Support device, support method, and program

Abstract

We provide support devices that enable assistance for specific tasks. [Solution] The business support device 10 for supporting specific tasks includes an organization information storage unit DB 106 that stores organization information representing the relationship between an organization and users belonging to that organization, and a chat processing unit 102 that, when initiating communication with another user, refers to the organization information and identifies a first user as the communication partner, who is another user belonging to the organization to which the user belongs and who monitors the user's work. If the first user is not available for communication, the chat processing unit 102 identifies a second user as the communication partner, who is a user in the organization one level above the user's organization, or a third user, who is a predetermined user, based on the user's position within the organization as a whole.

Description

Technical Field

[0001] The present invention relates to a support device, a support method, and a program.

Background Art

[0002] In recent years, an application called business chat has been used as a communication tool in companies (for example, Non-Patent Document 1). Many call center (or contact center) systems also have a chat function together with a voice recognition function, a FAQ function, etc., and are used, for example, for communication between an operator and a supervisor for the purpose of improving the quality of response to customers. Note that the FAQ function is sometimes called a knowledge function.

Prior Art Documents

Non-Patent Documents

[0003]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the conventional chat function has not necessarily been able to sufficiently support the work of operators and supervisors.

[0005] For example, when an operator starts a chat with a supervisor, it is necessary to select the supervisor as a chat partner from a user list, so it may take some time until the chat starts, and there is a risk that the quality of response to customers will deteriorate. Also, for example, the chat function has remained a communication tool between an operator and a supervisor, and the chat results have not been sufficiently utilized for things such as knowledge construction and call content analysis.

[0006] One embodiment of the present invention has been made in view of the above points and aims to provide support for specific tasks. [Means for solving the problem]

[0007] To achieve the above objective, a support device according to one embodiment is a support device for supporting specific tasks, comprising: an organization information storage unit that stores organization information representing the relationship between an organization and users belonging to the organization; and an identification unit that, when initiating communication with another user, refers to the organization information and identifies a first user as the communication partner, who is another user belonging to the organization to which the user belongs and who monitors the user's tasks; and if the first user is not available for communication, the identification unit identifies a second user as the communication partner, who is a user in an organization one level above the user's organization, or a third user, who is a predetermined user, based on the user's position within the entire organization to which the user belongs. [Effects of the Invention]

[0008] It can provide support for specific tasks. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows an example of the overall configuration of the contact center system according to this embodiment. [Figure 2] This figure shows an example of the functional configuration of the business support device according to this embodiment. [Figure 3] This is a diagram illustrating an example of organizational information. [Figure 4] This is a diagram illustrating an example of a customer support screen. [Figure 5] This flowchart shows an example of the process for identifying a chat partner. [Figure 6] This is a diagram illustrating an example of a speech recognition log and a chat log. [Figure 7] This is a diagram illustrating an example of extracting question and answer texts. [Figure 8] This is a flowchart illustrating an example of the knowledge building process. [Figure 9] This is a diagram illustrating an example of a response confirmation screen. [Figure 10] This flowchart shows an example of the process for displaying the response confirmation screen. [Figure 11] This is a diagram illustrating another example (part 1) of the response confirmation screen. [Figure 12] This is a diagram illustrating another example (part 2) of the response confirmation screen. [Figure 13] This is a diagram illustrating an example of filtering. [Modes for carrying out the invention]

[0010] The following describes one embodiment of the present invention. In this embodiment, a contact center system 1 is described that can support the work of operators and supervisors in a contact center. Examples of operator tasks include answering customer calls and performing after-call work (ACW), such as creating order slips from the content of the call after it has ended. On the other hand, examples of supervisor tasks include supporting operators' telephone work by answering inquiries from operators via a chat function, monitoring operator calls, analyzing the content of each operator's calls, and building knowledge such as FAQs. However, it goes without saying that these tasks are just examples, and operators and supervisors can perform a variety of other tasks. Furthermore, these tasks may be performed by persons other than operators and supervisors. For example, the task of analyzing the content of each operator's calls may be performed by an analyst, and the task of building knowledge may be performed by a knowledge building manager.

[0011] Note that targeting the contact center is just an example, and the present invention can be similarly applied to, for example, offices and the like to support the telephone answering service, post-work, monitoring / support, call analysis, knowledge construction, etc. of the people working there.

