KR102713221B1 - Customized call center operation system through voice analysis-based consultation type classification - Google Patents

Abstract

A customized call center operation system is disclosed through classification of consultation types based on voice analysis. The cloud-based call center operation system comprises a customer terminal configured to transmit consultation content for consultation, a plurality of counselor terminals connected to the customer terminal and performing calls, and receives the consultation content of the customer terminal, determines a first consultation type corresponding to the consultation content, determines a target counselor terminal corresponding to the determined first consultation type among the plurality of counselor terminals, and communicates and connects the target counselor terminal and the customer terminal.

Description

{CUSTOMIZED CALL CENTER OPERATION SYSTEM THROUGH VOICE ANALYSIS-BASED CONSULTATION TYPE CLASSIFICATION}

The present invention relates to a call center operation system, and more specifically, to a customized call center operation system through consultation type classification based on voice analysis.

Recently, as customer service has developed, many companies are operating call centers by deploying counselors. In particular, recently, efforts are being made to reduce the workload of counselors and conduct counseling efficiently by processing customer calls through server-based applications such as chatbots instead of directly connecting them to counselors, and then connecting them to counselors.

As one of the chatbot-based conventional technologies mentioned above, the conversational voice bot server and the unmanned consultation method using the same proposed in domestic patent application number 10-2021-0125399 A provide call processing, scenario management, and colloquial processing functions by using the conversational voice bot server that modularizes functions common to various types of voice bots. The call processing function converts the customer's voice input from the switch into text, analyzes the converted text to generate an outgoing text, converts the outgoing text into voice and transmits it to the customer, and enables recording by conversation topic. The scenario management function enables the search and item change of the conversation scenario, and the colloquial processing function enables the refinement, substitution, and rhetorical conversion of the colloquial text.

However, even through applications like these chatbots, there is a persistent problem that customer needs are not accurately analyzed, making consultations inefficient, and thus, improvement is needed.

The problem that the present invention seeks to solve is to provide a cloud-based call center system.

In particular, the problem that the present invention seeks to solve is to provide a cloud-based call center system that can analyze the content of consultation from a customer to determine a consultation type and provide a connection to a counselor terminal corresponding to the determined consultation type.

A cloud-based call center operating system according to embodiments of the present invention comprises: a customer terminal configured to transmit consultation content for consultation; a plurality of counselor terminals connected to the customer terminal and performing a call; and receiving the consultation content of the customer terminal, determining a first consultation type corresponding to the consultation content, determining a target counselor terminal corresponding to the determined first consultation type among the plurality of counselor terminals, and connecting the target counselor terminal and the customer terminal for communication.

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 appropriate for the consultation content of the customer terminal to 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 short remaining consultation time to the customer terminal.

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

The present invention can have various modifications and various embodiments, and specific embodiments are 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, but should be understood to include all modifications, equivalents, or substitutes included in the spirit and technical scope of the present invention. In describing each drawing, similar reference numerals are used for similar components.

The terms first, second, A, B, etc. may be used to describe various components, but the components should not be limited by these terms. These terms are only used to distinguish one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component. The term and/or includes any combination of a plurality of related described items or any item among a plurality of related described items.

When it is said that a component is "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components in between. On the other hand, when it is said that a component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

The terminology used in this application is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprises" or "has" and the like are intended to specify the presence of a feature, number, step, operation, component, part or combination thereof described in the specification, but do not exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms defined in commonly used dictionaries, such as those defined in common dictionaries, should be interpreted as having a meaning consistent with the meaning they have in the context of the relevant art, and will not be interpreted in an idealized or overly formal sense unless expressly defined in this application.

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

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

Referring to FIG. 1, a cloud-based call center operation system (hereinafter, call center operation system; 10) may include a customer terminal (100), a counselor terminal (200), and a call center operation server (300). According to embodiments, there may be multiple counselor terminals (200).

