SKILL LEVEL CALCULATION DEVICE, RESPONDENT DISTRIBUTION SYSTEM DEVICE, SKILL LEVEL CALCULATION METHOD, RESPONDENT DISTRIBUTION METHOD, PROGRAM, AND RECORDING MEDIUM

Abstract

To provide a skill level calculation device capable of calculating an operator's skill level.SOLUTION: In a skill level calculation device 10 of the present invention, a skill information acquisition unit 11 uses any keyword extracted from dialogue information including an inquiry content from a user and a response content of a responder by an inquiry content analysis device as skill information, an analysis result acquisition unit 12 acquires an analysis result obtained by analyzing the dialogue information from the inquiry content analysis device, a parameter calculation unit 13 calculates the number of parameters from the analysis result and a skill level calculation unit 14 calculates a skill level for each skill information of the responder by using the number of the parameters and a preset ratio for each parameter.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a skill level calculation device, a responder allocation system device, a skill level calculation method, a responder allocation method, a program, and a recording medium. [Background technology]

[0002] 2. Description of the Related Art In a call center system, a technique has been proposed for allocating an appropriate operator in response to an inquiry from a user (for example, Patent Document 1, etc.).

[0003] Additionally, technology has been proposed that allocates appropriate operators by manually registering the operator's knowledge (skills) and proficiency (skill level) in the system in advance. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2010-239598 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, since the skills and skill levels are based on self-reporting or the judgment of the administrator, there is a problem in that it is difficult to quantitatively set and register them.

[0006] Therefore, an object of the present invention is to provide a skill level calculation device capable of calculating the skill level of an operator, a responder allocation system device, a skill level calculation method, a responder allocation method, a program, and a recording medium. [Means for solving the problem]

[0007] In order to achieve the above object, a skill level calculation device of the present invention comprises: The present invention includes a skill information acquisition unit, an analysis result acquisition unit, a parameter calculation unit, and a skill level calculation unit, The skill information acquisition unit acquires, as skill information, any keyword extracted by an inquiry content analysis device from dialogue information including the content of an inquiry from a user and the content of a response by a responder; the analysis result acquisition unit acquires an analysis result obtained by analyzing the dialogue information from the inquiry content analysis device; the parameter calculation unit calculates a type of a parameter and a value of the parameter; The skill level calculation unit is a device that calculates a skill level of the responder for each piece of skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters.

[0008] The responder distribution system device of the present invention comprises: The present invention includes a skill level calculation device, an inquiry content analysis device, and a responder allocation device, The responder distribution device includes an inquiry acquisition unit and a distribution unit, The inquiry acquisition unit acquires the presence or absence of an inquiry and the type of the inquiry, The distribution unit distributes, when there is an inquiry, a responder to each of the inquiries based on the type of the inquiry; the inquiry content analysis device includes a dialogue information acquisition unit, a keyword extraction unit, and an analysis unit; The dialogue information acquisition unit acquires dialogue information including the content of the inquiry from the user and the response content of the respondent to the distributed inquiry, The keyword extraction unit extracts any keyword from the dialogue information, The analysis unit analyzes the dialogue information, In the skill level calculation device, the skill information acquisition unit acquires the arbitrary keyword extracted by the inquiry content analysis device as skill information; the analysis result acquisition unit acquires an analysis result obtained by analyzing the dialogue information from the inquiry content analysis device; the parameter calculation unit calculates a type of parameter and a value of the parameter from the analysis result; The skill level calculation unit is a device that calculates a skill level of the responder for each piece of skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters.

[0009] The skill level calculation method of the present invention includes the steps of: The method includes a skill information acquisition step, an analysis result acquisition step, a parameter calculation step, and a skill level calculation step, The skill information acquiring step acquires, as skill information, any keyword extracted by an inquiry content analyzing device from dialogue information including the content of an inquiry from a user and the content of a response by a responder; The analysis result acquisition step includes acquiring an analysis result of analyzing the dialogue information from the inquiry content analysis device, The parameter calculation step calculates types of parameters and values ​​of the parameters from the analysis results, The skill level calculation step is a method for calculating a skill level of the operator for each piece of skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters.

[0010] The respondent distribution method of the present invention includes the steps of: The method includes a skill level calculation step, an inquiry content analysis step, and a responder allocation step, The responder distribution step includes an inquiry acquisition step and a distribution step, The inquiry acquisition step acquires whether or not an inquiry has been made and the type of the inquiry, The distribution step includes, when an inquiry is received, distributing a respondent to each of the inquiries based on the type of the inquiry; The inquiry content analysis step includes a dialogue information acquisition step, a keyword extraction step, and an analysis step, The dialogue information acquisition step acquires dialogue information including the content of the inquiry from the user and the response content of the assigned respondent, The keyword extraction step includes extracting any keyword from the dialogue information, The analyzing step includes analyzing the dialogue information, The skill level calculation step is a skill level calculation method of the present invention, the skill information acquiring step acquires the arbitrary keyword extracted by the inquiry content analysis device as skill information; The analysis result acquisition step includes acquiring an analysis result of analyzing the dialogue information from the inquiry content analysis device, The parameter calculation step calculates types of parameters and values ​​of the parameters from the analysis results, The skill level calculation step is a method for calculating a skill level of the operator for each piece of skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters. Effect of the Invention

[0011] According to the present invention, the skill level of an agent can be calculated. Also, according to the present invention, a more appropriate agent can be assigned to respond to an inquiry from a user based on the skill level. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a block diagram showing a configuration of an example of the apparatus according to the first embodiment. [Diagram 2] FIG. 2 is a block diagram showing an example of a hardware configuration of the apparatus according to the first embodiment. [Diagram 3] FIG. 3 is a flowchart showing an example of processing in the device of the first embodiment. [Figure 4] FIG. 4 is a schematic diagram illustrating an example of a routing table. [Diagram 5] FIG. 5 is a block diagram showing an example of a configuration of a responder distribution system device according to the third embodiment. [Figure 6]FIG. 6(A) is a block diagram showing an example of the configuration of an inquiry content analysis device in a responder distribution system device of embodiment 3, and FIG. 6(B) is a block diagram showing an example of the configuration of the hardware configuration of the inquiry content analysis device. [Figure 7] Figure 7(A) is a block diagram showing the configuration of an example of a responder distribution device in a responder distribution system device of this embodiment 3, and Figure 7(B) is a block diagram showing the configuration of an example of the hardware configuration of the responder distribution device. [Figure 8] FIG. 8 is a flowchart showing an example of a process in the responder distribution system device of the third embodiment. [Figure 9] FIG. 9 is a chart showing an example of processing at each stage when the present invention is applied to a call center. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] The skill level calculation device of the present invention, for example, Further, the method includes: The update unit may update an existing skill level based on the calculated skill level by using the calculated skill level and a learning rate.