[0012] Hereinafter, the contact center system 1 that realizes the following (1) to (3) will be described.

[0013] (1) Automatically identify the chat partner when the operator starts a chat, and shorten the time until the chat starts.

[0014] (2) Build knowledge that makes use of not only the call content between the customer and the operator but also the chat content.

[0015] (3) When checking the call content afterwards or in the background, display the call content and the chat content in association with each other.

[0016] By the above (1), for example, the telephone answering service with customers is made more efficient, and the response quality to customers is improved. By the above (2), for example, more useful knowledge (FAQ) is built, and the response quality to customers, the efficiency of the knowledge construction business, etc. are achieved. By the above (3), for example, the post-work (ACW), the analysis business of the call content, etc. are made more efficient, and it becomes possible to improve the response quality to customers and the like.

[0017] <Overall Configuration of Contact Center System 1> Figure 1 shows an example of the overall configuration of the contact center system 1 according to this embodiment. As shown in Figure 1, the contact center system 1 according to this embodiment includes a business support device 10, one or more operator terminals 20, one or more supervisor terminals 30, a PBX (Private branch exchange) 40, and customer terminals 50. Here, the business support device 10, operator terminals 20, supervisor terminals 30, and PBX 40 are installed in the contact center environment E, which is the system environment of the contact center. Note that the contact center environment E is not limited to a system environment in the same building, but may be, for example, a system environment in multiple buildings geographically separated.

[0018] The business support device 10 converts the voice call between the customer and the operator into text in real time using speech recognition, and then displays a screen (hereinafter also referred to as the "response support screen") on the operator terminal 20 that includes this text, the chat content between the operator and their chat partner, and the knowledge (FAQ) searched by the operator. The business support device 10 also creates knowledge information (FAQ information) from both the call content and the chat content, and builds the knowledge base. Furthermore, the business support device 10 displays a screen (hereinafter also referred to as the "response confirmation screen") on the operator terminal 20 or supervisor terminal 30 that allows the operator to check the association between the call content and the chat content after the fact or in the background.

[0019] The operator terminal 20 is a type of terminal used by the operator, such as a PC (personal computer), and functions as an IP (Internet Protocol) telephone. During a call with a customer, the operator terminal 20 displays a support screen for customer interaction. Furthermore, after a call, the operator terminal 20 can display a confirmation screen showing the call and the chat that occurred during that call.

[0020] The supervisor terminal 30 is a type of terminal used by the supervisor, such as a PC (personal computer). The supervisor terminal 30 can display a response confirmation screen for the call and the chat during the call in the background, either after the call or while the call is in progress. A supervisor is a person who monitors the operator's calls and assists the operator with their telephone handling duties if any problems seem likely to occur or if the operator requests it. Typically, one supervisor monitors the calls of several to a dozen or so operators.

[0021] PBX40 is a telephone exchange (IP-PBX) connected to a communication network 60 that includes a VoIP (Voice over Internet Protocol) network and a PSTN (Public Switched Telephone Network). When a call is received from a customer terminal 50, PBX40 calls one or more predetermined operator terminals 20 and connects the customer terminal 50 to one of the operator terminals 20 that answers the call.

[0022] Customer terminals 50 are various devices used by customers, such as smartphones, mobile phones, and landline phones.

[0023] Note that the overall configuration of the contact center system 1 shown in Figure 1 is just one example, and other configurations are possible. For example, in the example shown in Figure 1, the business support device 10 is included in the contact center environment E (i.e., the business support device 10 is on-premise), but all or part of the functions of the business support device 10 may be implemented by cloud services or the like. Similarly, in the example shown in Figure 1, the PBX 40 is an on-premise telephone exchange, but it may also be implemented by cloud services.

[0024] <Functional Configuration of Business Support Device 10> Figure 2 shows the functional configuration of the business support device 10 according to this embodiment. As shown in Figure 2, the business support device 10 according to this embodiment includes a speech recognition text conversion unit 101, a chat processing unit 102, a knowledge processing unit 103, an association unit 104, and a UI provision unit 105. Each of these units is realized, for example, by processing that one or more programs installed in the business support device 10 cause a processor such as a CPU (Central Processing Unit) to execute.

