Information processing device, information processing method, and program
The information processing device links calls with operators by associating user identification information and performing fraud detection, addressing the challenge of missing CTI integration in contact centers, ensuring accurate speech recognition result delivery.
Patent Information
- Application Number
- JP2024201398
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-11-19
- Publication Date
- 2025-08-06
- Estimated Expiration
- 2042-03-31
AI Technical Summary
Contact centers face challenges in linking speech recognition results with operators due to the absence of CTI integration functionality or capacity in existing PBX systems, especially in free address systems, making it impossible to determine which results relate to which operators' calls.
An information processing device that associates user identification information with voice recognition, performs fraud detection, and transmits speech recognition results to the correct operator terminal by using a storage unit to link calls with operators without requiring CTI integration.
Enables effective linking of calls with operators, preventing fraud, and ensuring accurate association of speech recognition results, even in environments without CTI integration.
Smart Images

Figure 0007719938000001 
Figure 0007719938000002 
Figure 0007719938000003
Abstract
Description
[Technical Field]
[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]
[0002] In recent years, contact centers (also called call centers) have increasingly introduced CTI (Computer Telephony Integration) for the purposes of supporting operators' work, improving work efficiency, and increasing customer satisfaction. CTI is a system that integrates and links computers, such as voice recognition systems and customer management systems, with telephones and PBXs (Private Branch Exchanges) (see, for example, Non-Patent Document 1). By introducing CTI, it becomes possible, for example, to link a voice recognition system with a PBX and perform voice recognition on calls made at the contact center. Hereinafter, the introduction of CTI and linking computers with telephones and PBXs will also be referred to as "CTI integration."
[0003] In recent years, an increasing number of contact centers have adopted a free address system for operator seating. A free address system is a system in which operators do not have fixed seats, but can choose their seats freely or according to certain rules. In a free address system, operators' seats can change daily, but by using voice recognition through CTI integration, it is possible to link voice-recognized calls with operators. [Prior art documents] [Non-patent literature]
[0004] [Non-Patent Document 1] "CTI Middleware "CTBASE / Core" | NTT Technocross", Internet<URL:https: / / www.ntt-tx.co.jp / products / ctbase / core.html> Summary of the Invention [Problem to be solved by the invention]
[0005] However, while there is a desire to introduce a voice recognition system into a contact center to recognize voice calls, there are cases where it is not possible to introduce CTI due to various reasons. For example, there are cases where the existing PBX does not have CTI integration functionality or does not have enough capacity to integrate with CTI, but the cost of replacing the PBX is unacceptable.
[0006] In such cases, especially in contact centers that use a free address system, there is a problem in that it is not possible to link speech recognition results with operators, making it impossible to determine which speech recognition results relate to which operators' calls.
[0007] The present disclosure has been made in consideration of the above points, and provides a technology for linking a call with an operator. [Means for solving the problem]
[0008] An information processing device according to one aspect of the present disclosure includes a storage unit that stores correspondence information in a storage unit that associates user identification information used to authenticate a first terminal with first identification information transmitted from the first terminal; a first identification unit that identifies second identification information from packet data in a communication process; a voice recognition unit that converts voice represented by voice data included in the packet data into text by voice recognition; a second identification unit that uses the correspondence information stored in the storage unit to identify user identification information associated with first identification information that matches the second identification information; a fraud detection unit that uses the second identification information to determine whether the first identification information included in the correspondence information is fraudulent; and, when the fraud detection unit determines that the first identification information is fraudulent, performs identification by the user identification information. and a transmitting unit that transmits the text to a first terminal logged on with the user identification information identified by the second identifying unit, wherein the fraud detection unit determines that the first identification information is not fraudulent if the text representing the speech recognition result of an opening scene, which is a scene representing the start of communication realized by the communication processing, includes the surname of the user identified by the user identification information, and determines that the first identification information is fraudulent if the text does not include the surname of the user identified by the user identification information. [Effects of the Invention]
[0009] According to the present disclosure, a technique for linking a call with an operator is provided. [Brief explanation of the drawings]
[0010] [Figure 1] 1 is a diagram illustrating an example of the overall configuration of a contact center system according to a first embodiment. [Figure 2]3A and 3B are diagrams for explaining an example of a method for linking a call with an operator according to the first embodiment and transmission of a voice recognition result using the method. [Figure 3] FIG. 2 is a diagram illustrating an example of a functional configuration of a contact center according to the first embodiment. [Figure 4] FIG. 10 is a sequence diagram illustrating an example of a process at the time of logon according to the first embodiment. [Figure 5] FIG. 10 is a diagram illustrating an example of a log-on screen. [Figure 6] FIG. 10 is a diagram illustrating an example of an extension number input screen. [Figure 7] FIG. 10 is a diagram showing another example of the extension number input screen. [Figure 8] FIG. 3 is a sequence diagram illustrating an example of a voice recognition process according to the first embodiment. [Figure 9] FIG. 10 is a diagram illustrating an example of an operator screen. [Figure 10] FIG. 10 is a diagram illustrating an example of a functional configuration of a contact center according to a second embodiment. [Figure 11] FIG. 10 is a sequence diagram illustrating an example of a voice recognition process according to a second embodiment. [Figure 12] FIG. 11 is a sequence diagram illustrating an example of operator information / log association processing according to the second embodiment. [Figure 13] FIG. 10 is a sequence diagram illustrating an example of a log complement / correction process according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION
[0011] Hereinafter, a first embodiment and a second embodiment will be described as one embodiment of the present invention. In each embodiment, a contact center system 1 will be described that is targeted at a contact center and that, when performing speech recognition on a call (voice call) with a customer, can link the call with the operator handling the call without CTI linkage. However, a contact center is just one example, and the system can be similarly applied to a location other than a contact center, for example, when linking a call with a person handling the call, for example, when targeting a person working in an office. More generally, the system can be similarly applied to linking a call with the person handling the call.