[0014] The skill level calculation device of the present invention, for example, Further, the device includes a storage unit, The storage unit may store the skill level.

[0015] The responder distribution system device of the present invention includes, for example, In the responder distribution device, The distribution unit may be configured to, when an inquiry is made, allocate a respondent to each inquiry based on the type of inquiry and with reference to the skill level calculated by the skill level calculation device.

[0016] The skill level calculation method of the present invention includes, for example, Further, the method includes an updating step, The updating step may be implemented by updating an existing skill level based on the calculated skill level, using the calculated skill level and a learning rate.

[0017] The skill level calculation method of the present invention includes, for example, Further, a storing step is included, The storing step may include storing the skill level.

[0018] The respondent distribution method of the present invention includes, for example, In the respondent distribution step, The distribution step may be such that, when an inquiry is received, a respondent is distributed for each inquiry based on the type of inquiry and with reference to the skill level calculated by the skill level calculation device.

[0019] The program of the present invention is a program for causing a computer to execute each step of the method of the present invention as a procedure.

[0020] The recording medium of the present invention is a computer-readable recording medium having the program of the present invention recorded thereon.

[0021] The application field of the present invention is not particularly limited, and may be any field that is equipped with a contact center system and requires the allocation of responders (also called operators) to inquiries from users. The contact center system (hereinafter also called contact center) is hardware, software, etc. for implementing operations to respond to the inquiries using various means such as telephone, fax, web pages, email, and chat. The contact center is also called, for example, a call center, an operation center, a support center, a customer center, a help desk center, and a customer service center.

[0022] In the present invention, the means of "inquiry" and "response to inquiry" are not particularly limited, and examples thereof include, as mentioned above, telephone, fax, web page, e-mail, chat, etc. Furthermore, in the present invention, regardless of the means, the exchange between the user and the responder is called a dialogue or conversation.

[0023] Next, an embodiment of the present invention will be described with reference to the drawings. The present invention is not limited to the following embodiment. In each of the drawings, the same parts are given the same reference numerals. In addition, the explanations of each embodiment can be mutually incorporated unless otherwise specified, and the configurations of each embodiment can be combined unless otherwise specified.

[0024] [Embodiment 1] Fig. 1 is a block diagram showing an example of the configuration of a skill level calculation device 10 according to the present embodiment. As shown in Fig. 1, the device 10 includes a skill information acquisition unit 11, an analysis result acquisition unit 12, a parameter calculation unit 13, a skill level calculation unit 14, an update unit 15, and a storage unit 16. The update unit 15 and the storage unit 16 are of any configuration and do not need to be included in the device 10.

[0025] The device 10 may be, for example, a single device including each of the above-mentioned units, or a device in which each of the above-mentioned units can be connected via a communication line network, i.e., a device in which each of the above-mentioned units operates on separate hardware. The device 10 may also be connected to an external device described later via the communication line network. The communication line network is not particularly limited, and any known network may be used, for example, wired or wireless. Examples of the communication line network include an Internet line, a WWW (World Wide Web), a telephone line, a LAN (Local Area Network), a SAN (Storage Area Network), and a DTN (Delay Tolerant Networking). Examples of wireless communication include WiFi (Wireless Fidelity) and Bluetooth (registered trademark). The wireless communication may be either a form in which each device directly communicates (Ad Hoc communication) or an indirect communication via an access point. The device 10 may be incorporated into a server as a system, for example. The device 10 may be, for example, a personal computer (PC, for example, desktop type or notebook type) on which the program of the present invention is installed, a smartphone, a tablet terminal, etc. Furthermore, the device 10 may be, for example, in the form of cloud computing in which at least one of the units is on a server and the other units are on a terminal, or in the form of edge computing, etc.

[0026] 2 illustrates a block diagram of the hardware configuration of the device 10. The device 10 includes, for example, a central processing unit (CPU, GPU, etc.) 101, a memory 102, a bus 103, a storage device 104, an input device 105, a display device 106, and a communication device 107. The components of the device 10 are connected to each other via the bus 103 and their respective interfaces (I / F).

[0027] The central processing unit 101 is responsible for the overall control of the device 10. In the device 10, the central processing unit 101 executes, for example, the program of the present invention and other programs, and also reads and writes various information. Specifically, for example, the central processing unit 101 functions as a skill information acquisition unit 11, an analysis result acquisition unit 12, a parameter calculation unit 13, a skill level calculation unit 14, and an update unit 15.

[0028] The bus 103 can also be connected to, for example, an external device. Examples of the external device include an external storage device (external database, etc.), a printer, etc. The present device 10 can be connected to an external network (the above-mentioned communication line network) by, for example, a communication device 107 connected to the bus 103, and can also be connected to other devices via the external network.

[0029] An example of the memory 102 is a main memory (primary storage device). When the central processing unit 101 performs processing, the memory 102 reads various operation programs, such as the program of the present invention, stored in the storage device 104 described below, and the central processing unit 101 receives data from the memory 102 and executes the program. The main memory is, for example, a RAM (random access memory). The memory 102 may also be, for example, a ROM (read only memory).

[0030] The storage device 104 is also called an auxiliary storage device, for example, in contrast to the main memory (primary storage device). As described above, the storage device 104 stores an operation program including the program of the present invention. The storage device 104 may be, for example, a combination of a recording medium and a drive for reading and writing from and to the recording medium. The recording medium is not particularly limited, and may be, for example, an internal or external type, such as a hard disk (HD), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, or memory card. The storage device 104 may be, for example, a hard disk drive (HDD) in which a recording medium and a drive are integrated, or a solid state drive (SSD).

[0031] In the present device 10, the memory 102 and the storage device 104 can also store user log information and information acquired from an external database (not shown). The storage unit 16 can use, for example, the memory 102 or the storage device 104.

[0032] The device 10 may further include, for example, an input device 105 and a display device 106. The input device 105 is, for example, a touch panel, a keyboard, a mouse, etc. The display device 106 is, for example, an LED display, a liquid crystal display, etc.

[0033] Next, an example of the skill level calculation method of this embodiment will be described with reference to the flowchart of Fig. 3. The skill level calculation method of this embodiment is implemented as follows, for example, using the skill level calculation device 10 of Fig. 1. Note that the skill level calculation method of this embodiment is not limited to use of the skill level calculation device 10 of Fig. 1.

