KR20240066948A - Call center operation system to minimize waiting time by predicting remaining consultation time - Google Patents

Abstract

A call center operating system for minimizing waiting time by predicting the remaining consultation time includes a customer terminal configured to transmit consultation content for consultation, and a call center connected to the customer terminal to make a call. A target agent terminal that receives consultation content from a plurality of agent terminals and the customer terminal, determines a first consultation type corresponding to the consultation content, and corresponds to the first consultation type determined among the plurality of agent terminals. is determined, and communication is established between the target agent terminal and the customer terminal.

Description

A call center operation system to minimize waiting time by predicting the remaining consultation time {CALL CENTER OPERATION SYSTEM TO MINIMIZE WAITING TIME BY PREDICTING REMAINING CONSULTATION TIME}

The present invention relates to a call center operation system, and more specifically, to a call center operation system for minimizing waiting time by predicting remaining consultation time.

As customer service services have recently developed, many companies are deploying counselors to operate call centers. In particular, in recent years, efforts have been made to reduce the work burden on counselors and conduct consultations more efficiently by partially processing customer calls through server-based applications such as chatbots rather than directly connecting them to a counselor, and then connecting them to a counselor later. I'm losing.

As one of the above-mentioned chatbot-based prior technologies, the interactive voice bot server and unmanned consultation method using it proposed by domestic patent application number 10-2021-0125399 A is an interactive voice bot server that modularizes functions common to various types of voice bots. It provides call processing, scenario management, and spoken language processing functions using a voice bot server. The call processing function converts the customer's voice input from the switchboard into text, analyzes the converted text, creates outgoing text, converts the outgoing text into voice and transmits it to the customer, and enables recording of each conversation topic. The scenario management function enables viewing of conversation scenarios and changing items, and the colloquial language processing function enables purification, substitution, and rhetorical conversion of colloquial text.

However, even through applications such as these chatbots, the customer's needs are not accurately analyzed and the problem of inefficient consultation continues to occur, which requires improvement.

The problem to be solved by the present invention is to provide a cloud-based call center system.

In particular, the problem to be solved by the present invention is to provide a cloud-based call center system that can determine the consultation type by analyzing the contents of the consultation from the customer and provide a connection to the agent terminal corresponding to the determined consultation type. .

The cloud-based call center operating system according to embodiments of the present invention includes a customer terminal configured to transmit consultation contents for consultation, a plurality of agent terminals that are connected to the customer terminal and perform a call, and receive consultation contents of the customer terminal. Then, a first consultation type corresponding to the consultation content is determined, a target counselor terminal corresponding to the determined first consultation type is determined among a plurality of counselor terminals, and communication is connected between the target counselor terminal and the customer terminal.

The cloud-based call center operating system according to embodiments of the present invention has the effect of providing more accurate consultation by connecting a counselor terminal suitable for the consultation content of the customer terminal with the customer terminal.

The cloud-based call center operating system according to embodiments of the present invention has the effect of providing more accurate and faster consultation by connecting a counselor terminal that is suitable for the consultation content of the customer terminal and has a relatively small remaining consultation time with the customer terminal. .

Figure 1 shows a cloud-based call center operating system according to embodiments of the present invention.
Figure 2 shows a call center operation server according to embodiments of the present invention.
Figure 3 shows agent terminals of a call center operating system according to embodiments of the present invention.
Figure 4 is a flow chart showing the operation of a call center operation server according to embodiments of the present invention.
Figure 5 is a flow chart for explaining the operation of determining a target agent terminal by a call center operation server according to embodiments of the present invention.
Figure 6 is a diagram showing necessary information corresponding to a consultation type according to embodiments of the present invention.
Figure 7 is a diagram for explaining the process of calculating the remaining consultation time according to embodiments of the present invention.
Figure 8 is a flow chart for explaining the operation of determining a target agent terminal according to embodiments of the present invention.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention. While describing each drawing, similar reference numerals are used for similar components.

Terms such as first, second, A, and B may be used to describe various components, but the components should not be limited by these terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be named a second component without departing from the scope of the present invention, and similarly, the second component may also be named a first component. The term and/or includes any of a plurality of related stated items or a combination of a plurality of related stated items.