[0012] [First embodiment] First, the first embodiment will be described.
[0013] <Overall configuration of contact center system 1> An example of the overall configuration of a contact center system 1 according to this embodiment is shown in Fig. 1. As shown in Fig. 1, the contact center system 1 according to this embodiment includes a voice recognition system 10, a plurality of operator terminals 20, a plurality of telephones 30, one or more supervisor terminals 40, one or more manager terminals 50, a PBX 60, a NW switch 70, and a customer terminal 80. Here, the voice recognition system 10, the operator terminals 20, the telephones 30, the supervisor terminals 40, the manager terminal 50, the PBX 60, and the NW switch 70 are installed in a contact center environment E, which is a system environment of a contact center. Note that the contact center environment E is not limited to a system environment within the same building, and may be, for example, a system environment within multiple geographically separated buildings.
[0014] The voice recognition system 10 converts the call between the customer and the operator into text by voice recognition using packets (voice packets) sent from the NW switch 70, and identifies the operator who is handling the call.
[0015] The operator terminal 20 is a terminal such as a PC (personal computer) used by an operator. The telephone 30 is an IP (Internet Protocol) telephone (such as a fixed IP telephone or a mobile IP telephone) used by an operator. Hereinafter, it is assumed that a free address system is adopted in the contact center, and that the operator's seat may change daily (or at some timing, for example, between morning and afternoon, or when the assigned work is changed). Furthermore, in a typical contact center, one operator terminal 20 and one telephone 30 are often installed at each operator's seat. Therefore, in this embodiment, it is assumed that such a contact center is adopted, a free address system is adopted, the operator's seat may change daily, and each of the seats is installed with one operator terminal 20 and one telephone 30.
[0016] The supervisor terminal 40 is a terminal such as a PC used by a supervisor. A supervisor is, for example, a person who monitors the calls of an operator and supports the operator in answering calls when a problem is likely to occur or at the request of the operator. Usually, one supervisor monitors the calls of several to a dozen operators.
[0017] The administrator terminal 50 is a terminal such as a PC used by a system administrator of the contact center environment E. Although only one administrator terminal 50 is shown in the example shown in Fig. 1, multiple administrator terminals 50 may exist.
[0018] The PBX 60 is a telephone exchange (IP-PBX) and is connected to a communication network 90 including a Voice over Internet Protocol (VoIP) network and a Public Switched Telephone Network (PSTN).
[0019] The NW switch 70 relays packets between the telephone 30 and the PBX 60 , and also captures the packets and transmits them to the voice recognition system 10 .
[0020] The customer terminal 80 is a variety of terminals used by customers, such as a smartphone, a mobile phone, or a landline phone.
[0021] The overall configuration of the contact center system 1 shown in Fig. 1 is an example, and other configurations may be used. For example, in the example shown in Fig. 1, the voice recognition system 10 is included in the contact center environment E (i.e., the voice recognition system 10 is an on-premise type), but all or part of the functions of the voice recognition system 10 may be implemented by a cloud service or the like. Similarly, in the example shown in Fig. 1, the PBX 60 is an on-premise type telephone exchange, but may be implemented by a cloud service.
[0022] <Linking calls to operators and sending voice recognition results using that linking> A case where a call is associated with an operator in the contact center system 1 according to this embodiment and a voice recognition result is transmitted to the operator terminal 20 used by the operator using the associated association will be described with reference to FIG. 2. Here, each operator selects his / her own seat when starting a call handling task and logs on to the operator terminal 20 at that seat using his / her operator ID and the corresponding password. The operator ID is identification information that uniquely identifies an operator. Instead of the operator ID, other identification information such as a logon ID and the corresponding password may be used for logging on.
[0023] Typically, an operator selects a seat and logs on when coming to work, but this is not limited to this. For example, if different seats are used in the morning and afternoon, seat selection and logging on may be performed at the start of the morning shift and the start of the afternoon shift. Also, if different seats are used in response to a change in assigned work, seat selection and logging on may be performed at the start of the previous assigned work and the start of the new assigned work. In addition to these, seat selection and logging on may be performed at some other timing.
[0024] The operator logs out from the operator terminal 20 when finishing work, such as when leaving work, or when changing the work he or she is responsible for. However, since this is the same as in the prior art, a description thereof will be omitted in this embodiment.
[0025] At this time, the contact center system 1 according to this embodiment associates the call with the operator by the following steps (1-1) to (1-6), and displays the voice recognition result of the call on the operator terminal 20 used by the operator.
[0026] (1-1) First, in response to a logon operation by an operator, the operator terminal 20 transmits the logon information (operator ID and corresponding password) entered in this logon operation to the voice recognition system 10. The operator ID and the corresponding password (correct password) may be held by the voice recognition system 10, but this is not limitative and they may be held by a system or device other than the voice recognition system 10, such as an authentication system.
[0027] (1-2) Next, the operator terminal 20 transmits an extension number (for example, "XXXX") to the voice recognition system 10 in response to the operator's input operation of the extension number. Here, the operator inputs the extension number of the telephone 30 installed at his / her own seat (i.e., the telephone 30 installed at the same seat as the operator terminal 20 logged on in (1-1) above). The extension number of the telephone 30 may be displayed on the display of the telephone 30, or may be posted on a piece of paper or the like on the seat where the telephone 30 is installed.