[0034] First, the skill information acquisition unit 11 acquires as skill information any keyword extracted by the inquiry content analysis device from dialogue information including the inquiry content from the user and the response content of the responder by the inquiry content analysis device (S11). The inquiry analysis device is a device that extracts any keyword from at least one of the inquiry content and the response content of the responder who responded to the inquiry by morphological analysis or the like, and is not particularly limited. For example, the skill information acquisition unit 11 may acquire the extracted keyword as it is as the skill information. In addition, the skill information acquisition unit 11 may acquire, for example, two or more similar keywords as one piece of skill information. Specifically, for example, when keywords such as "order", "want to buy", "purchase", and "want" are extracted, the skill information acquisition unit 11 may recognize and acquire those keywords as the skill information "order". For example, a known technology may be used to determine whether the keywords are similar.

[0035] Next, the analysis result acquisition unit 12 acquires an analysis result obtained by analyzing the dialogue information from the inquiry content analysis device (S12). The person who responds is also called an operator, for example. The analysis result is, for example, a result of analysis for each inquiry. An example of the analysis result based on the information about the inquiry is an emotion analysis result. The emotion that is the target of the emotion analysis is not particularly limited, and is, for example, joy, anger, sadness, and joy. An example of the analysis result based on the response information of the person who responds is the number of times the call is put on hold, the number of times a specific keyword (for example, a word that should not be used (NG word)) appears, and the evaluation result of a supervisor. An example of the analysis result based on both the information about the inquiry and the response information of the person who responds is the length of the response time, the dialogue speed, the number of times the dialogue between the user and the person who responds overlap, and the timing. The timing indicates, for example, the speech interval between different speakers (for example, a customer and an operator, etc.) and the timing of conversation exchanges such as "yes" and "uh". Note that these analysis results are merely examples and are not limited thereto. The analysis result acquisition unit 12 may acquire one analysis result, or may acquire two or more analysis results.

[0036] Next, the parameter calculation unit 13 calculates the type of parameter and the value of the parameter from the analysis result (S13). The type of parameter corresponds to the analysis result, and may be, for example, a sentiment analysis, the number of times on hold, the number of times a specific keyword (for example, a word that should not be used (NG word)) appears, the supervisor's evaluation result, the length of the response time, the dialogue speed, the number of times the dialogue between the user and the responder overlaps, timing, etc. That is, the parameter calculation unit 13 uses, for example, the analysis result as the parameter item. The method of the calculation is not particularly limited. The calculated value may be, for example, a total value, an average value, a median value, a maximum value, a minimum value, etc. for each of the analysis results. The method of the calculation may be different for each of the parameter types.

[0037] The step (S11) and the steps (S12) to (S13) may be performed in parallel or in sequence, for example, as shown in Fig. 3. The order is not particularly limited.

[0038] Then, the skill level calculation unit 14 calculates the skill level of the responder for each of the skill information items by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters (S14), and ends the process (END). The ratio is not particularly limited and can be set arbitrarily. Specifically, the ratio can be set to any value within the range of, for example, 0 to 1.0, 0 to 100, etc. More specifically, for example, a case will be described in which the number of pending calls is 0.5, the number of NG words is 1.0, and the length of response time is 0.0 as the type of the parameter and the value of the parameter. In this case, the skill level calculation unit 14 can use the ratio to calculate the skill level, thereby placing importance on the NG words but not considering the length of response time. The calculated skill level can be expressed, for example, as a decimal number or a percentage.

[0039] More specifically, the skill level calculation unit 14 calculates the skill level by using, for example, the following formula (1): In the following formula (1), the parameter value is p, the type of the parameter is k, the ratio is r, and the skill level is x.

number

[0040] An example of calculating the skill level using the above formula (1) will be described. An example will be described in which the parameter type (k) and parameter value (p) are 4 for the length of response time, 2 for the number of times on hold, and 3 for sentiment analysis. In this case, if the ratio (r) is a constant ratio (e.g., 0.5) for all parameters, the following formula is established. 4×0.5+2×0.5+3×0.5=4.5 Among the types of parameters, if there is a parameter that is to be prioritized (emphasized), the ratio of the parameter to be prioritized may be made closer to 1 (note that in this example, the ratio is a numerical value in the range of 0 to 1). Furthermore, the numerical value of each parameter in this example is a value quantified by the inquiry content analysis device (i.e., for example, the unit of the value for the length of the response time is not "minutes" or the like). On the other hand, the skill level calculation unit 14 may perform the quantification, for example, based on the analysis result.

[0041] The calculation of the skill level (x) by the skill level calculation unit 14 is not limited to the method of calculation using the above formula (1), and may be, for example, a method of calculating a high skill level (x) when at least one of the following conditions is satisfied. Here, in the present invention, "high" means, for example, a case where it is higher than a preset arbitrary reference value, or a case where it is higher compared to other skill levels and parameter values, etc. Meanwhile, in the present invention, "low" or "low" means, for example, a case where it is lower or lower than a preset arbitrary reference value, or a case where it is lower or lower compared to other skill levels and parameter values, etc. Condition 1: The type (k) of the parameter is the length of the response time, and the value (p) of the parameter is small (the length of the response time is short). Condition 2: The type of parameter (k) is the number of reserved times, and the value of the parameter (p) is small (the number of reserved times is small). Condition 3: The type (k) of the parameter is an emotion analysis of "anger" and the value (p) of the parameter is small (the number of occurrences of anger is small). Condition 4: The type (k) of the parameter is an NG word, and the value (p) of the parameter is small (the number of times the NG word is said is small) Condition 5: The type (k) of the parameter is a supervisor's evaluation, and the value (p) of the parameter is high (high evaluation from the supervisor). Condition 6: The type of parameter (k) is at least one of the dialogue speed and timing, and the difference between the value of the parameter (p) and a reference value (e.g., a reference speed or number of times) is small (the dialogue speed and timing, etc., are approximately the same as the reference value).

[0042] The skill level calculation unit 14 may, for example, perform weighting to calculate the skill level.

[0043] In addition, in the skill level calculation method of the present embodiment, for example, after the step (S14), the update unit 15 may update the existing skill level based on the calculated skill level and a learning rate (S15). The existing skill level may be, for example, a skill level registered based on the responder's self-report or the administrator's judgment, or may be a skill level calculated and stored in the n-1th (n is an integer equal to or greater than 1) processing. The learning rate is a parameter indicating how much a value is moved in optimizing machine learning. The learning rate can be set to any value, for example, a value between 0 and 1. By using the learning rate, the present invention can reduce the number of learning times until an optimal solution is obtained and prevent excessive learning. More specifically, the update unit 15 updates the existing skill level using, for example, the following formula (2). In the following formula (2), the stored skill level, i.e., the skill level before the update, is expressed as y t Let the updated skill level be y t+1 The newly calculated skill level is defined as x, and the learning rate is defined as α.

number

[0044] An example of calculating the skill level using the above formula (2) will be described. t ) is 2.5, the newly calculated skill level (x) is 3, and the learning rate α is 0.5. In this case, the following formula is established. 2.5(1-0.5)+3×0.5=2.75 That is, the updated skill level (y t+1 ) is calculated as 2.75.