[0025] Furthermore, the business support device 10 according to this embodiment includes an organizational information DB 106, a call history information DB 107, and a knowledge information DB 108. Each of these DBs (databases) is implemented by an auxiliary storage device such as an HDD (Hard Disk Drive) or SSD (Solid State Drive). At least one of these DBs may be implemented by a database server connected to the business support device 10 via a communication network, for example.

[0026] The speech recognition text conversion unit 101 converts the voice call between the operator terminal 20 and the customer terminal 50 into text using speech recognition. Furthermore, the speech recognition text conversion unit 101 performs speech recognition and converts the voice of each speaker into text. As a result, both the operator's voice and the customer's voice are converted into text. Hereinafter, the text obtained through speech recognition will also be referred to as "speech recognition text." This speech recognition text is displayed in real time on the customer service support screen.

[0027] The chat processing unit 102 sends and receives chat messages between the operator making the voice call with the customer and the person assisting the operator with their telephone support duties (e.g., a supervisor) when the operator is making a voice call with a customer (for example, relaying chat messages exchanged between the operator terminal 20 and the supervisor terminal 30). Furthermore, when an operator initiates a chat, the chat processing unit 102 automatically identifies the user the operator will chat with by referring to the organizational information stored in the organizational information DB 106. While chat messages are often text-based, they are not limited to text; they may also include stamps, images, etc. The chat messages are displayed in real time on the support screen.

[0028] When an operator is making a voice call with a customer, the knowledge processing unit 103 searches for knowledge information (FAQ information) from the knowledge information DB 108 in response to the operator's actions during the voice call, and sends the retrieved knowledge information to the operator terminal 20. When the operator terminal 20 receives the knowledge information, the knowledge represented by this knowledge information is displayed on the customer service support screen.

[0029] Furthermore, the knowledge processing unit 103 creates knowledge information from the speech recognition logs and chat logs contained in the call history information stored in the call history information DB 107. Here, the speech recognition log is a collection of speech recognition texts of the call represented by the call history information, and the chat log is a collection of chat messages of the call represented by the call history information.

[0030] The association unit 104 associates the voice recognition text and the chat message in chronological order when displaying the response confirmation screen on the operator terminal 20 or supervisor terminal 30.

[0031] The UI provision unit 105 provides display information for displaying the response support screen and display information for displaying the response confirmation screen to the operator terminal 20, supervisor terminal 30, etc.

[0032] Organizational Information DB106 stores organizational information that represents the structure of the organizations to which users, such as operators and supervisors, belong. Details of organizational information will be described later. Note that organizational information is updated as needed when, for example, the organizational structure changes, users are added or deleted, or users move between organizations.

[0033] The Call History Information DB107 stores call history information that represents information about the history of calls. Call history information includes, for example, a call ID that uniquely identifies the call, the date and time of the call, the duration of the call, a user ID that uniquely identifies the operator who answered the call, the operator's extension number, the customer's telephone number, the speech recognition text (speech recognition log) of the call, chat messages (chat log), etc. Call history information is created for each call between the customer and the operator and stored in the Call History Information DB107.

[0034] Knowledge Information DB108 stores knowledge information that includes question texts and corresponding answers. When knowledge information is retrieved from Knowledge Information DB108, for example, the search keyword may be compared with the question text contained in the knowledge information, or if key information representing search keywords, etc., is included in the knowledge information, the search keyword may be compared with the key information.

[0035] <Organization information> Here, an example of organizational information stored in the organizational information DB106 is shown in Figure 3. As shown in Figure 3, organizational information is information that represents the hierarchical structure of organizations such as business units and groups that make up the contact center, and the relationship between those organizations and the users belonging to them.

[0036] For example, in the example shown in Figure 3, the contact center is composed of organizations such as the "Communications Division" and the "XXX Division," and the "Communications Division" is composed of organizations such as the "Optical Network Group" and the "Mobile Group." Furthermore, the "Communications Division" includes "Communications Division Manager A." Similarly, the "Optical Network Group" includes "Supervisor B," "Operator B-1," "Operator B-2," etc., and the "Mobile Group" includes "Supervisor C," "Operator C-1," "Operator C-2," etc.