[0028] (1-3) The voice recognition system 10 associates and stores the operator ID included in the logon information transmitted from the operator terminal 20 with the extension number transmitted from the operator terminal 20. This makes it possible to identify the operator ID from the extension number.
[0029] (1-4) When the telephone 30 receives a call from the customer terminal 80, the voice recognition system 10 captures packets of the call between the customer terminal 80 and the telephone 30, and identifies the extension number of the telephone 30 from the packets. This makes it possible to identify the operator ID from the extension number, and therefore the call and the operator are linked.
[0030] (1-5) The voice recognition system 10 performs voice recognition on the voice data contained in the packets of the call between the customer terminal 80 and the telephone 30, and converts the voice represented by the voice data into text (hereinafter also referred to as "voice recognition text").
[0031] (1-6) Then, the speech recognition system 10 transmits speech-recognized text, which is a speech recognition result, to the operator terminal 20 used by the operator associated with the call. This makes it possible to display the speech-recognized text on the operator terminal 20 in real time. In this case, the speech recognition system 10 may store, for example, operator terminal information, such as identification information or an IP address of the operator terminal 20 used for logging on by the operator, in association with an operator ID, and use this operator terminal information to identify the operator terminal 20 to which the speech-recognized text is to be sent. Although not specifically mentioned below, as described above, the speech recognition system 10 transmits the speech-recognized text after identifying the operator terminal 20 to which the speech-recognized text is to be sent, and a screen for displaying the speech-recognized text is generated in the operator terminal 20. However, this is not limited to this. For example, the operator terminal 20 may transmit a request including an operator ID or the like to the speech recognition system 10, and the speech-recognized text (or information on the screen on which the speech-recognized text is to be displayed, etc.) may be returned from the speech recognition system 10 to the operator terminal 20 in response to the request.
[0032] <Functional configuration of contact center system 1> FIG. 3 shows the functional configuration of the voice recognition system 10 and the operator terminal 20 included in the contact center system 1 according to this embodiment.
[0033] <Voice Recognition System 10> As shown in FIG. 3, the speech recognition system 10 according to this embodiment includes an authentication unit 101, an extension number storage unit 102, an extension number identification unit 103, and a speech recognition unit 104. These units are realized, for example, by a processor such as a CPU (Central Processing Unit) executing one or more programs installed in the speech recognition system 10. The speech recognition system 10 according to this embodiment also includes a storage unit 110. The storage unit 110 can be realized, for example, by a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a flash memory. However, the storage unit 110 may also be realized, for example, by a storage device connected to the speech recognition system 10 via a communication network.
[0034] The authentication unit 101 authenticates the operator terminal 20 using the logon information (operator ID and the corresponding password) received from the operator terminal 20.
[0035] The extension number holding unit 102 holds in the storage unit 110 the extension number transmitted from the operator terminal 20 that has been successfully authenticated, in association with the operator ID included in the logon information used to authenticate the operator terminal 20.
[0036] The extension number identification unit 103 identifies the extension number of the telephone set 30 that is making a call with the customer terminal 80 from the packet sent from the NW switch 70 .
[0037] The voice recognition unit 104 performs voice recognition on the voice data included in the packet transmitted from the NW switch 70, and converts the voice represented by the voice data into voice-recognized text. The voice recognition unit 104 also refers to the correspondence between extension numbers and operator IDs stored in the storage unit 110, identifies the operator ID corresponding to the extension number identified by the extension number identification unit 103, and transmits the voice-recognized text to the operator terminal 20 logged on with that operator ID.
[0038] Information representing the correspondence between an extension number and an operator ID is stored in the storage unit 110. In addition to this, various other information (for example, information necessary for authenticating the operator terminal 20, etc.) may also be stored in the storage unit 110.
[0039] <Operator terminal 20> 3, the operator terminal 20 according to this embodiment includes a logon request unit 201, an extension number transmission unit 202, and a UI control unit 203. These units are realized, for example, by processing in which one or more programs installed in the operator terminal 20 are executed by a processor such as a CPU.
[0040] In response to an operator's operation, the logon request unit 201 transmits to the voice recognition system 10 the logon information (operator ID and the corresponding password) entered in this logon operation.
[0041] The extension number transmitting unit 202 transmits the extension number to the voice recognition system 10 in response to an operator's input operation of the extension number.
[0042] The UI control unit 203 displays various screens (such as a log-on screen, an extension number input screen, an operator screen, etc., which will be described later) on the display of the operator terminal 20. The UI control unit 203 also accepts various input operations from the operator on these various screens.
[0043] <Logon process> The process when an operator logs on to the operator terminal 20 will be described below with reference to FIG.
[0044] The UI control unit 203 of the operator terminal 20 accepts an input operation of logon information by the operator (step S101). Here, the operator can perform the input operation of logon information on a logon screen G1000 such as that shown in Fig. 5. That is, on the logon screen G1000 shown in Fig. 5, the operator can perform the input operation of logon information by inputting his / her own operator ID in an operator ID input field G1001, inputting the password corresponding to that operator ID in a password input field G1002, and then pressing an OK button G1003.
[0045] The logon request unit 201 of the operator terminal 20 transmits the logon information (operator ID and the corresponding password) input by the input operation in step S101 to the voice recognition system 10 (step S102).
