Information processing device, information processing method and program

Abstract

To support grasping of an interaction content.SOLUTION: An information processing device includes: a specification unit for specifying a scene representing a scene of interaction when utterance is made based on utterance in prescribed interaction; and a creation unit for creating visualization information for visualizing a time series of utterance in interaction, a time series of the scenes and a relation between the scenes based on relationship definition information defining the scenes having relationship. The relationship definition information includes at least hierarchy structure definition in which the scenes with a parent-child relation are defined and relation definition defining the scenes in a depending relation. The creation unit creates visualization information for giving a component which hides a second scene and displays the second scene according to selection operation of a user to a first scene to be displayed when one or more second scenes having the first scene as a parent continue immediately after the first scene in the time series of the scenes.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] Contact centers (also known as call centers) generally perform work known as after-call work (ACW). ACW refers to work that is done after a customer has finished answering the phone, such as creating a record of the call or placing an order for products or services.

[0003] While ACW is an important task, it is also a time when an operator cannot respond to customers, and therefore there is a demand for improving the efficiency of ACW. To address this, one known technology for improving the efficiency of creating interaction records is to convert utterances made during a call with a customer into text using speech recognition technology and identify the scene of the utterance from the text (see, for example, Patent Document 1). Here, a scene refers to a scene in a conversation between an operator and a customer, and examples include "opening," which refers to a scene where an initial greeting is made, "inquiry understanding," which refers to a scene where the content of a customer's inquiry is understood, "response," which refers to a case where an answer and response is made to the content of the inquiry, and "closing," which refers to a scene where a final greeting is made, etc. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2020 / 036189 Summary of the Invention [Problem to be solved by the invention]

[0005] However, when conversations on various topics take place during a call, various scenes are identified, making it difficult to grasp the relationships between the scenes (e.g., the structural relationships between the scenes, the associations between the scenes, etc.). This makes it difficult to grasp the content of the entire conversation, and for example, it can take a long time to create a call record.

[0006] An embodiment of the present invention has been made in consideration of the above points, and aims to support understanding of the contents of a conversation. [Means for solving the problem]

[0007] In order to achieve the above object, an information processing device according to one embodiment includes: an identification unit that identifies, based on an utterance in a predetermined dialogue, a scene representing a scene of the dialogue when the utterance was made; and a creation unit that creates visualization information for visualizing a timeline of the utterance in the dialogue, a timeline of the scenes, and the relationships between the scenes, based on relationship definition information that defines scenes that are related to each other, wherein the relationship definition information includes at least a hierarchical structure definition that defines scenes that are in a parent-child relationship, and an association definition that defines scenes that are dependent on each other, and the creation unit creates visualization information for hiding the second scene when a first scene is immediately followed by one or more second scenes that have the first scene as a parent, and for displaying the second scene by attaching a component to the first scene in response to a user selection operation. [Effects of the Invention]

[0008] It can help understand the content of the conversation. [Brief explanation of the drawings]

[0009] [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] 1 is a diagram illustrating an example of a functional configuration of a contact center system according to a first embodiment; [Figure 3]FIG. 10 is a diagram illustrating an example of a hierarchical structure definition included in definition information. [Figure 4] FIG. 10 is a diagram illustrating an example of a related definition included in definition information. [Figure 5] 10 is a flowchart illustrating an example of a call visualization process according to the first embodiment. [Figure 6] FIG. 1 is a diagram (part 1) for explaining an example of an operator screen that visualizes the hierarchical structure of a scene. [Figure 7] FIG. 2 is a diagram (part 2) for explaining an example of an operator screen that visualizes the hierarchical structure of a scene. [Figure 8] FIG. 10 is a diagram for explaining an example of an operator screen that visualizes the relevance of scenes. [Figure 9] FIG. 10 is a diagram illustrating an example of an operator screen that visualizes scene relevance and supplementary information. [Figure 10] FIG. 10 is a diagram schematically illustrating a specific example of a modified example. [Figure 11] FIG. 10 is a diagram illustrating an example of a functional configuration of a contact center system according to a second embodiment. [Figure 12] 10 is a flowchart illustrating an example of a call visualization process according to the second embodiment. [Figure 13] FIG. 10 is a diagram illustrating an example of an operator screen in which a talk script according to a scene is visualized as support information. [Figure 14] FIG. 10 is a diagram illustrating an example of an operator screen that visualizes next scene candidates and their transition probabilities as support information. DETAILED DESCRIPTION OF THE INVENTION

[0010] A first embodiment and a second embodiment will be described below 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 can assist a contact center operator in understanding the content of a conversation (i.e., the content of a call) between a contact center and a customer. However, the contact center is just one example, and the system can be similarly applied to a location other than a contact center, for example, when understanding the content of a call made by a person working in an office. Furthermore, a call is not limited to two parties, but may be made between three or more parties.