A component is "connected" to another component. present or "connected" When it is mentioned that there is, it may be directly connected or connected to the other component, but it should be understood that other components may exist in the middle. On the other hand, a component is "directly connected" to another component. or "directly connected" When mentioned, it should be understood that no other intermediate components exist.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, "include" or "have" Terms such as are intended to designate the presence of features, numbers, steps, operations, components, parts, or a combination thereof described in the specification, but are intended to indicate the presence of one or more other features, numbers, steps, operations, components, parts, or It should be understood that the existence or addition possibility of combinations of these is not excluded in advance.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings.

Figure 1 shows a cloud-based call center operating system according to embodiments of the present invention.

Referring to FIG. 1, a cloud-based call center operating system (hereinafter referred to as call center operating system) 10 may include a customer terminal 100, an agent terminal 200, and a call center operating server 300. Depending on embodiments, there may be multiple counselor terminals 200.

Each of the components 100, 200, and 300 in FIG. 1 may be connected through a network. Depending on embodiments, the customer terminal 100 may be connected to the call center operation server 300 through a network, and may also be directly or indirectly connected to at least one agent terminal 200 through the call center operation server 300. there is. At this time, the network refers to a connection structure that allows information exchange between each node, such as a plurality of terminals and servers. Examples of such networks include the 3rd Generation Partnership Project (3GPP) network and the Long Term Evolution (LTE) network. ) network, 5GPP (5rd Generation Partnership Project) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), It includes, but is not limited to, PAN (Personal Area Network), Bluetooth network, NFC network, satellite broadcasting network, analog broadcasting network, and DMB (Digital Multimedia Broadcasting) network.

The customer terminal 100 may be a terminal of a customer who wishes to receive consultation through a call center. The customer terminal 100 can transmit consultation content in the form of voice, number, or text to the call center operation server 300, and receive consultation results corresponding to the consultation content from the call center operation server 300. At this time, the consultation results may be provided in the form of voice, number, or text.

The customer terminal 100 may be a device that can access a remotely located device through a network. For example, the customer terminal 100 may be a laptop, desktop, smartphone, wearable device, etc., but is not limited thereto.

The counselor terminal 200 may be a terminal of a counselor who responds to counseling. At least one counselor terminal 200 may output a response to the consultation in the form of voice, number, or text. According to embodiments, the agent terminal 200 receives the consultation content provided from the customer terminal 100 through the call center operation server 300, and sends the response content in the form of voice, number, or text to the call center operation server 300. Can be transmitted.

The counselor terminal 200 may be a device that can access a remotely located device through a network. For example, the agent terminal 200 may be a laptop, desktop, smartphone, wearable device, etc., but is not limited thereto.

The call center operation server 300 may provide a call center service that provides answers corresponding to consultations from the customer terminal 100. In particular, the call center operation server 300 according to embodiments of the present invention can provide a cloud-based call center service that provides answers to the customer terminal 100 through a network.

The call center operation server 300 may receive a call signal from the customer terminal 100. The call center operation server 300 may exchange questions and answers with the customer terminal 100 in response to call signals, and may provide consultation results to the customer terminal 100 according to the analysis results of the question and answers. According to embodiments, the call center operation server 300 provides a query to the customer terminal 100 that transmitted the call signal, receives a response corresponding to the query, analyzes the response, and according to the analysis result, provides a query to the customer terminal 100. ) can provide consultation results. At this time, questions and answers may be sequentially performed multiple times.

Depending on embodiments, the call center operation server 300 may provide a counseling session. At this time, the counseling session may be provided directly or indirectly through an app page, web page, application, program, etc. The consultation session is created and provided by a chatbot application run by the call center operation server 300, and the customer terminal 100 can access the consultation session, check the inquiry, enter a response to the inquiry, and provide the consultation. Results can be provided.

At this time, the consultation result may be generated by a chatbot application, or may be transmitted from the agent terminal 200 connected to the customer terminal 100.

The call center operation server 300 according to embodiments of the present invention may perform a question-and-answer session with the customer terminal 100 through a consultation session, and determine a consultation type corresponding to the customer terminal 100 according to the question-answer. The call center operation server 300 may communicate with the customer terminal 100 and connect the agent terminal 200 corresponding to the determined consultation type.