[0045] The update unit 15 may update the existing skill level, for example, after the inquiry (i.e., the dialogue between the user and the responder) is completed. The update unit 15 may also update the skill information in a routing table (described later) by using the skill information acquired by the skill information acquisition unit 11, for example.

[0046] The skill level calculation method of this embodiment may end (END) after the processing of the step (S15), for example.

[0047] Furthermore, in the skill level calculation method of this embodiment, for example, the skill level may be stored (S16) by the storage unit 16 after the processing of the step (S14) or the step (S15). The storage format is not particularly limited, and may be stored, for example, in a table format based on the skill information and the respondent, or may be stored in a file format on a database or computer. The table format information is also called, for example, a routing table. Hereinafter, the storage format will be described taking a table format as an example, but is not limited thereto. The routing table will be described later. The step (S16) may be actually processed, for example, after the step (S14) and before the step (S15).

[0048] The skill level calculation method of this embodiment may end (END) after the processing of the step (S16), for example.

[0049] According to this embodiment, the skill level of an agent can be calculated taking into account the agent's response record (the response information). When the skill level calculation device of this embodiment is applied to a contact center system, for example, it is possible to assign a more appropriate agent to respond to an inquiry from a user based on the agent's skill level.

[0050] [Embodiment 2] The routing table will now be described in detail. As described above, in the present invention, the format for storing the skill levels is not limited to a table format, but may be a file format.

[0051] FIG. 4 is a schematic diagram showing an example of a routing table. In the routing table shown in FIG. 4, items such as "order", "inquiry", and "delivery" are listed as the skill information (also called "skill"). Also, identification information of operators (responders) such as 1 to 3 are listed as the responders. That is, in FIG. 4, the skill level of operator 1 in "order" is 1.5. Also, in the routing table shown in FIG. 4, rows and columns of asterisks (*) indicate skill levels calculated from at least one of the skill levels of all operators and all skills. The skill level in the asterisk (*) is, for example, an average value or a median value of at least one of the skill levels of all operators and all skills. The storage unit 16 may, for example, expand and store the routing table based on the acquired skill information. That is, the routing table may be in a format that allows automatic expansion of skills (column direction) based on, for example, the skill information acquired by the skill information acquisition unit 11.

[0052] The apparatus 10 may output the routing table to the outside by the communication device 107, or may display the routing table on the display device .

[0053] A specific example of the use and utilization of the routing table will be described below. The device 10 may include a central processing unit that functions as a detection unit, a distribution unit, a calculation unit, etc., as appropriate, in order to realize the following specific examples. The device 10 may use the routing table, for example, to use the skill level of each skill in an algorithm such as a probability distribution, or to determine an operator to be assigned by sorting the routing table in descending order. The device 10 can detect skills that need to be strengthened by, for example, comparing the overall skill level (*:*) with the skill level of each skill (order:*, inquiry:*, etc.). Specifically, in the example shown in FIG. 4, for example, the skill level of "inquiry" (inquiry:*) is lower than the overall skill level (*:*), and it is found that training of the operator is necessary to be strengthened. This allows the manager or the like to grasp the skills that need to be strengthened. Furthermore, the device 10 can extract and distribute operators having skills suitable for the classification of the content of the inquiry by, for example, comparing the skill level of each operator (order:1, inquiry:1, etc.). Specifically, in the example shown in FIG. 4, it is possible to extract and distribute operators in charge, such as assigning operator 1 to handle inquiries regarding "delivery" and operator 2 to handle inquiries regarding "orders."

[0054] The device 10 may store the routing table in at least one unit of year, month, and day (hereinafter also referred to as year / month / day unit) in the storage unit 16. This allows the device 10, etc., to calculate, for example, the transition of the skill level and detect the degree of growth or deterioration of the skill level.

[0055] Furthermore, the device 10 etc. may change the call flow scenario based on the skill information in the routing table. Specifically, for example, if the call flow scenario does not include "delivery," the device 10 etc. may review the call flow so as to add "delivery" to the scenario. This makes it possible to determine skills that are lacking or unnecessary for voice guidance etc., based on keywords (skill information) used in the dialogue, for example.

[0056] For example, the device 10 may set a filter based on a threshold value, the use or non-use of a specific skill level, etc., in calculating the average value of the skill level, etc. When the process by the skill level calculation device of this embodiment is executed for the first time, or when a contact center system including the skill level calculation device of this embodiment is introduced, etc., the skill level calculation unit 14 can calculate an initial skill level (also called an initial value) by using a test call, a stored past conversation, etc.

[0057] [Embodiment 3] The responder distribution system device of this embodiment will be described with reference to Figs.

[0058] FIG. 5 is a block diagram showing an example of a configuration of a responder distribution system device (hereinafter, also referred to as the present system) of this embodiment. As shown in FIG. 5, this system includes the skill level calculation device 10, the inquiry content analysis device 20, and the responder distribution device 30 described in the first and second embodiments. The skill level calculation device 10 can communicate with the inquiry content analysis device 20 and the responder distribution device 30 via the communication line network. For example, this system may further include an automatic response system device 300, a telephone exchange (PBX: Private Branch eXchange) 40, an operator terminal 50, and the like as optional components. This system is also referred to as, for example, a contact center system.

[0059] FIG. 6(A) is a block diagram showing an example of the configuration of the inquiry content analysis device 20 in this system, and FIG. 6(B) is a block diagram showing an example of the configuration of the hardware configuration of the inquiry content analysis device 20. As shown in FIG. 6(A), the inquiry content analysis device 20 includes a dialogue information acquisition unit 21, a keyword extraction unit 22, and an analysis unit 23. The keyword extraction unit 22 may include, for example, a text conversion unit 221 as an optional configuration. The hardware configuration of the inquiry content analysis device 20 is the same as the hardware configuration of the skill level calculation device 10 shown in FIG. 3, except that, as shown in FIG. 6(B), the central processing unit 101 functions as the dialogue information acquisition unit 21, the keyword extraction unit 22, the text conversion unit 221, and the analysis unit 23. The inquiry content analysis device 20 may be incorporated in a server as a system, for example. In addition, the inquiry content analysis device 20 may be, for example, a personal computer (PC, for example, desktop type, notebook type), a smartphone, a tablet terminal, or the like in which the program of the present invention is installed. The inquiry content analysis device 20 is capable of communicating with the skill level calculation device 10, the responder allocation device 30, and the operator terminal 50 via the communication line network.