[0011] Furthermore, in the following, it is assumed that a contact center operator will be making a voice call with a customer, but this is not limited to this, and the same can be applied to cases such as text chat (including those that can send and receive stamps, attachments, etc. in addition to text) and video calls.

[0012] [First embodiment] First, a first embodiment will be described. In this embodiment, a case will be described in which the relationship between scenes is visualized to make it easier to understand the contents of a call, with the aim of improving the efficiency of ACW, such as creating a call log. Here, ACW generally refers to post-processing work that is performed after a call with a customer has ended (i.e., offline), and includes, in addition to creating a call log, tasks such as ordering products or services.

[0013] <Overall structure> 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 call visualization device 10, a speech recognition system 20, an operator terminal 30, a manager terminal 40, a PBX (Private Branch Exchange) 50, and a customer terminal 60. Here, the call visualization device 10, the speech recognition system 20, the operator terminal 30, the manager terminal 40, and the PBX 50 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 call visualization device 10 creates information (hereinafter also referred to as visualization information) for visualizing utterances in a call between a customer and an operator, the scenes in which the utterances occur, and the relationships between the scenes, and transmits the visualization information to the operator terminal 30 (or the administrator terminal 40). The visualization information is information for displaying an operator screen, etc., which will be described later, on the display of the operator terminal 30, and is, for example, screen information defined in HTML (Hypertext Markup Language), CSS (Cascading Style Sheets), etc.

[0015] The voice recognition system 20 performs voice recognition on a call between a customer and an operator, and converts utterances made during the call into text (character strings). Hereinafter, it is assumed that voice recognition is performed on both the customer's utterance and the operator's utterance, but this is not limiting, and for example, voice recognition may be performed on only one of the utterances.

[0016] The operator terminal 30 is a terminal of any type, such as a PC (personal computer), used by an operator who responds to inquiries from customers, and functions as an IP (Internet Protocol) telephone.

[0017] The manager terminal 40 is a terminal such as a PC used by a manager who manages operators (such a manager is also called a supervisor).

[0018] The PBX 50 is a telephone exchange (IP-PBX) and is connected to a communication network 70 including a Voice over Internet Protocol (VoIP) network and a Public Switched Telephone Network (PSTN).

[0019] The customer terminal 60 is a variety of terminals used by customers, such as a smartphone, a mobile phone, or a landline phone.

[0020] Note that the overall configuration of the contact center system 1 shown in FIG. 1 is just an example, and other configurations may be used. For example, in the example shown in FIG. 1, the call visualization device 10 is included in the contact center environment E (i.e., the call visualization device 10 is an on-premise type), but all or part of the functions of the call visualization device 10 may be implemented by a cloud service or the like. Similarly, in the example shown in FIG. 1, the speech recognition system 20 is an on-premise type, but all or part of the functions of the speech recognition system 20 may be implemented by a cloud service or the like. Similarly, in the example shown in FIG. 1, the PBX 50 is an on-premise type telephone exchange, but it may be implemented by a cloud service.

[0021] Furthermore, although the operator terminal 30 has been described as functioning as an IP telephone, for example, a telephone separate from the operator terminal 30 may be included in the contact center system 1.

[0022] <Functional configuration> FIG. 2 shows the functional configurations of the call visualization device 10, the operator terminal 30, and the manager terminal 40 included in the contact center system 1 according to this embodiment.

[0023] ≪Call visualization device 10≫ As shown in Fig. 2, the call visualization device 10 according to this embodiment includes a scene identification unit 101 and a visualization information creation unit 102. These units are realized, for example, by processing executed by a processor such as a CPU (Central Processing Unit) by one or more programs installed in the call visualization device 10. The call visualization device 10 according to this embodiment also includes a relationship definition information storage unit 110 and a call history information storage unit 120. These units can be realized, for example, by storage devices such as HDDs (Hard Disk Drives), SSDs (Solid State Drives), and flash memories.

[0024] The scene identification unit 101 identifies the scene of each utterance in a call between a customer and an operator based on the speech recognition results for the call (i.e., the text representing the customer's utterance and the text representing the operator's utterance). The scene of each utterance can be identified using a known scene identification technique or scene classification technique. For example, the scene of each utterance can be identified using the technique described in Patent Document 1.

[0025] Furthermore, the scene identification unit 101 stores time-series information that associates the speaker (customer or operator), text representing the utterance, and the scene of the utterance in the call history information storage unit 120 as call history information 121. Note that the call history information 121 also includes information such as a call ID for identifying the call, the operator ID of the operator who answered the call, the call date and time, etc.

[0026] Here, a scene refers to a scene of a conversation between an operator and a customer, and the types of scenes that exist are predefined. Typical scenes include, for example, an "opening" scene representing an initial greeting, an "inquiry understanding" scene representing a scene in which the content of a customer's inquiry is understood, a "response" scene representing a case in which an answer and response are given to the inquiry, and a "closing" scene representing a final greeting, etc.