Each of the components (100, 200, 300) of Fig. 1 may be connected via a network. According to embodiments, a customer terminal (100) may be connected to a call center operation server (300) via a network, and may also be directly or indirectly connected to at least one counselor terminal (200) via the call center operation server (300). At this time, the network means a connection structure in which information can be exchanged between each node, such as a plurality of terminals and servers, and examples of such networks include, but are not limited to, a 3GPP (3rd Generation Partnership Project) network, an LTE (Long Term Evolution) network, a 5GPP (5th Generation Partnership Project) network, a WIMAX (World Interoperability for Microwave Access) network, the Internet, a LAN (Local Area Network), a Wireless LAN (Wireless Local Area Network), a WAN (Wide Area Network), a PAN (Personal Area Network), a Bluetooth network, an NFC network, a satellite broadcasting network, an analog broadcasting network, and a 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) may transmit consultation content in the form of voice, number, or text to the call center operation server (300), and may 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 connect to a remotely located device via a network. For example, the customer terminal (100) may be, but is not limited to, a laptop, a desktop, a smartphone, a wearable device, etc.

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

The counselor terminal (200) may be a device that can connect to a remotely located device via a network. For example, the counselor terminal (200) may be, but is not limited to, a laptop, a desktop, a smartphone, a wearable device, etc.

The call center operation server (300) can provide a call center service that provides answers corresponding to consultations from a 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 a customer terminal (100) through a network.

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

According to embodiments, the call center operation server (300) may provide a consultation session. At this time, the consultation session may be provided directly or indirectly through an app page, a web page, an application, a program, etc. The consultation session is created and provided by a chatbot application executed by the call center operation server (300), and the customer terminal (100) may access the consultation session to check an inquiry, input a response to the inquiry, and receive a consultation result.

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

The call center operation server (300) according to embodiments of the present invention can perform a question-and-answer session with a customer terminal (100) and determine a consultation type corresponding to the customer terminal (100) based on the question-and-answer session. The call center operation server (300) can connect a counselor terminal (200) corresponding to the determined consultation type to the customer terminal (100).

In this specification, the call center operation server (300) connecting the customer terminal (100) and the counselor terminal (200) to communicate may mean that the call center operation server (300) configures the customer terminal (100) and the counselor terminal (200) to be able to exchange data such as text/voice, or to be able to exchange data such as text/voice right away.

Figure 2 illustrates 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. According to embodiments, the communication unit (310) can exchange data with an external device using a wired communication method or a wireless communication method.

According to embodiments, the communication unit (310) can exchange data with the customer terminal (100) and the counselor terminal (200). For example, the communication unit (310) can transmit data associated with a counseling session to the customer terminal (100).

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

The control unit (320) can control the overall operation of the call center operation server (300). That is, even without a separate explanation, the operation of the call center operation server (300) described below can be understood to be performed under the control of the control unit (320).

According to embodiments, the control unit (320) can control data communication between the call center operation server (300) and external terminals (100, 200), and the control unit (320) can control the operation of the call center operation server (300) for the external terminals (100, 200).

According to embodiments, the control unit (320) may analyze the question and response exchanged between the call center operation server (300) and the customer terminal (100), and, based on the analysis result, determine a consultation type corresponding to the question and response from among a plurality of previously stored consultation types.

In addition, the control unit (320) can support communication with customers and management of counselors by providing text messages, emails, chats, and shared bulletin boards to terminals (e.g., user terminals, etc.) that access the call sensor operation server (300).

The storage unit (330) can store data required for the operation of the call center operation server (300). For example, the storage unit (330) can include non-volatile memory or volatile memory. According to embodiments, the storage unit (330) can store a plurality of commands for controlling the operation of the call center operation server (300). The control unit (320) can perform control over the call center operation server (300) by loading the commands stored in the storage unit (330).

The storage unit (330) can store the types of consultations that can be supported by the call center operation server (300) and the corresponding consultation results. At this time, the storage unit (330) can store questions and responses corresponding to multiple branch nodes that constitute each of the multiple consultation types.

In one example, the storage unit (330) may be configured to generate recording data (e.g., voice data) based on the results of a consultation, and the generated recording data may be viewed through an administrator terminal.

In addition, the control unit (320) supports viewing of recorded data through the administrator terminal, and at the same time, receives a message from the administrator terminal according to viewing of recorded data, and provides the received message to the counselor terminal (200) through a real-time pop-up before, during, or after the consultation.