[0037] Thus, organizational information defines the hierarchical structure of the organizations that make up the contact center, and the user IDs of the users (responsible persons, supervisors, operators, etc.) belonging to those organizations. By referring to this organizational information, it becomes possible to identify the supervisor who will monitor and support each operator as their chat partner, and to identify the responsible persons belonging to higher levels of the hierarchy.

[0038] It goes without saying that the example shown in Figure 3 is just one example, and organizational information is not limited to this. For example, in the example shown in Figure 3, the contact center is composed of a three-tiered organization, but it could be less than three tiers or four tiers or more.

[0039] <Customer Support Screen> As described above, while the customer and the operator are having a voice call, a support screen is displayed on the operator terminal 20's display.

[0040] An example of a customer support screen is shown in Figure 4. The customer support screen 1000 shown in Figure 4 includes a voice recognition field 1100, a chat field 1200, and a knowledge field 1300.

[0041] The speech recognition section 1100 displays the speech recognition text converted by the speech recognition text conversion unit 101 in real time. The speech recognition text conversion unit 101 captures audio packets representing the customer's utterance to the operator and audio packets representing the operator's utterance to the customer, respectively, and performs speech recognition on these audio packets to generate speech recognition text representing the customer's and operator's utterances in real time (i.e., with almost no delay). In the example shown in Figure 4, the speech recognition text representing the customer's utterance is displayed on the left, and the speech recognition text representing the operator's utterance is displayed on the right.

[0042] The chat field 1200 displays chat messages in real time between the chat recipient identified by the chat processing unit 102. In the example shown in Figure 4, a supervisor is identified as the chat recipient, and the chat messages between this identified supervisor and the operator are displayed.

[0043] The chat field 1200 also includes a message input field 1210 and a send button 1220. When a message is entered in the message input field 1210 and the send button 1220 is pressed, the message is sent to the chat partner via the business support device 10.

[0044] In other words, when the send button 1220 is pressed with a message entered in the message input field 1210, the operator terminal 20 sends the message to the business support device 10. The chat processing unit 102 of the business support device 10 then sends the message received from the operator terminal 20 to the chat partner's terminal (for example, the supervisor terminal 30 of the supervisor who monitors and supports the operator). As a result, the message is displayed on the chat partner's terminal. When the business support device 10 receives a message from the chat partner's terminal, the operator terminal 20 displays the message in the chat field 1200.

[0045] The Knowledge section 1300 includes a search keyword input field 1310, a search button 1320, and a search results display area 1330. When a search keyword is entered in the search keyword input field 1310 and the search button 1320 is pressed, the question and answer text contained in the knowledge information retrieved by that search keyword are displayed in the search results display area 1330.

[0046] In other words, when the search button 1320 is pressed with a search keyword entered in the search keyword input field 1310, the operator terminal 20 sends a search request containing the search keyword to the business support device 10. The knowledge processing unit 103 of the business support device 10 then searches the knowledge information DB 108 for knowledge information using the search keyword included in the search request and sends the search results containing the retrieved knowledge information to the operator terminal 20. As a result, the search results display field 1330 of the knowledge field 1300 included in the operator terminal 20's response support screen 1000 displays the question and answer text of the knowledge information included in the search results.

[0047] In this way, while the customer and the operator are having a voice call, the operator terminal 20 displays a support screen 1000 that includes a voice recognition field 1100, a chat field 1200, and a knowledge field 1300. Therefore, the operator can check the voice recognition field 1100 to understand the content of the call with the customer, request support from a supervisor or other person in the chat field 1200, and check the knowledge field 1300 for FAQs.

[0048] <Identifying the chat partner> The following explains the process by which an operator identifies the chat recipient when initiating a chat, with reference to Figure 5.

[0049] First, the chat processing unit 102 refers to the organizational information stored in the organizational information DB 106 to identify the user ID of the supervisor of the organization to which the operator's user ID belongs (step S101). For example, in the example shown in Figure 3, if the operator belongs to the "Optical Line Group", the user ID of "Supervisor B" is identified. Generally, the supervisor of the organization (group) to which the operator belongs has the normal duty of monitoring and supporting the operator. Therefore, this supervisor usually becomes the chat partner for the operator.