[0060] FIG. 7(A) is a block diagram showing an example of the configuration of the responder distribution device 30 in this system, and FIG. 7(B) is a block diagram showing an example of the configuration of the hardware configuration of the responder distribution device 30. As shown in FIG. 7(A), the responder distribution device 30 includes an inquiry acquisition unit 31 and a distribution unit 32. The hardware configuration of the responder distribution device 30 is the same as the hardware configuration of the skill level calculation device 10 shown in FIG. 3, except that the central processing unit 101 functions as the inquiry acquisition unit 31 and the distribution unit 32 as shown in FIG. 7(B). The responder distribution device 30 may be, for example, a device in an automatic response system device 300 as shown in FIG. 5. The automatic response system device 300 is a computer system that automatically responds by, for example, voice guidance, and is also called an IVR (Interactive Voice Response) system. The automatic voice response system device 300 may include, for example, a flow control device 310, a queue holding device 320, and other devices in addition to the responder distribution device 30. In the following, the responder allocation device 30 will be described as a device in the automated voice response system device 300, but is not limited thereto. The automated voice response system device 300 can communicate with the skill level calculation device 10, the inquiry content analysis device 20, the telephone exchange 40, and the operator terminal 50, respectively, via the communication line network.

[0061] Next, an example of the responder distribution method of this embodiment will be described based on the flowchart of Fig. 8. The responder distribution method of this embodiment is implemented as follows, for example, using the responder distribution system device of Fig. 5. Note that the responder distribution method of this embodiment is not limited to the use of the responder distribution system device of Fig. 5.

[0062] The method for allocating operators of the present embodiment processes, in this order, a process for allocating operators (S20), a process for analyzing the contents of an inquiry (S30), and a process for calculating a skill level (S10), and then ends (END). The process for allocating operators (S20) includes a process for acquiring an inquiry (S21) and a process for allocating an operator (S22). The process for analyzing an inquiry (S30) includes a process for acquiring dialogue information (S31), a process for extracting keywords (S32), and a process for analyzing (S33).

[0063] The responder allocation step (S20) will be described below. The responder allocation device 30 first acquires the presence or absence of an inquiry and the type of the inquiry by the inquiry acquisition unit 31 (S21). The presence or absence of an inquiry can be acquired, for example, from a queue such as a call queue held by the queue holding device 320. Here, the queue holding device 320 is a device that holds a call queue, and can also hold a call from a user before allocating an operator, as described later. The type of inquiry can be acquired, for example, from the result of classification of an inquiry by the flow control device 310. Here, the flow control device 310 is a device that automatically responds to an inquiry from a user by guidance such as voice guidance. In addition, the flow control device 310 acquires a response from the user to the response, and classifies the content of the inquiry from the response. A specific example will be described later.

[0064] Next, when there is an inquiry, the responder distribution device 30 distributes a responder to each inquiry based on the type of the inquiry by the distribution unit 32 (S22). The distribution is also called ACD (Automatic Call Distribution), for example. The method of distribution in the step (S22) is not particularly limited, and may be, for example, based on a routing method to be described later. Also, the method of distribution in the step (S22) may be, for example, by referring to the skill level (routing table) calculated by the skill level calculation device 10 when the skill level (routing table) is held in advance. The skill level held in advance may be, for example, an initial value as described above, a skill level at the time of the n-1th (n=integer) processing, or a skill level updated for each inquiry.

[0065] The inquiry content analysis step (S30) will be described below. The inquiry content analysis device 20 first acquires, by the dialogue information acquisition unit 21, dialogue information including the contents of the inquiry from the user and the contents of the response of the assigned responder (S31). The dialogue information can be acquired, for example, from the operator terminal 50 after the responder allocation device 30 allocates a responder for each inquiry. Specifically, the operator terminal 50 of the allocated responder is connected to the user terminal 60 of the user by the telephone exchange 40 via a telephone line. Then, the responder and the user converse using the operator terminal 50 and the user terminal 60. Then, the dialogue information acquisition unit 21 acquires the contents uttered by the user and the contents uttered by the responder, i.e., the dialogue information, via the operator terminal 50.

[0066] The inquiry content analysis device 20 then extracts any keyword from the dialogue information by the keyword extraction unit 22 (S32). In the present invention, when a telephone is used as a means of "inquiry" and "responding to the inquiry", for example, the keyword extraction unit 22 may further include a text conversion unit 221. The text conversion unit 221 converts the dialogue information, which is voice information, into text information. Then, the keyword extraction unit 22 extracts the keyword from the text information. The keyword can be extracted by a known method such as morphological analysis.

[0067] The inquiry content analysis device 20 then analyzes the dialogue information by the analysis unit 23 (S33). For example, known methods can be used for the analysis. Specifically, for example, dialogue evaluation, detection of dissatisfied calls, and VOC (Voice of Customer) analysis can be used. More specifically, the analysis target based on the user (the content of the inquiry) can be, for example, the user's emotions such as joy, anger, sadness, and happiness. The analysis target based on the responder (the response content) can be, for example, the number of times the call is put on hold, the number of times a specific keyword (for example, a word that should not be used (NG word)) appears, and the evaluation result of a supervisor. The analysis target based on both the user and the responder can be, for example, the length of the response time, the dialogue speed, the number of times the dialogue between the user and the responder overlap, and the timing.

[0068] The acquisition of the dialogue information, the extraction of the keywords, the analysis, and the like may be performed, for example, simultaneously with the dialogue, or after the dialogue ends. When performing the acquisition of the dialogue simultaneously with the dialogue, the inquiry content analysis device 20, for example, acquires the dialogue in real time by the dialogue information acquisition unit 21. Then, the keyword extraction unit 22 extracts (detects) a specific keyword (for example, "can't connect") that is set in advance from the dialogue. The inquiry content analysis device 20 may, for example, notify an administrator terminal of an administrator (supervisor) that the keyword has been extracted. The administrator supports an operator using the administrator terminal, for example. In addition, the inquiry content analysis device 20 may, for example, cooperate with a FAQ (Frequently Asked Questions) search system, and display example questions and example answers corresponding to the keywords based on the extracted keywords.

[0069] The step (S32) and the step (S33) may be performed in parallel or in sequence, for example, as shown in Fig. 3. The sequence is not particularly limited.