In addition, the control unit (320) can generate statistical situation data according to the progress of real-time consultation and support external administrator terminals to view the generated statistical situation data. The statistical situation data can include the time of call reception, the number of calls received, information on the customer responding to the call, the call receiving counselor, etc.

In addition, the control unit (320) provides a user interface that can record reservation call status information that occurs during a real-time consultation to the counselor terminal (200), and can receive reservation call status information through the counselor terminal (200) and store it in the storage unit (330). The reservation call status information can include reservation call time, reservation call target customer information, etc.

FIG. 3 illustrates counselor terminals of a call center operation 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 result 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.

In addition, multiple counselor terminals (200) may be configured into multiple groups (200A, 200B, 200C) in response to each counseling type (CTYPE). For example, the counselor terminals (200A) of the first group may correspond to a delivery-related type of counseling. At this time, the group of the counselor terminals (200) may be determined based on the counseling content that each of the counselor terminals (200) has performed in the past, but is not limited thereto.

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

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

The call center operation server (300) can provide a query to a customer terminal (100) and receive a response to the query from the customer terminal (100). At this time, the call center operation server (300) can provide the 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 query and response with the customer terminal (100) and determine the type of consultation using the sequential responses transmitted from the customer terminal (100).

According to embodiments, the call center operation server (300) may receive a voice response provided from a customer terminal (100), convert the received voice into text through STT (speech to text) conversion, analyze the converted text, and determine a consultation type corresponding to the response of the customer terminal (100) from among a plurality of possible consultation types. For example, the call center operation server (300) may analyze the response by performing word division of the converted text, etc. to separate it into meaningful units.

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

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

The call center operation server (300) can connect the determined target counselor terminal and the customer terminal (S140). According to embodiments, the call center operation server (300) can set the customer terminal (100) and the target counselor terminal to perform data communication. For example, the call center operation server (300) can transmit data transmitted from the customer terminal (100) to the target counselor terminal and transmit data transmitted from the target counselor terminal to the customer terminal (100). Accordingly, the target counselor terminal and the customer terminal (100) can be connected to each other through a call.

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

Referring to Fig. 5, the call center operation server (300) can determine a counselor terminal corresponding to a consultation type (S131). According to embodiments, each of the counselor terminals (200) can correspond to each predetermined consultation type.

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

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

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

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

The required information may be set differently for each type of consultation and stored in the call center operation server (300). For example, as shown in Fig. 6, if the consultation type is 'order confirmation', the required information corresponding thereto may be 'name', 'telephone number', and 'order date'. The call center operation server (300) may obtain the required information corresponding to the consultation type from the storage unit (330).

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

Referring to FIG. 7, the call center operation server (300) can calculate (or predict) the remaining consultation time based on the consultation content of the currently consulting counselor (i.e., the counselor 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 content of each of the currently consulting counselor terminals (200) from the storage unit (330).

The call center operation server (300) can analyze the current consultation content of each of the counselor terminals (200), extract information included in the consultation content, and determine matching information that matches the necessary information corresponding to the consultation type of the consultation of the counselor terminals (200) among the extracted information. According to embodiments, the call center operation server (300) can determine whether matching information exists in the consultation content by comparing the information included in the current consultation content with the necessary information.

In this specification, matching specific information with required information means not only that the specific information is data-identical or similar to the required information, but also that the meaning of the specific information is identical or similar to the meaning of the required information. For example, the call center operation server (300) can compare the text (or keyword) constituting the required information with the text (or keyword) 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 determination by utilizing various comparison algorithms such as natural language processing, semantic analysis, and word similarity.

The call center operation server (300) can calculate the progress of the current consultation of each counselor terminal (200) using the matching information, and can calculate the remaining consultation time based on the calculated progress.

According to embodiments, the call center operation server (300) may calculate the remaining consultation time for each of the counselor terminals (200) by using the average consultation time, calculated progress, and elapsed time for the consultation type corresponding to each consultation of the counselor terminals (200). For example, the call center operation server (300) may calculate the remaining consultation time according to the following mathematical expression 1.

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

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 connection point of the customer terminal (100) and the consultation agent terminal (200).