[0050] Next, the chat processing unit 102 determines whether the user with the user ID identified in step S101 is available to chat (step S102). Cases in which it is determined that chat is not available include, for example, when the user with that user ID is on vacation, in a meeting or away from their desk, or when they are unable to chat for other reasons.

[0051] If it is determined in step S102 that the user is not available to chat, the chat processing unit 102 refers to the organizational information stored in the organizational information DB 106 to identify the user ID of the user in the next higher level (or, if the next higher level is the highest level, another predetermined user) (step S103), and returns to step S102.

[0052] For example, in the example shown in Figure 3, if the operator belongs to the "Optical Line Group" and "Supervisor B," whose user ID was identified in step S101 above, is not available for chat, then the user ID of "Communications Business Division Manager A," who belongs to the "Communications Business Division" at the next level, is identified.

[0053] Furthermore, for example, in the example shown in Figure 3, if the organization one level above the organization to which the user ID identified in this step belongs is "Contact Center," then the user IDs of other predetermined users will be identified. These predetermined users include, for example, users of other organizations at the same level as the organization to which the user belongs (in the example shown in Figure 3, if the user ID identified in this step is "Head of Communications Division A," then users of the "XXX Division," etc.), and supervisors of other organizations at the same level as the organization to which the operator belongs (in the example shown in Figure 3, "Supervisor C" of the "Mobile Group," etc.).

[0054] If the user is determined to be available for chat in step S102, the chat processing unit 102 designates the user with the finally identified user ID as the operator's chat partner (step S104). This identifies the operator's chat partner. Therefore, when an operator starts a chat, they do not need to perform an operation such as selecting a chat partner (especially a supervisor who monitors and supports them) from a user list, and can start a chat efficiently. As a result, they can quickly obtain responses from supervisors, etc., via chat, which reduces the time customers are kept waiting and improves the quality of service.

[0055] The process of identifying the chat partner described above may be performed, for example, when the operator starts their workday, or after each call. If it is performed when the operator starts their workday, the chat partner will remain the same throughout the day. On the other hand, if it is performed after each call, the chat partner may change after each call. In addition, the process of identifying the chat partner may be performed at predetermined intervals, such as every hour, or if the identified chat partner becomes unavailable for chat, the process of identifying the chat partner may be performed again.

[0056] <Knowledge Building> The following describes how to build knowledge from speech recognition logs and chat logs contained in a call history information database (DB107). In this description, the chat logs will primarily consist of chat messages between the operator and the supervisor.

[0057] As an example, let's assume the speech recognition log 2100 and chat log 2200 shown in Figure 6 are used as speech recognition logs and chat logs, respectively. The speech recognition log 2100 shown in Figure 6 consists of speech recognition texts 2101 to 2106. On the other hand, the chat log 2200 shown in Figure 6 consists of chat messages 2201 to 2203.

[0058] Here, generally, each speech recognition text in the speech recognition log is associated with the utterance date and time t and the speaker x1 who made the utterance. That is, if the speech recognition text is y1, it can be represented as (t, x1, y1). Therefore, the speech recognition log is represented as {(t, x1, y1) | t ∈ T1}. Note that T1 is the set of possible values ​​for the utterance date and time t. Also, x1 is a flag that can take values ​​representing either a customer or an operator; for example, x1 = 0 represents a customer, and x1 = 1 represents an operator.

[0059] Similarly, each chat message in the chat log is generally associated with the message sending date and time t and the sender x2. That is, if the chat message is y2, it can be represented as (t, x2, y2). Therefore, the chat log is represented as {(t, x2, y2) | t ∈ T2}. Note that T2 is the set of possible values ​​for the message sending date and time t. Also, x2 is a flag that can represent either the chat partner or an operator; for example, x2 = 0 represents the supervisor, and x2 = 1 represents an operator.

[0060] At this point, we create a set of speech recognition text and chat messages {(t,x,y)|t∈T1∪T2} which is a set that associates each speech recognition text in the speech recognition log with each chat message in the chat log in chronological order (in other words, a set arranged in chronological order). Here, when t∈T1, x=x1 and y=y1, and when t∈T2, x=x2 and y=y2. Note that t∈T1∩T2 can also occur, in which case we simply need to assume that for the same t, (t,x1,y1) and (t,x2,y2) are included in the speech recognition text and chat message set in this order.