In this specification, when the call center operation server 300 connects the customer terminal 100 and the agent terminal 200 to communication, it means that the call center operation server 300 allows the customer terminal 100 and the agent terminal 200 to send text/text messages to each other. This may mean configuring a state in which data such as voice can be exchanged, or data such as text/voice can be exchanged.

Figure 2 shows a call center operation server according to embodiments of the present invention.

Referring to FIG. 2, the call center operation server 300 may include a communication unit 310, a control unit 320, and a storage unit 330.

The communication unit 310 can exchange data with an external device. Depending on embodiments, the communication unit 310 may exchange data with an external device according to a wired communication method or a wireless communication method.

Depending on embodiments, the communication unit 310 may exchange data with the customer terminal 100 and the agent terminal 200. For example, the communication unit 310 may transmit data related to a counseling session to the customer terminal 100.

The control unit 320 may control the overall operation of the call center operation server 300. For example, the control unit 320 may include at least one processor, and the at least one processor may include a central processing unit (CPU), a micro controller unit (MCU), a graphical processing unit (GPU), and an application processing unit (ASIC). It may be a specified integrated circuit) or a field programmable gate array (FPGA), but embodiments of the present invention are not limited thereto.

The control unit 320 may control the overall operation of the call center operation server 300. That is, even if there is no separate explanation, the operation of the call center operation server 300 described below can be understood as being performed under the control of the control unit 320.

Depending on the embodiments, the control unit 320 may control data communication between the call center operation server 300 and the external terminals 100 and 200, and the control unit 320 may control data communication for the external terminals 100 and 200. The operation of the call center operation server 300 can be controlled.

According to embodiments, the control unit 320 analyzes the questions and answers exchanged between the call center operation server 300 and the customer terminal 100, and selects a question and answer corresponding to the question and answer from a plurality of pre-stored consultation types according to the analysis results. You can decide on the type of consultation.

In addition, the control unit 320 provides text, email, chat, and a shared bulletin board to terminals (for example, user terminals, etc.) connected to the call sensor operation server 300, thereby facilitating communication with customers and agent management. We can support you to make it possible.

The storage unit 330 may store data necessary for the operation of the call center operation server 300. For example, the storage unit 330 may include non-volatile memory or volatile memory. Depending on embodiments, the storage unit 330 may store a plurality of commands for controlling the operation of the call center operation server 300. The control unit 320 may control the call center operation server 300 by loading the commands stored in the storage unit 330.

The storage unit 330 may store consultation types that can be supported by the call center operation server 300 and consultation results corresponding thereto. At this time, the storage unit 330 may store questions and responses corresponding to a plurality of branch nodes constituting each of a plurality of consultation types.

In one example, the storage unit 330 may be configured to generate recorded data (eg, voice data) according to the consultation results, and the generated recorded data can be viewed through an administrator terminal.

In addition, the control unit 320 supports viewing of recorded data through the administrator terminal, and simultaneously receives messages from the administrator terminal according to the viewing of the recorded data, and sends the received messages through real-time pop-ups before, during, or after the consultation. It can be provided to the counselor terminal 200.

In addition, the control unit 320 can generate statistical situation data according to the progress of real-time consultation and support an external manager terminal to view the generated statistical situation data. Statistical situation data may include call reception time, call reception number, call response customer information, call reception counselor, etc.

In addition, the control unit 320 provides the agent terminal 200 with a user interface that can record reservation call status information that occurs during real-time consultation, and receives the reservation call status information through the agent terminal 200 and stores it in the storage unit. It can be saved at (330). Reservation call status information may include reservation call timing, reservation call target customer information, etc.

Figure 3 shows agent terminals of a call center operating system according to embodiments of the present invention.

Referring to FIG. 3, the consultation call (CL) of the customer terminal 100 may correspond to one of a plurality of consultation types (CTYPE). At this time, the consultation type (CTYPE) may be determined according to the results of the inquiry and response between the customer terminal 100 and the call center operation server 300. For example, the consultation type (CTYPE) may include a delivery-related type, an order-related type, and a refund-related type, but embodiments of the present invention are not limited thereto.

Additionally, a plurality of agent terminals 200 may be configured into a plurality of groups 200A, 200B, and 200C corresponding to each consultation type (CTYPE). For example, the first group of agent terminals 200A may respond to delivery-related consultation types. At this time, the group of counselor terminals 200 may be determined by the content of counseling each of the counselor terminals 200 has performed in the past, but is not limited to this.