[0027] An utterance is a segment of speech (or text representing the results of speech recognition of that speech). The range of a segment can be set arbitrarily, but for example, the end-of-speech unit described in Patent Document 1 can be set as a segment. An end-of-speech unit is a unit of speech that a speaker wants to speak, and is, for example, a range delimited by a period "." or a question mark "?" when speech is converted into text by speech recognition.

[0028] The visualization information creation unit 102 creates visualization information for visualizing text representing each speaker's utterance, the scenes of the utterance, and the relationships between the scenes, based on the relationship definition information 111 stored in the relationship definition information storage unit 110. Then, the visualization information creation unit 102 transmits the visualization information to the operator terminal 30 (or the administrator terminal 40). The relationship definition information 111 is information that defines the relationships between scenes (for example, the structural relationships between scenes, the associations between scenes, etc.). Specific examples of the relationship definition information 111 will be described later.

[0029] The relationship definition information storage unit 110 stores relationship definition information 111. The call history information storage unit 120 stores call history information 121. The relationship definition information 111 is created in advance and stored in the relationship definition information storage unit 110.

[0030] Here, the relationship definition information 111 includes at least a hierarchical structure definition that defines the hierarchical structural relationship (parent-child relationship) between scenes, and a relationship definition that defines the relationship between scenes.

[0031] An example of a hierarchical structure definition is shown in Figure 3. The example shown in Figure 3 defines the structural relationship between three scenes: "Accident situation understanding," "Injury status understanding," and "Drivability understanding." Specifically, the relationship is defined such that "Accident situation understanding" is the parent, and "Injury status understanding" and "Drivability understanding" are the children. Such parent-child relationships are defined based on, for example, the semantic inclusion relationship between scenes or the conceptual hierarchical relationship.

[0032] An example of a relationship definition is shown in Figure 4. The example shown in Figure 4 defines the relationship between two scenes, "cancel option" and "bill notice." Specifically, the relationship defined expresses the relationship that if "cancel option" appears during a call, then "bill notice" must also appear. Such relationships are defined, for example, based on the dependency between scenes. A dependency between scenes means that if one scene appears during a call, then another scene must also appear.

[0033] In addition to the hierarchical structure definition and the relationship definition, various other relationships may be defined in the relationship definition information 111. For example, when the same scene appears multiple times, a relationship that the same scenes are related to each other may be defined as a relationship definition to link the same scenes. Furthermore, for example, a parallel relationship or an opposite relationship that indicates semantic opposites may be defined. In addition to this, for example, a relationship that indicates a relationship between a scene that was interrupted midway and a scene where it is resumed may be defined. The relationship that indicates a relationship between a scene that was interrupted midway and a scene where it is resumed will be described in more detail in a modified example described below.

[0034] <Operator terminal 30> 2, the operator terminal 30 according to this embodiment includes a UI control unit 301. The UI control unit 301 is realized, for example, by a process in which one or more programs installed in the operator terminal 30 are executed by a processor such as a CPU.

[0035] The UI control unit 301 displays an operator screen, which will be described later, on the display based on the visualization information received from the call visualization device 10.

[0036] <Administrator terminal 40> 2, the administrator terminal 40 according to this embodiment includes 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 administrator terminal 40 are executed by a processor such as a CPU.

[0037] Based on the visualization information received from the call visualization device 10, the UI control unit 401 displays a screen similar to an operator screen (which may be called a supervisor screen or an administrator screen, etc.) on the display, as will be described later.

[0038] <Call visualization processing> Hereinafter, with the aim of improving the efficiency of ACW, a process of displaying an operator screen on the display of the operator terminal 30 after the call with the customer has ended and visualizing the content of the call will be described with reference to Fig. 5. In the following, it is assumed that the voice recognition system 20 performs voice recognition on the call between the customer and the operator, and the voice recognition result is sent to the call visualization device 10.

[0039] First, the scene identification unit 101 identifies the scene of each utterance in the call based on the speech recognition result received from the speech recognition system 20 (step S101). As a result, call history information 121 in which the speaker (customer or operator), text representing the utterance, and the scene of the utterance are associated with each other is created and stored in the call history information storage unit 120. As described above, the scene identification unit 101 may identify the scene of each utterance using a known scene identification technique or scene classification technique, such as the technique described in Patent Document 1.

[0040] Next, the visualization information creation unit 102 creates visualization information for visualizing the text representing each speaker's utterance, the scenes of the utterance, and the relationships between the scenes, based on the relationship definition information 111 stored in the relationship definition information storage unit 110 (step S102).

[0041] Then, the visualization information creation unit 102 transmits the visualization information created in step S102 to the operator terminal 30 of the operator who answered the call (step S103). As a result, an operator screen (to be described later) is displayed on the display of the operator terminal 30 by the UI control unit 301 based on the visualization information received from the call visualization device 10.