[0061] For example, the set of speech recognition texts and chat messages obtained by arranging the speech recognition texts 2101 to 2106 contained in the speech recognition log 2100 shown in Figure 6, and the chat messages 2201 to 2203 contained in the chat log 2200 shown in Figure 6, in chronological order, is shown in Figure 7.

[0062] Next, the system identifies the speech recognition text and chat messages to be extracted as questions and the speech recognition text and chat messages to be extracted as answers from the above-mentioned set of speech recognition text and chat messages. Generally, in contact centers, questions are often made by customers to operators and by operators to supervisors, and answers are often made by supervisors to operators and by operators to customers. Therefore, taking these characteristics into consideration, the system identifies the speech recognition text and chat messages to be extracted as questions and the speech recognition text and chat messages to be extracted as answers from the set of speech recognition text and chat messages. Specifically, the speech recognition text representing the customer's requirement utterances and question utterances up to the appearance of the chat message in the set of speech recognition text and chat messages, as well as the operator's repetition utterances in response to them, and their corresponding chat messages are extracted as questions. On the other hand, the supervisor's chat text after the chat message extracted as a question and the operator's explanatory utterance after the chat ends are extracted as answers. The type of utterance (whether it is a requirement utterance, a question utterance, or an explanatory utterance) can be identified using existing technology.

[0063] For example, in the example shown in Figure 7, speech recognition texts 2101-2102 and chat message 2201 are extracted as questions, and chat message 2202 and speech recognition text 2105 are extracted as answers. This allows knowledge (FAQ) information to be created using existing technology with the extracted questions and answers. In existing technology for creating knowledge information, knowledge information containing both questions and answers is created by identifying the answer that corresponds to each question.

[0064] The process for creating the knowledge information described above (knowledge building) will be explained with reference to Figure 8.

[0065] First, the knowledge processing unit 103 retrieves the speech recognition log and chat log from the call history information stored in the call history information DB 107 (step S201).

[0066] Next, the knowledge processing unit 103 extracts the question and answer from the speech recognition log and chat log acquired in step S201 (step S202). The method for extracting the question and answer is as described above.

[0067] Then, the knowledge processing unit 103 creates knowledge information from the question and answer text extracted in step S203 (step S203). This knowledge information is stored in the knowledge information DB 108. Note that the knowledge information can be created using existing technologies as described above.

[0068] This creates knowledge information that operators can search and review during calls. This knowledge information is created not only from past call content between customers and operators, but also from past chat content between supervisors and operators, for example, allowing for the creation of more accurate knowledge information than before.

[0069] <Contact Confirmation Screen> As described above, operators can display a call confirmation screen on the operator terminal 20 to review the content of their call after it has ended. Supervisors can also display a call confirmation screen on the supervisor terminal 30 to review the content of past calls, or display a call confirmation screen on the supervisor terminal 30 to review the content of a call while an operator they are monitoring or supporting is on that call.

[0070] The response confirmation screen displays at least the voice recognition text and the chat message. In the following explanation, we will assume that only the voice recognition text and the chat message are displayed on the response confirmation screen, and will omit further explanation of other displayed content. However, it goes without saying that content other than the voice recognition text and the chat message may also be displayed on the response confirmation screen.

[0071] For simplicity, in the following, we will assume that the speech recognition text and chat messages displayed on the response confirmation screen are the speech recognition texts 2101 to 2106 included in the speech recognition log 2100 and the chat messages 2201 to 2203 included in the chat log 2200, as shown in Figure 6.

[0072] An example of a response confirmation screen is shown in Figure 9. The response confirmation screen 3000 shown in Figure 9 includes a speech recognition text / chat message field 3100, in which elements of the speech recognition text / chat message set {(t,x,y)|t∈T1∪T2} (i.e., speech recognition text or chat messages) are displayed in chronological order. As mentioned above, this speech recognition text / chat message set {(t,x,y)|t∈T1∪T2} is a set that associates the speech recognition log {(t,x1,y1)|t∈T1} and the chat log {(t,x2,y2)|t∈T2} in chronological order.

[0073] In the example shown in Figure 9, the speech recognition text / chat message field 3100 displays speech recognition texts 2101-2104, chat messages 2201-2203, and speech recognition texts 2105-2106 in that order.