Figure 4 is a flow chart showing the operation of a call center operation server according to embodiments of the present invention.

Referring to FIG. 4, the call center operation server 300 may receive consultation content from the customer terminal 100 (S110). According to embodiments, the customer terminal 100 may transmit a call signal using a phone number corresponding to the call center operation server 300, and the call center operation server 300 may receive the transmitted call signal. After the customer terminal 100 and the call center operation server 300 are connected through a call signal, the consultation content of the customer terminal 100 may be transmitted to the call center operation server 300. At this time, the call center operation server 300 may receive the identifier of the customer terminal 100 along with the call signal.

The call center operation server 300 may determine the consultation type corresponding to the response delivered from the customer terminal 100 (S120). According to embodiments, the call center operation server 300 analyzes the response from the customer terminal 100 and uses the analysis result to determine a consultation type corresponding to the response of the customer terminal 100 from among a plurality of possible consultation types. You can.

The call center operation server 300 may provide a query to the customer terminal 100 and receive a response to the query from the customer terminal 100. At this time, the call center operation server 300 may provide a query, receive a response, analyze the response, and provide a follow-up query corresponding to the response to the customer terminal 100. According to this method, the call center operation server 300 can perform sequential inquiry and response with the customer terminal 100 and determine the type of consultation using sequential responses transmitted from the customer terminal 100.

According to embodiments, the call center operation server 300 receives a response in the form of a voice provided from the customer terminal 100, converts the received voice into text through STT (speech to text) conversion, and sends the converted text. Through analysis, among a plurality of possible consultation types, the consultation type corresponding to the response of the customer terminal 100 can be determined. For example, the call center operation server 300 may perform word separation of the converted text, separate it into meaningful units, and analyze the response.

In this case, the call center operation server 300 may analyze the converted text by refining or replacing it with a pre-designated standard text. For example, the call center operation server 300 may use a pre-stored dictionary of similar words/synonyms to refine or replace the converted text with standard text having the same/similar meaning, but is not limited to this.

The call center operation server 300 may determine a target agent terminal corresponding to the determined consultation type (S130). According to embodiments, the call center operation server 300 may determine a target agent terminal suitable for the consultation type of the customer terminal 100 from among the plurality of agent terminals 200.

The call center operation server 300 may connect the determined target agent terminal and the customer terminal (S140). Depending on embodiments, the call center operation server 300 may be configured to enable the customer terminal 100 and the target agent terminal to perform data communication. For example, the call center operation server 300 may transmit data transmitted from the customer terminal 100 to the target agent terminal, and may transmit data transmitted from the target agent terminal to the customer terminal 100. Accordingly, the target agent terminal and the customer terminal 100 may be connected to each other.

Figure 5 is a flow chart for explaining the operation of determining a target agent terminal by a call center operation server according to embodiments of the present invention.

Referring to FIG. 5, the call center operation server 300 may determine a counselor terminal corresponding to the consultation type (S131). Depending on embodiments, each of the counselor terminals 200 may correspond to a predetermined counseling type.

The call center operation server 300 may calculate the remaining consultation time of the consultation currently being performed by agent terminals corresponding to the determined consultation type (S133). Here, the remaining consultation time refers to the time until each agent terminal completes the consultation with the customer terminal that is currently being performed. At this time, the remaining consultation time of the agent terminal that is not conducting consultation with any customer terminal may be calculated as 0.

The call center operation server 300 may determine a counselor terminal whose remaining counseling time is less than or equal to a predetermined reference time among the counselor terminals as the target counselor terminal (S135). For example, the call center operation server 300 may determine the agent terminal with the minimum remaining consultation time as the target agent terminal. Accordingly, the waiting time for connection of the customer terminal 100 to the agent terminal 200 can be minimized.

Figure 6 is a diagram showing necessary information corresponding to a consultation type according to embodiments of the present invention.

Referring to FIG. 6, the call center operation server 300 may store information on necessary information corresponding to each consultation type. At this time, the necessary information is information needed to complete the consultation, and the consultation can be completed normally only when all of the relevant information appears in the consultation content.

Necessary information may be set differently for each consultation type and stored in the call center operation server 300. For example, as shown in Figure 6, when the consultation type is 'order confirmation', the corresponding necessary information may be 'name', 'phone number', and 'order date'. The call center operation server 300 may obtain necessary information corresponding to the consultation type from the storage unit 330.