[0042] In the above step S103, the visualization information is sent to the operator terminal 30. However, for example, the visualization information may be sent to the administrator terminal 40 in response to a request from the administrator terminal 40. In this case, the UI control unit 401 displays a supervisor screen on the display of the administrator terminal 40 based on the visualization information received from the call visualization device 10.

[0043] <Operator screen> An operator screen displayed on the display of the operator terminal 30 will be described below as an example.

[0044] Operator screen example 1-1 It is assumed that visualization information that visualizes the hierarchical structure of the relationships between scenes has been created based on the relationship definition information 111 stored in the relationship definition information storage unit 110. In this case, an example of an operator screen displayed by the UI control unit 301 based on the visualization information will be described with reference to FIGS. 6 and 7.

[0045] 6 includes a scene display field 1100 and an utterance display field 1200. The scene display field 1100 displays scene buttons corresponding to scenes identified during the call in chronological order. The utterance display field 1200 displays utterances of scenes corresponding to a scene button selected from the scene display field 1100 in chronological order.

[0046] In the example shown in Figure 6, scene display field 1100 displays scene button 1110 corresponding to "Opening," scene button 1120 corresponding to "Understanding the Circumstances," scene button 1130 corresponding to "Understanding the Accident Situation," scene button 1140 corresponding to "Insurance Response," and scene button 1150 corresponding to "Closing."

[0047] Additionally, scene button 1130 corresponding to "Accident Situation Grasp" is provided with an unfold button 1131 for displaying scene buttons corresponding to scenes that have "Accident Situation Grasp" as their parent (in other words, child scenes of "Accident Situation Grasp"). Similarly, scene button 1140 corresponding to "Insurance Response" is provided with an unfold button 1141 for displaying scene buttons corresponding to scenes that have "Insurance Response" as their parent (in other words, child scenes of "Insurance Response").

[0048] For example, when the expand button 1131 is selected by the operator, as shown in Fig. 7, a scene button 1160 corresponding to the scene "Understanding Injury Status," which has "Understanding Accident Situation" as its parent, and a scene button 1170 corresponding to the scene "Understanding Self-Driving Status," which has "Understanding Accident Situation" as its parent, are displayed. This indicates that "Understanding Accident Situation" appears as a scene during the call, followed by "Injury Status," and then "Understanding Self-Driving Status." At this time, the expand button 1131 changes to a compress button 132, which hides the scene buttons 1160 and 1170 and returns to the state shown in Fig. 6.

[0049] In this way, on the operator screen according to this embodiment, if a scene identified during a call has a parent-child relationship with another scene, and one or more child scenes appear immediately after the parent scene, the child scenes are hidden and an expand button for displaying these child scenes is added to the scene button corresponding to the parent scene. As a result, even if the scene structure during a call has a complex hierarchical structure, only the scene at the highest level is displayed, allowing the operator to easily grasp the scene structure of the entire call.

[0050] Furthermore, if the operator wants to check a more detailed scene structure (i.e., a scene structure including scenes at lower levels), he or she can press an expand button to display the child scenes of the scene to which the expand button is attached. This allows the operator to easily grasp the scene structure of the entire call, while also being able to check a more detailed scene structure if necessary.

[0051] In the examples shown in Figures 6 and 7, "Accident Situation Grasp" has child scenes "Injury Status Grasp" and "Drivability Grasp," and the hierarchical structure between scenes is two levels, but this is just an example, and the hierarchical structure between scenes may be three levels or more. For example, in the case of a three-level structure where a child scene of a certain scene has further child scenes (grandchild scenes), an expansion button for displaying the grandchild scenes is added to the scene button corresponding to the child scene of the certain scene. The same applies to a structure with four or more levels.

[0052] Operator screen example 1-2 It is assumed that visualization information that visualizes the association between scenes as a relationship is created based on the relationship definition information 111 stored in the relationship definition information storage unit 110. In this case, an example of an operator screen displayed by the UI control unit 301 based on the visualization information will be described with reference to FIG.

[0053] 8 includes a scene display field 2100 and an utterance display field 2200. The scene display field 2100 displays scene buttons corresponding to scenes identified during the call in chronological order. The utterance display field 2200 displays utterances of scenes corresponding to a scene button selected from the scene display field 2100 in chronological order.

[0054] In the example shown in Figure 8, scene display field 2100 displays scene button 2110 corresponding to "Opening," scene button 2120 corresponding to "Understanding the purpose," scene button 2130 corresponding to "Identity verification," scene button 2140 corresponding to "Change delivery address," scene button 2150 corresponding to "Understanding the purpose," scene button 2160 corresponding to "Cancel option," scene button 2170 corresponding to "Billing notice," and scene button 2180 corresponding to "Closing."

[0055] Furthermore, the scene button 2160 corresponding to "cancel option" and the scene button 2170 corresponding to "notice of billing" are connected by a relation line 2310. This indicates that "cancel option" and "notice of billing" are related scenes.

[0056] Furthermore, the scene button 2120 corresponding to "understand the subject" and the scene button 2150 corresponding to "understand the subject" are connected by a connection line 2320. This indicates that "understand the subject" appears multiple times.