[0074] This allows operators and supervisors to correlate and verify speech recognition text with chat messages, enabling them to understand, for example, what kind of chat took place in the context of a call. As a result, operators can streamline post-call tasks such as ACW (Account Call Work), and supervisors can streamline call content analysis, ultimately leading to improvements in the quality of customer service.

[0075] <Display of response confirmation screen> The process for displaying the above-described response confirmation screen on the operator terminal 20 or supervisor terminal 30 will be explained with reference to Figure 10. Below, we will explain the case where a response confirmation screen containing speech recognition text and chat messages from a certain call history entry stored in the call history information DB 107 is displayed.

[0076] First, the association unit 104 obtains the speech recognition log and chat log from the call history information (step S301).

[0077] Next, the association unit 104 creates a set of speech recognition text and chat messages by associating the speech recognition text contained in the speech recognition log obtained in step S301 with the chat messages contained in the chat log in chronological order (step S302).

[0078] Then, the UI provider unit 105 creates display information for a response confirmation screen in which the elements of the voice recognition text chat message set created in step S302 are displayed in chronological order, and sends it to the operator terminal 20 or supervisor terminal 30 (step S303). As a result, the response confirmation screen is displayed on the operator terminal 20 or supervisor terminal 30 based on this display information.

[0079] The above describes the case where the operator terminal 20 displays a confirmation screen regarding its own call after the call ends, or where the supervisor terminal 30 displays a confirmation screen regarding past calls. However, it is also possible to similarly implement a case where, for example, the supervisor terminal 30 displays a confirmation screen regarding the call in the background of the currently ongoing call. In this case, however, instead of call history information, the speech recognition text and chat messages from the currently ongoing call are used.

[0080] <Variation> Modified examples of this embodiment will be described below.

[0081] ≪Extreme Variation 1≫ On the response confirmation screen, instead of displaying the chat message itself, a link button or similar to allow viewing the chat message on a separate screen may be displayed instead. In this case, in step S303 of Figure 10, the UI provision unit 105 creates the display information for such a response confirmation screen.

[0082] For example, in the response confirmation screen 4000 shown in Figure 11, the voice recognition text / chat message field 4100 displays voice recognition texts 2101-2106 and also includes a link button display field 4110. The link button display field 4110 also displays link buttons 4111-4116 for referencing chat messages. Each link button is displayed chronologically between the voice recognition text and other link buttons, according to the chat message sent date and time corresponding to that link button.

[0083] When these link buttons are pressed, the chat window 4200 is displayed, and the chat message corresponding to that link button is displayed within the chat window 4200.

[0084] In the example shown in Figure 11, a link button 4112 is pressed, and the corresponding chat message 2202 is displayed in the center of the chat window 4200. Note that each link button is displayed in a different color depending on whether it is a chat message from the operator or a chat message from the chat partner (in the example shown in Figure 11, the supervisor).

[0085] In the example shown in Figure 11, the chat window is on a separate screen from the response confirmation screen, but the chat window may be on the same screen as the response confirmation screen.

[0086] <<Variation 2>> On the response confirmation screen, only the chat message may be displayed, and the voice recognition text may be displayed according to the user's (operator's or supervisor's) selection. In this case, in step S303 of Figure 10, the UI provision unit 105 creates the display information for such a response confirmation screen.

[0087] For example, in the voice recognition text chat message field 4100 of the response confirmation screen 5000 shown in Figure 11, chat messages 2201 to 2203 are displayed. At this time, if the user (operator or supervisor) hovers the mouse cursor over chat message 2201, for example, a selection window 5110 will be displayed. This selection window 5110 includes a "Check Previous Utterance" button to check the utterance immediately preceding chat message 2201, and a "Check Next Utterance" button to check the utterance immediately following chat message 2201.

[0088] When any of these buttons are pressed, the speech recognition window 5200 is displayed, and the speech recognition text corresponding to that button is displayed within the speech recognition window 5200.

[0089] In the example shown in Figure 12, the "Check previous utterance" button is pressed in the selection window 5110, and the speech recognition text 2104 corresponding to that button is displayed in the speech recognition window 5200.