Figure 7 is a diagram for explaining the process of estimating the remaining consultation time according to embodiments of the present invention.

Referring to FIG. 7, the call center operation server 300 may calculate (or predict) the remaining consultation time based on the consultation content of the currently consulting agent (i.e., agent terminals). For example, the call center operation server 300 can calculate (or predict) the remaining consultation time for the current consultation by reading the consultation contents of each of the agent terminals 200 currently in consultation from the storage unit 330. .

The call center operation server 300 analyzes the current consultation content of each of the agent terminals 200, extracts information included in the consultation content, and selects information corresponding to the type of consultation of the agent terminals 200 from among the extracted information. Matching information that matches the necessary information can be determined. According to embodiments, the call center operation server 300 may determine whether matching information exists in the consultation content by comparing information included in the current consultation content with necessary information.

In this specification, matching specific information with required information not only means that the specific information is data-wise identical or similar to the required information, but also includes that the meaning of the specific information is the same or similar to the meaning of the required information. . For example, the call center operation server 300 may compare text (or keywords) constituting necessary information with text (or keywords) constituting the extracted information to determine whether matching information exists in the consultation content. At this time, the call center operation server 300 can make the decision using various comparison algorithms such as natural language processing, semantic analysis, and similarity between words.

The call center operation server 300 can calculate the progress rate for the current consultation of each agent terminal 200 using the matching information, and calculate the remaining consultation time according to the calculated progress rate.

According to embodiments, the call center operation server 300 uses, for each of the agent terminals 200, the average consultation time, calculated progress rate, and elapsed time for the consultation type corresponding to the consultation of each of the agent terminals 200. Thus, the remaining consultation time can be calculated. For example, the call center operation server 300 may calculate the remaining consultation time according to Equation 1 below.

Here, T _r is the remaining consultation time for the currently in progress consultation, T _avg is the average consultation time for the corresponding consultation type, p _rate is the calculated progress rate for the currently in progress consultation, and T _sp is the consultation time for the currently in progress consultation. Indicates elapsed time.

The call center operation server 300 can store the average consultation time for each consultation type and calculate the elapsed time by counting the time required from the time of connection between the customer terminal 100 and the agent terminal 200.

The call center operation server 300 may calculate the progress rate of the current consultation for each of the counselor terminals 200 based on the matching information included in the consultation content. According to embodiments, the call center operation server 300 may calculate the progress rate of the current consultation of each of the counselor terminals 200 depending on the presence or absence of matching information included in the consultation content. The call center operation server 300 can calculate the progress rate higher as the content of the current consultation of each of the agent terminals 200 includes more matching information. For example, as shown in Figure 7, Agent 1 is conducting a consultation with the consultation type being 'order confirmation', and the consultation essential keyword corresponding to the necessary information for the consultation with the consultation type being 'order confirmation' is 'name'. , 'Phone number' and 'Order date', but the matching keyword that is included in the consultation content to date and corresponds to the essential consultation keyword is 'Name'. On the other hand, Agent 2 is conducting a consultation where the consultation type is 'return', and the required consultation keywords for the consultation where the consultation type is 'return' are 'name', 'phone number', 'order date', and 'order product'. and 'return address', and matching keywords included in the consultation content to date may be 'name', 'phone number', and 'order date'. In this case, the call center operation server 300 may calculate the progress rate of counselor 1's consultation as 25% and the progress rate of agent 2's consultation as 75%.

In a more specific embodiment, in order to identify matching keywords corresponding to essential keywords for consultation, the call center operation server 300 converts voice data identified from the customer terminal 100 into text data, and extracts information from the converted text data in advance. A plurality of words identical to words recorded in the constructed counseling word dictionary can be extracted, and each of the plurality of words can be converted into embedding vectors corresponding to each of the extracted words. At this time, the widely known Word2Vec or various other types of embedding techniques can be applied as a method of converting words into embedding vectors, so detailed descriptions are omitted.

After converting the extracted words into embedding vectors, the call center operation server 300 may calculate a representative consultation value corresponding to each of the multiple words extracted using the converted embedding vectors. For example, the representative counseling value is calculated according to the following equation.