[0057] In this way, on the operator screen according to this embodiment, if there are related scenes among the scenes identified during a call (including the case where there are multiple identical scenes), those scenes are connected by a related line, which allows the operator to easily grasp the related scenes among the scenes of the entire call.

[0058] If a scene identified during a call has a parent-child relationship and one or more child scenes appear immediately after the parent scene, the child scenes are hidden and an expand button for displaying these child scenes is added to the scene button corresponding to the parent scene. For example, in the example shown in Figure 8, an expand button is added to the scene button 2160 corresponding to "Cancel option."

[0059] In addition, although the example shown in FIG. 8 shows a case where two scenes are related, a case where three or more scenes are related is also similarly connected by a relation line.

[0060] Operator screen example 1-3 Here, the relationship definition information 111 may define not only the relationships between scenes but also conditions, such as visualizing some information (hereinafter referred to as supplementary information) when a certain relationship is not satisfied. In the following, it is assumed that visualization information has been created that visualizes supplementary information when multiple identical scenes exist or when one of two scenes in a dependent relationship does not exist, in addition to the relationships between scenes. In this case, an example of an operator screen displayed by the UI control unit 301 based on the visualization information will be described with reference to FIG. 9.

[0061] 9 includes a scene display field 3100, an utterance display field 3200, and a supplemental information display field 3300. In the scene display field 3100, scene buttons corresponding to scenes identified during the call are displayed in chronological order. In the utterance display field 3200, utterances of the scene corresponding to the scene button selected from the scene display field 3100 are displayed in chronological order. In the supplemental information display field 3300, supplemental information is displayed.

[0062] In the example shown in Figure 9, scene display field 3100 displays scene button 3110 corresponding to "Opening", scene button 3120 corresponding to "Understanding the purpose", scene button 3130 corresponding to "Identity verification", scene button 3140 corresponding to "Change delivery address", scene button 3150 corresponding to "Understanding the purpose", scene button 3160 corresponding to "Cancel option", and scene button 3170 corresponding to "Closing".

[0063] Furthermore, scene button 3120 corresponding to "Understanding the Subject Matter" and scene button 3150 corresponding to "Understanding the Subject Matter" are connected by a relation line 3310. On the other hand, although scene button 3160 corresponding to "Cancel Option" exists, "Notice of Billing," which is a scene related to "Cancel Option," does not appear.

[0064] For this reason, the supplementary information display field 3300 displays the supplementary information "There are multiple matters to be understood" and the supplementary information "The necessary scene (bill notification) was not identified." In the example shown in Fig. 9, the supplementary information is further classified into levels according to the importance, with "There are multiple matters to be understood" being at the INFO level and "The necessary scene (bill notification) was not identified." being at the WARN level.

[0065] In this way, the operator screen according to this embodiment displays supplemental information when the conditions defined in the relationship definition information 111 are not met (for example, when a certain relationship is not met). This allows the operator to easily understand, for example, when there are multiple instances of the same scene, or when a scene among multiple scenes that are in a dependent relationship does not exist.

[0066] <Summary of the First Embodiment> As described above, the contact center system 1 according to this embodiment displays an operator screen on the operator terminal 30 after a call with a customer has ended, allowing the operator to easily understand the contents of the call, primarily for the purpose of improving the efficiency of ACW. This operator screen visualizes not only the chronological order of utterances made during the call and the chronological order of the scenes in which those utterances occurred, but also the relationships between scenes (e.g., the hierarchical structure between scenes, the relationships between scenes, etc.) and supplementary information. This allows the operator to easily understand the contents of the call necessary for ACW.

[0067] Although this embodiment is primarily intended to improve the efficiency of ACW and is directed to cases where an operator screen is displayed offline, it can also be applied to online situations (i.e., during a call with a customer). That is, the relationships between scenes (e.g., the hierarchical structure between scenes, the association between scenes, etc.) and supplementary information described in this embodiment may also be visualized on the operator screen displayed during a call with a customer.

[0068] Modifications In a call with a customer, it is possible that after transitioning to a certain scene A, the conversation will transition to one or more other scenes, and then transition back to the original scene A. In this case, scene A will be interrupted, the conversation will transition to one or more other scenes, and then scene A will be resumed. In this modified example, it is assumed that at least a relationship that expresses a relationship between the scene that was interrupted midway and the scene where it was resumed is defined in the relationship definition information 111.

[0069] A specific example is the case where the scene transitions in the order of (1) to (8) below. In this case, (2) "understanding the purpose (requesting address change)" is interrupted and then resumed at (4).

[0070] (1) Opening (2) Understanding the purpose (request for address change) (3) Identity verification (4) Understanding the purpose (request for address change) (5) Support (address change support) (6) Understanding the purpose (checking the contents of the invoice) (7) Response (confirmation of billing details) (8) Closing At this time, in the scene display column of the operator screen, the scene button corresponding to (2) “Understanding the matter (request for address change)” and the scene button corresponding to (4) “Understanding the matter (request for address change)” are connected by a relationship line.