[0046] When the authentication unit 101 of the voice recognition system 10 receives logon information from the operator terminal 20, it authenticates the operator terminal 20 using this logon information (step S103). That is, the authentication unit 101 verifies whether the operator ID and password included in the logon information are correct, and if the verification is successful, it determines that the authentication is successful, and if not, it determines that the authentication is unsuccessful. Note that while it is possible to verify whether the operator ID and password are correct in various ways, a common method is to verify whether the operator ID and password included in the logon information are correct by, for example, referring to an authentication information table in which correct operator IDs and passwords are stored.
[0047] The authentication unit 101 returns the above authentication result (authentication success or authentication failure) to the operator terminal 20. In the following, the description will be continued assuming that an authentication result indicating authentication success has been returned.
[0048] The UI control unit 203 of the operator terminal 20 accepts the operator's input operation of the extension number (step S104). Here, the operator can perform the input operation of the extension number on, for example, an extension number input screen G2000 as shown in Fig. 6. That is, on the extension number input screen G2000 shown in Fig. 6, the operator can perform the input operation of the extension number by inputting the extension number of the telephone 30 installed at his / her desk in the extension number input field G2001 and then pressing the OK button G2002.
[0049] The extension number transmitting unit 202 of the operator terminal 20 transmits the extension number input by the input operation in step S104 to the voice recognition system 10 (step S105).
[0050] When the extension number storage unit 102 of the voice recognition system 10 receives the extension number from the operator terminal 20, it associates this extension number with the operator ID included in the logon information received in step S103 and stores the association in the storage unit 110 (step S106). As a result, information associating the extension number with the operator ID in the format of (extension number, operator ID) (hereinafter also referred to as correspondence information) is stored in the storage unit 110. Note that, for example, if correspondence information including the same extension number as the extension number received from the operator terminal 20 is already stored in the storage unit 110, the extension number storage unit 102 may simply update the operator ID included in the correspondence information to the operator ID included in the logon information received in step S103.
[0051] Here, on the extension number input screen G2000 shown in Fig. 6, the operator can freely input an extension number in the extension number input field G2001. This may result in an input error in the extension number. Furthermore, if the extension number of another seat is input, it may be possible to view calls made by other operators on the operator screen described below. Therefore, it is preferable that the operator be able to select from a number of predetermined extension numbers rather than being able to freely input an extension number.
[0052] In this case, for example, instead of the extension number input screen G2000 shown in Fig. 6, it is possible to display an extension number input screen G3000 as shown in Fig. 7. A pull-down button G3011 is provided in an extension number input field G30001 of the extension number input screen G3000 shown in Fig. 7, and when the operator presses the pull-down button G3011, extension numbers selectable by the operator are displayed as a pull-down menu G3012. Therefore, the operator selects the extension number of the telephone 30 installed at his / her own desk from the pull-down menu G3012, and then presses the OK button G3002 to enter the extension number. This makes it possible to prevent an incorrect extension number from being entered, or an extension number of another desk from being improperly entered, etc.
[0053] In general, contact centers often have several seats grouped together (i.e., arranged in a so-called island layout) according to the type of telephone handling work (e.g., contract work, support work, sales work, etc.). For this reason, for example, in the case of a free address system in which an operator selects his or her own seat from a specific group of seats according to the type of telephone handling work, the extension numbers selectable by the operator may be determined for each group of seats. Alternatively, for example, the extension numbers selectable by the operator may be determined for each area in which a seat or group of seats is located. In addition to these, for example, if operators are divided into groups according to the type of telephone handling work, the group to which the operator belongs may be identified from the operator ID used to log on, and the selectable extension numbers may be determined according to the group.
[0054] In addition, in the above example, logon information is entered on the logon screen and the extension number is entered on the extension number entry screen, but this is not limited to this; for example, both logon information and the extension number may be entered on the same screen.
[0055] <Speech recognition processing> In the following, it is assumed that an operator is logged on to the operator terminal 20 and is talking to a customer terminal 80 using a telephone 30 installed at the same seat as the operator terminal 20. At this time, the processing for performing voice recognition on the call and displaying the results on the display of the operator terminal 20 will be described with reference to Fig. 8. Here, while a call is being made between the telephone 30 and the customer terminal 80, packets (voice packets) of the call are captured by the NW switch 70 and sent to the voice recognition system 10 each time or after buffering a predetermined amount of packets.
[0056] When the NW switch 70 receives the captured packet (step S201), the extension number identification unit 103 of the speech recognition system 10 identifies the extension number of the telephone 30 making the call from the packet (step S202). As a result, the operator ID can be identified from the identified extension number and the correspondence information stored in the storage unit 110, and the call and the operator are linked.
[0057] Generally, a packet contains an extension number, and therefore extension number identification unit 103 can identify the extension number by analyzing the packet. However, analysis is difficult if the packet is encrypted or if the packet protocol is not a common protocol. In such cases, under the assumption that the IP address of telephone 30 is fixed, extension number identification unit 103 can identify the extension number from the IP address of the packet by referring to an extension number table that stores the IP address of telephone 30 and its extension number.
[0058] Next, the voice recognition unit 104 of the voice recognition system 10 performs voice recognition on the voice data included in the packet, and converts the voice represented by the voice data into voice-recognized text (step S203).
[0059] Next, the voice recognition unit 104 of the voice recognition system 10 refers to the correspondence information stored in the storage unit 110 and identifies the operator ID corresponding to the extension number identified in step S202 above (step S204).
[0060] Next, the voice recognition unit 104 of the voice recognition system 10 transmits the voice recognition text (voice recognition result) obtained in step S203 to the operator terminal 20 logged on with the operator ID identified in step S204 (step S205).