The call center operation server (300) can calculate the progress rate of the current consultation of 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) can calculate the progress rate of the current consultation of each of the counselor terminals (200) based on the presence or absence of matching information included in the consultation content. The call center operation server (300) can calculate a higher progress rate as the content of the current consultation of each of the counselor terminals (200) includes more matching information. For example, as illustrated in FIG. 7, counselor 1 is conducting a consultation of the consultation type of 'order confirmation', and the consultation essential keywords corresponding to the necessary information for the consultation of the consultation type of 'order confirmation' are 'name', 'telephone number', and 'order date', but the matching keyword included in the consultation content up to now and corresponding to the consultation essential keywords is 'name'. On the other hand, counselor 2 is conducting a consultation of the 'return' type, and the essential keywords for the consultation of the 'return' type are 'name', 'phone number', 'order date', 'ordered product', and 'return address', and the matching keywords included in the consultation content up to this point may be 'name', 'phone number', and 'order date'. In this case, the call center operation server (300) can calculate the progress rate of counselor 1's consultation as 25%, and can calculate the progress rate of counselor 2's consultation as 75%.

In a more specific embodiment, in order to identify a matching keyword corresponding to a consultation essential keyword, the call center operation server (300) may convert voice data identified from a customer terminal (100) into text data, extract a plurality of words identical to words recorded in a pre-built consultation word dictionary from the converted text data, and convert each of the extracted plurality of words into embedding vectors corresponding to each of the extracted plurality of words. At this time, since the widely known word-to-vector (Word2Vec) or various other types of embedding techniques may be applied as a method of converting the words into embedding vectors, a detailed description thereof will be omitted.

After converting the words extracted into embedding vectors, the call center operation server (300) can calculate a representative value corresponding to each of the extracted words using the converted embedding vectors. For example, the representative value is calculated according to the following mathematical formula.

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

The call center operation server (300) can calculate the difference values between the consultation representative value corresponding to each of the extracted multiple words and the essential consultation representative values corresponding 1:1 to each of the essential consultation keywords set as necessary information corresponding to the corresponding consultation type. Here, each of the essential consultation representative values can be calculated by converting the essential consultation keyword into an embedding vector and performing an operation according to the aforementioned mathematical expression 2 using the converted embedding vector. In other words, each of the essential consultation keywords can be calculated by viewing it as an extracted word and performing an operation according to the aforementioned mathematical expression 2. However, at this time, the bias value (bs) can be set to a higher value as the number of words identical to or similar to the corresponding essential consultation keyword in the consultation word dictionary increases. More specifically, the bias value (bs) is set to be proportional to the root value of the number of words identical to or similar to the corresponding essential consultation keyword, thereby controlling it so that it is not reflected as an excessively high value when the number of words similar to the corresponding essential consultation keyword is too large. At this time, the similarity between the essential consultation keyword and the word is determined by calculating the difference vector between the embedding vectors corresponding to each of the essential consultation keyword and the word, and performing an operation according to the following mathematical formula 3 on the calculated difference vector. If the result is less than or equal to a preset threshold value, the words are determined to be similar.

In mathematical expression 3, θ can mean the angle between the difference vectors in the coordinate system.

After the differential values are calculated, the call center operation server (300) calculates a comparison threshold value according to the following mathematical expression 4 using the calculated differential values, compares the absolute value size of each of the calculated comparison threshold values and the differential values, and determines words for which a differential value smaller than the comparison threshold value is calculated as matching keywords as a result of the comparison.

The call center operation server (300) can determine the ratio of the determined matching keywords to the total words extracted in advance as the progress rate (Prate) for the current consultation.

In mathematical expression 4, Vth is a comparison threshold, and di can mean the ith difference value among k difference values.

According to embodiments, the call center operation server (300) can calculate the progress of the current consultation of each of the counselor terminals (200) based on the progress weights for each of the matching information and necessary information included in the consultation content of each of the counselor terminals (200).

According to embodiments, the call center operation server (300) may calculate a progress weight corresponding to a consultation type based on the proportion of consultation time related to necessary information compared to the total consultation time from the consultation content already performed by the counselor terminal (200), multiply the calculated progress weight by the aforementioned progress to calculate a weighted progress rate, and use the calculated weighted progress rate instead of the progress rate of the aforementioned mathematical expression 1 to calculate the remaining consultation time. For example, the call center operation server (300) may calculate the progress weight according to the following mathematical expression 5.