[0070] The skill level calculation step (S10) will be described below. Steps (S11) to (S16) in the skill level calculation step (S10) shown in FIG. 8 are the same as the steps (S11) to (S16) shown in FIG. 3 of the skill calculation method described in the first and second embodiments. That is, the skill information acquisition unit 11 acquires the arbitrary keyword as skill information from the inquiry content analysis device 20 after the step (S32) (S11), the analysis result acquisition unit 12 acquires the analysis result of analyzing the dialogue information from the inquiry content analysis device 20 after the step (S33) (S12), the parameter calculation unit 13 calculates the type of parameter and the value of the parameter from the analysis result (S13), and the skill level calculation unit 14 calculates the skill level of the responder for each of the skill information using the type of parameter, the value of the parameter, and a preset ratio for each of the parameters (S14), and ends (END). Furthermore, the skill level calculation step (S10) may include processing for updating the existing skill level by the update unit 15 (S15) and storing the skill level (routing table) by the storage unit 16 (S16), as described above.

[0071] According to this embodiment, it is possible to calculate a skill level that takes into account the response record of the agent (the response information) in the same manner as the skill level calculation device 10 described in the first and second embodiments. Furthermore, according to this embodiment, it is possible to allocate a more appropriate agent to a user's inquiry based on the agent's skill level.

[0072] [Embodiment 4] An example in which the present invention is applied to a call center will be described.

[0073] Fig. 9 is a chart showing an example of the process at each stage when the present invention is applied to a call center. Specifically, the chart in Fig. 9 shows the process of each device at each stage of "accepting an incoming call", "routing", "during a call", and "calculating a skill level".

[0074] First, the processing of each device at the stage of receiving an incoming call will be described. The user terminal 60 (telephone) makes a call to the call center. Next, the automatic response system device 300 (IVR system) uses the flow control device 310 to provide voice guidance to the user terminal 60, asking for specific inquiry details and the department to which the inquiry is addressed. Then, the user terminal 60 (telephone) presses a button on the user terminal 60 (telephone) according to the voice guidance and enters a number. If there is next guidance, the flow control device 310 provides further voice guidance guidance. These voice guidances allow the inquiry contents to be classified before the start of the dialogue. On the other hand, if there is no next guidance, the queue holding device 320 holds the call queue. That is, the queue holding device 320 holds the incoming call from the user terminal 60 on hold, and registers the incoming call in, for example, a call queue management table.

[0075] Next, the processing of each device in the routing stage will be described. First, the inquiry acquisition unit 31 of the responder distribution device 30 acquires the call queue management table and checks waiting incoming calls. Next, the distribution unit 32 of the responder distribution device 30 distributes an operator. Note that the distribution may be performed by referring to the routing table stored in advance, as described above. Then, the responder distribution device 30 causes the call to be received at the operator terminal 50 of the distributed operator. The operator terminal 50 answers the incoming call.

[0076] Next, the processing of each device during a call will be described. First, the user and the person in charge have a dialogue (conversation) using the user terminal 60 and the operator terminal 50. Here, the inquiry content analysis device 20 acquires the dialogue by the dialogue information acquisition unit 21. Next, the inquiry content analysis device 20 converts the dialogue into text information via the operator terminal 50 by the text conversion unit 221. Then, the inquiry content analysis device 20 extracts keywords by the keyword extraction unit 22. After the dialogue between the user and the person in charge ends, the inquiry content analysis device 20 analyzes the dialogue by the analysis unit 23. The analysis result may be newly registered in an analysis result table, for example, or may be registered by updating an existing analysis result table.

[0077] Next, the processing of each device in the skill level calculation stage will be described. First, the skill level calculation device 10 refers to the analysis result table by the analysis result acquisition unit 12 and acquires the analysis result. Next, the skill level calculation device 10 calculates the type of parameter and the value of the parameter by the parameter calculation unit 13. Furthermore, the skill level calculation device 10 acquires the extracted keyword by the skill information acquisition unit 11. Then, the skill level calculation device 10 calculates the skill level of the responder for each of the skill information by the skill level calculation unit 14. The calculated skill level is stored as the routing table by the storage unit 16. Furthermore, the skill level calculation device 10 may update the existing routing table based on the calculated skill level by the update unit 15.

[0078] As a method (routing method) for distributing a responder to each inquiry, there are, for example, the following methods. · Mass call, ring all A method in which all operator phones ring simultaneously. In this case, the person who picks up the receiver (goes off the hook) first will answer the call. Random A method of ringing all phones randomly. List order, round robin (sequential) A method in which an agent creates a list and phones ring in order. Minimum number of calls, waiting time (least recent) A method of directing calls to the operator with the longest waiting time. ·Number of calls A method of assigning calls to the operator who has received the fewest calls. Skill-based A method in which skills are assigned to each operator and calls are allocated according to their skill level.

[0079] The skill-based method is realized by manually registering the knowledge (skills) and proficiency (skill level) of the operators in the system in advance, and then allocating the inquiry to an operator who is good at the inquiry. The skill-based method allows allocation that makes use of the work experience of the operators. However, since the skills and skill levels are based on self-reporting or the judgment of the manager, there is a problem that it is difficult to quantitatively set (register) them. In addition, the classification of the skills registered in advance may differ from the inquiry content, and in order to accurately link the skills and the inquiry content, it is necessary to correct the registered skills after the dialogue ends. Furthermore, there is a problem that management work such as creating, registering, and updating the skill information is costly. There is also a problem that allocation that takes into account the operator's inquiry response track record is not possible.

[0080] However, the responder allocation system device and the responder allocation method of the present embodiment lead to, for example, the efficiency of operation and management of the contact center system. Specifically, for example, the time required for registering and updating skill information and skill levels can be reduced, skill information and skill levels can be calculated based on the content of the inquiry and the response information with objective criteria, and skills that are lacking or unnecessary for guidance can be determined from keywords used in the dialogue. In addition, the responder allocation system device and the responder allocation method of the present embodiment can reduce, for example, the response time of a responder for one inquiry and complaints from users. Specifically, for example, by preferentially allocating an operator with a good response record, such as a short call time, based on the skill level, the number of responses and customer satisfaction can be improved.

[0081] [Embodiment 5] The program of the present embodiment is a program for causing a computer to execute each step of the method of the present invention as a procedure. In the present invention, the "procedure" may be read as "processing." The program of the present embodiment may be recorded, for example, in a computer-readable recording medium. The recording medium is not particularly limited, and examples thereof include a read-only memory (ROM), a hard disk (HD), and an optical disk.