[0061] When the UI control unit 203 of the operator terminal 20 receives the speech recognition text representing the speech recognition result, it displays this speech recognition text on the display (step S206). For example, it is assumed that an operator screen G4000 such as that shown in Fig. 9 is displayed on the display of the operator terminal 20. This operator screen G4000 includes an utterance display field G4001 that displays speech recognition text representing the utterances of the operator and the customer, and when the speech recognition text is received, the UI control unit 203 displays the speech recognition text in chronological order for each speaker in the utterance display field G4001. This allows the operator to check the content of each utterance by each speaker during the call in text in real time.
[0062] [Second embodiment] Next, a second embodiment will be described. As described above, the extension number input screen G2000 shown in Fig. 6 may result in incorrect or unauthorized input of an extension number. In contrast, the extension number input screen G3000 shown in Fig. 7 can prevent incorrect or unauthorized input of an extension number. However, for example, if the extension numbers that an operator can select for each seat group are determined, it is possible to input an extension number for the same seat group as the seat that the operator selected. Therefore, for example, it may be possible to input the extension number of another seat in the same seat group as the seat that the operator selected, and thereby illegally view the calls of operators sitting at other seats.
[0063] Therefore, in this embodiment, a case will be described in which an alert is sent to a supervisor or the like when fraud is detected, with the aim of preventing the above-mentioned fraud. Also, a case will be described in which an extension number or the like entered by an operator is saved as a log together with a voice recognition text or the like for future audits or the like. In addition, if an operator ID is not included in a log due to the data format of the log, it becomes unclear which log belongs to which operator. Therefore, a case will be described in which such a log is associated with information representing the operator (hereinafter also referred to as operator information). Even if an operator ID can be included in a log, if an extension number is not entered or an incorrect extension number is entered, a log without an operator ID or a log with an incorrect operator ID will be created. Therefore, a case will be described in which such a log is supplemented and corrected.
[0064] In this embodiment, differences from the first embodiment will be described, and descriptions of components that are the same as those in the first embodiment will be omitted.
[0065] <Functional configuration of contact center system 1> FIG. 10 shows the functional configuration of the voice recognition system 10, the operator terminal 20, the supervisor terminal 40, and the manager terminal 50 included in the contact center system 1 according to this embodiment.
[0066] <Voice Recognition System 10> 10, the speech recognition system 10 according to this embodiment differs from the first embodiment in that it further includes a fraud detection unit 105 and a log storage unit 106. The fraud detection unit 105 and the log storage unit 106 are realized, for example, by a process in which one or more programs installed in the speech recognition system 10 are executed by a processor such as a CPU.
[0067] The fraud detection unit 105 detects if the extension number transmitted from the operator terminal 20 that has been successfully authenticated is fraudulent. Furthermore, if fraud is detected, the fraud detection unit 105 transmits a notice (hereinafter also referred to as a fraud detection notice) to the supervisor terminal 40 indicating that an invalid extension number may have been input.
[0068] The log storage unit 106 creates a log including the extension number identified by the extension number identification unit 103 and the speech recognition text converted by the speech recognition unit 104, and stores the log in the storage unit 110 as a call log. The log includes, for example, the time, the extension number, the speech recognition text, and the like. However, this is merely an example and is not limited thereto. For example, the log may include information such as a call ID, an operator ID, the name of the operator identified by the operator ID, the call start time, the telephone number of the customer terminal 80, and the like. Furthermore, the log may include, for example, information such as the operator's arrival time and departure time, the logon time when the operator logged on to the operator terminal 20, and the logout time when the operator logged out. Furthermore, for example, if the log storage period varies depending on the log, information such as the storage period may be included in the log. The log may be identified by a log ID, or, since a log is created for each call, by a call ID.
[0069] In addition to the functions described in the first embodiment, the voice recognition unit 104 also transmits the operator ID and the voice-recognized text to the supervisor terminal 40 that monitors the operator with the specified operator ID.
[0070] <Supervisor terminal 40> 10, the supervisor terminal 40 according to this embodiment has a UI control unit 401. The UI control unit 401 is realized, for example, by a process in which one or more programs installed in the supervisor terminal 40 are executed by a processor such as a CPU.
[0071] When receiving a fraud detection notification from the voice recognition system 10, the UI control unit 401 displays an alert indicating that an invalid extension number may have been entered. The UI control unit 401 also displays the voice-recognized text and the like received from the voice recognition system 10 on a predetermined screen (for example, a monitoring screen for monitoring the operator's calls).
[0072] <Administrator terminal 50> 10, the administrator terminal 50 according to this embodiment includes a UI control unit 501. The UI control unit 501 is realized, for example, by a process in which one or more programs installed in the administrator terminal 50 are executed by a processor such as a CPU.
[0073] The UI control unit 501 displays a predetermined screen (hereinafter also referred to as an operator information / log matching screen) for associating operator information with logs, and a predetermined screen (hereinafter also referred to as a log completion / correction screen) for completing / correcting logs.
[0074] Furthermore, the UI control unit 501 accepts an input operation of operator information-log association information that indicates the association between operator information and logs on the operator information-log association screen, and transmits the operator information-log association information that includes the information input by the operation to the speech recognition system 10. Here, the operator information is information that includes at least an operator ID. The operator information may include information other than the operator ID, such as the operator's name and the operator's working hours. On the other hand, the operator information-log association information is information for associating operator information with logs, and includes at least an operator ID and an extension number, for example. In the input operation of the operator information-log association information, the operator ID, extension number, etc. can be input, but various other information may also be input.