In Equation 2, δ _j is the consultation representative value corresponding to the j word (j is a natural number greater than 1 and less than or equal to the total number of extracted words) among the extracted words, and W _j is the value for each word. As a predetermined weight constant, the value may be set in advance to a higher value for words that are more closely related to the corresponding counseling type. Additionally, y _j may mean the size of the converted embedding vector when the jth word is converted into an embedding vector, and bs may be a bias value determined according to the length of the sentence to which the word belongs in text data. For example, the bias value (bs) may be set to a higher value as the length of the sentence becomes longer. In more detail, the bias value (bs) is set to be proportional to a value taken as the root of the length of the sentence, so that it is not reflected as an excessively high value when the length of the sentence is longer than a certain level. In one implementation, the length of a sentence may be defined as the number of words in the sentence.

The call center operation server 300 stores the consultation representative values corresponding to each of a plurality of extracted words and the essential consultation representative values corresponding 1:1 with each of the required consultation keywords set as necessary information corresponding to the corresponding consultation type. The difference values of can be calculated. Here, each of the essential counseling representative values can be calculated by converting the essential counseling keywords into an embedding vector and performing an operation according to Equation 2 described above using the converted embedding vector. In other words, it can be calculated by viewing each essential counseling keyword as an extracted word and performing an operation according to Equation 2 described above. However, at this time, the bias value (bs) may be set to a higher value as the number of words that are the same or similar to the corresponding essential counseling keyword in the counseling word dictionary increases. In more detail, the bias value (bs) is set to be proportional to the value taken as the root of the number of words identical or similar to the required consultation keyword, so that it is not reflected as an excessively high value when the number of words similar to the required consultation keyword is too large. It is regulated. At this time, the judgment of similarity between the essential counseling keywords and the word is calculated by calculating a difference vector between the embedding vectors corresponding to each of the essential counseling keywords and words, and performing an operation according to Equation 3 below on the calculated difference vector. When is below a preset threshold, it is judged to be similar.

In Equation 3, θ may mean the included angle of the difference vector in the coordinate system.

After the difference values are calculated, the call center operation server 300 calculates a comparison threshold value according to Equation 4 below using the calculated difference values, and compares the absolute value size of each of the calculated comparison threshold and difference values. And, as a result of the comparison, words for which a difference value smaller than the comparison threshold is calculated can be determined as matching keywords.

The call center operation server 300 may determine the ratio of the determined matching keywords to all previously extracted words as the progress rate (Prate) for the current consultation.

In Equation 4, Vth is a comparison threshold, and di may mean the ith difference value among k difference values.

According to embodiments, the call center operation server 300 determines the current consultation of each of the counselor terminals 200 based on the progress weight for each of the matching information and necessary information included in the consultation content of each of the counselor terminals 200. Progress can be calculated.

According to embodiments, the call center operation server 300 calculates a progress weight corresponding to the consultation type based on the proportion of consultation time related to necessary information compared to the total consultation time from the consultation content previously performed by the agent terminal 200. Then, the calculated progress weight is multiplied by the above-mentioned progress rate to calculate the weighted progress rate, and the calculated weighted progress rate can be used instead of the progress rate of Equation 1 described above to calculate the remaining consultation time. For example, the call center operation server 300 may calculate the progress weight according to Equation 5 below.

Here, α _i is the progress weight for the ith consultation type among the n consultation types, and T _ask,i is one of the essential consultation keywords set as necessary information corresponding to the ith consultation type that is transmitted from the agent terminal to the customer terminal. represents the point in time (or time) provided, and T _ask,i is the consultation representative value corresponding to each word extracted from text data obtained from voice data collected from the customer terminal, and necessary information corresponding to the ith consultation type. It represents the point in time (or time) when the word for which the smallest difference value is derived among the difference values between each of the essential consultation keywords set as and the essential consultation representative values corresponding 1:1 is provided from the customer terminal to the agent terminal, T _tot represents the total consultation time. At this time, T _rep,i , T _ask,I, and T _tot may be values derived from the contents of one consultation, or may be the sum of values derived from multiple consultations.

Figure 8 is a flow chart for explaining the operation of determining a target agent terminal according to embodiments of the present invention.

Referring to FIG. 8, the call center operation server 300 may determine first agent terminals corresponding to the first consultation type (S210). At this time, the first consultation type may be determined based on the response provided from the customer terminal 100.