Here, α _i is the progress weight for the ith consultation type among n consultation types, T _ask,i represents the time point (or time) at which any one of the essential consultation keywords set as necessary information corresponding to the ith consultation type is provided from the counselor terminal to the customer terminal, T _ask,i represents the time point (or time) at which the word for which the smallest difference value is derived from among the differences between the consultation representative values corresponding to each of the words extracted from the text data acquired from the voice data collected from the customer terminal and the essential consultation representative values corresponding 1:1 to each of the essential consultation keywords set as necessary information corresponding to the ith consultation type is provided from the customer terminal to the counselor terminal, and 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 content of one consultation, but may also be the sum of values derived from multiple consultations.

FIG. 8 is a flow chart for explaining an operation of determining a target counselor terminal according to embodiments of the present invention.

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

The call center operation server (300) can calculate the remaining consultation time of the first counselor terminals (S220). Since the calculation of the remaining consultation time has been explained with reference to Fig. 5, the explanation is omitted below.

The call center operation server (300) can determine whether there is a first counselor terminal whose remaining consultation time is less than the standard time (S230).

According to the result of the judgment (S230), if there is a first counselor terminal whose remaining consultation time is less than or equal to the standard time (Y of S230), the first counselor terminal can be determined as the target terminal (S240).

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

The call center operation server (300) can calculate the remaining consultation time of the second counselor terminals (S260). Since the calculation of the remaining consultation time has been explained with reference to Fig. 5, the explanation is omitted below.

The call center operation server (300) can calculate the similarity between the first consultation type and the second consultation type and calculate the weighted remaining consultation 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 consultation time by reflecting a weight that is inversely proportional to the similarity between the first consultation type and the second consultation type. Since the consultation efficiency may be relatively low when consulting a consultation type other than the original corresponding consultation type, the calculated remaining consultation time may be weighted.

The call center operation server (300) can determine a second counselor terminal whose weighted remaining consultation time is less than or equal to the standard time as a target terminal (S280).

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

The method according to the embodiments of the present invention may be implemented in the form of program commands that can be executed by a computing device and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the computer-readable medium may be those specially designed and configured for the present invention or may be known and available to those skilled in the art of computer software.

Examples of computer-readable media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions may include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, and the like. The above-described hardware devices may be configured to operate with at least one software module to perform the operations of the present invention, and vice versa.

In addition, the above-described method or device may be implemented by combining all or part of its configuration or function, or may be implemented separately.

Although the present invention has been described above with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various modifications and changes may be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

Claims (1)

In a customized call center operation system through consultation type classification based on voice analysis,
A customer terminal configured to transmit consultation content for consultation;
Multiple counselor terminals; and
Including an operating server that receives consultation content from the customer terminal, determines a first consultation type of the customer terminal from the consultation content, determines a target counselor terminal corresponding to the determined first consultation type among the plurality of counselor terminals, and connects the target counselor terminal and the customer terminal for communication.
The above operating server is,
Among the above multiple counselor terminals, first counselor terminals corresponding to the determined first counseling type are determined,
Determine the information necessary to complete the consultation corresponding to the first consultation type determined above,
The current consultation content of each of the above first counselor terminals is read, and based on text data converted from voice data according to the current consultation content, matching keywords matching the essential consultation keywords included in the above necessary information are determined.
Calculate the progress of the current consultation of each of the first counselor terminals according to the determined matching keywords,
Calculate the remaining consultation time for each of the first counselor terminals based on the calculated progress,
Among the above first counselor terminals, the counselor terminal whose calculated remaining counseling time is less than or equal to the standard time is determined as the target counselor terminal.
The above operating server is,
Providing a query to the customer terminal and receiving a response to the provided query in voice form from the customer terminal;
The received response is converted into text through STT (speech to text) conversion, and the converted text is refined or replaced with a standard text having the same or similar meaning using a dictionary of similar words/synonyms stored in advance.
By analyzing the above standard text that has been refined or replaced, the consultation type corresponding to the response of the customer terminal is determined as the first consultation type among a plurality of pre-designated consultation types,
The above multiple types of consultations include delivery-related types, order-related types, and refund-related types.
A customized call center operation system through consultation type classification based on voice analysis.