[0075] Furthermore, the UI control unit 501 accepts an input operation of log completion / correction information on the log completion / correction screen, and transmits the log completion / correction information including the information input by that operation to the speech recognition system 10. Here, the input operation of log completion / correction information can input an operator ID, etc., but other various information such as the arrival time, departure time, log-on time, log-out time, etc. of the operator identified by the operator ID may also be input.
[0076] <Speech recognition processing> Hereinafter, it is assumed that an operator is logged on to the operator terminal 20 and is talking to a customer terminal 80 using a telephone 30 installed at the same seat as the operator terminal 20. At this time, the processing for performing voice recognition on the call and displaying the results on the display of the operator terminal 20 will be described with reference to Fig. 11. Here, while a call is being made between the telephone 30 and the customer terminal 80, packets (voice packets) of the call are captured by the NW switch 70 and sent to the voice recognition system 10 each time or after buffering a predetermined amount of packets.
[0077] Steps S301 to S304 in FIG. 11 are similar to steps S201 to S204 in FIG. 8, respectively, and therefore will not be described again.
[0078] Following step S304, the fraud detection unit 105 of the voice recognition system 10 detects if the extension number transmitted from the operator terminal 20 that has been successfully authenticated is fraudulent (step S305). That is, the fraud detection unit 105 uses the operator ID identified in step S304 to determine whether the extension number associated with this operator ID is fraudulent, and if it is determined to be fraudulent, it determines that fraud has been detected.
[0079] Here, the fraud detection unit 105 may detect whether the extension number is fraudulent by, for example, the following method 1 or 2.
[0080] Method 1: Contact center operators typically answer calls according to a manual called a talk script. The talk script defines the operator's speech for each call-handling scenario. The "opening" scenario, which begins with an introduction, typically begins with a prompt like, "Thank you for calling. This is XXX (operator's last name) from the XXX call center." Therefore, Method 1 compares (matches) the speech-recognized text representing the introduction in the "opening" scenario with the last name of the operator identified by the operator ID. If the speech-recognized text contains the operator's last name, the extension number associated with the operator ID is determined to be valid; otherwise, the extension number associated with the operator ID is determined to be invalid. This comparison (matching) can be achieved, for example, by string pattern matching.
[0081] Method 2: Using a known technology called voiceprint authentication, the voice of the call is compared with the voice of the operator identified by the operator ID. If the degree of match is above a predetermined threshold, the extension number associated with that operator ID is determined to be authentic. If the degree of match is below the predetermined threshold, the extension number associated with that operator ID is determined to be authentic. Note that voice data representing the voice of the operator identified by the operator ID and data representing the features of the operator's voice must be registered in advance. By using voiceprint authentication, it is possible to detect the entry of an invalid or incorrect extension number, even if the operator is working in a remote location (e.g., the operator's home, a remote base, a shared office, etc.).
[0082] If fraud is detected in step S305, the fraud detection unit 105 of the speech recognition system 10 transmits a fraud detection notification to the supervisor terminal 40 that monitors the operator of the corresponding operator ID (step S306). Note that this fraud detection notification includes, for example, the corresponding operator ID and the extension number associated with this operator ID by the association information.
[0083] When the UI control unit 401 of the supervisor terminal 40 receives the fraud detection notification, it displays an alert on the display indicating that an invalid extension number may have been entered (step S307). At this time, the UI control unit 401 also displays the operator ID and extension number included in the fraud detection notification together with the alert. The name of the operator identified by the operator ID may also be displayed together with the operator ID. Furthermore, information about the call represented by the extension number (e.g., call start time, call end time, log, etc.) may be displayed, or information other than the call (e.g., arrival time, departure time, logon time, logout time, etc.) may be displayed. The alert may be displayed in a display format such as a pop-up window or in any other display format. Furthermore, the alert may be displayed together with sound or may be output as voice using a technology such as voice synthesis.
[0084] This allows the supervisor to easily know if an incorrect extension number has been entered.
[0085] Steps S308 and S309 in FIG. 11 are similar to steps S205 and S206 in FIG. 8, respectively, and therefore will not be described further.
[0086] Next, the speech recognition unit 104 of the speech recognition system 10 transmits the operator ID identified in step S304 and the speech recognition text (speech recognition result) obtained in step S303 to the supervisor terminal 40 that monitors the operator with the operator ID identified in step S304 (step S310).
[0087] When the UI control unit 401 of the supervisor terminal 40 receives the operator ID and the voice-recognized text, it displays the name of the operator identified by the operator ID and the voice-recognized text on the monitoring screen (step S311). This allows the supervisor to check the operator's name and the content of the call in real time, making it possible to confirm whether the operator is actually making the call. This makes it possible to deter the operator from entering an invalid extension number, and it is also expected that it will be possible to discover the entry of an invalid extension number even if an alert is not displayed.
[0088] Meanwhile, the log storage unit 106 of the voice recognition system 10 creates a log that includes at least the extension number identified in step S302 and the voice recognition text of the call (i.e., the voice recognition text created in step S303), and stores this log in the storage unit 110 (step S312). At this time, if the operator ID was identified in step S304 and the data format allows the operator ID to be included in the log, the log storage unit 106 creates a log that also includes the operator ID. This makes it possible to use the log for, for example, an audit to confirm that an invalid extension number has not been entered at a later date.