[0071] Note that "Understanding the Subject Matter (Confirming the Invoice Contents)" in (6) and "Understanding the Subject Matter (Requesting a Change of Address)" in (2) and (3) can be considered to be scenes that have the same parent scene, "Understanding the Subject Matter." Therefore, the scene button corresponding to "Understanding the Subject Matter (Confirming the Invoice Contents)" in (6), the scene button corresponding to "Understanding the Subject Matter (Requesting a Change of Address)" in (2), and the scene button corresponding to "Understanding the Subject Matter (Requesting a Change of Address)" in (3) can be connected by a relational line. In this case, these three scene buttons can be connected in parallel by connecting lines, or the scene buttons for "Understanding the Subject Matter (Requesting a Change of Address)" in (2) and (3) can be connected to each other by connecting lines, and then the two scenes connected by these connecting lines can be connected by connecting lines to the scene button for "Understanding the Subject Matter (Confirming the Invoice Contents)" in (6).

[0072] Specifically, if the scene button corresponding to (2) "Understanding the matter (requesting address change)" is A1, the scene button corresponding to (3) "Understanding the matter (requesting address change)" is A2, the scene button corresponding to (4) "Understanding the matter (requesting address change)" is A', and the connecting line is represented as "-", the connection may be "A1-A2-A'" or "(A1-A2)-A'". A specific example of connecting the scene buttons to "(A1-A2)-A'" is shown in Figure 10.

[0073] [Second embodiment] Next, a second embodiment will be described. In this embodiment, a case will be described in which an operator screen is displayed to support online operators in understanding the contents of calls and assisting them in responding to customers. In the following, differences from the first embodiment will be mainly described, and explanations of components that are the same as or similar to those in the first embodiment will be omitted.

[0074] <Functional configuration> FIG. 11 shows the functional configurations of the call visualization device 10, the operator terminal 30, and the manager terminal 40 included in the contact center system 1 according to this embodiment.

[0075] ≪Call visualization device 10≫ As shown in Fig. 11, the call visualization device 10 according to this embodiment includes a scene identification unit 101, a visualization information creation unit 102, and a support information acquisition and creation unit 103. Each of these units is realized, for example, by a processor such as a CPU executing one or more programs installed in the call visualization device 10. The call visualization device 10 according to this embodiment also includes a relationship definition information storage unit 110, a call history information storage unit 120, and a talk script storage unit 130. Each of these units can be realized, for example, by a storage device such as an HDD, SSD, or flash memory.

[0076] The visualization information creation unit 102 creates visualization information based on the relationship definition information 111 stored in the relationship definition information storage unit 110 and the support information acquired or created by the support information acquisition / creation unit 103. Then, the visualization information creation unit 102 transmits the visualization information to the operator terminal 30 (or the manager terminal 40). The support information is information for supporting responses to customers. In this embodiment, the support information is assumed to be a talk script 131 (described later) and transition probability information to the next scene candidate.

[0077] The support information acquisition and creation unit 103 acquires or creates support information based on the current scene identified by the scene identification unit 101. That is, for example, if a talk script 131 is assumed as support information, the support information acquisition and creation unit 103 acquires the talk script 131 for the current scene from the talk script storage unit 130. On the other hand, for example, if transition probability information to a next scene candidate is assumed as support information, the support information acquisition and creation unit 103 creates transition probability information to the next scene candidate for the current scene based on the call history information 121. Here, the call history information 121 is time-series information that associates speakers, text representing their utterances, and scenes of those utterances. Therefore, the support information acquisition and creation unit 103 can statistically calculate the transition probability from the current scene to the next scene candidate using multiple pieces of call history information 121 stored in the call history information storage unit 120. For this reason, the support information acquisition and creation unit 103 creates the next scene candidate and its transition probability as support information.

[0078] The talk script storage unit 130 stores a talk script 131. The talk script 131 is a collection of exemplary utterances (so-called script) of an operator determined for each scene.

[0079] <Call visualization processing> Hereinafter, with the aim of supporting an operator online, a process of displaying an operator screen on the display of the operator terminal 30 during a call with a customer and visualizing information for supporting the operator's response to the customer along with the content of the call will be described with reference to Fig. 12. In the following, it is assumed that the voice recognition system 20 performs voice recognition on the call between the customer and the operator in real time (for example, for each utterance), and the voice recognition results are also transmitted to the call visualization device 10 in real time.

[0080] First, the scene identification unit 101 identifies the scene of the speech represented by the speech recognition result based on the speech recognition result received from the speech recognition system 20 (step S201).

[0081] Next, the support information acquisition / creation unit 103 sets the scene identified in step S201 as the current scene, and acquires or creates support information based on the current scene (step S202).