The call center operation server 300 may calculate the remaining consultation time of the first agent terminals (S220). Since the calculation of the remaining consultation time has been described with reference to FIG. 5, further description will be omitted.

The call center operation server 300 may determine whether there is a first agent terminal whose remaining consultation time is less than or equal to the reference time (S230).

According to the result of the judgment (S230), if there is a first agent terminal whose remaining consultation time is less than the reference time (Y in S230), the first agent terminal may be determined as the target terminal (S240).

According to the result of the judgment (S230), if there is no first agent terminal whose remaining consultation time is less than the standard time (N in S230), the call center operation server 300 responds to the second consultation type rather than the first consultation type. The second agent terminal can be determined (S250). For example, if there is no agent terminal whose remaining consultation time is less than or equal to the reference time among the agent terminals corresponding to the delivery type, the call center operation server 300 may determine the agent terminals corresponding to the order type.

The call center operation server 300 may calculate the remaining consultation time of the second agent terminals (S260). Since the calculation of the remaining consultation time has been explained with reference to FIG. 5, the description below will be omitted.

The call center operation server 300 may calculate the similarity between the first consultation type and the second consultation type, and calculate the weighted consultation remaining time reflecting the similarity (S270).

The similarity between the first and second counseling types is

According to embodiments, the call center operation server 300 may calculate the weighted remaining counseling time by reflecting a weight that is inversely proportional to the similarity between the first counseling type and the second counseling type. If a counseling type other than the original corresponding counseling type is provided, the counseling efficiency may be relatively low, so the calculated remaining counseling time may be added.

The call center operation server 300 may determine the second agent terminal whose weighted consultation remaining time is less than or equal to the reference time as the target terminal (S280).

According to embodiments of the present invention, when the remaining consultation time of the agent terminal corresponding to the consultation type of the customer terminal 100 is long, the agent terminal corresponding to another consultation type similar to the determined consultation type can be assigned as the target agent terminal. there is. Accordingly, the waiting time for connection of the customer terminal 100 to the agent terminal 200 can be minimized.

Methods according to embodiments of the present invention may be implemented in the form of program instructions that can be executed by a computing device and recorded on a computer-readable medium. Computer-readable media may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on a computer-readable medium may be specially designed and constructed for the present invention or may be known and usable by those skilled in the computer software art.

Examples of computer-readable media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions may include machine language code such as that created by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The above-described hardware device may be configured to operate with at least one software module to perform the operations of the present invention, and vice versa.

Additionally, the above-described method or device may be implemented by combining all or part of its components or functions, or may be implemented separately.

Although the present invention has been described above with reference to preferred embodiments, those skilled in the art may make various modifications and changes to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that you can do it.

Claims (1)

In a call center operation system to minimize waiting time by predicting the remaining consultation time,
a customer terminal configured to transmit consultation content for consultation;
A plurality of agent terminals; and
Receiving consultation contents from the customer terminal, determining a first consultation type of the customer terminal from the consultation contents, determining a target counselor terminal corresponding to the determined first consultation type among the plurality of counselor terminals, and determining the target counselor terminal. It includes an operation server that connects the agent terminal and the customer terminal for communication,
The operating server is,
Determining first agent terminals corresponding to the determined first counseling type among the plurality of agent terminals,
Determine the information necessary to complete the consultation corresponding to the first consultation type determined above,
Reading the current consultation content of each of the first counselor terminals, and determining matching keywords that match essential consultation keywords included in the necessary information based on text data converted from voice data according to the current consultation content,
Calculate the current consultation progress rate of each of the first agent terminals according to the determined matching keywords,
Calculate the remaining consultation time for each of the first agent terminals based on the calculated progress rate,
Among the first counselor terminals, a counselor terminal whose calculated remaining counseling time is less than or equal to the reference time is determined as the target counselor terminal,
The remaining counseling time is calculated according to Equation 1 below,
[Equation 1]

In Equation 1, T _r is the remaining consultation time for the currently in progress consultation, T _avg is the average consultation time for the corresponding first consultation type, p _rate is the calculated progress rate for the currently in progress consultation, and T _sp is the elapsed time for the currently ongoing consultation,
A call center operation system to minimize waiting time by predicting the remaining consultation time.