[0089] <Operator information and log matching process> In the following, it is assumed that the log does not include the operator ID (that is, the log data format does not include the operator ID). In this case, it becomes unclear which log belongs to which operator. Therefore, the following describes the process of associating operator information with logs with each other, with reference to FIG. 12.
[0090] The UI control unit 501 of the administrator terminal 50 accepts an input operation of operator information / log association information by the administrator (step S401). Here, the administrator can input the operator information / log association information by, for example, specifying the operator ID included in the operator information and the extension number included in the log on the operator information / log association screen. At this time, the administrator may specify an appropriate operator ID and extension number by referring to the clock-in time zone included in the operator information and the clock-in and clock-out times included in the log. This makes it possible, for example, to match the operator's clock-in time zone with the actual clock-in and clock-out times, thereby preventing the same operator from being associated with logs of different extension numbers in the same time zone, or to prevent logs from being associated with the operator even when the operator is absent, thereby achieving more accurate association. Furthermore, even if the operator enters an incorrect extension number, the operator's clock-in time zone can be matched with the operator's actual clock-in and clock-out times, thereby correctly associating the operator information with the log.
[0091] The UI control unit 501 of the administrator terminal 50 transmits the operator information-log association information input by the input operation in step S501 to the voice recognition system 10 (step S402).
[0092] When the log saving unit 106 of the speech recognition system 10 receives the operator information / log association information, it saves this operator information / log association information in the storage unit 110 (step S403). As a result, the operator information / log association information that associates the operator information with the log is saved in the storage unit 110, and which log belongs to which operator is associated.
[0093] Here, an example of an administrator's input operation for operator information / log association information has been described, but the present invention is not limited to this. For example, when an operator logs on (successfully authenticates) from the operator terminal 20, an operator ID is associated with an extension number, and the log-on and log-off times are recorded. Meanwhile, the log records at least the extension number, call start time, and call end time (or individual utterance times). In this case, the log and operator information can be automatically associated by matching the call start time and call end time (or individual utterance times) with the time from log-on to log-off. Therefore, operator information / log association information can be created and saved based on the matching results. In this way, operator information / log association information can be created without recording operator information in a log. Furthermore, if operator terminal information such as the identification information and IP address of the operator terminal 20 is stored, this information may be used to perform the association.
[0094] <Log completion and correction processing> In the following, it is assumed that the log may include an operator ID (that is, the data format of the log allows the operator ID to be included in the log).
[0095] For example, if the operator does not log on to the operator terminal 20 (that is, if the extension number is not entered), the operator ID will not be included in the log created in step S312 of Fig. 11. Also, if an incorrect extension number is entered, for example, the incorrect operator ID will be included in the log created in step S312 of Fig. 11. Therefore, the following describes the process of adding an operator ID to a log or correcting an operator ID included in a log, with reference to Fig. 13.
[0096] The UI control unit 501 of the administrator terminal 50 accepts an input operation of log supplementation / correction information by the administrator (step S501). Here, the administrator can perform an input operation of log supplementation / correction information by, for example, specifying the log to be supplemented / corrected on the log supplement / correction screen using a log ID (or a call ID), and then inputting the information to be supplemented / corrected (for example, an operator ID, etc.). Note that, as described above, the information to be supplemented / corrected is not limited to the operator ID, and may be, for example, the operator's arrival time, departure time, log-on time, log-out time, log storage period, etc.
[0097] The UI control unit 501 of the administrator terminal 50 transmits the log completion / correction information input by the input operation in step S501 to the speech recognition system 10 (step S502).
[0098] When the log storage unit 106 of the speech recognition system 10 receives the log completion / correction information, it uses the log completion / correction information to complete and correct the log stored in the storage unit 110 (step S503).
[0099] For example, if the log ID "001" and the operator ID "user1" are included in the log supplement / correction information, and the log with the log ID "001" stored in the storage unit 110 does not contain an operator ID, the log storage unit 106 sets the operator ID of that log to "user1." As a result, if the operator ID is not included in that log, the operator ID "user1" is supplemented.
[0100] Furthermore, for example, if the log ID "002" and the operator ID "user2" are included in the log supplement / correction information, and the log with the log ID "002" stored in the storage unit 110 contains the operator ID "user3," the log storage unit 106 corrects the operator ID of that log from "user3" to "user2." As a result, if the log contains an incorrect operator ID "user3," the operator ID is corrected to "user2." However, for the purpose of a future audit or the like, the information before correction (for example, the operator ID before correction) may be left in the log.
[0101] In addition to this, for example, if the log supplement / correction information contains a log ID "001," an arrival time of "9:00," and a departure time of "17:00," the log storage unit 106 may set the arrival time of the log with the log ID "001" stored in the storage unit 110 to "9:00" and the departure time to "17:00." In this way, after a log is created, it is also possible to set the arrival time and departure time (which may also be the log-on time or log-out time) of the operator identified by the operator ID included in the log. This makes it possible to make the log more useful for audits, for example.
[0102] [summary] As described above, the contact center system 1 according to the first and second embodiments can link a call to the operator handling the call using information (operator ID, extension number of the telephone 30) entered at the operator terminal 20 installed at the same seat as the telephone 30. This makes it possible for the contact center system 1 according to the first and second embodiments to display speech recognition text on the operator terminal 20 without CTI linkage. In addition to this, by linking a call to the operator handling the call, it becomes possible to realize various functions that become possible when CTI linkage is performed (for example, evaluation of call quality for each operator).
[0103] Therefore, even if there are various circumstances that make it impossible to introduce CTI (for example, when the existing PBX does not have CTI integration functionality or when CTI integration is difficult due to insufficient capacity, but the cost of replacing the PBX is unacceptable), it is still possible to realize various functions, such as providing support to operators and evaluating the quality of calls.