[0082] Next, the visualization information creation unit 102 creates visualization information based on the relationship definition information 111 stored in the relationship definition information storage unit 110 and the support information acquired or created in step S202 above (step S203).

[0083] Then, the visualization information creation unit 102 transmits the visualization information created in step S203 to the operator terminal 30 of the operator attending the call (step S204). As a result, an operator screen (to be described later) is displayed on the display of the operator terminal 30 by the UI control unit 301 based on the visualization information received from the call visualization device 10.

[0084] In the above step S204, the visualization information is sent to the operator terminal 30. In addition, for example, in response to a request from the administrator terminal 40, the visualization information may be sent to the administrator terminal 40. In this case, the UI control unit 401 displays a supervisor screen on the display of the administrator terminal 40 based on the visualization information received from the call visualization device 10.

[0085] <Operator screen> An operator screen displayed on the display of the operator terminal 30 will be described below as an example.

[0086] Operator screen example 2-1 It is assumed that visualization information has been created based on the relationship definition information 111 stored in the relationship definition information storage unit 110 and the talk script 131 (support information) of the scene (current scene) identified in step S201. At this time, an example of an operator screen displayed by the UI control unit 301 based on the visualization information will be described with reference to FIG.

[0087] The operator screen 4000 shown in Fig. 13 includes a scene display field 4100, an utterance display field 4200, and a talk script display field 4300. Each time a scene is identified during the call, the scene display field 4100 displays a scene button corresponding to the scene in chronological order. The utterance display field 4200 displays the speech recognition result (text) from the speech recognition system 20 in chronological order for each utterance. The speech recognition result from the speech recognition system 20 is transmitted in real time from the speech recognition system 20 to the operator terminal 30. The talk script display field 4300 displays the talk script 131 of the current scene ("Understanding the Accident Situation" in the example shown in Fig. 13).

[0088] In this way, the talk script 131 of the current scene during a call with a customer is displayed on the operator terminal screen according to this embodiment, allowing the operator to know what to say to the customer or confirm in the current scene.

[0089] In the example shown in Figure 13, each scene button displayed in the scene display field 4100 is not assigned an expand button or connected by a related line, but this is for simplicity's sake; as explained in the first embodiment, an expand button (or compress button) may be assigned or the buttons may be connected by a related line.

[0090] Operator screen example 2-2 It is assumed that visualization information has been created based on the relationship definition information 111 stored in the relationship definition information storage unit 110 and the transition probability information (support information) of the next scene candidate of the scene (current scene) identified in the above step S201. At this time, an example of an operator screen displayed by the UI control unit 301 based on the visualization information will be described with reference to FIG.

[0091] 14 includes a scene display field 5100 and an utterance display field 5200. In the scene display field 5100, each time a scene is identified during the call, a scene button corresponding to the scene is displayed in chronological order, along with the next scene candidate and its transition probability. In the utterance display field 5200, the speech recognition result (text) of the speech recognition system 20 is displayed in chronological order for each utterance. The speech recognition result of the speech recognition system 20 is transmitted to the operator terminal 30 from the speech recognition system 20 in real time.

[0092] 14, scene display field 5100 displays scene button 5110 corresponding to "Opening," scene button 5120 corresponding to "Understanding the Purpose," and scene button 5130 corresponding to the current scene, "Understanding the Accident Situation." Also displayed are the next scene candidate "Insurance Handling" and its transition probability of "60%," the next scene candidate "Contact Information Confirmation" and its transition probability of "15%, and the next scene candidate "Repair Shop" and its transition probability of "5%." In this example, the top three scene candidates with the highest transition probabilities and their transition probabilities are displayed.

[0093] In this way, on the operator screen according to this embodiment, the next scene candidates for the current scene during a call with a customer are displayed together with their transition probabilities, allowing the operator to know the scene to transition to next after the current scene.

[0094] In the example shown in Figure 14, each scene button displayed in the scene display field 5100 is not assigned an expand button or connected by a related line, but this is for simplicity's sake; as explained in the first embodiment, an expand button (or compress button) may be assigned or the buttons may be connected by a related line.

[0095] 14 may also include an auxiliary information display field 5300 that displays auxiliary information such as precautions to take when transitioning to the scene candidate with the highest transition probability among the next scene candidates (for example, information that needs to be provided to the customer, etc.), etc. This allows the operator to know precautions to take when transitioning to the next scene.

[0096] 14 displays next scene candidates and their transition probabilities, the present invention is not limited to this, and the operator screen may be displayed in various modes using the transition probability information of the next scene candidates. For example, the next scene candidates may be displayed in different sizes or colors depending on the transition probabilities of the next scene candidates or the separately defined importance of each scene. For example, instead of displaying the transition probabilities as values, the next scene candidates may be categorized into large, medium, small, etc., and the next scene candidates and the category of their transition probabilities may be displayed. For example, only next scene candidates whose transition probabilities are equal to or greater than a certain threshold (e.g., 0.3) may be displayed.

