 ... Customer information area E5 ... Customer service video display area E6 ... Satisfaction Degree graph area E7 ... playback operation area R ... accounting receipt SY ... customer service support system

Claims (12)

A conversation acquisition unit for acquiring a conversation between a store clerk and a customer;
A customer satisfaction calculating unit for calculating customer satisfaction based on the voice of the customer included in the acquired conversation;
A customer service data recording unit for associating the customer, the store clerk, and the customer satisfaction, and recording it in a database as customer service data;
A customer identification section for identifying customers who have visited the store;
Referring to the database, and based on the one or more customer service data associated with the identified customer, a sales clerk selection unit that selects a sales clerk to serve from a plurality of sales clerk;
A customer service support device, comprising: a store visit notification unit for notifying the selected sales clerk of the customer's store visit.   The clerk selection unit determines the priority of the clerk based on the customer satisfaction included in the one or more customer service data, and selects the clerk according to the priority. Item 3. A customer service support device according to item 1. The customer service data recording unit associates sales results for the customer with the customer and the store clerk, and records it in the database as the customer service data,
The said salesclerk selection part determines the priority of the said salesclerk based on the said sales performance contained in the said 1 or more customer service data, and selects the said salesclerk according to the said priority. 2. A customer service support device according to 2.   The clerk selection unit determines a priority of the clerk by setting a weight of the customer satisfaction higher than the sales record, and selects the clerk according to the priority. 3. A customer service support device according to 3. Based on the conversation acquired by the conversation acquisition unit, further comprising a service time measuring unit for measuring the service time,
The customer service data recording unit associates the customer service time with the customer and the store clerk, records the customer service data in the database,
The salesperson clerk selection unit is configured to provide a total customer service time that is a total number of customer service times corresponding to the number of customer service data recorded in the database and one or more customer service data recorded in the database. 5. The customer service support device according to claim 2, wherein a priority of the store clerk is determined based on at least one of the two, and the store clerk is selected according to the priority. A work status storage unit for storing the work status of the store clerk;
6. The customer service support according to claim 1, wherein the sales clerk selection unit refers to the work status storage unit and selects the sales clerk from among the sales clerk in the working state. apparatus. A customer service status storage unit for storing a customer service status indicating whether the store clerk is currently serving customers;
The customer service support according to claim 6, wherein the salesclerk selection unit refers to the customer service status storage unit, and selects the salesclerk from among the salesclerks who are in the working state and are not serving customers. apparatus. A customer service status rewriting unit for rewriting the customer service status storage unit;
The customer service status rewriting unit is capable of rewriting the customer service status of an arbitrary store clerk according to an operation of an operation unit, and rewriting the customer service status of the responsible store clerk during customer service by notification of the store visit notification unit. The service support apparatus according to claim 7. The salesclerk selection unit, as a result of referring to the customer service status storage unit, if there is no non-customer salesclerk, one or more of the one or more associated with the identified customer from among the salesclerk in the working state Select an alternate store clerk based on customer service data,
The customer service support device according to claim 7 or 8, wherein when the substitute store clerk is selected by the responsible store clerk selecting unit, the store visit notification unit instructs the substitute store clerk to take a temporary response. A customer information storage unit for storing customer information for each customer;
The said store visit notification part notifies the said customer information with reference to the said customer information storage part while notifying the said customer's store visit to the said salesclerk. The customer service support device according to Item 1. Computer
A conversation acquisition step for acquiring a conversation between the store clerk and the customer;
A customer satisfaction calculating step for calculating a customer satisfaction based on the voice of the customer included in the acquired conversation;
A customer service data recording step for associating the customer, the store clerk, and the customer satisfaction, and recording it in a database as customer service data;
A customer identification step for identifying the customer who visited the store;
A responsible clerk selection step of referring to the database and selecting a clerk to serve from among a plurality of clerk based on the one or more customer service data associated with the identified customer;
And a store visit notifying step of notifying the selected sales clerk of the customer's visit to the store. The program for making a computer perform each step in the customer service support method of Claim 11.

Images