[0082] Although the present invention has been described above with reference to the embodiment, the present invention is not limited to the above embodiment. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0083] <Additional Notes> Some or all of the above embodiments may be described as follows, but are not limited to the following supplementary notes. (Appendix 1) The present invention includes a skill information acquisition unit, an analysis result acquisition unit, a parameter calculation unit, and a skill level calculation unit, The skill information acquisition unit acquires, as skill information, any keyword extracted by an inquiry content analysis device from dialogue information including the content of an inquiry from a user and the content of a response by a responder; the analysis result acquisition unit acquires an analysis result obtained by analyzing the dialogue information from the inquiry content analysis device; the parameter calculation unit calculates a type of a parameter and a value of the parameter; The skill level calculation unit calculates the skill level of the responder for each piece of skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters. (Appendix 2) Further, the method includes: 2. The skill level calculation device according to claim 1, wherein the update unit updates an existing skill level based on the calculated skill level by using the calculated skill level and a learning rate. (Appendix 3) Further, the device includes a storage unit, 3. The skill level calculation device according to claim 1, wherein the memory unit stores the skill level. (Appendix 4) A skill level calculation device, an inquiry content analysis device, and a responder distribution device according to any one of claims 1 to 3, The responder distribution device includes an inquiry acquisition unit and a distribution unit, The inquiry acquisition unit acquires the presence or absence of an inquiry and the type of the inquiry, The distribution unit distributes, when there is an inquiry, a responder to each of the inquiries based on the type of the inquiry; the inquiry content analysis device includes a dialogue information acquisition unit, a keyword extraction unit, and an analysis unit; The dialogue information acquisition unit acquires dialogue information including the content of the inquiry from the user and the response content of the respondent to the distributed inquiry, The keyword extraction unit extracts any keyword from the dialogue information, The analysis unit analyzes the dialogue information, In the skill level calculation device, the skill information acquisition unit acquires the arbitrary keyword extracted by the inquiry content analysis device as skill information; the analysis result acquisition unit acquires an analysis result obtained by analyzing the dialogue information from the inquiry content analysis device; the parameter calculation unit calculates a type of parameter and a value of the parameter from the analysis result; The skill level calculation unit calculates the skill level of the responder for each of the skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters. (Appendix 5) In the responder distribution device, The distribution unit, when an inquiry is received, distributes a responder to each inquiry based on the type of inquiry and by referring to the skill level calculated by the skill level calculation device. (Appendix 6) The method includes a skill information acquisition step, an analysis result acquisition step, a parameter calculation step, and a skill level calculation step, The skill information acquiring step acquires, as skill information, any keyword extracted by an inquiry content analyzing device from dialogue information including the content of an inquiry from a user and the content of a response by a responder; The analysis result acquisition step includes acquiring an analysis result of analyzing the dialogue information from the inquiry content analysis device, The parameter calculation step calculates types of parameters and values ​​of the parameters from the analysis results, The skill level calculation method includes calculating a skill level of the responder for each piece of skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters, in the skill level calculation step. (Appendix 7) Further, the method includes an updating step, 7. The skill level calculation method according to claim 6, wherein the updating step updates an existing skill level based on the calculated skill level by using the calculated skill level and a learning rate. (Appendix 8) Further, a storing step is included, 8. The skill level calculation method according to claim 6, wherein the storing step stores the skill level. (Appendix 9) The method includes a skill level calculation step, an inquiry content analysis step, and a responder allocation step, The responder distribution step includes an inquiry acquisition step and a distribution step, The inquiry acquisition step acquires whether or not an inquiry has been made and the type of the inquiry, The distribution step includes, when an inquiry is received, distributing a respondent to each of the inquiries based on the type of the inquiry; The inquiry content analysis step includes a dialogue information acquisition step, a keyword extraction step, and an analysis step, The dialogue information acquisition step acquires dialogue information including the content of the inquiry from the user and the response content of the assigned respondent, The keyword extraction step includes extracting any keyword from the dialogue information, The analyzing step includes analyzing the dialogue information, The skill level calculation step is a skill level calculation method according to any one of Supplementary Notes 6 to 8, the skill information acquiring step acquires the arbitrary keyword extracted by the inquiry content analysis device as skill information; The analysis result acquisition step includes acquiring an analysis result of analyzing the dialogue information from the inquiry content analysis device, The parameter calculation step calculates types of parameters and values ​​of the parameters from the analysis results, The skill level calculation step calculates the skill level of the responder for each of the skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters. (Appendix 10) In the respondent distribution step, The method for allocating responders described in Appendix 9, wherein, when an inquiry is received, the distribution step allocates responders to each inquiry based on the type of inquiry and by referring to the skill level calculated by the skill level calculation device. (Appendix 11) A program for causing a computer to execute procedures including a skill information acquisition procedure, an analysis result acquisition procedure, a parameter calculation procedure, and a skill level calculation procedure; The skill information acquisition step includes acquiring, as skill information, any keyword extracted by an inquiry content analysis device from dialogue information including the content of an inquiry from a user and the content of a response from a responder; the analysis result acquisition step includes acquiring an analysis result of analyzing the dialogue information from the inquiry content analysis device; the parameter calculation step includes calculating a type of parameter and a value of the parameter from the analysis result; The skill level calculation step calculates a skill level of the operator for each piece of skill information by using the type and value of the parameter and a preset ratio for each of the parameters. (Appendix 12) Further, including an update procedure, 12. The program of claim 11, wherein the update step updates an existing skill level based on the calculated skill level using the calculated skill level and a learning rate. (Appendix 13) Further comprising a storage step, 13. The program according to claim 11 or 12, wherein the storing step stores the skill level. (Appendix 14) A computer is provided with a procedure for calculating a skill level, a procedure for analyzing the contents of an inquiry, and a procedure for allocating personnel to respond to the inquiry. a program for carrying out steps including: The responder distribution procedure includes an inquiry acquisition procedure and a distribution procedure; The inquiry acquisition step acquires the presence or absence of an inquiry and the type of the inquiry, The distribution step includes, when an inquiry is received, distributing a responder to each of the inquiries based on the type of the inquiry; The inquiry content analysis step includes a dialogue information acquisition step, a keyword extraction step, and an analysis step; The dialogue information acquisition step acquires dialogue information including the content of the inquiry from the user and the response content of the respondent to the distributed inquiry, The keyword extraction step includes extracting any keyword from the dialogue information, The analysis step includes analyzing the dialogue information, The skill level calculation step is a program according to any one of Supplementary Notes 11 to 13, the skill information acquisition step includes acquiring the arbitrary keyword extracted by the inquiry content analysis device as skill information; the analysis result acquisition step includes acquiring an analysis result of analyzing the dialogue information from the inquiry content analysis device; the parameter calculation step includes calculating a type of parameter and a value of the parameter from the analysis result; The skill level calculation step calculates a skill level of the operator for each piece of skill information by using the type and value of the parameter and a preset ratio for each of the parameters. (Appendix 15) In the responder distribution procedure, The program of claim 14, wherein the distribution procedure, when an inquiry is received, distributes a responder to each inquiry based on the type of inquiry and by referring to the skill level calculated by the skill level calculation device. (Appendix 16) A computer-readable recording medium having recorded thereon a program according to any one of appendixes 11 to 15. [Industrial Applicability]