[0090] In the example shown in Figure 12, the voice recognition window is on a separate screen from the response confirmation screen, but the voice recognition window may be on the same screen as the response confirmation screen.

[0091] <<Variation 3>> In the embodiments described above, chat messages were explained as being text-based messages, but chat messages can also be messages representing stamps, images, etc. Furthermore, some chat messages simply express replies, such as "Yes" or "Understood," and are not very useful for understanding the content of a call or building knowledge. In addition, a single sentence may be split and sent across multiple chat messages, which can also be inappropriate for understanding the content of a call or building knowledge.

[0092] Therefore, it is possible to filter chat messages to remove stamps, images, and chat messages such as "Yes." and "Understood.", and to merge multiple chat messages that represent a single sentence into a single chat message.

[0093] For example, consider the chat log 6100 shown in Figure 13. This chat log 6100 consists of chat messages 6101 to 6107. In this case, a filter may be applied to chat log 6100 to create chat log 6200. In the example shown in Figure 13, chat message 6104, which represents "Yes," chat message 6106, which represents "Understood," and chat message 6107, which represents a stamp, have been deleted. Also, since chat messages 6101 to 6102 are chat messages that represent a single sentence, they have been merged into chat message 6201.

[0094] In this case, when building knowledge or displaying the response confirmation screen, the filtered chat log is used to create a collection of speech-recognized text chat messages.

[0095] The filtering process described above is just one example; other methods may also be used, such as converting or processing a specific expression into another. Such filtering can be implemented using existing filtering methods used in natural language processing, and can be achieved with existing technologies.

[0096] The present invention is not limited to the embodiments specifically disclosed above, and various modifications, changes, and combinations with known technologies are possible without departing from the scope of the claims. [Explanation of Symbols]

[0097] 1. Contact Center System 10 Business support equipment 20 Operator terminals 30 Supervisor terminals 40 PBX 50 Customer terminals 60 Communication Networks 101 Speech Recognition Text Conversion Unit 102 Chat Processing Unit 103 Knowledge Processing Unit 104 Association section 105 UI provision department 106 Organizational information DB 107 Call History Information Database 108 Knowledge Information Database

Claims

1. A support device for assisting specific tasks, Organizational information storage unit that stores organizational information representing the relationship between an organization and users belonging to said organization, When initiating communication with another user, the identification unit refers to the organizational information and identifies a first user, which is another user belonging to the organization to which the user belongs and which monitors the user's work, as the communication partner. It has, The specified part is, A support device that, if the first user is unable to communicate, identifies a second user representing a user in an organization one level above the first user's organization, or a third user representing a predetermined user, as the communication partner, based on the first user's position within the organization to which the first user belongs.

2. The support device according to claim 1, wherein the third user is another user who monitors the work of a user in another organization that is in a position parallel to the organization to which the user belongs.

3. The aforementioned specific duties are telephone answering duties at a contact center or call center. The specified part is, The support device according to claim 1 or 2, wherein when an operator initiates communication with another user, the device identifies a supervisor belonging to the organization to which the operator belongs as the first user from the organization information, and identifies the identified supervisor as the communication partner.

4. Support devices for specific tasks, Organizational information storage procedure for storing organizational information representing the relationship between an organization and users belonging to said organization in a storage unit, When initiating communication with another user, the identification procedure involves referring to the aforementioned organizational information to identify a first user, who is another user belonging to the organization to which the user belongs and who monitors the user's work, as the communication partner. Execute, The aforementioned identification procedure is, A support method that, if the first user is unable to communicate, identifies a second user representing a user in an organization one level above the first user's organization, or a third user representing a predetermined user, as the communication partner, based on the first user's position within the organization to which the first user belongs.

5. Support devices for assisting specific tasks, Organizational information storage procedure for storing organizational information representing the relationship between an organization and users belonging to said organization in a storage unit, When initiating communication with another user, the identification procedure involves referring to the aforementioned organizational information to identify a first user, who is another user belonging to the organization to which the user belongs and who monitors the user's work, as the communication partner. Make it run, The aforementioned identification procedure is, A program that, if the first user is unable to communicate, identifies a second user representing a user in the organization one level above the first user's organization, or a third user representing a predetermined user, as the communication partner, based on the first user's position within the organization to which the first user belongs.

Images