[0097] Furthermore, other than these, for example, it may be set to display or not display next scene candidates depending on the current scene. This is because the next scene after a certain scene may be almost decided. As a specific example, since the scene after an "opening" is often "understanding the purpose," it may be set not to display next scene candidates when the current scene is an "opening."

[0098] Furthermore, instead of displaying the next scene candidate immediately upon transition to the current scene, the next scene candidate may be displayed after a certain amount of time has passed, because it is often not necessary to think about the next scene immediately upon transition to the current scene.

[0099] <Summary of the second embodiment> As described above, the contact center system 1 according to this embodiment is primarily intended to support online operators by displaying an operator screen on the operator terminal 30, which allows the operator to easily understand the content of a call during a call with a customer and to support the operator in responding to the customer. This operator screen visualizes the talk script 131 in real time, as well as next scene candidates and their transition probabilities. This makes it easy for the operator to determine what utterances to make online and how to respond to the customer. It goes without saying that both the talk script 131 of the current scene and the next scene candidates for the current scene and their transition probabilities may be visualized on the operator screen.

[0100] 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.

[0101] This application is based on basic application No. 2021-166652 filed in Japan on October 11, 2021, the entire contents of which are incorporated herein by reference. [Explanation of symbols]

[0102] 1. Contact Center System 10 Call visualization device 20 Voice Recognition System 30 Operator Terminal 40 Administrator terminal 50 PBX 60 Customer terminals 70 Communication Network 101 Scene Identification Section 102 Visualization information creation department 103 Support Information Acquisition and Creation Department 110 Relationship definition information storage unit 111 Relationship definition information 120 Call history information storage unit 121 Call history information 130 Talk script memory unit 131 Talk Script 301 UI control section 401 UI control section E. Contact Center Environment

Claims

1. an identification unit that identifies a scene representing a scene of a predetermined dialogue when the utterance was made, based on the utterance in the dialogue; a creating unit that creates visualization information for visualizing a time series of the utterances in the dialogue, a time series of the scenes, and a relationship between the scenes, based on relationship definition information that defines scenes having a relationship; and the relationship definition information includes at least a hierarchical structure definition that defines scenes having a parent-child relationship and a relation definition that defines scenes having a dependency relationship; The creation unit When a first scene is immediately followed by one or more second scenes having the first scene as a parent in the time series of the scenes, the information processing device creates visualization information for hiding the second scene and attaching a component that displays the second scene to the first scene in response to a user's selection operation.

2. an identification unit that identifies a scene representing a scene of a predetermined dialogue when the utterance was made, based on the utterance in the dialogue; a creation unit that creates visualization information for visualizing a time series of the utterances in the dialogue, a time series of the scenes, and a relationship between the scenes; and The creation unit The information processing device creates visualization information for displaying a predetermined warning when only some of a plurality of scenes having a dependency relationship exist in the time series of the scenes.

3. an identification unit that identifies a scene representing a scene of a predetermined dialogue when the utterance was made, based on the utterance in the dialogue; a creation unit that creates visualization information for visualizing a time series of the utterances in the dialogue, a time series of the scenes, and a relationship between the scenes; and The creation unit an information processing device that creates visualization information for displaying candidate scenes to transition from the current scene and transition probabilities based on a current scene in the time series of scenes and past dialogue history information;

4. an identification step of identifying a scene representing a scene of a predetermined dialogue when the utterance was made, based on the utterance in the dialogue; a creation procedure for creating visualization information for visualizing the time series of the utterances in the dialogue, the time series of the scenes, and the relationships between the scenes, based on relationship definition information that defines the scenes having a relationship; The computer executes the relationship definition information includes at least a hierarchical structure definition that defines scenes having a parent-child relationship and a relation definition that defines scenes having a dependency relationship; The creation procedure is as follows: an information processing method for creating visualization information for displaying a first scene by adding a component to the first scene in response to a user's selection operation, when a first scene is immediately followed by one or more second scenes that have the first scene as a parent.

5. an identification step of identifying a scene representing a scene of a predetermined dialogue when the utterance was made, based on the utterance in the dialogue; a creation procedure for creating visualization information for visualizing a time series of the utterances in the dialogue, a time series of the scenes, and a relationship between the scenes; The computer executes The creation procedure is as follows: The information processing method creates visualization information for displaying a predetermined warning when only some of a plurality of scenes having a dependency relationship exist in the time series of the scenes.

6. an identification step of identifying a scene representing a scene of a predetermined dialogue when the utterance was made, based on the utterance in the dialogue; a creation procedure for creating visualization information for visualizing a time series of the utterances in the dialogue, a time series of the scenes, and a relationship between the scenes; The computer executes The creation procedure is as follows: An information processing method for creating visualization information for displaying candidate scenes to transition from the current scene and transition probabilities based on a current scene in the time series of scenes and past dialogue history information.

7. A program that causes a computer to function as the information processing device according to any one of claims 1 to 3.

Images