[0084] According to the present invention, the skill level of an operator can be calculated, and therefore the present invention is useful in the field of allocating operators to respond to calls. [Explanation of symbols]

[0085] 10 Skill Level Calculator 11 Skill Information Acquisition Department 12 Analysis result acquisition section 13 Parameter Calculation Section 14 Skill Level Calculation Section 15 Update section 16 Memory section 20 Inquiry content analysis device 21 Dialogue information acquisition unit 22 Keyword Extraction Section 221 Text conversion section 23 Analysis Department 30 Responder Distribution Device 31 Inquiry Acquisition Department 32 Distribution section 40 Telephone exchange 50 Operator terminal 60 User terminal 300 Automatic response system device 310 Flow Control Device 320 Cue Holder 101 Central Processing Unit 102 Memory 103 Bus 104 Storage device 105 Input Device 106 Display device 107 Communication Devices

Claims

1. The method includes a skill information acquisition step, an analysis result acquisition step, a parameter calculation step, and a skill level calculation step, The skill information acquisition step includes acquiring, as skill information, any keyword extracted by an inquiry content analysis device from dialogue information including the content of an inquiry from a user and the content of a response from a responder; the analysis result acquisition step includes acquiring an analysis result of analyzing the dialogue information from the inquiry content analysis device; the parameter calculation step includes calculating at least one selected from a total value, an average value, a median value, a maximum value, and a minimum value for each of the analysis results based on the types and values ​​of the parameters that are the analysis results; the skill level calculation step calculates a skill level of the operator for each of the skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters; A skill level calculation program for causing a computer to execute each of the above procedures.

2. Further, including an update procedure, 2. The skill level calculation program according to claim 1, wherein the updating step updates an existing skill level based on the calculated skill level by using the calculated skill level and a learning rate.

3. Further comprising a storage step, 3. The skill level calculation program according to claim 1, wherein said storing step stores said skill level.

4. The method includes a skill level calculation procedure, an inquiry content analysis procedure, and a responder allocation procedure, The responder distribution procedure includes an inquiry acquisition procedure and a distribution procedure; The inquiry acquisition step acquires the presence or absence of an inquiry and the type of the inquiry, The distribution step includes, when an inquiry is received, distributing a responder to each of the inquiries based on the type of the inquiry; The inquiry content analysis step includes a dialogue information acquisition step, a keyword extraction step, and an analysis step; The dialogue information acquisition step acquires dialogue information including the content of the inquiry from the user and the response content of the respondent to the distributed inquiry, The keyword extraction step includes extracting any keyword from the dialogue information, The analysis step includes analyzing the dialogue information by at least one of a dialogue evaluation, a dissatisfied call detection, and a VOC (Voice of Customer) analysis; The skill level calculation step is a skill level calculation program according to any one of claims 1 to 3, the skill information acquisition step includes acquiring the extracted arbitrary keyword as skill information; The analysis result acquisition step acquires an analysis result obtained by analyzing the dialogue information, the parameter calculation step includes calculating at least one selected from a total value, an average value, a median value, a maximum value, and a minimum value for each of the analysis results based on the type and value of the parameter that is the analysis result; the skill level calculation step calculates a skill level of the operator for each of the skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters; A responder distribution program for causing a computer to execute each of the above procedures.

5. In the responder distribution procedure, 5. The program for allocating personnel to handle a response according to claim 4, wherein the allocation step allocates a response person to handle each response based on the type of the response, by referring to the skill level calculated by the skill level calculation step, when the response is received.

6. The method includes a skill information acquisition step, an analysis result acquisition step, a parameter calculation step, and a skill level calculation step, The skill information acquiring step acquires, as skill information, any keyword extracted by an inquiry content analyzing device from dialogue information including the content of an inquiry from a user and the content of a response from a responder; The analysis result acquisition step includes acquiring an analysis result of analyzing the dialogue information from the inquiry content analysis device, the parameter calculation step includes calculating at least one selected from a total value, an average value, a median value, a maximum value, and a minimum value for each of the analysis results based on the types and values ​​of the parameters that are the analysis results; the skill level calculation step calculates a skill level of the operator for each of the skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters; A skill level calculation method, wherein each of the steps is executed by a computer.

7. Further, the method includes an updating step, 7. The skill level calculation method according to claim 6, wherein the updating step updates an existing skill level based on the calculated skill level by using the calculated skill level and a learning rate.

8. The method includes a skill level calculation step, an inquiry content analysis step, and a responder allocation step, The responder distribution step includes an inquiry acquisition step and a distribution step, The inquiry acquisition step acquires whether or not an inquiry has been made and the type of the inquiry, The distribution step includes, when an inquiry is received, distributing a respondent to each of the inquiries based on the type of the inquiry; The inquiry content analysis step includes a dialogue information acquisition step, a keyword extraction step, and an analysis step, The dialogue information acquisition step acquires dialogue information including the content of the inquiry from the user and the response content of the assigned respondent, The keyword extraction step includes extracting any keyword from the dialogue information, The analyzing step includes analyzing the dialogue information by at least one of a dialogue evaluation, a dissatisfied call detection, and a VOC (Voice of Customer) analysis. The skill level calculation step is a skill level calculation method according to claim 6 or 7, The skill information acquiring step acquires the extracted arbitrary keyword as skill information, The analysis result acquisition step acquires an analysis result obtained by analyzing the dialogue information, the parameter calculation step includes calculating at least one selected from a total value, an average value, a median value, a maximum value, and a minimum value for each of the analysis results based on the types and values ​​of the parameters that are the analysis results; the skill level calculation step calculates a skill level of the operator for each of the skill information by using the type of the parameter, the value of the parameter, and a preset ratio for each of the parameters; A responder allocation method, wherein each of the steps is executed by a computer.

9. In the respondent distribution step, 9. The method for allocating personnel according to claim 8, wherein, when an inquiry is received, the allocation step allocates a person to handle each inquiry based on the type of the inquiry and with reference to the skill level calculated in the skill level calculation step.

Images