[0104] Furthermore, the contact center system 1 according to the second embodiment can detect incorrect or unauthorized input of extension numbers, which may occur in the first embodiment, and can also store logs for auditing such errors or unauthorized input. This allows for operation with better security than the contact center system 1 according to the first embodiment.
[0105] The present invention is not limited to the above-described specifically disclosed embodiments, and various modifications, changes, and combinations with known technologies are possible without departing from the scope of the claims. [Explanation of symbols]
[0106] 1. Contact Center System 10 Voice Recognition System 20 Operator terminal 30 telephone 40 Supervisor Terminal 50 Administrator terminal 60 PBX 70 Network Switch 80 Customer terminals 90 Communication Network 101 Authentication Department 102 Extension number storage unit 103 Extension Number Identification Part 104 Voice Recognition Unit 105 Fraud Detection Unit 106 Log storage unit 110 Storage section 201 Logon Request Part 202 Extension number sending section 203 UI control section 401 UI control section 501 UI control unit E. Contact Center Environment
Claims
1. a storage unit that stores correspondence information in a storage unit, the correspondence information associating user identification information used in authenticating a first terminal with first identification information transmitted from the first terminal; a first identification unit that identifies second identification information from packet data in a communication process; a voice recognition unit that converts voice represented by voice data included in the packet data into text by voice recognition; a second identification unit that identifies user identification information associated with first identification information that matches the second identification information, using the correspondence information stored in the storage unit; a fraud detection unit that uses the second identification information to determine whether the first identification information included in the correspondence information is fraudulent; a presentation unit that, when the fraud detection unit determines that the first identification information is fraudulent, transmits presentation information to a second terminal of a monitor who monitors the user identified by the user identification information, for presenting a presentation to the monitor requesting confirmation of the association between the user identification information and the first identification information in the correspondence information; a transmitting unit that transmits the text to a first terminal that is logged on with the user identification information identified by the second identifying unit; and The fraud detection unit An information processing device that determines that the first identification information is not fraudulent if the last name of the user identified by the user identification information is included in text representing the speech recognition result of an opening scene, which is a scene that represents the start of communication realized by the communication processing, and determines that the first identification information is fraudulent if the last name of the user identified by the user identification information is not included in the text.
2. a storage unit that stores correspondence information in a storage unit, the correspondence information associating user identification information used in authenticating a first terminal with first identification information transmitted from the first terminal; a first identification unit that identifies second identification information from packet data in a communication process; a voice recognition unit that converts voice represented by voice data included in the packet data into text by voice recognition; a second identification unit that identifies user identification information associated with first identification information that matches the second identification information, using the correspondence information stored in the storage unit; a transmitting unit that transmits the text to a first terminal that is logged on with the user identification information identified by the second identifying unit; a log storage unit that creates log information including at least the second identification information and the text and stores the log information in the storage unit; and The log storage unit An information processing device that adds the specified target information to the log information or modifies the target information included in the log information to the specified target information in accordance with the specification of the log information and target information including at least one of the user identification information and time information on a specified screen displayed on a third terminal.
3. a storage step of storing correspondence information in a storage unit, the correspondence information associating user identification information used in authenticating a first terminal with first identification information transmitted from the first terminal; a first identification procedure for identifying second identification information from packet data in a communication process; a speech recognition step of converting speech represented by the speech data included in the packet data into text by speech recognition; a second identification step of identifying user identification information associated with first identification information that matches the second identification information, using correspondence information stored in the storage unit; a fraud detection step of determining whether the first identification information included in the correspondence information is fraudulent by using the second identification information; a presentation step of transmitting, when the first identification information is determined to be fraudulent by the fraud detection step, presentation information to a second terminal of a monitor who monitors the user identified by the user identification information, for presenting a presentation to the monitor requesting confirmation of the association between the user identification information and the first identification information in the correspondence information; a sending step of sending the text to a first terminal logged on with the user identification information identified by the second identifying step; The computer executes The fraud detection procedure includes: An information processing method, comprising: determining that the first identification information is not fraudulent if the surname of the user identified by the user identification information is included in text representing the speech recognition result of an opening scene, which is a scene representing the start of communication realized by the communication processing; and determining that the first identification information is fraudulent if the surname of the user identified by the user identification information is not included in the text.
4. a storage step of storing correspondence information in a storage unit, the correspondence information associating user identification information used in authenticating a first terminal with first identification information transmitted from the first terminal; a first identification procedure for identifying second identification information from packet data in a communication process; a speech recognition step of converting speech represented by the speech data included in the packet data into text by speech recognition; a second identification step of identifying user identification information associated with first identification information that matches the second identification information, using correspondence information stored in the storage unit; a sending step of sending the text to a first terminal logged on with the user identification information identified by the second identifying step; a log storage step of creating log information including at least the second identification information and the text, and storing the log information in the storage unit; The computer executes The log storage procedure includes: An information processing method in which, in accordance with the specification of the log information and target information including at least one of the user identification information and time information on a specified screen displayed on a third terminal, the specified target information is added to the log information, or the target information included in the log information is modified to the specified target information.
5. A program that causes a computer to function as the information processing device according to claim 1 or 2.
Citation Information
Patent Citations
System and method for dictating call content
JP2005123869A
Operator's operation support system
JP2009031810A
Communication terminal, communication method, and communication system
JP2011066730A
Call center system and call center management method
JP2021158413A